diff --git a/PTL1/Transcriptomes/Scripts/1a_ContigFiltStats.py b/PTL1/Transcriptomes/Scripts/1a_ContigFiltStats.py
new file mode 100644
index 0000000..fc23727
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/1a_ContigFiltStats.py
@@ -0,0 +1,269 @@
+#!/usr/bin/env python3.6
+
+##__Updated__: 01_04_2023
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 1_ContigFiltStats.py
+##__Options__: python 1_ContigFiltStats.py --help
+
+##########################################################################################
+## This script is intended to remove small transcripts or small contigs below a given ##
+## minimum size from a transcriptome assembly. ##
+## ##
+## Prior to running this script, ensure the following: ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## ##
+## COMMAND Example Below ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## AutoBactVsEuk.py (removes SSU then Bact) or 2a_removeSSU.py then 2b_removeBact.py ##
+## ##
+##########################################################################################
+
+
+import argparse, os, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+from Bio import SeqIO
+from Bio.SeqUtils import GC
+
+
+#----------------------------- Colors For Print Statements ------------------------------#
+
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD+'\nThis script will remove Contigs (and provide a summary of statistics)'\
+ +'\nfrom your Assembly that are shorter than a given length.'+color.ORANGE+\
+ '\n\nA good minimum length to start with is 200bp.'+color.END+color.BOLD+\
+ '\n\nThe minimum length value should be adjusted for your data sets.\n'+color.END+usage_msg(),
+ usage=SUPPRESS,formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+" Fasta file of Protein/Nucleotide sequences\n"+color.END)
+
+ required_arg_group.add_argument('--output_file','-out',
+ help=color.BOLD+color.GREEN+" Desired Output Name\n\n"+color.END)
+
+ required_arg_group.add_argument('--minLen','-min', default=200, type=int,
+ help=color.BOLD+color.GREEN+" Minimum number of base pairs for contigs\n (default = 200)"+color.END)
+ required_arg_group.add_argument('--maxLen','-max', default=15000, type=int,
+ help=color.BOLD+color.GREEN+" Minimum number of base pairs for contigs\n (default = 15000)"+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+
+ optional_arg_group.add_argument('--spades','-spades', action='store_true',
+ help=color.BOLD+color.GREEN+'rnaSPAdes transcriptome assembly\n'+color.END)
+
+ optional_arg_group.add_argument('--genbank','-gb', action='store_true',
+ help=color.BOLD+color.GREEN+'Assembly from Genbank\n (Will include Accession Number in'\
+ ' contig name)\n'+color.END)
+
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Print author contact information\n'+color.END)
+
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ args = parser.parse_args()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 1_ContigFiltStats.py'\
+ ' --input_file ../Op_me_Xxma_rnaSPAdes_scaffolds_15_05.fasta --output_file '\
+ 'Op_me_Xxma --minLen 200 --spades'+color.END
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ if args.output_file == None:
+ valid_arg += 1
+
+ return valid_arg
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+ Home_folder_name = args.output_file
+
+ if os.path.isdir(args.output_file) != True:
+ os.system('mkdir ' + args.output_file)
+
+ if os.path.isdir(args.output_file + '/OriginalFasta/') != True:
+ os.system('mkdir ' + args.output_file +'/OriginalFasta/')
+
+ if os.path.isdir(args.output_file + '/SizeFiltered/') != True:
+ os.system('mkdir ' + args.output_file +'/SizeFiltered/')
+
+ if os.path.isdir('/'.join(args.output_file.split('/')[:-1]) + '/XlaneBleeding/') != True:
+ os.system('mkdir ' + '/'.join(args.output_file.split('/')[:-1]) + '/XlaneBleeding/')
+
+
+###########################################################################################
+###---------- Renames the Contigs, Writes them out, and Calculates Basic Info ----------###
+###########################################################################################
+
+def rename_Transcriptome(args):
+
+ home_folder = args.output_file + '/SizeFiltered/'
+
+ print (color.BOLD+'\n\nPrepping '+color.GREEN+args.input_file.split('/')[-1]+color.END)
+
+ inFasta = [i for i in SeqIO.parse(args.input_file,'fasta') if len(i.seq) >= args.minLen and len(i.seq) <= args.maxLen]
+ inFasta.sort(key=lambda seq_rec: -len(seq_rec.seq))
+
+ renamed_seqs = []
+ seq_code_dict = {}
+
+ count = 1
+
+ seq_name_start = 'Contig'
+
+ if args.genbank == True:
+ for seq_rec in inFasta:
+ seq_code_dict.setdefault(seq_rec.id,[]).append(seq_rec.id.split('_')[-1].split('.')[0]+'_Contig_'+str(count)+'_Len'+str(len(seq_rec.seq)))
+ seq_code_dict.setdefault(seq_rec.id,[]).append(str(seq_rec.seq).upper())
+ renamed_seqs.append('>'+seq_rec.id.split('_')[-1].split('.')[0]+'_Contig_'+str(count)+'_Len'+str(len(seq_rec.seq))+'\n'+str(seq_rec.seq).upper())
+ count += 1
+ elif args.spades == True:
+ for seq_rec in inFasta:
+ seq_code_dict.setdefault(seq_rec.description,[]).append(seq_name_start+'_'+str(count)+'_Len'+str(len(seq_rec.seq))+'_Cov'+str(int(round(float(seq_rec.description.split('_')[-3])))))
+ seq_code_dict.setdefault(seq_rec.description,[]).append(seq_rec.description.split('_')[5])
+ seq_code_dict.setdefault(seq_rec.description,[]).append(str(seq_rec.seq).upper())
+ renamed_seqs.append('>'+seq_name_start+'_'+str(count)+'_Len'+str(len(seq_rec.seq))+'_Cov'+str(int(round(float(seq_rec.description.split('_')[-3]))))+'\n'+str(seq_rec.seq).upper())
+ count += 1
+ else:
+ for seq_rec in inFasta:
+ seq_code_dict.setdefault(seq_rec.description,[]).append(seq_name_start+'_'+str(count)+'_Len'+str(len(seq_rec.seq)))
+ seq_code_dict.setdefault(seq_rec.description,[]).append(str(seq_rec.seq).upper())
+ renamed_seqs.append('>'+seq_name_start+'_'+str(count)+'_Len'+str(len(seq_rec.seq))+'\n'+str(seq_rec.seq).upper())
+ count += 1
+
+ print (color.BOLD+'\n\nThere are '+color.RED+str(len(renamed_seqs))+' contigs > '+str(args.minLen)\
+ +color.END+color.BOLD+' in '+color.DARKCYAN+args.input_file.split('/')[-1]+color.END)
+
+ with open(home_folder + args.output_file.split('/')[-1] + '.' + str(args.minLen)+'bp.fasta','w+') as w:
+ for seq in renamed_seqs:
+ w.write(seq+'\n')
+
+ if args.spades != True:
+ with open(home_folder + args.output_file.split('/')[-1] + '.' + str(args.minLen) + 'bp.SeqCodes.tsv','w+') as w:
+ w.write('Original Name\tNew Name\tSeq Length\t Seq GC\n')
+ for k, v in seq_code_dict.items():
+ w.write(k+'\t'+v[0]+'\t'+str(len(v[1]))+'\t'+str(GC(v[1]))+'\n')
+ else:
+ with open(home_folder + args.output_file.split('/')[-1] + '.' + str(args.minLen) + 'bp.SeqCodes.tsv','w+') as w:
+ w.write('Original Name\tNew Name\tSeq Length\tSeq GC\tSeq Coverage\n')
+ for k, v in seq_code_dict.items():
+ w.write(k+'\t'+v[0]+'\t'+str(len(v[2]))+'\t'+str(GC(v[2]))+'\t'+str(v[1])+'\n')
+
+
+###########################################################################################
+###-------------------------- Cleans Up the PostAssembly Folder ------------------------###
+###########################################################################################
+
+def clean_up(args):
+
+ os.system('cp ' + args.input_file + ' ' + args.output_file + '/OriginalFasta/' + args.input_file.split('/')[-1].replace('.fasta', '.Original.fasta'))
+
+ os.system('cp ' + args.output_file + '/SizeFiltered/' + args.output_file.split('/')[-1] + '.' + str(args.minLen)+'bp.fasta ' + '/'.join(args.output_file.split('/')[:-1]) + '/XlaneBleeding/')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ print (color.BOLD+'\n\nLook for '+color.DARKCYAN+args.output_file+'.'+str(args.minLen)+\
+ 'bp.fasta'+color.END+color.BOLD+'\n\n')
+
+ print ('Next Script is: '+color.GREEN+'2_Auto_rRNA_BvE.py'+color.END\
+ +color.BOLD+'\n(Alternatively'+color.GREEN+' 2a_remove_rRNA.py followed by 2b_remove_Bact.py'\
+ +color.END+color.BOLD+')\n\n'+ color.END)
+
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ args = check_args()
+
+ prep_folders(args)
+
+ temp = rename_Transcriptome(args)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
+
diff --git a/PTL1/Transcriptomes/Scripts/1b_XSpeciesContaminationAgnes.py b/PTL1/Transcriptomes/Scripts/1b_XSpeciesContaminationAgnes.py
new file mode 100644
index 0000000..bf697ed
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/1b_XSpeciesContaminationAgnes.py
@@ -0,0 +1,153 @@
+#!/usr/bin/python3
+
+__author__ = 'Jean-David Grattepanche'
+__version__ = 'ACL fixed sequence naming issue Feb 23, 2022'
+__email__ = 'jeandavid.grattepanche@gmail.com'
+
+
+
+import sys
+import os
+import re
+import time
+import string
+import os.path
+from Bio import SeqIO
+from sys import argv
+listtaxa=[]
+toosim = 0.99
+seqcoverage = 0.7
+
+def merge_files(folder, minlen, conspecific_names):
+ mergefile = open('/'.join(folder.split('/')[:-1]) + '/forclustering.fasta','w+')
+ print("MERGE following files")
+ for taxafile in os.listdir(folder):
+ if taxafile[0] != ".":
+ listtaxa.append(taxafile.split('.' + str(minlen) + 'bp')[0])
+
+ for line2 in SeqIO.parse(folder+'/'+taxafile, 'fasta'):
+ if int(len(str(line2.seq))) >= int(minlen):
+ mergefile.write('>'+taxafile.split('.' + str(minlen) + 'bp')[0] + '_' + line2.description + '\n' + str(line2.seq) + '\n')
+ else:
+ print(line2, " is too short")
+ mergefile.close()
+
+ sort_cluster(folder, listtaxa, minlen, conspecific_names)
+
+
+def sort_cluster(folder, listtaxa, minlen, conspecific_names):
+ if not os.path.exists('/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/'):
+ os.makedirs('/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/')
+
+ fastalist = []; fastadict= {}
+ conspecific_names_dict = { line.split('\t')[0] : line.split('\t')[1].strip() for line in open(conspecific_names) }
+
+ print('CREATE a dictionnary of sequences')
+ for record in SeqIO.parse(open('/'.join(folder.split('/')[:-1]) + '/forclustering.fasta','r'),'fasta'):
+ if record.id[:10] not in conspecific_names_dict:
+ print('\nError in cross-plate contamination assessment: the ten-digit code ' + record.id[:10] + ' is not found in the conspecific names file. Please check that this file is correct and try again.\n')
+ quit()
+
+ IDL = record.description, int(record.description.split('_Cov')[1].replace('\n',''))
+ fastalist.append(IDL)
+ fastadict[record.description] = record.seq
+
+ print("CLUSTER sequences that overlap at least 70%")
+ os.system('vsearch --cluster_fast ' + '/'.join(folder.split('/')[:-1]) + '/forclustering.fasta --strand both --query_cov '+str(seqcoverage)+' --id '+str(toosim) +' --uc ' + '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/results_forclustering.uc --threads 60' )
+
+ #input2 = open('/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/results_forclustering.uc','r')
+ #input2 = open('/Output_PostClusterBackup/clusteringresults_vsearch/results_forclustering.uc','r')
+ cluster_output = '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/results_forclustering.uc'
+ out2 = open('/'.join(folder.split('/')[:-1]) + '/fastatokeep.fas','w+')
+ out3 = open('/'.join(folder.split('/')[:-1]) + '/fastatoremoved.fas','w+')
+ out4 = open('/'.join(folder.split('/')[:-1]) + '/fastatoremoved.uc','w+')
+ print("CREATE a dictionary with clustering results")
+ clustdict= {}; clustlist = []; allseq = []; clustline = {}; list= []; i=0; j=0
+ for row2 in open(cluster_output, 'r'):
+ if row2.split('\t')[0] == 'C' and int(row2.split('\t')[2]) < 2: # keep all unique sequences
+ out2.write('>'+row2.split('\t')[8] + '\n' + str(fastadict[row2.split('\t')[8]])+ '\n')
+ if row2.split('\t')[0] == 'C' and int(row2.split('\t')[2]) > 1: # create another dictionary
+# print("create dico: ", row2.split('\t')[8])
+ clustdict.setdefault(row2.split('\t')[8], [row2.split('\t')[8]])
+ clustlist.append(row2.split('\t')[8])
+
+ for row3 in open(cluster_output, 'r'):
+ if row3.split('\t')[0] == 'H':
+# print("add dico: ", row3.split('\t')[9], row3.split('\t')[8])
+ clustdict[row3.split('\t')[9].replace('\n','')].append(row3.split('\t')[8].replace('\n',''))
+ clustline[row3.split('\t')[8].replace('\n','')] = row3.replace('\n','')
+ clustline[row3.split('\t')[9].replace('\n','')] = row3.replace('\n','')
+
+ print("PARSE the clusters: keep seed sequences (highest coverage) for each cluster")
+ for clust in clustlist:
+ list = sorted(clustdict[clust], reverse = True, key=lambda x: int(x.split('_Cov')[1]))
+ master = list[0]
+ Covmaster = int(list[0].split('_Cov')[1])
+ master8dig = ('_').join(list[0].split('_')[0:3])[:-2]
+ for seq in list:
+ clustered = seq.replace('\n','')
+ Covclustered = int(clustered.split('_Cov')[1])
+ clustered8dig = ('_').join(clustered.split('_')[0:3])[:-2]
+# print(master8dig, Covmaster, '//', clustered8dig, Covclustered)
+ if float(Covmaster/Covclustered) < 10:
+ out2.write('>'+clustered + '\n' + str(fastadict[clustered])+ '\n')
+ i +=1
+ elif conspecific_names_dict[master[:10]] == conspecific_names_dict[clustered[:10]]:
+ out2.write('>'+clustered + '\n' + str(fastadict[clustered])+ '\n')
+ i +=1
+ elif Covclustered >= 50:
+ out2.write('>'+clustered + '\n' + str(fastadict[clustered])+ '\n')
+ i +=1
+ else:
+ j +=1
+ out4 = open('/'.join(folder.split('/')[:-1]) + '/fastatoremoved.uc','a')
+ out3.write('>'+clustered + '\n' + str(fastadict[clustered])+ '\n')
+ print(clustline[clustered],'\t' , master )
+ out4.write(clustline[clustered]+ '\t' + master + '\n')
+ out4.close()
+
+
+ print('there are ', str(i),' sequences kept and ',str(j),' sequences removed')
+
+ out2.close()
+ out3.close()
+
+ splittaxa(folder, listtaxa, minlen)
+
+def splittaxa(folder, listtaxa, minlen):
+ for taxa in listtaxa:
+ tax_sf_path = '/'.join(folder.split('/')[:-1]) + '/' + taxa + '/SizeFiltered/'
+ os.system('mv ' + tax_sf_path + taxa + '.' + str(minlen) + 'bp.fasta' + ' ' + tax_sf_path + taxa + '.' + str(minlen) + 'bp.preXPlate.fasta')
+
+ with open(tax_sf_path + taxa + '.' + str(minlen) + 'bp.fasta','w') as o:
+ for kept in SeqIO.parse('/'.join(folder.split('/')[:-1]) + '/fastatokeep.fas','fasta'):
+ if taxa in kept.description:
+ o.write('>' + kept.description.replace(taxa + '_', '') + '\n' + str(kept.seq) + '\n')
+
+ os.system('mv ' + '/'.join(folder.split('/')[:-1]) + '/fastatokeep.fas ' + '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/')
+ os.system('mv ' + '/'.join(folder.split('/')[:-1]) + '/fastatoremoved.fas ' + '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/')
+ os.system('mv ' + '/'.join(folder.split('/')[:-1]) + '/fastatoremoved.uc ' + '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/')
+ os.system('mv ' + '/'.join(folder.split('/')[:-1]) + '/forclustering.fasta ' + '/'.join(folder.split('/')[:-1]) + '/clusteringresults_vsearch/')
+
+def main():
+
+ script, folder, minlen, conspecific_names = argv
+ merge_files(folder, minlen, conspecific_names)
+
+main()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/PTL1/Transcriptomes/Scripts/2a_remove_rRNA.py b/PTL1/Transcriptomes/Scripts/2a_remove_rRNA.py
new file mode 100644
index 0000000..d9c7719
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/2a_remove_rRNA.py
@@ -0,0 +1,285 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 18_08_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 2a_remove_rDNA.py --help
+
+##########################################################################################
+## This script is intended to identify and isolate SSU/LSU sequences ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Have the Databases set up correctly (e.g. with BLAST or Diamond) and in their ##
+## respective folders! See the manual if you need help ##
+## ##
+## COMMAND Example Below ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 2b_removeBact.py ##
+## ##
+##########################################################################################
+
+
+import argparse, os, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+from Bio import SeqIO
+
+
+#------------------------------ Colors For Print Statements ------------------------------#
+
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD+'\nThis script will remove '+color.RED+'rDNA contigs (both SSU and LSU)'+color.END\
+ +color.BOLD+'\nfrom your Assembly using a set of '+color.RED+'SSU/LSU rDNAs '+color.END\
+ +color.BOLD+'from diverse\n'+color.ORANGE+'Eukaryotes, Bacteria and Archaea'+color.END\
+ +color.BOLD+'.'+color.END+usage_msg(), usage=SUPPRESS,formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+"Fasta file of Nucleotide sequences"+color.END)
+ required_arg_group.add_argument('--databases','-d', action='store',
+ help=color.BOLD+color.GREEN+"Path to databases"+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+ optional_arg_group.add_argument('--threads','-t', default='2',
+ help=color.BOLD+color.GREEN+' Number of threads to use for BLAST\n (default = 2)\n'+color.END)
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Print author contact information\n'+color.END)
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 2a_remove_rRNA.py --input_file ../Op_me_Xxma_rna.200bp.fasta'+color.END
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ elif args.input_file.endswith('bp.fasta') != True:
+ print (color.BOLD + '\n\nCheck that you are giving an appropriately Named/Processed'\
+ 'Fasta file(s) to this script\n\nNOTE that this script CURRENTLY expects your'\
+ ' Fasta files to contain '+color.RED+ '"rna"'+color.END+color.BOLD+' in \nthe Fasta File'\
+ ' Name and must end with ' + color.RED + '"bp.fasta"\n\n' + color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ if os.path.isdir(args.databases + '/db_BvsE') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ +color.ORANGE+'db_BvsE Folder!\n\n'+color.END+color.BOLD+'Ensure that this folder '\
+ 'can be found in the main '+color.ORANGE+'Databases Folder'+color.END+color.BOLD\
+ +'\n\nThen try once again.')
+ valid_arg += 1
+ elif os.path.isfile(args.databases + '/db_BvsE/SSULSUdb.nhr') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ 'BLAST+ formatted '+color.ORANGE+'SSU-LSU databases!\n\n'+color.END+color.BOLD+\
+ 'Ensure that they can be found in the '+color.ORANGE+'db_BvsE folder'+color.END+\
+ color.BOLD+',\nwhich can be found in the main '+color.ORANGE+'Databases Folder'+\
+ color.END+color.BOLD+'\n\nThen try once again.')
+ valid_arg += 1
+
+ return valid_arg
+
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+ code = args.input_file.split('/')[-1][:10]
+ rRNA_folder = args.input_file.split('SizeFiltered')[0] + '/rRNA_Removal/'
+
+ if os.path.isdir(rRNA_folder) != True:
+ os.system('mkdir '+rRNA_folder)
+
+ return code, rRNA_folder
+
+
+###########################################################################################
+###---------------------- Uses BLAST to identify SSU/LSU Sequences ---------------------###
+###########################################################################################
+
+def remove_rDNA(args, rRNA_folder):
+
+ blast_output = rRNA_folder + args.input_file.split('/')[-1].split('.200bp.fasta')[0]+'_allSSULSUresults.tsv'
+
+ BLASTN_cmd = 'blastn -query ' + args.input_file + ' -evalue 1e-10 -max_target_seqs 1 -outfmt'\
+ ' 6 -db ' + args.databases + '/db_BvsE/SSULSUdb -num_threads 2 -out ' + blast_output
+
+ print (color.BOLD+'\n\nBLASTing '+color.DARKCYAN+args.input_file.split('/')[-1]+color.END\
+ +color.BOLD+ ' against the rDNA database\n\n' + color.END)
+
+ os.system(BLASTN_cmd)
+
+ rDNA_Hits = list(set([i.split('\t')[0] for i in open(blast_output).readlines()]))
+
+ print (color.BOLD+'Binning Sequences from '+color.DARKCYAN+args.input_file.split('/')[-1]\
+ +color.END+color.BOLD+'\nas rDNA OR Potentially Protein-Coding\n\n'+color.END)
+
+ no_SSULSU = 0
+ with_SSULSU = 0
+
+ inFasta = [seq_rec for seq_rec in SeqIO.parse(args.input_file,'fasta')]
+
+ with open(rRNA_folder + args.input_file.split('/')[-1].split('.200bp.fasta')[0]+'_rRNAseqs.fasta','w+') as HasSSU:
+ for seq_rec in inFasta:
+ if seq_rec.description in rDNA_Hits:
+ HasSSU.write('>'+seq_rec.description+'\n'+str(seq_rec.seq)+'\n')
+ with_SSULSU += 1
+
+ with open(rRNA_folder + args.input_file.split('/')[-1].split('.200bp.fasta')[0] + '_NorRNAseqs.fasta','w+') as NoSSU:
+ for seq_rec in inFasta:
+ if seq_rec.description not in rDNA_Hits:
+ NoSSU.write('>'+seq_rec.description+'\n'+str(seq_rec.seq)+'\n')
+ no_SSULSU += 1
+
+ return str(with_SSULSU), str(no_SSULSU)
+
+
+###########################################################################################
+###--------------------------- Updates Log of SSU/LSU Removal --------------------------###
+###########################################################################################
+
+def update_log(args, with_SSU, no_SSU):
+
+ if os.path.isdir('../PostAssembly_Logs/') != True:
+ os.system('mkdir ../PostAssembly_Logs/')
+
+ print (color.BOLD+'There are '+color.RED+with_SSU+' rRNA contigs'+color.END+color.BOLD\
+ +' and '+color.PURPLE+no_SSU+' Putative Protein-coding contigs'+color.END+color.BOLD\
+ +'\nin '+color.DARKCYAN+args.input_file.split('/')[1]+'\n' + color.END)
+
+ with open('../PostAssembly_Logs/'+args.input_file.split('/')[1].split('.fas')[0]+'.Log.txt','a') as LogFile:
+ LogFile.write('rDNA Contigs\t'+with_SSU+'\tn/a\tn/a\n')
+ LogFile.write('Non-rDNA Contigs\t'+no_SSU+'\tn/a\tn/a\n')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ print (color.BOLD+'\nLook for '+color.ORANGE+args.input_file.split('/')[1].split('_rna')[0]\
+ + '_NorRNAseqs.fasta'+color.END+color.BOLD+'\nin the '+args.input_file.split('/')[1].split('_rna')[0]\
+ +' Folder\n\n' + color.END)
+ print (color.BOLD + 'Next Script is: ' + color.GREEN + '2b_remove_Bact.py\n\n'+ color.END)
+
+
+###########################################################################################
+###-------------------------- Cleans Up the PostAssembly Folder ------------------------###
+###########################################################################################
+
+def clean_up(args):
+
+ home_folder = args.input_file.split('SizeFiltered')[0]
+
+ os.system('cp ' + home_folder + 'rRNA_Removal/*NorRNA*.fasta ' + home_folder)
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ args = check_args()
+
+ code, rRNA_folder = prep_folders(args)
+
+ with_SSULSU, no_SSULSU = remove_rDNA(args, rRNA_folder)
+
+ #update_log(args, with_SSULSU, no_SSULSU)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/PTL1/Transcriptomes/Scripts/2b_remove_Bact.py b/PTL1/Transcriptomes/Scripts/2b_remove_Bact.py
new file mode 100644
index 0000000..a67ee47
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/2b_remove_Bact.py
@@ -0,0 +1,410 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 18_08_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 2b_remove_Bact.py --help
+
+##########################################################################################
+## This script is intended to identify and isolate SSU/LSU sequences ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Have the Databases set up correctly (e.g. with BLAST or Diamond) and in their ##
+## respective folders! See the manual if you need help ##
+## 4. Run removeSSU.py on your Fasta file ##
+## ##
+## COMMAND Example Below ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 3_CountOGsDiamond.py ##
+## ##
+##########################################################################################
+
+
+import argparse, os, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+from distutils import spawn
+from Bio import SeqIO
+
+
+#------------------------------ Colors For Print Statements ------------------------------#
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###---------------------------- UPDATE DIAMOND PATH BELOW! -----------------------------###
+###########################################################################################
+ ## IF Diamond is IN YOUR PATH then no updating is needed...
+
+def check_diamond_path():
+
+ diamond_path = ''
+
+ if diamond_path == '':
+ diamond_path = spawn.find_executable("diamond")
+ #diamond_path = '/path/to/diamond'
+ else:
+ pass
+
+ if diamond_path == None:
+ print (color.BOLD + '\n\nPlease open this script and check that you have included'\
+ +' the PATH to the'+color.BLUE+' "Diamond" '+color.END+color.BOLD+'executable.\n\n'+color.END)
+ print (color.BOLD+color.BLUE+'LOOK FOR:\n\n'+color.RED\
+ +'#------------------------------ UPDATE DIAMOND PATH BELOW! -------------------------------#'\
+ +color.BLUE+'\n\nThis is somewhere around lines 50 - 80...\n\n'+color.END)
+
+ sys.exit()
+ else:
+ pass
+
+ return diamond_path
+
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD + '\nThis script will categorize Contigs as'+color.ORANGE+' STRONGLY '+color.END\
+ +color.BOLD+color.RED+'Eukaryotic \nOR Prokaryotic'+color.END+color.BOLD+' using a set of Proteins'\
+ ' from diverse\n'+color.ORANGE+'Eukaryotes, Bacteria and Archaea'+color.END\
+ +color.BOLD+'.'+color.END+usage_msg(), usage=SUPPRESS,formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+'Fasta file of Nucleotide sequences (with rRNAs removed)'+color.END)
+ required_arg_group.add_argument('--databases','-d', action='store',
+ help=color.BOLD+color.GREEN+"Path to databases"+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Print author contact information\n'+color.END)
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 2b_remove_Bact.py --input_file'\
+ ' ../Op_me_Xxma/Op_me_Xxma_NorRNAseqs.fasta'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ print(args.input_file)
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ elif args.input_file.endswith('NorRNAseqs.fasta') != True:
+ print (color.BOLD+'\n\nInvalid Fasta File! Only Fasta Files that were processed'\
+ ' with '+color.GREEN+'2a_remove_rRNA.py '+color.END+color.BOLD+'are valid\n\n'\
+ 'However, to bypass that issue, Fasta Files MUST end with '+color.CYAN+\
+ '"NorRNAseqs.fas"\n\n'+color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ if os.path.isdir(args.databases + '/db_BvsE') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ +color.ORANGE+'db_BvsE Folder!\n\n'+color.END+color.BOLD+'Ensure that this folder '\
+ 'can be found in the main '+color.ORANGE+'Databases Folder'+color.END+color.BOLD\
+ +'\n\nThen try once again.')
+ valid_arg += 1
+ elif os.path.isfile(args.databases + '/db_BvsE/eukout.dmnd') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ 'Diamond formatted '+color.ORANGE+'Eukaryotic Protein database!\n\n'+color.END+color.BOLD+\
+ 'Ensure that it can be found in the '+color.ORANGE+'db_BvsE folder'+color.END+\
+ color.BOLD+',\nwhich can be found in the main '+color.ORANGE+'Databases Folder'+\
+ color.END+color.BOLD+'\n\nThen try once again.'+color.END)
+ elif os.path.isfile(args.databases + '/db_BvsE/micout.dmnd') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ 'Diamond formatted '+color.ORANGE+'Bacterial/Archaeal Protein database!\n\n'+color.END+color.BOLD+\
+ 'Ensure that it can be found in the '+color.ORANGE+'db_BvsE folder'+color.END+\
+ color.BOLD+',\nwhich can be found in the main '+color.ORANGE+'Databases Folder'+\
+ color.END+color.BOLD+'\n\nThen try once again.'+color.END)
+
+ valid_arg += 1
+
+ return valid_arg
+
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+
+ BvE_folder = '/'.join(args.input_file.split('/')[:-1]) + '/BvE/'
+
+ if os.path.isdir(BvE_folder) != True:
+ os.system('mkdir '+BvE_folder)
+
+
+###########################################################################################
+###---------------- Runs Diamond on Bact and Euk small RefSeq Databases ----------------###
+###########################################################################################
+
+def ublast_BvE(args, diamond_path):
+
+ BvE_folder = '/'.join(args.input_file.split('/')[:-1]) + '/BvE/'
+ mic_output = args.input_file.split('/')[-1]+'micresults.'
+ euk_output = args.input_file.split('/')[-1]+'eukresults.'
+
+ print(color.BOLD+'\n\n"BLAST"-ing against PROK database using DIAMOND: ' + color.DARKCYAN + 'micout.dmnd' + color.END + '\n\n')
+
+ Prok_diamond_cmd = diamond_path + ' blastx -q ' + args.input_file + ' --max-target-seqs 1 -d ' + args.databases + '/db_BvsE/micout.dmnd --evalue 1e-5 --threads 60 --outfmt 6 -o ' + BvE_folder + 'allmicresults.tsv'
+
+ os.system(Prok_diamond_cmd)
+
+ print(color.BOLD+'\n\n"BLAST"-ing against EUK database using DIAMOND: ' + color.DARKCYAN + 'eukout.dmnd' + color.END + '\n\n')
+
+ Euk_diamond_cmd = diamond_path + ' blastx -q ' + args.input_file + ' --max-target-seqs 1 -d ' + args.databases + '/db_BvsE/eukout.dmnd --evalue 1e-5 --threads 60 --outfmt 6 -o ' + BvE_folder + 'alleukresults.tsv'
+
+ os.system(Euk_diamond_cmd)
+
+
+
+###########################################################################################
+###---------------- Compares Bacterial and Euk Hits for Classification -----------------###
+###########################################################################################
+
+def compare_hits(args):
+
+ BvE_folder = '/'.join(args.input_file.split('/')[:-1]) + '/BvE/'
+
+ EukDict = {}
+ ProkDict = {}
+ CompDict = {}
+
+ inFasta = [seq_rec for seq_rec in SeqIO.parse(args.input_file,'fasta')]
+
+ for seq_rec in inFasta:
+ EukDict[seq_rec.description] = ''
+ ProkDict[seq_rec.description] = ''
+ CompDict[seq_rec.description] = []
+
+ inEukHits = [i for i in open(BvE_folder + 'alleukresults.tsv').readlines()]
+ inEukHits.sort(key=lambda x: (float(x.split('\t')[-2]), -int(x.split('\t')[3])))
+
+ inProkHits = [i for i in open(BvE_folder + 'allmicresults.tsv').readlines()]
+ inProkHits.sort(key=lambda x: (float(x.split('\t')[-2]), -int(x.split('\t')[3])))
+
+ for i in inEukHits:
+ if EukDict[i.split('\t')[0]] == '':
+ EukDict[i.split('\t')[0]] = float(i.split('\t')[-2])
+
+ for i in inProkHits:
+ if ProkDict[i.split('\t')[0]] == '':
+ ProkDict[i.split('\t')[0]] = float(i.split('\t')[-2])
+
+ for k in CompDict.keys():
+ if EukDict[k] != '':
+ CompDict[k].append(EukDict[k])
+ else:
+ CompDict[k].append('no hit')
+ if ProkDict[k] != '':
+ CompDict[k].append(ProkDict[k])
+ else:
+ CompDict[k].append('no hit')
+
+ for k, v in CompDict.items():
+
+ ### Contigs lacking STRONG Eukaryotic OR Prokaryotic Hits
+ if v[0] == 'no hit' and v[1] == 'no hit':
+ CompDict[k].append('UNDETERMINED')
+
+ ### Contigs lacking STRONG Eukaryotic with a Prokaryotic Hit
+ elif v[0] != 'no hit' and v[1] == 'no hit':
+ CompDict[k].append('EUKARYOTIC')
+
+ ### Contigs with a Eukaryotic but without a Prokaryotic Hit
+ elif v[0] == 'no hit' and v[1] != 'no hit':
+ CompDict[k].append('PROKARYOTIC')
+
+ ### Uses Basic math to determine if contigs with are MORE Eukaryotic than Prokaryotic
+ else:
+ try:
+ prok_euk_ratio = float(v[1])/float(v[0])
+ euk_prok_ratio = float(v[0])/float(v[1])
+
+ if prok_euk_ratio >= 100:
+ CompDict[k].append('EUKARYOTIC')
+
+ elif euk_prok_ratio >= 1000:
+ CompDict[k].append('PROKARYOTIC')
+
+ else:
+ CompDict[k].append('UNDETERMINED')
+
+ except:
+ CompDict[k].append('divide by zero')
+
+ with open(BvE_folder + 'comparisons.txt','w+') as w:
+ for k, v in CompDict.items():
+ w.write(k+':'+':'.join([str(i) for i in v])+'\n')
+
+ BvE_folder = '/'.join(args.input_file.split('/')[:-1]) + '/BvE/'
+ BvE_output_base = BvE_folder+args.input_file.split('/')[-1].split('.fas')[0]
+
+### Gathers the sequences and categorizes them
+ Euk_Fasta = sorted((seq_rec for seq_rec in inFasta if CompDict[seq_rec.description][-1] == 'EUKARYOTIC'), key=lambda x: -int(len(x.seq)))
+ Prok_Fasta = sorted((seq_rec for seq_rec in inFasta if CompDict[seq_rec.description][-1] == 'PROKARYOTIC'), key=lambda x: -int(len(x.seq)))
+ Und_Fasta = sorted((seq_rec for seq_rec in inFasta if CompDict[seq_rec.description][-1] == 'UNDETERMINED'), key=lambda x: -int(len(x.seq)))
+ Zero_Fasta = sorted((seq_rec for seq_rec in inFasta if CompDict[seq_rec.description][-1] == 'divide by zero'), key=lambda x: -int(len(x.seq)))
+
+
+### Writes out all of the categorized sequences
+ with open(args.input_file.split('NorRNA')[0] + 'WTA_EPU.fasta', 'w') as epu:
+ with open(BvE_output_base+'.Not_Bact.fasta','w+') as nb:
+ for euk_seq in Euk_Fasta:
+ nb.write('>' + euk_seq.description + '\n' + str(euk_seq.seq) + '\n')
+ epu.write('>' + euk_seq.description + '_E' + '\n' + str(euk_seq.seq) + '\n')
+
+
+ with open(BvE_output_base+'.Bact_Hit.fasta','w+') as pr:
+ for prok_seq in Prok_Fasta:
+ pr.write('>' + prok_seq.description + '\n' + str(prok_seq.seq) + '\n')
+ epu.write('>' + prok_seq.description + '_P' + '\n' + str(prok_seq.seq) + '\n')
+
+ with open(BvE_output_base+'.Undetermined.fasta','w+') as und:
+ for und_seq in Und_Fasta:
+ und.write('>' + und_seq.description + '\n' + str(und_seq.seq) + '\n')
+ epu.write('>' + und_seq.description + '_U' + '\n' + str(und_seq.seq) + '\n')
+
+ if len(Zero_Fasta) != 0:
+ with open(BvE_output_base+'.DivideByZero.fasta','w+') as w:
+ for zero_seq in Zero_Fasta:
+ w.write('>' + zero_seq.description + '\n' + str(zero_seq.seq) + '\n')
+ epu.write('>' + zero_seq.description + '_U' + '\n' + str(zero_seq.seq) + '\n')
+ else:
+ pass
+
+ return str(len(Euk_Fasta)), str(len(Prok_Fasta)), str(len(Und_Fasta))
+
+
+###########################################################################################
+###----------------------- Updates Log of Prok vs Euk Comparisons ----------------------###
+###########################################################################################
+
+def update_log(args, Euk_Contigs, Prok_Contigs, Und_Contigs):
+
+ if os.path.isdir('../PostAssembly_Logs/') != True:
+ os.system('mkdir ../PostAssembly_Logs/')
+ else:
+ pass
+
+ print (color.BOLD +'\n\nThere are '+color.RED+Prok_Contigs+' Strongly Prokaryotic contigs'+color.END\
+ +color.BOLD+',\n'+color.ORANGE+Euk_Contigs+' Strongly Eukaryotic contigs'+color.END\
+ +color.BOLD+',\nand '+color.PURPLE+Und_Contigs+' Undetermined Contigs\n'+color.END\
+ +color.BOLD+'in '+args.input_file.split('/')[-1]+color.END)
+
+ for Logname in os.listdir(os.curdir+'./PostAssembly_Logs/'):
+ if Logname.startswith(args.input_file.split('/')[-1].split('_No')[0]) and Logname.endswith('Log.txt'): # ACL - ???
+ with open('../PostAssembly_Logs/'+Logname,'a') as Logfilename:
+ Logfilename.write('Prokaryotic Contigs\t'+Prok_Contigs+'\tn/a\tn/a\n')
+ Logfilename.write('Eukaryotic Contigs\t'+Euk_Contigs+'\tn/a\tn/a\n')
+ Logfilename.write('Undetermined Contigs\t'+Und_Contigs+'\tn/a\tn/a\n')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ print (color.BOLD+'\nLook for '+color.DARKCYAN+args.input_file.split('/')[-1]\
+ .split('NorRNA')[0]+'WTA_EPU.fasta'+color.END+color.BOLD+' in the '\
+ +args.input_file.split('/')[1]+' Folder\n\n' + color.END)
+ print (color.BOLD + 'Next Script is: ' + color.GREEN + '3_CountOGsDiamond.py\n\n'+ color.END)
+
+
+##########################################################################################
+###--------------------- Cleans up the Folder and Moves Final Files -------------------###
+##########################################################################################
+
+def clean_up(args):
+
+ home_folder = '/'.join(args.input_file.split('/')[:-1])
+
+ os.system('cp '+home_folder+'/*WTA_EPU.fasta '+home_folder+'/BvE/')
+ os.system('mv '+home_folder+'/*NorRNA*fasta '+home_folder+'/rRNA_Removal/')
+
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ usearch_path = check_diamond_path()
+
+ args = check_args()
+
+ prep_folders(args)
+
+ ublast_BvE(args, usearch_path)
+
+ Euk_Contigs, Prok_Contigs, Und_Contigs = compare_hits(args)
+
+ #update_log(args, Euk_Contigs, Prok_Contigs, Und_Contigs)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
diff --git a/PTL1/Transcriptomes/Scripts/3_CountOGsDiamond.py b/PTL1/Transcriptomes/Scripts/3_CountOGsDiamond.py
new file mode 100644
index 0000000..74b54d1
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/3_CountOGsDiamond.py
@@ -0,0 +1,372 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 16_10_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 3_CountOGsDiamond.py --help
+
+
+##########################################################################################
+## This script is intended to classify the STRONGLY Eukaryotic and UNDETERMINED/UNKNOWN ##
+## contigs into different OGs (e.g. orthologous gene-families) ##
+## ##
+## For more info about the OGs, check out: OrthoMCL.org ##
+## ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Removed SSU/LSU sequences from your Fasta File ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 4_StopFrequency.py ##
+## ##
+##########################################################################################
+
+import argparse, os, sys, re
+from argparse import RawTextHelpFormatter,SUPPRESS
+from distutils import spawn
+from Bio import SeqIO
+
+
+#------------------------------ Colors For Print Statements ------------------------------#
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###---------------------------- UPDATE DIAMOND PATH BELOW! -----------------------------###
+###########################################################################################
+ ## IF Diamond is IN YOUR PATH then no updating is needed...
+
+def check_diamond_path():
+
+ diamond_path = ''
+
+ if diamond_path == '':
+ diamond_path = spawn.find_executable("diamond")
+ #diamond_path = '/path/to/diamond'
+ else:
+ pass
+
+ if diamond_path == None:
+ print (color.BOLD + '\n\nPlease open this script and check that you have included'\
+ +' the PATH to the'+color.BLUE+' "usearch" '+color.END+color.BOLD+'executable.\n\n'+color.END)
+ print (color.BOLD+color.BLUE+'LOOK FOR:\n\n'+color.RED\
+ +'#------------------------------ UPDATE USEARCH PATH BELOW! -------------------------------#'\
+ +color.BLUE+'\n\nThis is somewhere around lines 50 - 80...\n\n'+color.END)
+
+ sys.exit()
+ else:
+ pass
+
+ return diamond_path
+
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD + '\n\nThis script will categorize Contigs into'+color.ORANGE+' "Homologous" '\
+ +color.END+color.BOLD+'Gene Families (OGs)\nbased on '+color.RED+'OrthoMCL'+color.END\
+ +color.BOLD+"'s Gene Family Grouping\n\n\nNotes on this script and "+color.GREEN+\
+ 'OrthoMCL Families'+color.END+color.BOLD+' can be found\nat the bottom of '+color.GREEN\
+ +'THIS script (3_CountOGsDiamond.py)\n'+color.END+usage_msg(), usage=SUPPRESS,
+ formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+'Fasta file of Nucleotide sequences enriched \nwith'\
+ ' Eukaryotic protein coding transcripts'+color.END)
+ required_arg_group.add_argument('--databases','-g', action='store',
+ help=color.BOLD+color.GREEN+"Path to fasta file with Hook sequences"+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+ optional_arg_group.add_argument('--threads','-t', default='2',
+ help=color.BOLD+color.GREEN+' Number of threads to use for BLAST\n (default = 2)\n'+color.END)
+ optional_arg_group.add_argument('--evalue','-e', default=1e-5, type = float,
+ help=color.BOLD+color.GREEN+' Maximum e-value for OG assignment\n (default = 1e-5)\n'+color.END)
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Prints author contact information\n'+color.END)
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 3_CountOGsDiamond.py'\
+ ' --input_file ../Op_me_Xxma/Op_me_Xxma_WTA_NBU.fasta'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ elif args.input_file.endswith('WTA_EPU.fasta') != True:
+ print (color.BOLD+'\n\nInvalid Fasta File! Only Fasta Files that were processed'\
+ ' with '+color.GREEN+'2b_remove_Bact.py '+color.END+color.BOLD+'are valid\n\n'\
+ 'However, to bypass that issue, Fasta Files MUST end with '+color.CYAN+\
+ '"WTA_NBU.fasta"\n\n'+color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ if os.path.isdir(args.databases + '/db_OG') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ +color.ORANGE+'db_OG Folder!\n\n'+color.END+color.BOLD+'Ensure that this folder '\
+ 'can be found in the main '+color.ORANGE+'Databases Folder'+color.END+color.BOLD\
+ +'\n\nThen try once again\n\n.'+color.END)
+ valid_arg += 1
+
+ ogdb_count = 0
+ for file in os.listdir(args.databases + '/db_OG'):
+ if file.endswith('.dmnd'):
+ ogdb_count += 1
+
+ if ogdb_count == 0:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ 'Diamond formatted '+color.ORANGE+'Gene Family databases!\n\n'+color.END+color.BOLD+\
+ 'Ensure that they can be found in the '+color.ORANGE+'db_OG folder'+color.END+\
+ color.BOLD+',\nwhich can be found in the main '+color.ORANGE+'Databases Folder'+\
+ color.END+color.BOLD+'\n\nThen try once again.\n\n'+color.END)
+ valid_arg += 1
+ elif ogdb_count > 1:
+ print('\nMultiple OG databases found. Please only provide 1 database in the db_OG folder.\n')
+ valid_arg += 1
+
+ return valid_arg
+
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+
+ OG_folder = '/'.join(args.input_file.split('/')[:-1]) + '/DiamondOG/'
+
+ if os.path.isdir(OG_folder) != True:
+ os.system('mkdir '+OG_folder)
+
+
+###########################################################################################
+###--------------------- Runs Diamond on Split OrthoMCL Databases ----------------------###
+###########################################################################################
+
+def OG_diamond(args, diamond_path):
+
+ print (color.BOLD+'\nStarting to "BLAST" against OG databases'+color.END)
+
+ OG_folder = '/'.join(args.input_file.split('/')[:-1]) + '/DiamondOG/'
+ db = [file for file in os.listdir(args.databases + '/db_OG') if file.endswith('.dmnd')][0]
+
+ print (color.BOLD + '\n\n"BLAST"-ing against OG database using DIAMOND: ' + color.DARKCYAN + db + color.END + '\n\n')
+
+ OG_diamond_cmd = diamond_path + ' blastx -q ' + args.input_file + ' -d ' + args.databases + '/db_OG/' + db + ' --evalue ' + str(args.evalue) + ' --threads 60 --subject-cover 0.35 --outfmt 6 -o ' + OG_folder + 'allOGresults.tsv'
+
+ os.system(OG_diamond_cmd)
+
+
+###########################################################################################
+###--------------- Keeps the Single BEST Hit (HSP-score) Per Transcript ----------------###
+###########################################################################################
+
+def keep_best(args):
+
+ print (color.BOLD+color.PURPLE+'\n\nProcessing OG-database results to keep only the BEST match for each transcript\n\n'+color.END)
+
+ OG_folder = '/'.join(args.input_file.split('/')[:-1]) + '/DiamondOG/'
+
+ inTSV = [i for i in open(OG_folder + 'allOGresults.tsv').readlines()]
+
+ inTSV.sort(key = lambda x: -float(x.split('\t')[-1]))
+
+ keep = []
+ for i in inTSV:
+ if any(i.split('\t')[0] in j for j in keep) != True:
+ keep.append(i)
+
+ updated_lines = list(set([line.split('\t')[0]+'_'+'_'.join(line.split('\t')[1].split('_')[-2:])+'\t'+'\t'.join(line.split('\t')[1:]) for line in keep]))
+
+ with open(args.input_file.replace('.fasta','.Renamed_allOGCleanresults.tsv'), 'w+') as w:
+ for i in updated_lines:
+ w.write(i)
+
+
+###########################################################################################
+###-------- Copies and Updates Names of Transcripts With OG Hits to New Fasta ----------###
+###########################################################################################
+
+def update_fasta(args):
+
+ print (color.BOLD+color.PURPLE+'Updating Fasta File Sequence Names with their BEST OG hits\n\n'+color.END)
+
+ Renamed_TSV = args.input_file.replace('.fasta','.Renamed_allOGCleanresults.tsv')
+
+ keep = [i for i in open(Renamed_TSV).readlines() if i != '\n']
+
+ keep_dict = { }
+ for line in keep:
+ try:
+ og_number = re.split('OG.{1}_', line.split('\t')[1])[1][:6]
+ og_prefix = line.split('\t')[1].split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ keep_dict.update({ re.split('_OG.{1}_', line.split('\t')[0])[0] : re.split('_OG.{1}_', line.split('\t')[0])[0] + '_' + og_prefix + line.split('\t')[1].split('_')[-1] })
+ except IndexError:
+ pass
+
+ inFasta = [i for i in SeqIO.parse(args.input_file,'fasta')]
+
+ updated_seq_name = ['>'+keep_dict[i.description]+'\n'+str(i.seq)+'\n' for i in inFasta if i.description in keep_dict.keys()]
+
+ seqs_without_OG = ['>'+i.description+'\n'+str(i.seq)+'\n' for i in inFasta if i.description not in keep_dict.keys()]
+
+ with open(args.input_file.replace('.fasta','.Renamed.fasta'),'w+') as w:
+ for i in updated_seq_name:
+ w.write(i)
+
+ with open(args.input_file.replace('.fasta','.LackOG.fasta'),'w+') as x:
+ for i in seqs_without_OG:
+ x.write(i)
+
+
+###########################################################################################
+###-------------------- Updates Log With OG Assignment Information ---------------------###
+###########################################################################################
+
+def update_log(args):
+
+ if os.path.isdir('../PostAssembly_Logs/') != True:
+ os.system('mkdir ../PostAssembly_Logs/')
+ else:
+ pass
+
+ home_folder = '/'.join(args.input_file.split('/')[:-1]) + '/'
+
+ Renamed_TSV = home_folder+args.input_file.split('/')[-1].replace('.fasta','.Renamed_allOGCleanresults.tsv')
+
+ keep = [line for line in open(Renamed_TSV).readlines()]
+ all_ogs = [line.split('\t')[1].split('_')[-1] for line in keep if len(re.split('_OG.{1}_', line.split('\t')[1])) > 1]
+
+ total_with_ogs = str(len(all_ogs))
+ unique_ogs = str(len(set(all_ogs)))
+
+ print (color.BOLD +'There are '+color.BLUE +total_with_ogs+' Contigs'+color.END\
+ +color.BOLD+' that hit '+color.DARKCYAN+unique_ogs+' Unique OGs\n'+color.END)
+
+
+ for Logname in os.listdir(os.curdir+'./PostAssembly_Logs/'):
+ if Logname.startswith(args.input_file.split('/')[2].split('_WTA')[0]) and Logname.endswith('Log.txt'):
+ with open('../PostAssembly_Logs/'+Logname,'a') as LogFile:
+ LogFile.write('Contigs With OG\t'+total_with_ogs+'\tn/a\tn/a\n')
+ LogFile.write('Unique OGs\t'+unique_ogs+'\tn/a\tn/a\n')
+
+
+##########################################################################################
+###--------------------- Cleans up the Folder and Moves Final Files -------------------###
+##########################################################################################
+
+def clean_up(args):
+
+ OG_folder = '/'.join(args.input_file.split('/')[:-1]) + '/DiamondOG/'
+
+ os.system('rm ' + args.input_file)
+
+ os.system('cp ' + args.input_file.replace('.fasta','.Renamed.fasta') + ' ' + OG_folder)
+
+ os.system('cp ' + args.input_file.replace('.fasta','.Renamed_allOGCleanresults.tsv') + ' ' + OG_folder)
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ home_folder = '../'+args.input_file.split('/')[1]+'/'
+
+ print (color.BOLD+'\nLook for '+color.DARKCYAN+args.input_file.split('/')[-1]\
+ .replace('.fasta','WTA_EPU.fasta')+color.END+color.BOLD+' in the '+home_folder\
+ +' Folder\n\n' + color.END)
+
+ print (color.BOLD+'Next Script is: '+color.GREEN+'4_InFrameStopFreq.py\n\n'+ color.END)
+
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ usearch_path = check_diamond_path()
+
+ args = check_args()
+
+ prep_folders(args)
+
+ OG_diamond(args, usearch_path)
+
+ keep_best(args)
+
+ update_fasta(args)
+
+ #update_log(args)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
diff --git a/PTL1/Transcriptomes/Scripts/4_InFrameStopFreq.py b/PTL1/Transcriptomes/Scripts/4_InFrameStopFreq.py
new file mode 100644
index 0000000..e5def97
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/4_InFrameStopFreq.py
@@ -0,0 +1,790 @@
+#!/usr/bin/env python
+
+##__Updated__: 18_08_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 4_InFrameStopFreq.py --help
+
+
+##########################################################################################
+## This script is intended to aid in identifying the genetic code of the data given ##
+## ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Removed SSU/LSU sequences from your Fasta File ##
+## 4. Classified your sequences as Strongly Prokaryotic/Eukaryotic or Undetermined ##
+## 5. Classified the Non-Strongly Prokaryotic sequences into OGs ##
+## ##
+## COMMAND Example Below ##
+## Extra Notes at Bottom of Script ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 5_GCodeTranslate.py ##
+## ##
+##########################################################################################
+
+
+import argparse, os, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+from distutils import spawn
+
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.Data.CodonTable import CodonTable
+
+
+#-------------------------- Set-up Codon Tables (Genetic Codes) --------------------------#
+
+tag_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'Q',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'Q', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAG'])
+
+c_uncinata_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAG': 'Q',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'Q', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAA'])
+
+#------------------------------ Colors For Print Statements ------------------------------#
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###---------------------------- UPDATE DIAMOND PATH BELOW! -----------------------------###
+###########################################################################################
+ ## IF Diamond is IN YOUR PATH then no updating is needed...
+
+def check_diamond_path():
+
+ diamond_path = ''
+
+ if diamond_path == '':
+ diamond_path = spawn.find_executable("diamond")
+ #diamond_path = '/path/to/diamond'
+ else:
+ pass
+
+ if diamond_path == None:
+ print (color.BOLD + '\n\nPlease open this script and check that you have included'\
+ +' the PATH to the'+color.BLUE+' "diamond" '+color.END+color.BOLD+'executable.\n\n'+color.END)
+ print (color.BOLD+color.BLUE+'LOOK FOR:\n\n'+color.RED\
+ +'#------------------------------ UPDATE DIAMOND PATH BELOW! -------------------------------#'\
+ +color.BLUE+'\n\nThis is somewhere around lines 50 - 80...\n\n'+color.END)
+
+ sys.exit()
+ else:
+ pass
+
+ return diamond_path
+
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD+'\n\nThis script is intended to '+color.RED+'AID You '+color.END+color.BOLD\
+ +'in determining the '+color.RED+'\nLikely Genetic Code'+color.END+color.BOLD+' of a'\
+ ' given Fasta File of transcripts\n\nInterpretation of the output (StopFreq.tsv) is difficult \nand so '+color.ORANGE\
+ +'TWO EXAMPLES'+color.END+color.BOLD+' can be found in the '+color.CYAN+'NOTES Section'\
+ +color.END+color.BOLD+' of\nTHIS Script '+color.GREEN+'(4_InFrameStopFreq.py)\n'+color.END\
+ +usage_msg(), usage=SUPPRESS,formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store', required=True,
+ help=color.BOLD+color.GREEN+'Fasta file of Nucleotide sequences enriched \nwith'\
+ ' Eukaryotic protein coding transcripts'+color.END)
+ required_arg_group.add_argument('--databases','-d', action='store',
+ help=color.BOLD+color.GREEN+"Path to databases"+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Prints author contact information\n'+color.END)
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 4_InFrameStopFreq.py'\
+ ' --input_file ../Op_me_Xxma/Op_me_Xxma_WTA_EPU.Renamed.fasta'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ elif args.input_file.endswith('WTA_EPU.Renamed.fasta') != True:
+ print (color.BOLD+'\n\nInvalid Fasta File! Only Fasta Files that were processed'\
+ ' with '+color.GREEN+'3_CountOGsUsearcy.py '+color.END+color.BOLD+'are valid\n\n'\
+ 'However, to bypass that issue, Fasta Files MUST end with '+color.CYAN+\
+ '"WTA_NBU.Renamed.fasta"\n\n'+color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ if os.path.isdir(args.databases + '/db_StopFreq') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ +color.ORANGE+'db_StopFreq Folder!\n\n'+color.END+color.BOLD+'Ensure that this folder '\
+ 'can be found in the main '+color.ORANGE+'Databases Folder'+color.END+color.BOLD\
+ +'\n\nThen try once again\n\n.'+color.END)
+ valid_arg += 1
+
+ elif os.path.isfile(args.databases + '/db_StopFreq/RepEukProts.dmnd') != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' Cannot find the '\
+ 'Diamond formatted '+color.ORANGE+'Representative Eukaryotic Protein Database!\n\n'+color.END+color.BOLD+\
+ 'Ensure that it can be found in the '+color.ORANGE+'db_StopFreq folder'+color.END+\
+ color.BOLD+',\nwhich can be found in the main '+color.ORANGE+'Databases Folder'+\
+ color.END+color.BOLD+'\n\nThen try once again.\n\n'+color.END)
+ valid_arg += 1
+
+ return valid_arg
+
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+
+ Stop_folder = '../'+args.input_file.split('/')[1]+'/StopCodonFreq/'
+
+ if os.path.isdir(Stop_folder) != True:
+ os.system('mkdir '+Stop_folder)
+
+ if os.path.isdir(Stop_folder+'StopCodonFastas') != True:
+ os.system('mkdir '+Stop_folder+'StopCodonFastas')
+
+ if os.path.isdir(Stop_folder+'SpreadSheets') != True:
+ os.system('mkdir '+Stop_folder+'SpreadSheets')
+
+ return Stop_folder+'StopCodonFastas/'
+
+
+###########################################################################################
+###--------------------- Translates Sequences with Each Stop Codon ---------------------###
+###########################################################################################
+
+def prep_translations(args):
+ print (color.BOLD+'\nIdentifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py\n'+color.END)
+
+ intsv = [i for i in open(args.input_file.replace('.fasta','_allOGCleanresults.tsv')).readlines() if i != '\n']
+
+ inFasta = [i for i in SeqIO.parse(args.input_file,'fasta')]
+
+ prot_dict = {}
+
+ for i in intsv:
+# print i
+ prot_dict.setdefault(i.split('\t')[0],[])
+ if int(i.split('\t')[6]) < int(i.split('\t')[7]):
+ prot_dict[i.split('\t')[0]].append('F')
+ if (int(i.split('\t')[6])) < 5:
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[6])-1)
+ else:
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[6])-1)
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[7])+3)
+ if int(i.split('\t')[7]) < int(i.split('\t')[6]):
+ prot_dict[i.split('\t')[0]].append('RC')
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[6]))
+ if (int(i.split('\t')[7])-4) < 5:
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[7]))
+ else:
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[7])-4)
+
+
+ #------------- Prep translation with 'TAA' as the only Stop -------------#
+
+ print (color.BOLD+'\n\nTranslating DNA using'+color.RED+' TAA'+color.END\
+ +color.BOLD+' as the sole STOP codon\n'+color.END)
+
+ for key, value in prot_dict.items():
+ for seq_rec in inFasta:
+ if key in seq_rec.description:
+ stop_pos = 0
+ if prot_dict[key][0] == 'F':
+ temp = seq_rec.seq[prot_dict[key][1]:]
+ temp_prot = str(temp.translate(table=c_uncinata_table))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][1]:prot_dict[key][2]])
+ if prot_dict[key][0] == 'RC':
+ temp = seq_rec.seq[:prot_dict[key][1]].reverse_complement()
+ temp_prot = str(temp.translate(table=c_uncinata_table))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][2]:prot_dict[key][1]].reverse_complement())
+
+
+ #------------- Prep translation with 'TGA' as the only Stop -------------#
+ print (color.BOLD+'\n\nTranslating DNA using'+color.RED+' TGA'+color.END\
+ +color.BOLD+' as the sole STOP codon\n'+color.END)
+
+ for key, value in prot_dict.items():
+ for seq_rec in inFasta:
+ if key in seq_rec.description:
+ stop_pos = 0
+ if prot_dict[key][0] == 'F':
+ temp = seq_rec.seq[prot_dict[key][1]:]
+ temp_prot = str(temp.translate(table=6))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][1]:prot_dict[key][2]])
+ if prot_dict[key][0] == 'RC':
+ temp = seq_rec.seq[:prot_dict[key][1]].reverse_complement()
+ temp_prot = str(temp.translate(table=6))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][2]:prot_dict[key][1]].reverse_complement())
+
+
+ #------------- Prep translation with 'TAG' as the only Stop -------------#
+ print (color.BOLD+'\n\nTranslating DNA using'+color.RED+' TAG'+color.END\
+ +color.BOLD+' as the sole STOP codon\n'+color.END)
+
+
+ for key, value in prot_dict.items():
+ for seq_rec in inFasta:
+ if key in seq_rec.description:
+ stop_pos = 0
+ if prot_dict[key][0] == 'F':
+ temp = seq_rec.seq[prot_dict[key][1]:]
+ temp_prot = str(temp.translate(table=tag_table))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][1]:prot_dict[key][2]])
+ if prot_dict[key][0] == 'RC':
+ temp = seq_rec.seq[:prot_dict[key][1]].reverse_complement()
+ temp_prot = str(temp.translate(table=tag_table))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[key].append(temp[:stop_pos])
+ else:
+ prot_dict[key].append(seq_rec.seq[prot_dict[key][2]:prot_dict[key][1]].reverse_complement())
+
+ #------------ Parsing through data to maintain OG assignments ------------#
+ inOGs = intsv
+ inOGs = [i.split('\t')[0]+';'+i.split('\t')[1][-10:] for i in inOGs]
+ inOGs2 = []
+ for i in inOGs:
+ if 'no_group' not in i.split(';')[1]:
+ inOGs2.append(i)
+ else:
+ inOGs2.append(i.split(';')[0]+';no_group')
+ inOGs2 = list(set(inOGs2))
+
+ #---------------- Write file with 'TAA' is the only Stop ----------------#
+
+ with open(args.input_file.split('.fas')[0]+'_taa_ORF.fasta','w+') as w:
+ print (color.BOLD+'\n\nWriting FASTA files with ORF and Protein sequences with'+color.RED\
+ +' TAA '+color.END+color.BOLD+'as only STOP codon\n'+color.END)
+
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(value[-3]).upper()+'\n')
+
+ with open(args.input_file.split('.fas')[0]+'_taa_ORF.aa.fasta','w+') as w:
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(Seq(str(value[-3])).translate(table=c_uncinata_table)).upper()+'\n')
+
+ #---------------- Write file with 'TGA' is the only Stop ----------------#
+
+ with open(args.input_file.split('.fas')[0]+'_tga_ORF.fasta','w+') as w:
+ print (color.BOLD+'\n\nWriting FASTA files with ORF and Protein sequences with'+color.RED\
+ +' TGA '+color.END+color.BOLD+'as only STOP codon\n'+color.END)
+
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(value[-2]).upper()+'\n')
+
+ with open(args.input_file.split('.fas')[0]+'_tga_ORF.aa.fasta','w+') as w:
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(Seq(str(value[-2])).translate(table=6)).upper()+'\n')
+
+ #---------------- Write file with 'TAG' is the only Stop ----------------#
+
+ with open(args.input_file.split('.fas')[0]+'_tag_ORF.fasta','w+') as w:
+ print (color.BOLD+'\n\nWriting FASTA files with ORF and Protein sequences with'+color.RED\
+ +' TAG '+color.END+color.BOLD+'as only STOP codon\n'+color.END)
+
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(value[-1]).upper()+'\n')
+
+ with open(args.input_file.split('.fas')[0]+'_tag_ORF.aa.fasta','w+') as w:
+ for key, value in prot_dict.items():
+ for j in inOGs2:
+ if key == j.split(';')[0]:
+ if len(prot_dict[key]) < 4:
+ pass
+ else:
+ w.write('>'+key+'_'+j.split(';')[1]+'\n'+str(Seq(str(value[-1])).translate(table=tag_table)).upper()+'\n')
+
+
+###########################################################################################
+###---------- Diamonds the Translations Against a SMALL Euk Protein Database ----------###
+###########################################################################################
+
+def diamond_ProtDB(args, diamond_path):
+ os.system(diamond_path + ' blastp -q ' + args.input_file.split('.fas')[0] + '_tag_ORF.aa.fasta -d ' + args.databases + '/db_StopFreq/RepEukProts.dmnd --evalue 1e-5 --max-target-seqs 1 --threads 60 --outfmt 6 -o ' + args.input_file.split('.fas')[0] + '_tag_ORF.RepEukProts.tsv')
+
+ os.system(diamond_path + ' blastp -q ' + args.input_file.split('.fas')[0] + '_tga_ORF.aa.fasta -d ' + args.databases + '/db_StopFreq/RepEukProts.dmnd --evalue 1e-5 --max-target-seqs 1 --threads 60 --outfmt 6 -o ' + args.input_file.split('.fas')[0] + '_tga_ORF.RepEukProts.tsv')
+
+ os.system(diamond_path + ' blastp -q ' + args.input_file.split('.fas')[0] + '_taa_ORF.aa.fasta -d ' + args.databases + '/db_StopFreq/RepEukProts.dmnd --evalue 1e-5 --max-target-seqs 1 --threads 60 --outfmt 6 -o ' + args.input_file.split('.fas')[0] + '_taa_ORF.RepEukProts.tsv')
+
+
+###########################################################################################
+###-------------------- Manages the search for In-Frame Stop Codons --------------------###
+###########################################################################################
+
+
+def hunt_for_stops(args):
+
+ #------------------------ Open Fasta Files ------------------------#
+ try:
+ TAGinFasta = [i for i in SeqIO.parse(args.input_file.split('.fas')[0]+'_tag_ORF.fasta','fasta') if str(i.seq).endswith('TAG')]
+ print (color.BOLD+'\n\nGathering Sequence information from FASTA and TSV files\n'+color.END)
+
+ except:
+ print (color.BOLD+color.RED+'\n\nMissing Necessary Inputs: Open Script for Usage'\
+ ' Information\n\n'+color.END)
+ sys.exit()
+
+ TGAinFasta = [i for i in SeqIO.parse(args.input_file.split('.fas')[0]+'_tga_ORF.fasta','fasta') if str(i.seq).endswith('TGA')]
+
+ TAAinFasta = [i for i in SeqIO.parse(args.input_file.split('.fas')[0]+'_taa_ORF.fasta','fasta') if str(i.seq).endswith('TAA')]
+
+ ## This section originally ONLY considered sequences WITH OG assignments:
+ ## TAAinFasta = [i for i in TAAinFasta if 'no_group' not in i.description and str(i.seq).endswith('TAA')]
+ ## This has been taken out for now
+
+ #----------------------- Open BLAST Reports -----------------------#
+
+ TAGinTSV = [i for i in open(args.input_file.split('.fas')[0]+'_tag_ORF.RepEukProts.tsv').read().split('\n') if i != '']
+
+ TGAinTSV = [i for i in open(args.input_file.split('.fas')[0]+'_tga_ORF.RepEukProts.tsv').read().split('\n') if i != '']
+
+ TAAinTSV = [i for i in open(args.input_file.split('.fas')[0]+'_taa_ORF.RepEukProts.tsv').read().split('\n') if i != '']
+
+## This section originally ONLY considered sequences WITH OG assignments:
+ ## TAAinTSV = i for i in TAAinTSV if i != ''and 'no_group' not in i.split('\t')[0]]
+ ## This has been taken out for now
+
+
+ #------------ Set-up Genetic Code Specific Dictionaries ------------#
+
+ tag_dict = {}
+ for i in TAGinTSV:
+ tag_dict.setdefault(i.split('\t')[0].replace('_TAG',''),[]).append(int(i.split('\t')[-6]))
+ tag_dict.setdefault(i.split('\t')[0].replace('_TAG',''),[]).append(int(i.split('\t')[-5]))
+
+ tga_dict = {}
+ for i in TGAinTSV:
+ tga_dict.setdefault(i.split('\t')[0].replace('_Ciliate',''),[]).append(int(i.split('\t')[-6]))
+ tga_dict.setdefault(i.split('\t')[0].replace('_Ciliate',''),[]).append(int(i.split('\t')[-5]))
+
+ taa_dict = {}
+ for i in TAAinTSV:
+ taa_dict.setdefault(i.split('\t')[0].replace('_Chilo',''),[]).append(int(i.split('\t')[-6]))
+ taa_dict.setdefault(i.split('\t')[0].replace('_Chilo',''),[]).append(int(i.split('\t')[-5]))
+
+ #-------------- Preparing In-Frame Stop Codon Counts --------------#
+
+# All the data when TGA is the sole stop codon
+ tga_codons = 0
+ tga_data_tag = 0
+ tga_data_tga = 0
+ tga_data_taa = 0
+ tga_seq_count = 0
+
+# All the data when TAG is the sole stop codon
+ tag_codons = 0
+ tag_data_tag = 0
+ tag_data_tga = 0
+ tag_data_taa = 0
+ tag_seq_count = 0
+
+# All the data when TAA is the sole stop codon
+ taa_codons = 0
+ taa_data_tag = 0
+ taa_data_tga = 0
+ taa_data_taa = 0
+ taa_seq_count = 0
+
+# All the data for each stop codon combined
+ tga_inframe = 0
+ tag_inframe = 0
+ taa_inframe = 0
+ total_codons = 0
+ total_seq_counts = len(open(args.input_file).read().split('>'))-1
+
+
+ #-------- Gathering In-frame Stop Codon Density Information --------#
+
+### Collect in-frame stop information for "TAA" and "TAG" when TGA is the ONLY stop
+ print (color.BOLD+'\nCollecting in-frame stop codon information when'+color.RED\
+ +' TGA'+color.END+color.BOLD+' is the only STOP\n'+color.END)
+
+ for i in TGAinFasta:
+ try:
+ if tga_dict[i.description][0] == 1:
+ for n in range((tga_dict[i.description][0]-1),((tga_dict[i.description][1])*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ tga_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ tga_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ tga_data_tga += 1
+ tga_inframe += 1
+ tga_codons += 1
+ total_codons += 1
+ tga_seq_count += 1
+
+ else:
+ for n in range(((tga_dict[i.description][0]-1)*3),((tga_dict[i.description][1])*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ tga_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ tga_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ tga_data_tga += 1
+ tga_inframe += 1
+ tga_codons += 1
+ total_codons += 1
+ tga_seq_count += 1
+ except:
+ pass
+
+### Collect in-frame stop information for "TAA" and "TGA" when TAG is the ONLY stop
+ print (color.BOLD+'\nCollecting in-frame stop codon information when'+color.RED\
+ +' TAG'+color.END+color.BOLD+' is the only STOP\n'+color.END)
+
+ for i in TAGinFasta:
+ try:
+ if tag_dict[i.description][0] == 1:
+ for n in range((tag_dict[i.description][0]-1),((tag_dict[i.description][1])*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ tag_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ tag_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ tag_data_tga += 1
+ tga_inframe += 1
+ tag_codons += 1
+ total_codons += 1
+ tag_seq_count += 1
+
+ else:
+ for n in range(((tag_dict[i.description][0]-1)*3),(tag_dict[i.description][1]*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ tag_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ tag_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ tag_data_tga += 1
+ tga_inframe += 1
+ tag_codons += 1
+ total_codons += 1
+ tag_seq_count += 1
+ except:
+ pass
+
+
+### Collect in-frame stop information for "TGA" and "TAG" when TAA is the ONLY stop
+ print (color.BOLD+'\nCollecting in-frame stop codon information when'+color.RED\
+ +' TAA'+color.END+color.BOLD+' is the only STOP\n'+color.END)
+
+ for i in TAAinFasta:
+ try:
+ if taa_dict[i.description][0] == 1:
+ for n in range((taa_dict[i.description][0]-1),((taa_dict[i.description][1])*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ taa_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ taa_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ taa_data_tga += 1
+ tga_inframe += 1
+ taa_codons += 1
+ total_codons += 1
+ taa_seq_count += 1
+
+ else:
+ for n in range(((taa_dict[i.description][0]-1)*3),(taa_dict[i.description][1]*3)-3,3):
+ if str(i.seq).upper()[n:n+3] == 'TAG':
+ taa_data_tag += 1
+ tag_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TAA':
+ taa_data_taa += 1
+ taa_inframe += 1
+ if str(i.seq).upper()[n:n+3].upper() == 'TGA':
+ taa_data_tga += 1
+ tga_inframe += 1
+ tag_codons += 1
+ total_codons += 1
+ taa_seq_count += 1
+ except:
+ pass
+
+ #-------------- Writing Data Out and Print Statement --------------#
+
+ with open(args.input_file.split('.fas')[0]+'_StopCodonStats.tsv','w+') as w:
+ w.write('Stop Codon\tNumber of Seqs Analyzed\tIn-frame TAG\tIn-frame TGA\tIn-frame TAA\tTotal Codons\tIn-frame TAG density\tIn-frame TGA density\tIn-frame TAA density\n')
+ if tga_codons != 0:
+ w.write('TGA\t'+str(tga_seq_count)+'\t'+str(tga_data_tag)+'\t'+str(tga_data_tga)+'\t'+str(tga_data_taa)+'\t'+str(tga_codons)\
+ +'\t'+"%.2f" % ((float(tga_data_tag)*1000)/float(tga_codons))+'\t'+"%.2f" % ((float(tga_data_tga)*1000)/float(tga_codons))+'\t'\
+ +"%.2f" % ((float(tga_data_taa)*1000)/float(tga_codons))+'\n')
+ else:
+ w.write('TGA\t0\t0\t0\t0\t0\t0\t0\t0\n')
+
+ if tag_codons != 0:
+ w.write('TAG\t'+str(tag_seq_count)+'\t'+str(tag_data_tag)+'\t'+str(tag_data_tga)+'\t'+str(tag_data_taa)+'\t'+str(tag_codons)\
+ +'\t'+"%.2f" % ((float(tag_data_tag)*1000)/float(tag_codons))+'\t'+"%.2f" % ((float(tag_data_tga)*1000)/float(tag_codons))+'\t'\
+ +"%.2f" % ((float(tag_data_taa)*1000)/float(tag_codons))+'\n')
+ else:
+ w.write('TAG\t0\t0\t0\t0\t0\t0\t0\t0\n')
+ if taa_codons != 0:
+ w.write('TAA\t'+str(taa_seq_count)+'\t'+str(taa_data_tag)+'\t'+str(taa_data_tga)+'\t'+str(taa_data_taa)+'\t'+str(taa_codons)\
+ +'\t'+"%.2f" % ((float(taa_data_tag)*1000)/float(taa_codons))+'\t'+"%.2f" % ((float(taa_data_tga)*1000)/float(taa_codons))+'\t'\
+ +"%.2f" % ((float(taa_data_taa)*1000)/float(taa_codons))+'\n')
+ else:
+ w.write('TAA\t0\t0\t0\t0\t0\t0\t0\t0\n')
+
+ w.write('\n \n')
+ w.write('Summary\t'+str(tga_seq_count+tag_seq_count+taa_seq_count)+'\t'+str(tag_inframe)+'\t'+str(tga_inframe)+'\t'+str(taa_inframe)\
+ +'\t'+str(total_codons)+'\t'+"%.2f" % ((float(tag_inframe)*1000)/float(total_codons))+'\t'+"%.2f" % ((float(tga_inframe)*1000)/float(total_codons))\
+ +'\t'+"%.2f" % ((float(taa_inframe)*1000)/float(total_codons))+'\n')
+ w.write('\nTotal Seqs in Fasta\t'+str(total_seq_counts))
+
+# print color.BOLD + color.BLUE + '\nSummary\t'+str(tag_inframe)+'\t'+str(tga_inframe)+'\t'+str(taa_inframe)+'\t'+str(total_codons)+'\t'+"%.2f" % ((float(tag_inframe)*1000)/float(total_codons))+'\t'\
+# +"%.2f" % ((float(tga_inframe)*1000)/float(total_codons))+'\t'+"%.2f" % ((float(taa_inframe)*1000)/float(total_codons))+'\n\n'\
+# + str(tag_seq_count) + '\t' + str(tga_seq_count) + '\t' + str(taa_seq_count) + color.END
+
+
+##########################################################################################
+###--------------------- Cleans up the Folder and Moves Final Files -------------------###
+##########################################################################################
+
+def clean_up(args):
+ if os.path.isdir('/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq') != True:
+ os.system('mkdir ' + '/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq/')
+ else:
+ pass
+
+ os.system('mkdir ' + '/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq/StopCodonFastas/')
+ os.system('mkdir ' + '/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq/SpreadSheets/')
+ os.system('mv ' + args.input_file.split('.fas')[0]+'_t*_ORF.*fasta ' + '/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq/StopCodonFastas/')
+ os.system('mv ' + args.input_file.split('.fas')[0]+'_t*Prots.tsv ' + '/'.join(args.input_file.split('/')[:-1]) + '/StopCodonFreq/SpreadSheets/')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ home_folder = '/'.join(args.input_file.split('/')[:-1])
+
+ print (color.BOLD+'\nLook for '+color.DARKCYAN+args.input_file.split('/')[-1]\
+ .replace('.fasta','_StopCodonStats.tsv')+color.END+color.BOLD+' in the '+home_folder\
+ +' Folder\n\n' + color.END)
+
+ print (color.BOLD+'Next Script is: '+color.GREEN+'5_GCodeTranslate.py\n\n'+ color.END)
+
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ diamond_path = check_diamond_path()
+
+ args = check_args()
+
+ prep_translations(args)
+
+ diamond_ProtDB(args, diamond_path)
+
+ hunt_for_stops(args)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
+
+
+#----------------------------------------- NOTES -----------------------------------------#
+#
+# This script is designed to HELP you make an informed decision about the genetic code being
+# used by your particular organism. Be aware that it will be limited by the quality of the
+# data given to it!
+#
+# You will need:
+#
+# Diamond, BioPython, AND the output from '3_CountOGSDiamond.py'
+#
+# If you are not using the Author's database, update your database name(s) in lines: 345-360
+#
+# katzlab$ python StopFrequency.py YourFastaFile.fasta
+#
+#
+#------------------------------- Interpretation of Results -------------------------------#
+#
+# FORMATTED BELOW WITH TEXTWRANGLER...
+#
+# Example output using CILIATE (TGA) genetic Code (NOTE THE In-Frame Densities):
+#
+# Stop Codon Number_of_Seqs_Analyzed In-frame TAG In-frame TGA In-frame TAA Total Codons In-frame TAG density In-frame TGA density In-frame TAA density
+# TGA 341 14 0 22 113156 1.2 0 0.92
+# TAG 424 0 0 34 140085 0 0 0.78
+# TAA 205 14 0 0 16714 0.84 0 0
+# Summary 970 28 0 56 269955 2.04 0 1.7
+#
+# VALUES in summary line (OR SUM of Density) that are > 1.5 likely indicate that the STOP
+# codon has been reassigned... in the case above, TAG and TAA look like they have been
+# reassigned.
+#
+#
+# Example output using UNIVERSAL genetic Code (NOTE THE In-Frame Densities):
+#
+# Stop Codon Number_of_Seqs_Analyzed In-frame TAG In-frame TGA In-frame TAA Total Codons In-frame TAG density In-frame TGA density In-frame TAA density
+# TGA 341 1 0 2 113156 0.2 0 0.05
+# TAG 424 0 2 4 140085 0 0 0.08
+# TAA 205 1 0 0 16714 0.04 0 0
+# Summary 970 2 2 6 269955 0.15 0 0.06
+#
+# VALUES in summary line (OR SUM of Density) that are > 0.5 likely indicate that the STOP
+# codon still acts as STOP... in the case above, TAG, TGA and TAA look like they still behave
+# as a stop codon.
+#
+# THIS IS A ROUGH GUIDE FOR INTERPRETING THE RESULTS!!!! BE VERY VERY WARY! NUMBER OF TOTAL
+# SEQUENCES AND TOTAL CODONS OBSERVED ARE IMPORTANT (TOO FEW AND ANY INTERPRETATION IS DEVOID
+# OF ANY MEANING).
diff --git a/PTL1/Transcriptomes/Scripts/5_GCodeTranslate.py b/PTL1/Transcriptomes/Scripts/5_GCodeTranslate.py
new file mode 100644
index 0000000..4ea3c08
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/5_GCodeTranslate.py
@@ -0,0 +1,770 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 20_09_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 5_GCodeTranslate.py --help
+
+
+##########################################################################################
+## This script is intended to aid in identifying the genetic code of the data given ##
+## ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with 1_ContigFiltStats.py ##
+## 3. Removed SSU/LSU sequences from your Fasta File ##
+## 4. Classified your sequences as Strongly Prokaryotic/Eukaryotic or Undetermined ##
+## 5. Classified the Non-Strongly Prokaryotic sequences into OGs ##
+## 6. You either know (or have inferred) the genetic code of the organism ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 6_FilterPatials.py (in FinalizeTranscripts Folder) ##
+## ##
+##########################################################################################
+
+import argparse, os, re, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.Data.CodonTable import CodonTable
+
+
+#-------------------------- Set-up Codon Tables (Genetic Codes) --------------------------#
+
+blepharisma_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAA','TAG'])
+
+condylostoma_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'Q', 'TAG': 'Q',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'W', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = [''])
+
+c_uncinata_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAG': 'Q',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'Q', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAA'])
+
+euplotes_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'C', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAA','TAG'])
+
+myrionecta_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'Y', 'TAG': 'Y',
+ 'TGT': 'C', 'TGC': 'C', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TGA'])
+
+no_stop_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'X', 'TAG': 'X',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'X', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = [''])
+
+peritrich_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'E', 'TAG': 'E',
+ 'TGT': 'C', 'TGC': 'C', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TGA'])
+
+tag_table = CodonTable(forward_table={
+ 'TTT': 'F', 'TTC': 'F', 'TTA': 'L', 'TTG': 'L',
+ 'TCT': 'S', 'TCC': 'S', 'TCA': 'S', 'TCG': 'S',
+ 'TAT': 'Y', 'TAC': 'Y', 'TAA': 'Q',
+ 'TGT': 'C', 'TGC': 'C', 'TGA': 'Q', 'TGG': 'W',
+ 'CTT': 'L', 'CTC': 'L', 'CTA': 'L', 'CTG': 'L',
+ 'CCT': 'P', 'CCC': 'P', 'CCA': 'P', 'CCG': 'P',
+ 'CAT': 'H', 'CAC': 'H', 'CAA': 'Q', 'CAG': 'Q',
+ 'CGT': 'R', 'CGC': 'R', 'CGA': 'R', 'CGG': 'R',
+ 'ATT': 'I', 'ATC': 'I', 'ATA': 'I', 'ATG': 'M',
+ 'ACT': 'T', 'ACC': 'T', 'ACA': 'T', 'ACG': 'T',
+ 'AAT': 'N', 'AAC': 'N', 'AAA': 'K', 'AAG': 'K',
+ 'AGT': 'S', 'AGC': 'S', 'AGA': 'R', 'AGG': 'R',
+ 'GTT': 'V', 'GTC': 'V', 'GTA': 'V', 'GTG': 'V',
+ 'GCT': 'A', 'GCC': 'A', 'GCA': 'A', 'GCG': 'A',
+ 'GAT': 'D', 'GAC': 'D', 'GAA': 'E', 'GAG': 'E',
+ 'GGT': 'G', 'GGC': 'G', 'GGA': 'G', 'GGG': 'G'},
+ start_codons = [ 'ATG'],
+ stop_codons = ['TAG'])
+
+
+#------------------------------ Colors For Print Statements ------------------------------#
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ PURPLE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###------------------------- Checks the Command Line Arguments -------------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD + '\n\nThis script will '+color.RED+'Translate '+color.END+color.BOLD+'a '\
+ 'given Fasta file of CDS\nsequences using a given'+color.PURPLE+' Genetic Code.'+color.END+\
+ color.BOLD+usage_msg(), usage=SUPPRESS, formatter_class=RawTextHelpFormatter)
+
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+' Fasta file with CDSs\n'+color.END)
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+
+ optional_arg_group.add_argument('--genetic_code','-g', action='store', default='universal',
+ help=color.BOLD+color.GREEN+' Genetic code to use for translation\n (default = '\
+ '"universal")\n'+color.END)
+
+ optional_arg_group.add_argument('--no_RP','-no_RP', action='store_true',
+ help=color.BOLD+color.GREEN+' Allows files to "skip" the removal\n of Partial Transcripts\n'\
+ +color.END)
+
+ optional_arg_group.add_argument('--list_codes','-codes', action='store_true',
+ help=color.BOLD+color.GREEN+' Lists supported genetic codes\n'+color.END)
+
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Prints author contact information\n'+color.END)
+
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ sys.exit()
+
+ ### Adding in names to 'arg' class for more easy use throughout the script
+ args.ntd_out = args.input_file.split('.fas')[0]+'_'+args.genetic_code.title()+'_NTD.ORF.fasta'
+ args.aa_out = args.input_file.split('.fas')[0]+'_'+args.genetic_code.title()+'_AA.ORF.fasta'
+ args.tsv_out = args.input_file.split('.fas')[0]+'_'+args.genetic_code.title()+'_allOGCleanresults.tsv'
+
+ args.home_folder = '/'.join(args.input_file.split('/')[:-1])
+ args.Diamond_Folder = args.home_folder+'/DiamondOG'
+ args.StopFreq = args.home_folder+'/StopCodonFreq'
+ args.all_output_folder = '/'.join(args.input_file.split('/')[:-2]) + '/'
+
+ args.tsv_file = args.input_file.split('.fas')[0]+ '_allOGCleanresults.tsv'
+
+
+
+
+
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 5g_GCodeTranslate.py'\
+ ' --input_file ../Stentor_coeruleus.WGS.CDS.Prep/Stentor_coeruleus.WGS.CDS.Renamed.fasta'\
+ ' --genetic_code Universal'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ supported_gcodes_names = ['bleph','blepharisma','chilo','chilodonella','condy',\
+ 'condylostoma','none','eup','euplotes','peritrich','vorticella','ciliate','universal',\
+ 'taa','tag','tga','mesodinium']
+
+ supported_gcodes_list = ['Blepharisma\t(TGA = W)','Chilodonella\t(TAG/TGA = Q)','Ciliate\t\t(TAR = Q)',\
+ 'Condylostoma\t(TAR = Q, TGA = W)','Euplotes\t(TGA = C)','Peritrich\t(TAR = E)','None\t\t(TGA/TAG/TAA = X)',\
+ 'Universal\t(TGA/TAG/TAA = STOP)','TAA\t\t(TAG/TGA = Q)', 'TAG\t\t(TRA = Q)', 'TGA\t\t(TAR = Q)']
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+
+ if args.genetic_code != None and args.genetic_code.lower() not in supported_gcodes_names:
+ print (color.BOLD+color.RED+'\nProvided genetic code is currently unsupported.\n\n'\
+ 'If you have a new genetic code, please contact the author (with some evidence).\n\n'\
+ 'Otherwise, use one of the currently supported genetic codes.\n'+color.END)
+ print (color.BOLD+color.ORANGE+'\n'.join(supported_gcodes_list)+'\n\n'+color.END)
+ print (author)
+ valid_arg += 1
+ else:
+ if args.list_codes == True:
+ print (color.BOLD+color.RED+'\nThese are the currently supported genetic codes.\n'+color.END)
+ print (color.BOLD+color.ORANGE+'\n'.join(supported_gcodes_list)+'\n\n'+color.END)
+ valid_arg += 1
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.input_file != None:
+ if os.path.isfile(args.input_file) != False:
+ if args.input_file.split('/')[-1] not in os.listdir('/'.join(args.input_file.split('/')[:-1])):
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+ elif args.input_file.endswith('WTA_EPU.Renamed.fasta') != True:
+ print (color.BOLD+'\n\nInvalid Fasta File! Only Fasta Files that were processed'\
+ ' with '+color.GREEN+'3_CountOGsDiamond.py '+color.END+color.BOLD+'are valid\n\n'\
+ 'However, to bypass that issue, Fasta Files MUST end with '+color.CYAN+\
+ '"WTA_EPU.Renamed.fasta"\n\n'+color.END)
+ valid_arg += 1
+ else:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Fasta file '\
+ '('+color.DARKCYAN+args.input_file.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_arg += 1
+
+ return valid_arg
+
+
+###########################################################################################
+###--------------------------- Does the Inital Folder Prep -----------------------------###
+###########################################################################################
+
+def prep_folders(args):
+
+ OG_folder = '/'.join(args.input_file.split('/')[:-1]) + '/DiamondOG/'
+
+ if os.path.isdir(OG_folder) != True:
+ os.system('mkdir '+OG_folder)
+
+ if os.path.isdir(args.all_output_folder + 'TranslatedTranscriptomes') != True:
+ os.system('mkdir ' + args.all_output_folder + 'TranslatedTranscriptomes')
+
+
+
+##########################################################################################
+###---------------- Scans 5-Prime End of Transcript for In-Frame "ATG" ----------------###
+##########################################################################################
+
+def check_new_start_new(some_seq, low_lim, upper_lim, old_start, codon_table):
+
+ ## Looks for in-frame STOP codons in the UTR of the transcript
+ prime5 = str(Seq(some_seq[low_lim:upper_lim]).translate(table=codon_table)).replace('*','x')
+ in_frame_stops = [stops.start() for stops in re.finditer('x',prime5)]
+
+ ## Looks for in-frame START codons in the UTR of the transcript
+ in_frame_starts = [starts.start() for starts in re.finditer('M',prime5)]
+
+ ## Checks that there are NO in-frame STOP codons between the possible "new" START codon
+ ## and the aligned portion of the transcript -- THIS is double checked!
+ if len(in_frame_starts) != 0:
+ if len(in_frame_stops) != 0:
+ if in_frame_stops[-1] < in_frame_starts[-1]:
+ new_start = low_lim+in_frame_starts[-1]*3
+ else:
+ new_start = old_start
+ else:
+ new_start = low_lim+in_frame_starts[-1]*3
+ else:
+ new_start = old_start
+
+ ## Skips the double-checking if there are no GOOD potential START codons
+ if new_start == old_start:
+ updated_start = old_start
+
+ else:
+ ## Double checks that there are NO IN-FRAME stop codons between the NEW-SUGGESTED Start
+ ## position and the OLD-SUPPORTED stop position!
+ between_new_old_start = str(Seq(some_seq[new_start:old_start]).translate(table=1)).replace('*','x')
+ in_frame_stops_check = [stops.start() for stops in re.finditer('x',between_new_old_start)]
+ in_frame_starts_check = [starts.start() for starts in re.finditer('M',between_new_old_start)]
+ if len(in_frame_starts_check) != 0:
+ if len(in_frame_stops_check) != 0:
+ if in_frame_stops_check[-1] < in_frame_starts_check[-1]:
+ updated_start = new_start+in_frame_starts_check[-1]*3
+ else:
+ updated_start = old_start
+ else:
+ updated_start = new_start
+ else:
+ updated_start = new_start
+
+ return updated_start
+
+
+##########################################################################################
+###--------------- Extracts the ORF from the Fasta File and SpreadSheet ---------------###
+##########################################################################################
+
+def extract_ORF(prot_dict, codon_table, args):
+
+ print (color.BOLD+'\n\nExtracting '+color.PURPLE+'ORFs'+color.END+color.BOLD+' from'\
+ ' the transcriptomic data-set\n\n'+color.END)
+
+ for k, v in prot_dict.items():
+
+ ## Attempting to find the most-likely START (ATG) position in the transcript (tricky)
+ ## Skips this if the initial Methionine (ATG) is likely present
+ ## (e.g. the alignment position of the protein = '1')
+ prot_start = int(v[3].split('..')[0])
+ old_start = v[1]
+ if prot_start != 1:
+ min_dist, max_dist = round_down_three(prot_start)
+ min_start = old_start-min_dist
+ max_start = old_start-max_dist
+ if min_start < 0:
+ min_start = old_start
+ if max_start < 0:
+ max_start = min_start%3
+# print k+'\tOld_start\t'+str(old_start)+'\tMin_Dist/Start\t'+str(min_dist)+'/'+str(min_start)+'\tMax_Dist/Start\t'+str(max_dist)+'/'+str(max_start)+'\n'
+ updated_start = check_new_start_new(v[-1], max_start, min_start, old_start, codon_table)
+ else:
+ updated_start = old_start
+ temp = prot_dict[k][-1][updated_start:]
+
+ ## Uses the given genetic code to identify the stop position of the ORF
+ temp_prot = str(Seq(temp).translate(table=codon_table))
+ if '*' in temp_prot:
+ stop_pos = (temp_prot.index('*')+1)*3
+ prot_dict[k].append(temp[:stop_pos])
+ else:
+ stop_pos = prot_dict[k][2] - prot_dict[k][1]
+ prot_dict[k].append(temp[:stop_pos])
+
+ ## Awkward_list is populated with unexpectedly SHORT ORFs!
+ ## Reasons for being short include:
+ # An error Xyrus introduced
+ # Not as great genetic code decision (in-frame stop)
+ # Crummy sequence/assembly quality (false in-frame stop codons)
+
+ awkward_list = []
+ look_good = []
+
+ for k, v in prot_dict.items():
+ expected_min = len(v[-2][v[1]:v[2]])-1
+ if len(v[-1]) < expected_min:
+ awkward_list.append(k)
+ else:
+ look_good.append(k)
+
+ if len(awkward_list) != 0:
+ with open('UnexpexctedShortStuffBlameXyrus.txt','w+') as x:
+ for entry in awkward_list:
+ x.write(entry+'\n')
+ else:
+ pass
+
+ print (color.BOLD+'\n\nTranslating '+color.PURPLE+'ORFs'+color.END+color.BOLD+' from'\
+ ' using the '+color.DARKCYAN+args.genetic_code.title()+' genetic code'+color.END)
+
+ for k, v in prot_dict.items():
+ prot_dict[k].append(str(Seq(v[-1]).translate(table=codon_table)).rstrip('*'))
+
+ return prot_dict
+
+##########################################################################################
+###------------ Grabs the Coding Coordinates from the OG-BLAST SpreadSheet ------------###
+##########################################################################################
+
+def prep_translations(args):
+
+ print (color.BOLD+'\n\nGrabbing useful info from the '+color.ORANGE+args.input_file\
+ .split('/')[-1]+color.END+color.BOLD+' Fasta File\nand from the '+color.ORANGE+args.tsv_file\
+ .split('/')[-1]+color.END+color.BOLD+' OG-Assignment Spreadsheet'+color.END)
+
+ inTSV = ['\t'.join(i.rstrip('\n').split('\t')[:-1]) for i in open(args.tsv_file).readlines() if i != '\n']
+ inFasta = [i for i in SeqIO.parse(args.input_file,'fasta')]
+
+ # ORF identification step here, uses the 'allOGCleanresults.tsv file to identify the ORF
+ prot_dict = {}
+
+ # Special scenario! Only for when the genetic code is not particularly useful ...
+ if args.genetic_code.lower() == 'none' or args.genetic_code.lower() == 'condylostoma' or args.genetic_code.lower() == 'condy':
+ for i in inTSV:
+ prot_dict.setdefault(i.split('\t')[0],[])
+ if int(i.split('\t')[6]) < int(i.split('\t')[7]):
+ ## Saves the Transcript Orientation (Coding vs. Template Strand)
+ prot_dict[i.split('\t')[0]].append('F')
+ ## Collects initial Start and Stop positions from the BLAST alignment
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[6])-1)
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[7])+3)
+ ## Implied Amino Acid alignment positions (e.g. does the alignment start at the 1st Methionine?)
+ prot_dict[i.split('\t')[0]].append('..'.join(i.split('\t')[-4:-2]))
+
+ if int(i.split('\t')[7]) < int(i.split('\t')[6]):
+ ## Saves the Transcript Orientation (Coding vs. Template Strand)
+ prot_dict[i.split('\t')[0]].append('RC')
+ ## Collects initial Start and Stop positions from the BLAST alignment
+ prot_dict[i.split('\t')[0]].append(int(i.split('_Len')[1].split('_')[0])-int(i.split('\t')[6]))
+ prot_dict[i.split('\t')[0]].append(int(i.split('_Len')[1].split('_')[0])-int(i.split('\t')[7])+1)
+ ## Implied Amino Acid alignment positions (e.g. does the alignment start at the 1st Methionine?)
+ prot_dict[i.split('\t')[0]].append('..'.join(i.split('\t')[-4:-2]))
+
+ ## Makes sure that the dictionary has the transcript in the correct orientation
+ for i in inFasta:
+ if i.description in prot_dict.keys():
+ if 'RC' == prot_dict[i.description][0]:
+ prot_dict[i.description].append(str(i.seq.reverse_complement()))
+ else:
+ prot_dict[i.description].append(str(i.seq))
+
+ else:
+ for i in inTSV:
+ prot_dict.setdefault(i.split('\t')[0],[])
+ if int(i.split('\t')[6]) < int(i.split('\t')[7]):
+ ## Saves the Transcript Orientation (Coding vs. Template Strand)
+ prot_dict[i.split('\t')[0]].append('F')
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[6])-1)
+ prot_dict[i.split('\t')[0]].append(int(i.split('\t')[7])+3)
+ ## Implied Amino Acid alignment positions (e.g. does the alignment start at the 1st Methionine?)
+ prot_dict[i.split('\t')[0]].append('..'.join(i.split('\t')[-4:-2]))
+ if int(i.split('\t')[7]) < int(i.split('\t')[6]):
+ ## Saves the Transcript Orientation (Coding vs. Template Strand)
+ prot_dict[i.split('\t')[0]].append('RC')
+ ## Collects initial Start and Stop positions from the BLAST alignment (but in the "correct" orientation)
+ prot_dict[i.split('\t')[0]].append(int(i.split('_Len')[1].split('_')[0])-int(i.split('\t')[6]))
+ prot_dict[i.split('\t')[0]].append(int(i.split('_Len')[1].split('_')[0])-int(i.split('\t')[7])+1)
+ ## Implied Amino Acid alignment positions (e.g. does the alignment start at the 1st Methionine?)
+ prot_dict[i.split('\t')[0]].append('..'.join(i.split('\t')[-4:-2]))
+
+ ## Makes sure that the dictionary has the transcript in the correct orientation
+ for i in inFasta:
+ if i.description in prot_dict.keys():
+ if 'RC' == prot_dict[i.description][0]:
+ prot_dict[i.description].append(str(i.seq.reverse_complement()))
+ else:
+ prot_dict[i.description].append(str(i.seq))
+
+ return prot_dict
+
+
+##########################################################################################
+###------------------------ Rounds Down Values to Nearest "3" -------------------------###
+##########################################################################################
+
+def round_down_three(num):
+ min_val = int(num*3*.5)-int(num*3*.5)%3
+ max_val = int(num*6)-int(num*6)%3
+ return min_val, max_val
+
+
+##########################################################################################
+###--------------------- Makes Translation Steps (Later) Easier -----------------------###
+##########################################################################################
+
+def standardize_gcode(given_code):
+ if given_code == 'ciliate' or given_code == 'tga':
+ codon_table = 6
+ elif given_code == 'chilodonella' or given_code == 'chilo' or given_code == 'taa':
+ codon_table = c_uncinata_table
+ elif given_code == 'blepharisma' or given_code == 'bleph':
+ codon_table = blepharisma_table
+ elif given_code == 'euplotes' or given_code == 'eup':
+ codon_table = euplotes_table
+ elif given_code == 'myrionecta' or given_code == 'mesodinium':
+ codon_table = myrionecta_table
+ elif given_code == 'peritrich' or given_code == 'vorticella':
+ codon_table = peritrich_table
+ elif given_code == 'none':
+ codon_table = no_stop_table
+ elif given_code == 'condylostoma' or given_code == 'condy':
+ codon_table = condylostoma_table
+ elif given_code == 'tag':
+ codon_table = tag_table
+ elif given_code == 'universal':
+ codon_table = 1
+ else:
+ print (color.BOLD+color.RED+'\n\nNo valid genetic code provided!\n\n'+color.END+\
+ color.BOLD+'Using the "Universal" genetic code (by default)\n\nPlease check that the'\
+ ' code you wish to use is supported:'+color.CYAN+'\n\npython 5_GCodeTranslate.py'\
+ ' -list_codes\n\n'+color.END)
+ codon_table = 1
+
+ return codon_table
+
+
+###########################################################################################
+###------------------ Updates Spreadsheet with Updated Contig Names --------------------###
+###########################################################################################
+
+def update_spreadsheet(args, updated_spreadsheet_dict):
+ if os.path.isdir(args.home_folder + '/DiamondOG/') != True:
+ os.system(args.home_folder + '/DiamondOG/')
+ else:
+ pass
+
+ inTSV = [line.rstrip('\n') for line in open(args.tsv_file).readlines() if line != '\n' and line.split('\t')[0] in updated_spreadsheet_dict.keys()]
+
+ updatedTSV = [updated_spreadsheet_dict[line.split('\t')[0]]+'\t'+'\t'.join(line.split('\t')[1:]) for line in inTSV]
+
+ with open(args.tsv_out,'w+') as w:
+ w.write('\n'.join(updatedTSV))
+
+
+###########################################################################################
+###-------------------- Updates Log With OG Assignment Information ---------------------###
+###########################################################################################
+
+def update_log(filename, codon_table):
+
+ if os.path.isdir('../PostAssembly_Logs/') != True:
+ os.system('mkdir ../PostAssembly_Logs/')
+ else:
+ pass
+
+ ntd_ORF = [i for i in SeqIO.parse(filename.split('.fas')[0]+'_'+gcode.title()+'_ORF.fasta','fasta')]
+ aa_ORF = [i for i in SeqIO.parse(filename.split('.fas')[0]+'_'+gcode.title()+'_ORF.aa.fasta','fasta')]
+
+ min_ntd_ORF = str(min([len(i.seq) for i in ntd_ORF]))
+ max_ntd_ORF = str(max([len(i.seq) for i in ntd_ORF]))
+ avg_ntd_ORF = '%.2f' % (sum([len(i.seq) for i in ntd_ORF])/float(len(ntd_ORF)))
+
+ min_aa_ORF = str(min([len(i.seq) for i in aa_ORF]))
+ max_aa_ORF = str(max([len(i.seq) for i in aa_ORF]))
+ avg_aa_ORF = '%.2f' % (sum([len(i.seq) for i in aa_ORF])/float(len(aa_ORF)))
+
+ for Logname in os.listdir(os.curdir+'./PostAssembly_Logs/'):
+ if Logname.startswith(filename.split('/')[2].split('_WTA')[0]) and Logname.endswith('Log.txt'):
+ with open('../PostAssembly_Logs/'+Logname,'a') as LogFile:
+ LogFile.write('Nucleotide ORFs\t'+str(len(ntd_ORF))+'\tn/a\tn/a\n')
+ LogFile.write('Nucleotide ORF Lengths\t'+avg_ntd_ORF+'\t'+min_ntd_ORF+'\t'+max_ntd_ORF+'\n')
+ LogFile.write('Protein ORFs\t'+str(len(aa_ORF))+'\tn/a\tn/a\n')
+ LogFile.write('Protein ORF Lengths\t'+avg_aa_ORF+'\t'+min_aa_ORF+'\t'+max_aa_ORF+'\n')
+
+
+##########################################################################################
+###----------------------- Write File with Provided Genetic Code ----------------------###
+##########################################################################################
+
+def write_data_out(prot_dict, codon_table, args):
+
+ update_spreadsheet_dict = {}
+
+ #The code below only works if rnaspades was used; constrained by addition of script 6b
+ for k, v in prot_dict.items():
+ #if 'Cov' in k:
+ new_name = k.split('_Len')[0]+'_Len'+str(len(v[-2]))+'_'+'_'.join(k.split('_')[-3:])
+ #update_spreadsheet_dict[k] = new_name
+ update_spreadsheet_dict[k] = k
+ #else:
+ #new_name = k.split('_Len')[0]+'_Len'+str(len(v[-2]))+'_'+'_'.join(k.split('_')[-2:])
+ #update_spreadsheet_dict[k] = new_name
+ #update_spreadsheet_dict[k] = k
+
+ with open(args.ntd_out,'w+') as w:
+ print (color.BOLD+'\n\nWriting FASTA file with '+color.PURPLE+'ORF'+color.END+color.BOLD\
+ +' sequences using the '+color.DARKCYAN+args.genetic_code.title()+' genetic code'+color.END)
+
+ for k, v in prot_dict.items():
+ w.write('>'+update_spreadsheet_dict[k]+'\n'+str(v[-2])+'\n')
+
+ with open(args.aa_out, 'w+') as w:
+ print (color.BOLD+'\n\nWriting FASTA file with '+color.PURPLE+'Translated ORF'+color.END+color.BOLD\
+ +' sequences using the '+color.DARKCYAN+args.genetic_code.title()+' genetic code'+color.END)
+
+ for k, v in prot_dict.items():
+ w.write('>'+update_spreadsheet_dict[k]+'\n'+str(v[-1])+'\n')
+
+ return update_spreadsheet_dict
+
+
+##########################################################################################
+###--------------------- Cleans up the Folder and Moves Final Files -------------------###
+##########################################################################################
+
+def clean_up(args):
+
+ if args.input_file.split('.fas')[0].split('/')[-1] + '_StopCodonStats.tsv' in os.listdir(args.home_folder):
+ os.system('mv ' + args.input_file.split('.fas')[0] + '_StopCodonStats.tsv ' + args.StopFreq)
+
+ os.system('mv '+args.tsv_file+' '+args.Diamond_Folder)
+ os.system('mv '+args.input_file+' '+args.Diamond_Folder)
+
+ if args.no_RP == True:
+ if os.path.isdir(args.all_output_folder + 'ToRename/') != True:
+ os.system('mkdir ' + args.all_output_folder + 'ToRename/')
+
+ os.system('cp ' + args.ntd_out + ' ' + args.all_output_folder + 'ToRename/')
+ os.system('cp ' + args.aa_out + ' ' + args.all_output_folder + 'ToRename/')
+ os.system('cp ' + args.tsv_out + ' ' + args.all_output_folder + 'ToRename/')
+
+ else:
+ os.system('cp ' + args.tsv_out + ' ' + args.all_output_folder)
+ os.system('cp ' + args.ntd_out + ' ' + args.all_output_folder)
+ os.system('cp ' + args.aa_out + ' ' + args.all_output_folder)
+
+ os.system('mv ' + args.home_folder + ' ' + args.all_output_folder + 'TranslatedTranscriptomes')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ print (color.BOLD+'\n\nLook for '+color.DARKCYAN+args.ntd_out.split('/')[-1]+color.END+\
+ color.BOLD+',\n'+color.DARKCYAN+args.aa_out.split('/')[-1]+color.END+color.BOLD+', and\n'\
+ +color.DARKCYAN+args.tsv_out.split('/')[-1]+color.END+color.BOLD+',\nwhich are in the '+\
+ color.ORANGE+args.home_folder.split('/')[-1]+' Folder'+color.END)
+
+ if args.no_RP == True:
+ print(color.BOLD+'\n\nNext Script is: '+color.GREEN+'7_FinalRename.py'+color.END+color.BOLD+\
+ ' in the '+color.PURPLE+'RemovePartials Folder'+color.END+color.BOLD+'\nwith a copy of'\
+ ' the outputs of this script!'+color.END)
+ print(color.BOLD+'\n\nRemember that you have chosen '+color.RED+'NOT '+color.END+color.BOLD+\
+ 'to remove partials\nand are skipping to the renaming step!\n\n'+color.END)
+
+ else:
+ print(color.BOLD+'\n\nNext Script is: '+color.GREEN+'6_FilterPartials.py'+color.END+color.BOLD+\
+ ' in the '+color.PURPLE+'FinalizeTranscripts Folder'+color.END+color.BOLD+'\nwith a copy of'\
+ ' the outputs of this script!\n\n'+color.END)
+
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ args = check_args()
+
+ prep_folders(args)
+
+ codon_table = standardize_gcode(args.genetic_code.lower())
+
+ prot_dict_Prepped = prep_translations(args)
+
+ prot_dict_Final = extract_ORF(prot_dict_Prepped, codon_table, args)
+
+ new_spreadsheet_names = write_data_out(prot_dict_Final, codon_table, args)
+
+ update_spreadsheet(args, new_spreadsheet_names)
+
+# update_log(fasta_file, gcode)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
\ No newline at end of file
diff --git a/PTL1/Transcriptomes/Scripts/6_FilterPartials.py b/PTL1/Transcriptomes/Scripts/6_FilterPartials.py
new file mode 100644
index 0000000..33cab5e
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/6_FilterPartials.py
@@ -0,0 +1,652 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 2020-11-29
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com; xyrus.maurer-alcala@izb.unibe.ch
+##__Usage__: python 6_FilterPartials.py --help
+
+
+##################################################################################################
+## This script is intended to remove incomplete transcripts that have a more complete mate ##
+## ##
+## Prior to running this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Removed SSU/LSU sequences from your Fasta File ##
+## 4. Classified your sequences as Strongly Prokaryotic/Eukaryotic or Undetermined ##
+## 5. Classified the Non-Strongly Prokaryotic sequences into OGs ##
+## 6. You either know (or have inferred) the genetic code of the organism ##
+## 7. You have translated the sequences and checked for the data in the RemovePartials folder ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## 7_FinalRename.py ##
+## ##
+##################################################################################################
+
+from Bio import SeqIO
+from Bio.Seq import Seq
+from statistics import mean
+
+from distutils import spawn
+import argparse, os, sys, time, re
+from argparse import RawTextHelpFormatter,SUPPRESS
+
+
+
+#------------------------------ Colors For Print Statements ------------------------------#
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###---------------------------- UPDATE DIAMOND PATH BELOW! -----------------------------###
+###########################################################################################
+ ## IF Diamond is IN YOUR PATH then no updating is needed...
+
+def check_diamond_path():
+
+ diamond_path = ''
+
+ if diamond_path == '':
+ diamond_path = spawn.find_executable("diamond")
+ #diamond_path = '/path/to/diamond'
+ else:
+ pass
+
+ if diamond_path == None:
+ print (color.BOLD + '\n\nPlease open this script and check that you have included'\
+ +' the PATH to the'+color.BLUE+' "diamond" '+color.END+color.BOLD+'executable.\n\n'+color.END)
+ print (color.BOLD+color.BLUE+'LOOK FOR:\n\n'+color.RED\
+ +'#------------------------------ UPDATE DIAMOND PATH BELOW! -------------------------------#'\
+ +color.BLUE+'\n\nThis is somewhere around lines 50 - 80...\n\n'+color.END)
+
+ sys.exit()
+ else:
+ pass
+
+ return diamond_path
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD + '\n\nThis script is intended to '+color.RED+'Identify and Collapse '+color.END\
+ +color.BOLD+'partial '+color.PURPLE+'ORFS\n'+color.END+color.BOLD+'present within a '\
+ +color.RED+'Given'+color.END+color.BOLD+' transcriptome (or replicate) transcriptome(s)'\
+ +usage_msg(), usage=SUPPRESS, formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--file_prefix','-fp', action='store',
+ help=color.BOLD+color.GREEN+' File prefix that is unique (or common)\n to the files '\
+ 'to be processed\n'+color.END)
+
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+
+ optional_arg_group.add_argument('--identity','-id', type=float, action='store', default=0.98,
+ help=color.BOLD+color.GREEN+' Identity threshold for identifying \n "partials" to larger'\
+ ' contigs\n (default = 0.98)\n'+color.END)
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Prints author contact information\n'+color.END)
+ optional_arg_group.add_argument('--hook_fasta','-f', help='Path to the fasta file of the Hook DB in the Databases/db_OG folder')
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ args.id_print = str(int(float(args.identity)*100))
+
+ args.all_output_folder = '/'.join(args.file_prefix.split('/')[:-1]) + '/'
+ args.file_prefix = args.file_prefix.split('/')[-1]
+
+ args.file_listNTD = [args.all_output_folder + i for i in os.listdir(args.all_output_folder) if args.file_prefix in i and i.endswith('NTD.ORF.fasta')]
+
+ args.file_listAA = [args.all_output_folder + i for i in os.listdir(args.all_output_folder) if args.file_prefix in i and i.endswith('AA.ORF.fasta')]
+
+ args.file_listTSV = [args.all_output_folder + i for i in os.listdir(args.all_output_folder) if args.file_prefix in i and i.endswith('results.tsv')]
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ print ('\n')
+ sys.exit()
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 6_RemovePartials.py'\
+ ' --file_prefix Op_me_Xxma'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_arg = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_arg += 1
+
+ if args.file_listNTD == []:
+ print (color.BOLD+'\n\nNo '+color.ORANGE+'Nucleotide Fasta Files'+color.END+color.BOLD+\
+ ' found!\n\nCheck that your'+color.GREEN+' File Prefix'+color.END+color.BOLD+\
+ 'is present in\nthe files of interest')
+ valid_arg += 1
+
+ if args.file_listAA == []:
+ print (color.BOLD+'\n\nNo '+color.ORANGE+'Protein Fasta Files'+color.END+color.BOLD+\
+ ' found!\n\nCheck that your'+color.GREEN+' File Prefix'+color.END+color.BOLD+\
+ 'is present in\nthe files of interest')
+ valid_arg += 1
+
+ if args.file_listTSV == []:
+ print (color.BOLD+'\n\nNo '+color.ORANGE+'OG-Assignment Spreadsheets'+color.END+color.BOLD+\
+ ' found!\n\nCheck that your'+color.GREEN+' File Prefix'+color.END+color.BOLD+\
+ 'is present in\nthe files of interest')
+ valid_arg += 1
+
+ if len(args.file_listNTD) == len(args.file_listAA) == len(args.file_listTSV):
+ pass
+ else:
+ print (color.BOLD+color.RED+'\n\nError:'+color.END+color.BOLD+' Unequal numbers of'\
+ ' input files found.\n\nDouble-check that there are:'+color.CYAN+'SINGLE'+color.END\
+ +color.BOLD+' Nucleotide and Protein fasta files and OG-assignment Spreadsheet for'\
+ ' each transcriptome\n\nThen try once again.'+color.END)
+ valid_arg += 1
+
+ return valid_arg
+
+
+##########################################################################################
+###------------------------- Creates Folders For Storing Data -------------------------###
+##########################################################################################
+
+def prep_folders(args):
+
+ if os.path.isdir(args.all_output_folder + 'ToRename') != True:
+ os.system('mkdir ' + args.all_output_folder + 'ToRename')
+
+ if os.path.isdir(args.all_output_folder + args.file_prefix) != True:
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix)
+
+ if os.path.isdir(args.all_output_folder + args.file_prefix + '/Original') != True:
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Original')
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Original/SpreadSheets')
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Original/Concatenated/')
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Original/Concatenated/SpreadSheets')
+
+ if os.path.isdir(args.all_output_folder + args.file_prefix + '/Processed') != True:
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Processed')
+ os.system('mkdir ' + args.all_output_folder + args.file_prefix + '/Processed/SpreadSheets')
+
+
+##########################################################################################
+###-------------------- Merges Fasta Files When Replicates Present --------------------###
+##########################################################################################
+
+def merge_fasta_replicates(args, type):
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/'
+
+ count = 0
+ fasta_to_merge = []
+
+ if type == 'NTD':
+ fasta_list = args.file_listNTD
+ else:
+ fasta_list = args.file_listAA
+
+ for file in fasta_list:
+ fasta_to_merge += ['>'+str(count)+'_'+i for i in open(file).read().split('>') if i != '']
+ count += 1
+
+ with open(cat_folder+args.file_prefix+'.'+type+'.Concatenated.fasta','w+') as w:
+ w.write(''.join(fasta_to_merge))
+
+ time.sleep(.75)
+
+
+##########################################################################################
+###--------------------- Merges TSV Files When Replicates Present ---------------------###
+##########################################################################################
+
+def merge_tsv_replicates(args):
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/SpreadSheets/'
+
+ count = 0
+ tsv_to_merge = []
+
+ for file in args.file_listTSV:
+ tsv_to_merge += [str(count)+'_'+i for i in open(file).read().split('\n') if i != '']
+ count += 1
+
+ with open(cat_folder+args.file_prefix+'_Concatenated.allOGCleanresults.tsv','w+') as w:
+ w.write('\n'.join(tsv_to_merge))
+
+ time.sleep(.75)
+
+
+##########################################################################################
+###------------------ Calls on the other Merge Functions by Data Type -----------------###
+##########################################################################################
+
+def merge_relevant_data(args):
+
+ print (color.BOLD+'\n\nMerging Transcriptome data together.'+color.END)
+
+ merge_fasta_replicates(args, 'NTD')
+ merge_fasta_replicates(args, 'AA')
+ merge_tsv_replicates(args)
+
+
+##########################################################################################
+###------------------- Uses Diamond to perform Self-vs-Self "BLAST" -------------------###
+##########################################################################################
+
+def self_blast(args, diamond_path):
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/'
+
+ diamond_makedb = diamond_path + ' makedb --in ' + cat_folder + args.file_prefix + '.AA.Concatenated.fasta -d ' + cat_folder + args.file_prefix + '.AA.Concatenated'
+
+ diamond_self = diamond_path + ' blastp -q ' + cat_folder + args.file_prefix + '.AA.Concatenated.fasta -d ' + cat_folder + args.file_prefix + '.AA.Concatenated --strand plus --no-self-hits --id '+str(args.identity)+\
+ ' --query-cover 0.7 --evalue 1e-15 --threads 60 --outfmt 6 -o ' + cat_folder + 'SpreadSheets/' + args.file_prefix + '.Concatenated.Self.'+str(args.id_print)+'ID.tsv'
+
+ print (color.BOLD+'\n\nBinning ALL '+color.ORANGE+'Nucleotide ORFs'+color.END+color.BOLD\
+ +' for '+color.GREEN+args.file_prefix+color.END+color.BOLD+' at '+args.id_print\
+ +'% identity.\n\n'+color.END)
+
+ os.system(diamond_makedb)
+ os.system(diamond_self)
+
+ return cat_folder+'SpreadSheets/'+args.file_prefix+'.Concatenated.Self.'+str(args.id_print)+'ID.tsv'
+
+
+##########################################################################################
+###------------------- Uses USearch to perform Self-vs-Self "BLAST" -------------------###
+##########################################################################################
+
+def check_Self_vs_Self(tsv_file):
+
+ evaluation = ''
+
+ tsv_in = [i for i in open(tsv_file).read().split('\n') if i != '']
+
+ if len(tsv_in) == 0:
+ evaluation = 'empty'
+ with open(tsv_file,'w+') as w:
+ w.write('No Self-vs-Self hits were found')
+ else:
+ evaluation = 'continue'
+
+ return evaluation
+
+
+
+##########################################################################################
+###-------------------- Removes Nearly Identical ORFs from Data Set -------------------###
+##########################################################################################
+
+def filter_NTD_data(args):
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/'
+ proc_folder = args.all_output_folder + args.file_prefix + '/Processed/'
+
+ ##########################################
+ ## Set-up Useful Lists and Dictionaries ##
+ ##########################################
+
+ nuc_Above98_hit = {}
+ seqs_to_toss = []
+ prepped_NTD = []
+ prepped_AA = []
+
+ nuc_tsv_100 = 0
+
+ replicates = ''
+
+ if len(args.file_listNTD) > 1:
+ replicates = 'yes'
+ else:
+ replicates = 'nope'
+
+ OGLenDB = {}
+ for rec in SeqIO.parse(args.hook_fasta, 'fasta'):
+ if rec.id[-10:] not in OGLenDB:
+ OGLenDB.update({ rec.id[-10:] : [] })
+
+ OGLenDB[rec.id[-10:]].append(len(str(rec.seq)))
+
+ for og in OGLenDB:
+ OGLenDB[og] = mean(OGLenDB[og])
+
+ print (color.BOLD+'\n\nRemoving Partial '+color.PURPLE+'ORFs'+color.END+color.BOLD+\
+ ' with >'+args.id_print+'% Nucleotide Identity over >70% of\ntheir length when '\
+ 'compared to more complete '+color.PURPLE+'ORFs '+color.END+color.BOLD+'from: '\
+ +color.CYAN+args.file_prefix+'\n\n'+color.END)
+
+ #####################################################################
+ ## Self-v-self BLAST Output Parsing - first checks for Seq-length! ##
+ #####################################################################
+
+ nuc_tsv_raw = [i.rstrip('\n') for i in open(cat_folder+'SpreadSheets/'+args.file_prefix\
+ +'.Concatenated.Self.'+str(args.id_print)+'ID.tsv').readlines() if i != '\n']
+
+ too_long = 0
+ for line in nuc_tsv_raw:
+ og_number = re.split('OG.{1}_', line)[-1][:6]
+ og_prefix = line.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ if og in OGLenDB.keys():
+ if int(line.split('Len')[-1].split('_')[0]) > 4.5*OGLenDB[og] or int(line.split('Len')[-1].split('_')[0]) < 1.5*OGLenDB[og]:
+ seqs_to_toss.append(line.split('\t')[1])
+ too_long += 1
+
+ nuc_tsv = [line for line in nuc_tsv_raw if line.split('\t')[1] not in seqs_to_toss]
+
+ if len(nuc_tsv) > 0:
+ if 'Cov' in nuc_tsv[0].split('\t')[0].split('_')[-3]:
+ nuc_tsv.sort(key=lambda x: (-int(x.split('\t')[1].split('Len')[-1].split('_')[0]),-int(x.split('\t')[1].split('Cov')[-1].split('_')[0])))
+ else:
+ nuc_tsv.sort(key=lambda x: -int(x.split('\t')[1].split('Len')[-1].split('_')[0]))
+
+
+ for line in nuc_tsv:
+ if line.split('\t')[1] not in seqs_to_toss:
+ nuc_Above98_hit.setdefault(line.split('\t')[1],[]).append(line.split('\t')[0])
+ seqs_to_toss.append(line.split('\t')[0])
+ if line.split('\t')[2] == '100.0':
+ nuc_tsv_100 += 1
+
+ seqs_to_toss = list(set(seqs_to_toss))
+ inFasta_NTD_rawLen = [i for i in SeqIO.parse(cat_folder+args.file_prefix+'.NTD.Concatenated.fasta', 'fasta') if i.description]
+ inFasta_NTD = [i for i in inFasta_NTD_rawLen if i.description not in seqs_to_toss]
+ inFasta_AA = [i for i in SeqIO.parse(cat_folder+args.file_prefix+'.AA.Concatenated.fasta','fasta') if i.description not in seqs_to_toss]
+
+ if replicates != '':
+ for i in inFasta_NTD:
+ if i.description not in nuc_Above98_hit.keys():
+ prepped_NTD.append('>'+'_'.join(i.description.split('_')[1:])+'_Trans1\n'+str(i.seq))
+ else:
+ Rep_Num = str(len(set([i.description.split('_')[0]]+[j.split('_')[0] for j in nuc_Above98_hit[i.description]])))
+ prepped_NTD.append('>'+'_'.join(i.description.split('_')[1:])+'_Trans'+Rep_Num+'\n'+str(i.seq))
+ for i in inFasta_AA:
+ if i.description not in nuc_Above98_hit.keys():
+ prepped_AA.append('>'+'_'.join(i.description.split('_')[1:])+'_Trans1\n'+str(i.seq).replace('*','X'))
+ else:
+ Rep_Num = str(len(set([i.description.split('_')[0]]+[j.split('_')[0] for j in nuc_Above98_hit[i.description]])))
+ prepped_AA.append('>'+'_'.join(i.description.split('_')[1:])+'_Trans'+Rep_Num+'\n'+str(i.seq).replace('*','X'))
+ else:
+ for i in inFasta_NTD:
+ if i.description not in nuc_Above98_hit.keys():
+ prepped_NTD.append('>'+i.description+'\n'+str(i.seq))
+ else:
+ prepped_NTD.append('>'+i.description+'\n'+str(i.seq))
+ for i in inFasta_AA:
+ if i.description not in nuc_Above98_hit.keys():
+ prepped_AA.append('>'+i.description+'\n'+str(i.seq).replace('*','X'))
+ else:
+ prepped_AA.append('>'+i.description+'\n'+str(i.seq).replace('*','X'))
+
+ with open(args.all_output_folder + args.file_prefix + '/'+args.file_prefix+'_SeqPairsAbove98.txt','w+') as w:
+ for k, v in nuc_Above98_hit.items():
+ w.write(k+'\t'+'\t'.join(v)+'\n')
+
+ ###################################################################################
+ ## Check for abnormally short sequences for the taxon for every Gene Family (OG) ##
+ ###################################################################################
+
+ print (color.BOLD+'Removing Abnormally Short (70% length) OR Long (200% length)'\
+ +color.PURPLE+' ORFs'+color.END+color.BOLD+'\ncompared to typical '+color.ORANGE+'Gene '\
+ 'Family '+color.END+color.BOLD+'member length for: '+color.CYAN+args.file_prefix+'\n\n'+color.END)
+
+ self_OGLenDB={} ##
+ seqs_to_toss = [] ##
+ too_long = too_short = 0 ##
+
+ for i in prepped_NTD:
+ og_number = re.split('OG.{1}_', i.split('\n')[0])[-1][:6]
+ og_prefix = i.split('\n')[0].split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ self_OGLenDB.setdefault(og,[]).append(len(i.split('\n')[-1]))
+
+ good_NTD_names = []
+ for i in prepped_NTD:
+ og_number = re.split('OG.{1}_', i.split('\n')[0])[-1][:6]
+ og_prefix = i.split('\n')[0].split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ if (0.7*sum(self_OGLenDB[og])/float(len(self_OGLenDB[og]))) <= len(i.split('\n')[-1]) <= (2*sum(self_OGLenDB[og])/float(len(self_OGLenDB[og]))):
+ good_NTD_names.append(i.split('\n')[0])
+
+ good_NTD_seqs = [i for i in prepped_NTD if i.split('\n')[0] in good_NTD_names]
+ good_AA_seqs = [i for i in prepped_AA if i.split('\n')[0] in good_NTD_names]
+
+ too_short = len(prepped_NTD) - len(good_NTD_names)
+
+ ####################################################################
+ ## Finalized Outputs are Summarized and Written Out to New Fastas ##
+ ####################################################################
+
+ print (color.BOLD+'There were '+color.CYAN+str(len(inFasta_NTD_rawLen))+color.END+color.BOLD\
+ +color.PURPLE+' ORFs '+color.END+color.BOLD+'originally, with '+color.ORANGE+\
+ str(nuc_tsv_100)+color.END+color.BOLD+' Partial '+color.PURPLE+'ORFs'+color.END+\
+ color.BOLD+' that\nwere '+color.RED+'100% Identical'+color.END+color.BOLD+' to larger'\
+ +color.PURPLE+' ORFs.\n\n'+color.END)
+
+ print(color.BOLD+'Of the '+color.CYAN+str(len(inFasta_NTD_rawLen))+color.END+color.BOLD\
+ +' original'+color.PURPLE+' ORFs'+color.END+color.BOLD+', '+color.ORANGE+str(len(set(seqs_to_toss)))+\
+ color.END+color.BOLD+' are '+color.PURPLE+'Partial ORFs '+color.END+color.BOLD+'(e.g. '+\
+ color.RED+'> '+args.id_print+'%'+color.END+color.BOLD+'\nNUCLEOTIDE identity) to larger'\
+ +color.PURPLE+' ORFs'+color.END+color.BOLD+' with '+color.ORANGE+str(too_short+too_long)\
+ +color.END+color.BOLD+' additional'+color.PURPLE+' ORFs\n'+color.END+color.BOLD+'that were either '+\
+ color.RED+'TOO LONG or SHORT.\n\n'+color.END)
+
+ print (color.BOLD+'Overall, there are '+color.GREEN+str(len(good_NTD_seqs))+' Unique ORFs'\
+ +color.END+color.BOLD+' for '+color.CYAN+args.file_prefix+'\n'+color.END)
+
+ with open(proc_folder+args.file_prefix+'_Filtered.Final.NTD.ORF.fasta','w+') as w:
+ for i in good_NTD_seqs:
+ w.write(i+'\n')
+ with open(proc_folder+args.file_prefix+'_Filtered.Final.AA.ORF.fasta','w+') as x:
+ for i in good_AA_seqs:
+ x.write(i+'\n')
+
+ return good_NTD_names
+
+
+##########################################################################################
+###------------------- Updates SpreadSheet with Update Sequence Names -----------------###
+##########################################################################################
+
+def update_tsv(args, NTD_list_names):
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/SpreadSheets/'
+ proc_folder = args.all_output_folder + args.file_prefix + '/Processed/'
+
+ inTSV = {'_'.join(i.split('\t')[0].split('_')[1:]):'\t'.join(i.split('\t')[1:]) for i in open(cat_folder+\
+ args.file_prefix+'_Concatenated.allOGCleanresults.tsv').readlines() if i != '\n'}
+
+ Updated_inTSV = [i.strip('>')+'\t'+inTSV[i.split('_Trans')[0].strip('>')] for i in NTD_list_names]
+
+ with open(proc_folder+'/SpreadSheets/'+args.file_prefix+'_Filtered.Final.allOGCleanresults.tsv','w+') as w:
+ for line in Updated_inTSV:
+ w.write(line+'\n')
+
+
+def no_partials_present(args, OGLenDB):
+
+ print (color.BOLD+color.RED+'\n\nWarning:'+color.END+color.BOLD+' No partial sequences'\
+ ' were found with > '+str(args.id_print)+'% nucleotide identity.\n\nThe data will still be '\
+ 'checked for ORFs that are unexpectedly '+color.ORANGE+'Short'+color.END+color.BOLD+' or'\
+ +color.ORANGE+' Long.\n\n'+color.END)
+
+ cat_folder = args.all_output_folder + args.file_prefix + '/Original/Concatenated/'
+ proc_folder = args.all_output_folder + args.file_prefix + '/Processed/'
+
+ NTD_file = cat_folder+args.file_prefix+'.NTD.Concatenated.fasta'
+ AA_file = cat_folder+args.file_prefix+'.AA.Concatenated.fasta'
+ TSV_file = cat_folder+'/SpreadSheets/'+args.file_prefix+'_Concatenated.allOGCleanresults.tsv'
+
+ OGLenDB = {}
+ for rec in SeqIO.parse(args.hook_fasta, 'fasta'):
+ if rec.id[-10:] not in OGLenDB:
+ OGLenDB.update({ rec.id[-10:] : [] })
+
+ OGLenDB[rec.id[-10:]].append(len(str(rec.seq)))
+
+ for og in OGLenDB:
+ OGLenDB[og] = mean(OGLenDB[og])
+
+ self_OGLenDB = {}
+ seqs_to_toss = []
+ too_long, too_short = 0, 0
+
+ ## Small changes in this section for Auden (ought to work now)
+ ## Lists -> Dictionaries and some data curation steps
+
+ inFasta = {i.description:str(i.seq) for i in SeqIO.parse(NTD_file,'fasta')}
+
+ for k,v in inFasta.items():
+ og_number = re.split('OG.{1}_', k)[-1][:6]
+ og_prefix = k.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ if len(v) >= 4.5*OGLenDB[og]:
+ seqs_to_toss.append(k)
+ too_long+= 1
+
+ prepped_NTD = [i for i in inFasta if i not in seqs_to_toss]
+
+ print (color.BOLD+'Removing Abnormally Short (70% length) OR Long (200% length)'\
+ +color.PURPLE+' ORFs'+color.END+color.BOLD+'\ncompared to typical '+color.ORANGE+'Gene '\
+ 'Family '+color.END+color.BOLD+'member length for: '+color.CYAN+args.file_prefix+'\n\n'+color.END)
+
+ ## toss those sequences from the sequence dictonary (less headache)
+ for crap_seq in seqs_to_toss:
+ del inFasta[crap_seq]
+
+ for k, v in inFasta.items():
+ og_number = re.split('OG.{1}_', k)[-1][:6]
+ og_prefix = k.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ self_OGLenDB.setdefault(og,[]).append(len(v))
+
+ self_OGLenDB_Final = {k:sum(v)/len(v) for k, v in self_OGLenDB.items()}
+
+ good_NTD_data = { }
+ for k, v in inFasta.items():
+ og_number = re.split('OG.{1}_', k)[-1][:6]
+ og_prefix = k.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ if 0.7*self_OGLenDB_Final[og] <= len(v) <= 2*self_OGLenDB_Final[og]:
+ good_NTD_data.update({ k : v })
+
+
+ good_AA_data = {i.description:str(i.seq) for i in SeqIO.parse(AA_file,'fasta') if i.description in good_NTD_data.keys()}
+
+ good_TSV_data = [i for i in open(cat_folder+'/SpreadSheets/'+args.file_prefix+'_Concatenated.allOGCleanresults.tsv')\
+ .read().split('\n') if i != '' and i.split('\t')[0] in good_NTD_data.keys()]
+
+ renamed_TSV_data = [i.split('\t')[0]+'_Trans1\t'+'\t'.join(i.split('\t')[1:]) for i in good_TSV_data]
+
+
+ with open(proc_folder+args.file_prefix+'_Filtered.Final.NTD.ORF.fasta','w+') as w:
+ for k,v in good_NTD_data.items():
+ w.write('>'+k+'_Trans1\n'+v+'\n')
+
+ with open(proc_folder+args.file_prefix+'_Filtered.Final.AA.ORF.fasta','w+') as x:
+ for k, v in good_AA_data.items():
+ x.write('>'+k+'_Trans1\n'+v+'\n')
+
+ with open(proc_folder+'/SpreadSheets/'+args.file_prefix+'_Filtered.Final.allOGCleanresults.tsv','w+') as y:
+ y.write('\n'.join(renamed_TSV_data))
+
+
+##########################################################################################
+###--------------------- Cleans up the Folder and Moves Final Files -------------------###
+##########################################################################################
+
+def clean_up(args):
+
+ for i in args.file_listNTD:
+ os.system('mv ' + i + ' ' + args.all_output_folder + args.file_prefix + '/Original/')
+ os.system('mv ' + i.replace('NTD.ORF.fasta','AA.ORF.fasta') + ' ' + args.all_output_folder + args.file_prefix + '/Original/')
+ os.system('mv ' + i.split('named')[0]+'named*allOGCleanresults.tsv ' + args.all_output_folder + args.file_prefix + '/Original/SpreadSheets/')
+
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script():
+
+ print(color.BOLD+'\nNext Script is: '+color.GREEN+'6b_update_cov_post_removepartials.py\n\n'+color.END)
+
+
+##########################################################################################
+###------------------- Checks Command Line Arguments and Calls Steps ------------------###
+##########################################################################################
+
+def main():
+
+ diamond_path = check_diamond_path()
+
+ args = check_args()
+
+ prep_folders(args)
+
+ merge_relevant_data(args)
+
+ self_BLAST_out = self_blast(args, diamond_path)
+
+ evaluation = check_Self_vs_Self(self_BLAST_out)
+
+ if evaluation != 'empty':
+ NTD_names = filter_NTD_data(args)
+ update_tsv(args, NTD_names)
+ else:
+ no_partials_present(args)
+
+ clean_up(args)
+
+ next_script()
+
+main()
diff --git a/PTL1/Transcriptomes/Scripts/6b_update_cov_post_removepartials.py b/PTL1/Transcriptomes/Scripts/6b_update_cov_post_removepartials.py
new file mode 100644
index 0000000..6d248b1
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/6b_update_cov_post_removepartials.py
@@ -0,0 +1,88 @@
+#!/usr/bin/python
+from __future__ import print_function
+
+__author__ = "Jean-David Grattepanche"
+__version__ = "2, August 28, 2017"
+__email__ = "jeandavid.grattepanche@gmail.com"
+
+
+import sys
+import os
+import re
+import time
+import string
+import os.path
+from Bio import SeqIO
+from sys import argv
+
+def Addcoverage(code):
+ seqfolder = code
+ all_output_folder = '/'.join(code.split('/')[:-1])
+ code = code.split('/')[-1]
+
+ covupd = {}
+ for seqcoll in open(seqfolder + '/' + code + '_SeqPairsAbove98.txt','r'):
+ CL = 0
+ for transc in seqcoll.split('\t'):
+ if CL == 0:
+ reftrans = ('_').join(transc.split('_')[1:])
+ coverage = int(transc.split('Cov')[1].split('_')[0])
+ Length = int(transc.split('Len')[1].split('_')[0])
+ CL += coverage * Length
+ covupd[reftrans] = CL
+
+ if os.path.isdir(seqfolder + '/Updated_Coverage/') != True:
+ os.system('mkdir ' + seqfolder + '/Updated_Coverage/')
+ if os.path.isdir(seqfolder + '/Updated_Coverage/SpreadSheets/') != True:
+ os.system('mkdir ' + seqfolder + '/Updated_Coverage/SpreadSheets/')
+
+ for spreadsh in os.listdir(seqfolder + '/Processed/SpreadSheets/'):
+ if spreadsh.endswith('.tsv'):
+ outtsvtokeep = open(seqfolder + '/Updated_Coverage/SpreadSheets/' + spreadsh.split('Final')[0] + 'UC.Final' + spreadsh.split('Final')[1],'w+')
+ for row in open(seqfolder + '/Processed/SpreadSheets/'+ spreadsh, 'r'):
+ if row.split('_Trans')[0] in covupd:
+ og_number = re.split('OG.{1}_', row)[-1][:6]
+ og_prefix = row.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ newcov2 = round(covupd[row.split('_Trans')[0]] / int(row.split('_Len')[1].split('_')[0]))
+ outtsvtokeep.write(row.split('Cov')[0]+'Cov'+str(newcov2)+'_' + og_prefix +row.split(og_prefix)[1].split('_Trans')[0] +'\t' +('\t').join(row.split('\t')[1:]))
+ else:
+ if 'Trans' in row:
+ outtsvtokeep.write(row.split('_Trans')[0]+ '\t' +('\t').join(row.split('\t')[1:]))
+ else:
+ outtsvtokeep.write(row)
+ outtsvtokeep.close()
+
+ for seqfile in os.listdir(seqfolder + '/Processed'):
+ if seqfile.endswith('.fasta'):
+ outseqtokeep = open(seqfolder + '/Updated_Coverage/' + seqfile.split('Final')[0] + 'UC.Final' + seqfile.split('Final')[1],'w+')
+ for Seq in SeqIO.parse(seqfolder + '/Processed/' + seqfile ,'fasta'):
+ if Seq.description.split('_Trans')[0] not in covupd:
+ outseqtokeep.write('>'+Seq.description.split('_Trans')[0]+ '\n'+str(Seq.seq) +'\n')
+ else:
+ og_number = re.split('OG.{1}_', Seq.description)[-1][:6]
+ og_prefix = Seq.description.split(og_number)[0][-4:]
+ og = og_prefix + og_number
+
+ newcov = round(covupd[Seq.description.split('_Trans')[0]] / int(Seq.description.split('_Len')[1].split('_')[0]))
+ outseqtokeep.write('>'+Seq.description.split('Cov')[0]+'Cov'+str(newcov)+'_' + Seq.description.split(og)[0][-2:] + og + '\n'+str(Seq.seq) +'\n')
+ outseqtokeep.close()
+
+ if os.path.isdir(all_output_folder + '/ToRename') != True:
+ os.system('mkdir ' + all_output_folder + '/ToRename')
+
+ os.system('cp ' + seqfolder + '/Updated_Coverage/*fasta ' + all_output_folder + '/ToRename/')
+ os.system('cp ' + seqfolder + '/Updated_Coverage/SpreadSheets/*tsv ' + all_output_folder + '/ToRename/')
+
+
+def main():
+ script, code = argv
+ Addcoverage(code)
+main()
+
+
+
+
+
+
diff --git a/PTL1/Transcriptomes/Scripts/7_FinalizeName.py b/PTL1/Transcriptomes/Scripts/7_FinalizeName.py
new file mode 100644
index 0000000..677a836
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/7_FinalizeName.py
@@ -0,0 +1,398 @@
+#!/usr/bin/env python3.5
+
+##__Updated__: 31_08_2017
+##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
+##__Usage__: python 6_FilterPartials.py --help
+
+##################################################################################################
+## This script is intended to rename the outputs of the FilterPartials script ##
+## to a given 10-character that is used in the Katz lab Phylogenomic Tree building methods ##
+## ##
+## Prior to r`ning this script, ensure the following: ##
+## ##
+## 1. You have assembled your transcriptome and COPIED the 'assembly' file ##
+## (contigs.fasta, or scaffolds.fasta) to the PostAssembly Folder ##
+## 2. Removed small sequences (usually sequences < 300bp) with ContigFilterPlusStats.py ##
+## 3. Removed SSU/LSU sequences from your Fasta File ##
+## 4. Classified your sequences as Strongly Prokaryotic/Eukaryotic or Undetermined ##
+## 5. Classified the Non-Strongly Prokaryotic sequences into OGs ##
+## 6. You either know (or have inferred) the genetic code of the organism ##
+## 7. You have translated the sequences and checked for the data in the RemovePartials folder ##
+## 8. Partial sequences have been removed from the transcriptomic data sets ##
+## ##
+## COMMAND Example Below ##
+## Extra Notes at Bottom of Script ##
+## ##
+## E-mail Xyrus (author) for help if needed: maurerax@gmail.com ##
+## ##
+## Next Script(s) to Run: ##
+## NONE! You're FINISHED! :D ##
+## ##
+##################################################################################################
+
+import argparse, os, sys
+from argparse import RawTextHelpFormatter,SUPPRESS
+
+#----------------------- Solely to Make Print Statements Colorful -----------------------#
+
+class color:
+ PURPLE = '\033[95m'
+ CYAN = '\033[96m'
+ DARKCYAN = '\033[36m'
+ ORANGE = '\033[38;5;214m'
+ BLUE = '\033[94m'
+ GREEN = '\033[92m'
+ YELLOW = '\033[93m'
+ RED = '\033[91m'
+ BOLD = '\033[1m'
+ UNDERLINE = '\033[4m'
+ END = '\033[0m'
+
+
+#------------------------------- Main Functions of Script --------------------------------#
+
+###########################################################################################
+###--------------------- Parses and Checks Command-Line Arguments ----------------------###
+###########################################################################################
+
+def check_args():
+
+ parser = argparse.ArgumentParser(description=
+ color.BOLD + '\n\nThis script is intended to '+color.RED+'Rename '+color.END\
+ +color.BOLD+'the core set of '+color.PURPLE+'ORFS\n'+color.END+color.BOLD+'with a valid '\
+ +color.RED+'10-character code'+color.END+color.BOLD+' for use in the KatzLab\nPhylogenomic Pipeline'\
+ +usage_msg(), usage=SUPPRESS, formatter_class=RawTextHelpFormatter)
+
+ required_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Required Options'+color.END)
+
+ required_arg_group.add_argument('--input_file','-in', action='store',
+ help=color.BOLD+color.GREEN+' One of the Fasta files that is to be renamed\n'+color.END)
+ required_arg_group.add_argument('--name','-n', action='store',
+ help=color.BOLD+color.GREEN+' A valid 10-Character code for updating the data\n'+color.END)
+
+
+ optional_arg_group = parser.add_argument_group(color.ORANGE+color.BOLD+'Options'+color.END)
+
+ optional_arg_group.add_argument('-author', action='store_true',
+ help=color.BOLD+color.GREEN+' Prints author contact information\n'+color.END)
+
+ if len(sys.argv[1:]) == 0:
+ print (parser.description)
+ print ('\n')
+ sys.exit()
+
+ args = parser.parse_args()
+
+ quit_eval = return_more_info(args)
+ if quit_eval > 0:
+ print ('\n')
+ sys.exit()
+
+ args.all_output_folder = '/'.join(args.input_file.split('/')[:-2])
+
+ if '.allOGCleanresults' in args.input_TSV:
+ args.out_XML = args.name+'_XX_'+args.input_TSV.split('/')[-1].replace('.allOGCleanresults.','.AA.ORF.')\
+ .replace('.tsv','.fasta')+'_1e-10keepall_BlastOutall.oneHit'
+ else:
+ args.out_XML = args.name+'_XX_'+args.input_TSV.split('/')[-1].replace('_allOGCleanresults.','_AA.ORF.')\
+ .replace('.tsv','.fasta')+'_1e-10keepall_BlastOutall.oneHit'
+
+ args.file_prefix = args.input_file.split('/')[-1].split('_Filtered.Final')[0]
+ if 'fasta' in args.file_prefix:
+ args.file_prefix = args.name
+
+ args.r2g_aa = args.all_output_folder + '/ReadyToGo/ReadyToGo_AA/'
+ args.r2g_ntd = args.all_output_folder + '/ReadyToGo/ReadyToGo_NTD/'
+ args.r2g_tsv = args.all_output_folder + '/ReadyToGo/ReadyToGo_TSV/'
+ args.r2g_xml = args.all_output_folder + '/ReadyToGo/ReadyToGo_XML/'
+
+
+ return args
+
+
+###########################################################################################
+###------------------------------- Script Usage Message --------------------------------###
+###########################################################################################
+
+def usage_msg():
+ return (color.BOLD+color.RED+'\n\nExample usage:'+color.CYAN+' python 7_FinalizeName.py'\
+ ' --input_file ../ToRename/Op_me_Xxma_Filtered.Final.AA.ORF.fasta --name Op_me_Xxma'+color.END)
+
+
+##########################################################################################
+###-------- Storage for LARGE (Annoying) Print Statements for Flagged Options ---------###
+##########################################################################################
+
+def return_more_info(args):
+
+ valid_args = 0
+
+ author = (color.BOLD+color.ORANGE+'\n\n\tQuestions/Comments? Email Xyrus (author) at'\
+ ' maurerax@gmail.com\n\n'+color.END)
+
+ if args.author == True:
+ print (author)
+ valid_args += 1
+
+ if args.input_file.endswith('AA.ORF.fasta'):
+ args.input_NTD = args.input_file.replace('AA.ORF.fasta','NTD.ORF.fasta')
+ args.input_AA = args.input_file
+# args.input_TSV = ('/').join(args.input_file.split('/')[:-1])+'/SpreadSheets/'+args.input_file.split('/')[-1].replace('AA.ORF.fasta','allOGCleanresults.tsv')
+ args.input_TSV = args.input_file.replace('AA.ORF.fasta','allOGCleanresults.tsv')
+
+ elif args.input_file.endswith('NTD.ORF.fasta'):
+ args.input_NTD = args.input_file
+ args.input_AA = args.input_file.replace('NTD.ORF.fasta','AA.ORF.fasta')
+# args.input_TSV = ('/').join(args.input_file.split('/')[:-1])+'/SpreadSheets/'+args.input_file.split('/')[-1].replace('NTD.ORF.fasta','allOGCleanresults.tsv')
+ args.input_TSV = args.input_file.replace('AA.ORF.fasta','allOGCleanresults.tsv')
+ print(args.input_TSV)
+
+ if os.path.isfile(args.input_NTD) != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Nucleotide '\
+ 'Fasta file ('+color.DARKCYAN+args.input_NTD.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_args += 1
+
+ if os.path.isfile(args.input_AA) != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided Protein '\
+ 'Fasta file ('+color.DARKCYAN+args.input_AA.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_args += 1
+
+ if os.path.isfile(args.input_TSV) != True:
+ print (color.BOLD+color.RED+'\nError:'+color.END+color.BOLD+' The provided TSV '\
+ ' file ('+color.DARKCYAN+args.input_TSV.split('/')[-1]+color.END+color.BOLD+')\ndoes not'\
+ ' exist or is incorrectly formatted.\n\nDouble-check then try again!\n\n'+color.END)
+ valid_args += 1
+
+ return valid_args
+
+###########################################################################################
+###-------------------- Double Checks Format for 10-Character Code ---------------------###
+###########################################################################################
+
+def check_code(args):
+
+ check_name = args.name.split('_')
+
+ if len(args.name) != 10:
+ print (color.BOLD+'\n\nNew Species Prefix is not 10 characters long\n\n')
+ print ('Three examples below:\n'+color.CYAN+'\n\tSr_ci_Cunc\n\n\tOp_me_Hsap\n\n\t'\
+ 'Am_ar_Ehis\n\n'+color.END)
+ sys.exit()
+
+ elif args.name.count('_') != 2:
+ print (color.BOLD+'\n\nCheck the format of your Species Prefix!\n\n')
+ print ('Three examples below:\n'+color.CYAN+'\n\tSr_ci_Cunc\n\n\tOp_me_Hsap\n\n\t'\
+ 'Am_ar_Ehis\n\n'+color.END)
+
+ sys.exit()
+
+ if len(check_name[0]) == 2 and len(check_name[1]) == 2 and len(check_name[2]) == 4:
+ print (color.BOLD+"\n\nRenaming "+color.ORANGE+args.input_file.split('/')[-1]\
+ .split('_Filtered')[0]+color.END+color.BOLD+"'s files with the following 10-character\n"\
+ "code: "+color.CYAN+args.name+color.END+'\n')
+ else:
+ print (color.BOLD+'\n\nCheck the format of your Species Prefix!\n\n')
+ print ('Three examples below:\n'+color.CYAN+'\n\tSr_ci_Cunc\n\n\tOp_me_Hsap\n\n\t'\
+ 'Am_ar_Ehis\n\n'+color.END)
+ sys.exit()
+
+
+##########################################################################################
+###------------------------- Creates Folders For Storing Data -------------------------###
+##########################################################################################
+
+def prep_folders(args):
+
+
+ if os.path.isdir(args.all_output_folder + '/ReadyToGo/') != True:
+ os.system('mkdir ' + args.all_output_folder + '/ReadyToGo')
+
+
+ if os.path.isdir(args.r2g_ntd) != True:
+ os.system('mkdir ' + args.r2g_ntd)
+ if os.path.isdir(args.r2g_aa) != True:
+ os.system('mkdir ' + args.r2g_aa)
+ if os.path.isdir(args.r2g_tsv) != True:
+ os.system('mkdir ' + args.r2g_tsv)
+ if os.path.isdir(args.r2g_xml) != True:
+ os.system('mkdir ' + args.r2g_xml)
+
+ if os.path.isdir(args.all_output_folder + '/' + args.file_prefix + '/Renamed') != True:
+ os.system('mkdir ' + args.all_output_folder + '/' + args.file_prefix + '/Renamed')
+
+###########################################################################################
+###----------- Renames the NTD and AA CDSs with the Given 10-Character Code ------------###
+###########################################################################################
+
+def rename_paralogs(args):
+
+ home_folder = args.all_output_folder + '/' + args.file_prefix + '/Renamed/'
+
+ print (color.BOLD+'\nRenaming Translated (Protein) '+color.PURPLE+'ORFs\n'+color.END)
+ renamed_Final_Prots = open(args.input_AA).read().replace('>','>'+args.name+'_XX_')
+
+ print (color.BOLD+'\nRenaming Nucleotide '+color.PURPLE+'ORFs\n'+color.END)
+ renamed_Final_Nucs = open(args.input_NTD).read().replace('>','>'+args.name+'_XX_')
+
+
+ print (color.BOLD+'\nUpdating CDS Names in the Spreadsheet'+color.END)
+ if '\n\n' in open(args.input_TSV).read():
+ renamed_Final_tsv = args.name+'_XX_'+open(args.input_TSV).read().rstrip('\n')\
+ .replace('\n\n','\n'+args.name+'_XX_')
+ else:
+ renamed_Final_tsv = args.name+'_XX_'+open(args.input_TSV).read().rstrip('\n')\
+ .replace('\n','\n'+args.name+'_XX_')
+
+ with open(home_folder+args.name+'_XX_'+args.input_AA.split('/')[-1],'w+') as w:
+ w.write(renamed_Final_Prots)
+
+ with open(home_folder+args.name+'_XX_'+args.input_NTD.split('/')[-1],'w+') as x:
+ x.write(renamed_Final_Nucs)
+
+
+ with open(home_folder+args.name+'_XX_'+args.input_TSV.split('/')[-1],'w+') as y:
+ y.write(renamed_Final_tsv)
+
+
+###########################################################################################
+###--------------------------------- Header/Tail Lines ---------------------------------###
+###########################################################################################
+
+def header_tail():
+ header = '\n\n'\
+ '\n blastp\n BLASTP 2.2.29+\n'\
+ ' Stephen F. Altschul, Thomas L. Madden, Alejandro A. Schäffer, Jinghui Zhang, Zheng Zhang, Webb Miller, and David J. Lipman (1997), "Gapped BLAST and PSI-BLAST: a new generation of protein database search programs", Nucleic Acids Res. 25:3389-3402.\n'\
+ ' ../OGBlastDB/renamed_aa_seqs_OrthoMCL-5_12653.fasta\n Query_1\n'
+
+ tail = '\n'
+ return header, tail
+
+
+###########################################################################################
+###------------------------------- TSV to XML Conversion -------------------------------###
+###########################################################################################
+
+def convert_TSV_data(args):
+
+ home_folder = args.all_output_folder + '/' + args.file_prefix + '/Renamed/'
+
+ TSVforConvert = home_folder+args.name+'_XX_'+args.input_TSV.split('/')[-1]
+
+ inTSV = [line.rstrip('\n') for line in open(TSVforConvert).readlines() if line != '\n']
+
+ iterations = []
+
+ for n in range(len(inTSV)):
+ if n == 0:
+ iterations.append(' '+inTSV[n].split('\t')[0]+'\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])+1))+'\n'\
+ ' \n \n BLOSUM62\n 1e-10\n'\
+ ' 11\n 1\n F\n'\
+ ' \n \n\n\n 1\n Query_1\n'\
+ ' '+inTSV[n].split('\t')[0]+'\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])+1))+'\n'\
+ '\n\n 1\n Fake_Entry\n '+inTSV[n].split('\t')[1]+'\n Fake_Accession\n'\
+ ' '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])+1))+'\n \n \n 1\n 1234\n'\
+ ' '+inTSV[n].split('\t')[-1]+'\n '+inTSV[n].split('\t')[-2]+'\n '+inTSV[n].split('\t')[-4]+'\n'\
+ ' '+inTSV[n].split('\t')[-3]+'\n '+inTSV[n].split('\t')[-4]+'\n '+inTSV[n].split('\t')[-3]+'\n'\
+ ' 0\n 0\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n'\
+ ' '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n 0\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n'\
+ ' \n \n \n \n \n\n'\
+ '\n\n \n \n 379660\n 197499634\n'\
+ ' 123\n 184705217500\n 0.041\n'\
+ ' 0.267\n 0.14\n \n \n\n')
+ else:
+ iterations.append('\n '+str(n+1)+'\n Query_'+str(n+1)+'\n'\
+ ' '+inTSV[n].split('\t')[0]+'\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])+1))+'\n'\
+ '\n\n 1\n Fake_Entry\n '+inTSV[n].split('\t')[1]+'\n Fake_Accession\n'\
+ ' '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])+1))+'\n \n \n 1\n 1234\n'\
+ ' '+inTSV[n].split('\t')[-1]+'\n '+inTSV[n].split('\t')[-2]+'\n '+inTSV[n].split('\t')[-4]+'\n'\
+ ' '+inTSV[n].split('\t')[-3]+'\n '+inTSV[n].split('\t')[-4]+'\n '+inTSV[n].split('\t')[-3]+'\n'\
+ ' 0\n 0\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n'\
+ ' '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n 0\n '+str(abs(int(inTSV[n].split('\t')[-3])-int(inTSV[n].split('\t')[-4])))+'\n'\
+ ' \n \n \n \n \n\n'\
+ '\n\n \n \n 379660\n 197499634\n'\
+ ' 123\n 184705217500\n 0.041\n'\
+ ' 0.267\n 0.14\n \n \n\n')
+
+ return iterations
+
+
+###########################################################################################
+###--------------------------- Writes Out the Fake XML File ----------------------------###
+###########################################################################################
+
+def write_Fake_XML(args):
+
+ home_folder = args.all_output_folder + '/' + args.file_prefix + '/'
+
+ print (color.BOLD+'\n\nConverting '+color.ORANGE+args.input_file.split('/')[-1]+color.END\
+ +color.BOLD+' to XML format\n'+color.END)
+
+ header, tail = header_tail()
+
+ iterations = convert_TSV_data(args)
+
+ with open(home_folder+args.out_XML,'w+') as w:
+ w.write(header)
+ w.write(''.join(iterations))
+ w.write(tail)
+
+##########################################################################################
+###-------------------- Cleans up the Folder and Moves Final Files --------------------###
+##########################################################################################
+def clean_up(args):
+
+ home_folder = args.all_output_folder + '/' + args.file_prefix + '/Renamed/'
+
+ os.system('cp ' + args.all_output_folder + '/' + args.file_prefix+'/'+args.out_XML+' '+args.r2g_xml)
+
+ os.system('cp '+home_folder+'*tsv '+args.r2g_tsv)
+
+ os.system('cp '+home_folder+'*_XX_*AA.ORF.fasta '+args.r2g_aa)
+ os.system('cp '+home_folder+'*_XX_*NTD.ORF.fasta '+args.r2g_ntd)
+
+ os.system('cp '+home_folder+'*_XX_*tsv ' + args.all_output_folder + '/' + args.file_prefix)
+ os.system('cp '+home_folder+'*_XX_*AA.ORF.fasta ' + args.all_output_folder + '/' + args.file_prefix)
+ os.system('cp '+home_folder+'*_XX_*NTD.ORF.fasta ' + args.all_output_folder + '/' + args.file_prefix)
+
+ os.system('rm ' + args.all_output_folder + '/ToRename/*'+args.file_prefix+'*')
+
+ if os.path.isdir(args.all_output_folder + '/Finished/') != True:
+ os.system('mkdir ' + args.all_output_folder + '/Finished')
+
+ os.system('mv ' + args.all_output_folder + '/' + args.file_prefix + ' ' + args.all_output_folder + '/Finished')
+
+###########################################################################################
+###-------------------------------- Next Script Message --------------------------------###
+###########################################################################################
+
+def next_script(args):
+
+ print (color.BOLD+'\nThere is no next script! The final '+color.ORANGE+args.out_XML\
+ .split('_XX')[0]+color.END+color.BOLD+' files can be\nfound in the '+color.RED+\
+ args.out_XML.split('_XX_')[-1].split('_Filtered')[0]+color.END+color.BOLD+' and '\
+ +color.RED+'ReadyToGo folders'+color.END+color.BOLD+' and are ready\n'\
+ 'for the KatzLab Phylogenomic Tree-Building Steps!\n\n'+color.END)
+
+##########################################################################################
+###--------------- Checks Command Line Arguments and Calls on Functions ---------------###
+##########################################################################################
+
+def main():
+
+ args = check_args()
+
+ check_code(args)
+
+ prep_folders(args)
+
+ rename_paralogs(args)
+
+ write_Fake_XML(args)
+
+ clean_up(args)
+
+ next_script(args)
+
+main()
\ No newline at end of file
diff --git a/PTL1/Transcriptomes/Scripts/8_SummaryStats.py b/PTL1/Transcriptomes/Scripts/8_SummaryStats.py
new file mode 100644
index 0000000..c356438
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/8_SummaryStats.py
@@ -0,0 +1,269 @@
+import os, sys
+import argparse
+from Bio import SeqIO
+import CUB
+from statistics import mean
+from math import ceil, floor
+from tqdm import tqdm
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def get_args():
+
+ parser = argparse.ArgumentParser(
+ prog = 'PTL6p1 Script 8: Stat Summary',
+ description = "Updated March 31th, 2023 by Auden Cote-L'Heureux"
+ )
+
+ parser.add_argument('-i', '--input', type = str, required = True, help = 'Input path to the "Output" folder produced by PhyloToL Part 1. This folder should contain both the "ReadyToGO" and "Intermediate" folders.')
+ parser.add_argument('-d', '--databases', type = str, default = '../Databases', help = 'Path to databases folder')
+ parser.add_argument('-r', '--r2g_jf', action = 'store_true', help = 'Create ReadyToGo files filtered to only include sequences between the 25th and 75th percentile of silent-site GC content. Please be aware that these are not necessarily the correct or non-contaminant sequences; examine the GC3xENc plots carefully before using these data.')
+
+ return parser.parse_args()
+
+
+def hook_lens(args):
+
+ print('\nGetting average OG lengths in the Hook DB...')
+
+ len_by_og = { }
+ for file in os.listdir(args.databases + '/db_OG'):
+ if file.endswith('.fasta') and os.path.isfile(args.databases + '/db_OG/' + file.replace('.fasta', '.dmnd')):
+ for rec in tqdm(SeqIO.parse(args.databases + '/db_OG/' + file, 'fasta')):
+ if rec.id[-10:] not in len_by_og:
+ len_by_og.update({ rec.id[-10:] : [] })
+
+ len_by_og[rec.id[-10:]].append(len(str(rec.seq)))
+
+ for og in len_by_og:
+ len_by_og[og] = mean(len_by_og[og])
+
+ return len_by_og
+
+
+def aa_comp_lengths(args, gcodes):
+
+ print('\nGetting amino acid composition data from ReadyToGo files...')
+
+ r2g_lengths = { }; aa_comp = { }; recid_by_contig_n = { }
+ for file in tqdm([f for f in os.listdir(args.input + '/ReadyToGo/ReadyToGo_AA')]):
+ if file.endswith('.fasta') and file[:10] in gcodes:
+ for rec in SeqIO.parse(args.input + '/ReadyToGo/ReadyToGo_AA/' + file, 'fasta'):
+ r2g_lengths.update({ rec.id : len(str(rec.seq)) * 3 })
+
+ fymink = 0; garp = 0; other = 0; total = 0
+ for char in str(rec.seq):
+ if char in 'FYMINK':
+ fymink += 1
+ elif char in 'GARP':
+ garp += 1
+ else:
+ other += 1
+
+ total += 1
+
+ aa_comp.update({ rec.id : { 'FYMINK' : fymink/total, 'GARP' : garp/total, 'Other' : other/total } })
+
+ recid_by_contig_n.update({ rec.id.split('Contig_')[-1].split('_')[0] : rec.id })
+
+ print('\nGetting transcript sequence data from original assembled transcript files...')
+
+ transcripts = { }; transcript_id_corr = { }
+ for tax in tqdm([f for f in os.listdir(args.input + '/Intermediate/TranslatedTranscriptomes')]):
+ if os.path.isdir(args.input + '/Intermediate/TranslatedTranscriptomes/' + tax + '/OriginalFasta'):
+ for file in os.listdir(args.input + '/Intermediate/TranslatedTranscriptomes/' + tax + '/OriginalFasta'):
+ if file.endswith('Original.fasta') and file[:10] in gcodes:
+ for rec in SeqIO.parse(args.input + '/Intermediate/TranslatedTranscriptomes/' + tax + '/OriginalFasta/' + file, 'fasta'):
+ transcripts.update({ rec.id : (file[:10], str(rec.seq)) })
+ if rec.id.split('NODE_')[-1].split('_')[0] in recid_by_contig_n:
+ transcript_id_corr.update({ recid_by_contig_n[rec.id.split('NODE_')[-1].split('_')[0]] : rec.id})
+
+ return aa_comp, transcripts, r2g_lengths, transcript_id_corr
+
+
+def get_nuc_comp(args, gcodes):
+
+ print('\nGetting nucleotide composition data from ReadyToGo files...')
+
+ nuc_comp = { }
+ for file in tqdm([f for f in os.listdir(args.input + '/ReadyToGo/ReadyToGo_NTD')]):
+ if file.endswith('.fasta') and file[:10] in gcodes:
+ cub_out = CUB.CalcRefFasta(args.input + '/ReadyToGo/ReadyToGo_NTD/' + file, gcodes[file[:10]])[0]
+ for k in cub_out:
+ nuc_comp.update({ k : cub_out[k] })
+
+ return nuc_comp
+
+
+def per_seq(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, transcript_id_corr):
+
+ og_mean_lens = hook_lens(args)
+
+ if not os.path.isdir(args.input + '/PerSequenceStatSummaries'):
+ os.mkdir(args.input + '/PerSequenceStatSummaries')
+
+ taxa = list(dict.fromkeys([seq[:10] for seq in nuc_comp]))
+
+ for taxon in taxa:
+ with open(args.input + '/PerSequenceStatSummaries/' + taxon + '.csv', 'w') as o:
+ o.write('Sequence,Taxon,OG,Transcript,TranscriptLength,CDSLength,AvgLengthOGinHook,AmbiguousCodons,GC-Overall,GC1,GC2,GC3,GC3-Degen,ExpWrightENc,ObsWrightENc_6Fold,ObsWrightENc_No6Fold,ObsWeightedENc_6Fold,ObsWeightedENc_No6Fold,FYMINK,GARP,OtherAA\n')
+ for rec in nuc_comp:
+ if rec[:10] == taxon:
+ o.write(rec + ',' + rec[:10] + ',' + rec[-10:])
+
+ try:
+ o.write(',' + transcript_id_corr[rec] + ',' + str(len(all_transcripts[transcript_id_corr[rec]][1])))
+ except KeyError:
+ o.write(',NA,NA')
+
+ o.write(',' + str(r2g_lengths[rec]) + ',' + str(og_mean_lens[rec[-10:]]))
+
+ v = nuc_comp[rec]
+ gcs = [str(v.gcOverall), str(v.gc1), str(v.gc2), str(v.gc3), str(v.gc4F)]
+ ENc = [str(v.expENc), str(v.obsENc_6F), str(v.obsENc_No6F), str(v.SunENc_6F),str(v.SunENc_No6F)]
+ o.write(',' + ','.join([str(v.amb_cdn)] + gcs + ENc))
+
+ o.write(',' + str(aa_comp[rec]['FYMINK']) + ',' + str(aa_comp[rec]['GARP']) + ',' + str(aa_comp[rec]['Other']) + '\n')
+
+
+def per_tax(args, nuc_comp, aa_comp, all_transcripts, r2g_lengths, gcodes):
+
+ taxa = list(dict.fromkeys([seq[:10] for seq in nuc_comp]))
+
+ with open(args.input + '/PerTaxonSummary.csv', 'w') as o:
+ o.write('Taxon,TranscriptsInput,Median_GCTranscripts,IQR_GCTranscripts,Median_LenTranscripts,IRQ_LenTranscripts,SeqsR2G,OGsR2G,Median_GC3R2G,IQR_GC3R2G,Median_ENcR2G,IQR_ENcR2G,Median_LenR2G,IQR_LenR2G,GeneticCode\n')
+
+ for taxon in taxa:
+ o.write(taxon)
+
+ transcripts = [all_transcripts[seq][1].upper() for seq in all_transcripts if all_transcripts[seq][0] == taxon]
+ o.write(',' + str(len(transcripts)))
+
+ transcript_gcs = []
+ for transcript in transcripts:
+ transcript_gcs.append((transcript.count('G') + transcript.count('C'))/len(transcript))
+
+ transcript_gcs = sorted(transcript_gcs)
+ o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.5)]))
+ o.write(',' + str(transcript_gcs[floor(len(transcripts)*0.75)] - transcript_gcs[floor(len(transcripts)*0.25)]))
+
+ transcript_lens = sorted([len(transcript) for transcript in transcripts])
+ o.write(',' + str(transcript_lens[floor(len(transcripts)*0.5)]))
+ o.write(',' + str(transcript_lens[floor(len(transcripts)*0.75)] - transcript_lens[floor(len(transcripts)*0.25)]))
+
+ r2g_ntds = [nuc_comp[seq] for seq in nuc_comp if seq[:10] == taxon]
+ o.write(',' + str(len(r2g_ntds)))
+ r2g_ogs = list(dict.fromkeys([seq[-10:] for seq in nuc_comp if seq[:10] == taxon]))
+ o.write(',' + str(len(r2g_ogs)))
+
+ r2g_gc3s = sorted([seq.gc4F for seq in r2g_ntds])
+ o.write(',' + str(r2g_gc3s[floor(len(r2g_ntds)*0.5)]))
+ o.write(',' + str(r2g_gc3s[floor(len(r2g_gc3s)*0.75)] - r2g_gc3s[floor(len(r2g_gc3s)*0.25)]))
+
+ r2g_encs = sorted([seq.obsENc_6F for seq in r2g_ntds])
+ o.write(',' + str(r2g_encs[floor(len(r2g_encs)*0.5)]))
+ o.write(',' + str(r2g_encs[floor(len(r2g_encs)*0.75)] - r2g_encs[floor(len(r2g_encs)*0.25)]))
+
+ tax_r2g_lens = sorted([r2g_lengths[seq] for seq in r2g_lengths if seq[:10] == taxon])
+ o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.5)]))
+ o.write(',' + str(tax_r2g_lens[floor(len(tax_r2g_lens)*0.75)] - tax_r2g_lens[floor(len(tax_r2g_lens)*0.25)]))
+
+ o.write(',' + gcodes[taxon] + '\n')
+
+
+def r2g_jf(args, nuc_comp, gcodes):
+
+ #Q: should there be an maximum IQR cutoff at which we do NOT produce a file here?
+
+ if not os.path.isdir(args.input + '/ReadyToGo/ReadyToGo_NTD_JF'):
+ os.mkdir(args.input + '/ReadyToGo/ReadyToGo_NTD_JF')
+
+ if not os.path.isdir(args.input + '/ReadyToGo/ReadyToGo_AA_JF'):
+ os.mkdir(args.input + '/ReadyToGo/ReadyToGo_AA_JF')
+
+ for file in os.listdir(args.input + '/ReadyToGo/ReadyToGo_NTD'):
+ if file.endswith('.fasta') and file[:10] in gcodes:
+ taxon = file[:10]
+
+ r2g_ntds = [nuc_comp[seq] for seq in nuc_comp if seq[:10] == taxon]
+ r2g_gc3s = sorted([seq.gc4F for seq in r2g_ntds])
+
+ with open(args.input + '/ReadyToGo/ReadyToGo_NTD_JF/' + file.replace('.fasta', '.JF.fasta'), 'w') as o:
+ for rec in SeqIO.parse(args.input + '/ReadyToGo/ReadyToGo_NTD/' + file, 'fasta'):
+ if nuc_comp[rec.id].gc4F > r2g_gc3s[floor(len(r2g_gc3s)*0.25)] and nuc_comp[rec.id].gc4F < r2g_gc3s[floor(len(r2g_gc3s)*0.75)]:
+ o.write('>' + rec.id + '\n' + str(rec.seq) + '\n\n')
+
+ with open(args.input + '/ReadyToGo/ReadyToGo_AA_JF/' + file.replace('.fasta', '.JF.fasta').replace('NTD', 'AA'), 'w') as o:
+ for rec in SeqIO.parse(args.input + '/ReadyToGo/ReadyToGo_AA/' + file.replace('NTD', 'AA'), 'fasta'):
+ if nuc_comp[rec.id].gc4F > r2g_gc3s[floor(len(r2g_gc3s)*0.25)] and nuc_comp[rec.id].gc4F < r2g_gc3s[floor(len(r2g_gc3s)*0.75)]:
+ o.write('>' + rec.id + '\n' + str(rec.seq) + '\n\n')
+
+
+def plot_jf(args, nuc_comp):
+
+ if not os.path.isdir(args.input + '/GC3xENc_Plots'):
+ os.mkdir(args.input + '/GC3xENc_Plots')
+
+ taxa = list(dict.fromkeys([rec[:10] for rec in nuc_comp]))
+
+ gc3_null = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100]
+ enc_null = [31, 31.5958, 32.2032, 32.8221, 33.4525, 34.0942, 34.7471, 35.411, 36.0856, 36.7707, 37.4659, 38.1707, 38.8847, 39.6074, 40.3381, 41.0762, 41.8208, 42.5712, 43.3264, 44.0854, 44.8471, 45.6102, 46.3735, 47.1355, 47.8949, 48.65, 49.3991, 50.1406, 50.8725, 51.593, 52.3, 52.9916, 53.6656, 54.32, 54.9525, 55.561, 56.1434, 56.6975, 57.2211, 57.7124, 58.1692, 58.5898, 58.9723, 59.3151, 59.6167, 59.8757, 60.0912, 60.2619, 60.3873, 60.4668, 60.5, 60.4668, 60.3873, 60.2619, 60.0912, 59.8757, 59.6167, 59.3151, 58.9723, 58.5898, 58.1692, 57.7124, 57.2211, 56.6975, 56.1434, 55.561, 54.9525, 54.32, 53.6656, 52.9916, 52.3, 51.593, 50.8725, 50.1406, 49.3991, 48.65, 47.8949, 47.1355, 46.3735, 45.6102, 44.8471, 44.0854, 43.3264, 42.5712, 41.8208, 41.0762, 40.3381, 39.6074, 38.8847, 38.1707, 37.4659, 36.7707, 36.0856, 35.411, 34.7471, 34.0942, 33.4525, 32.8221, 32.2032, 31.5958, 31]
+
+ for taxon in taxa:
+ comp_data = [(nuc_comp[rec].gc4F, nuc_comp[rec].obsENc_6F) for rec in nuc_comp if rec[:10] == taxon]
+
+ plt.figure()
+ plt.plot(np.array(gc3_null), np.array(enc_null), color = 'black', linewidth=2)
+ plt.scatter(np.array([val[0] for val in comp_data]), np.array([val[1] for val in comp_data]), s = 1)
+ plt.xlabel("GC content (3rd pos, 4-fold sites)")
+ plt.ylabel("Observed Wright ENc (6 Fold)")
+ plt.savefig(args.input + '/GC3xENc_Plots/' + taxon + '.png')
+
+if __name__ == "__main__":
+ args = get_args()
+
+ valid_codes = ['universal', 'blepharisma', 'chilodonella', 'condylostoma', 'euplotes', 'peritrich', 'vorticella', 'mesodinium', 'tag', 'tga', 'taa', 'none']
+
+ gcodes = { }
+ if os.path.isfile(args.input + '/Intermediate/gcode_output.tsv'):
+ for line in open(args.input + '/Intermediate/gcode_output.tsv'):
+ if len(line.split('\t')) == 5 and line.split('\t')[4].strip().lower() in valid_codes:
+ gcodes.update({ line.split('\t')[0] : line.split('\t')[4].strip() })
+ elif line.split('\t')[4].strip().lower() != '':
+ print('\nInvalid genetic code assignment for taxon ' + line.split('\t')[0] + '. Skipping this taxon in script 8 (summary statistics)\n')
+ else:
+ print('\nGenetic code assignment file (Output/Intermediate/gcode_output.tsv) not found. Quitting script 8 (summary statistics).\n')
+ exit()
+
+ aa_comp, transcripts, r2g_lengths, transcript_id_corr = aa_comp_lengths(args, gcodes)
+ nuc_comp = get_nuc_comp(args, gcodes)
+
+ per_tax(args, nuc_comp, aa_comp, transcripts, r2g_lengths, gcodes)
+ per_seq(args, nuc_comp, aa_comp, transcripts, r2g_lengths, transcript_id_corr)
+
+ if args.r2g_jf:
+ r2g_jf(args, nuc_comp, gcodes)
+
+ plot_jf(args, nuc_comp)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/PTL1/Transcriptomes/Scripts/CUB.py b/PTL1/Transcriptomes/Scripts/CUB.py
new file mode 100644
index 0000000..382e218
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/CUB.py
@@ -0,0 +1,523 @@
+#!/usr/bin/env python3
+# coding=utf-8
+
+'''Aim of this script is to generate lots of codon usage statistics to aid in
+identifying useful characteristics for de novo ORF calling'''
+
+# Author: Xyrus Maurer-Alcalá
+# Contact: maurerax@gmail.com or xyrus.maurer-alcala@izb.unibe.ch
+# Last Modified: 2020-09-17
+# usage: python CUB.py
+
+# Dependencies:
+# Python3, numpy, BioPython
+
+import os
+import re
+import sys
+#import matplotlib.pyplot as plt
+import numpy as np
+#import seaborn as sns
+
+from Bio import SeqIO
+from Bio.Seq import Seq
+from Bio.SeqUtils import GC
+
+
+class CalcCUB:
+ """
+ Returns the Effective Number of Codons used (observed and expected)
+ following the equations originally from Wright 1990.
+ """
+ def expWrightENc(gc3):
+ # Calculates the expected ENc from a sequence's GC3 under Wright 1990
+ if gc3 > 1:
+ # If GC3 looks as though it is > 1 (e.g. 100%), converts to a float ≤ 1.
+ # Calculations expect a value between 0 and 1
+ gc3 = gc3/100
+ exp_enc = 2+gc3+(29/((gc3**2)+(1-gc3)**2))
+ return round(exp_enc, 4)
+
+ def nullENcGC3():
+ # Calculates the expected ENc from the null distribution of GC3
+ # values (0, 100% GC)
+ null = [CalcCUB.expWrightENc(n) for n in np.arange(0,.51,0.01)]
+ null += null[:-1][::-1]
+ return [str(i)+'\t'+str(j) for i, j in zip([n for n in range(0, 101)],null)]
+
+
+ def calcWrightENc(cdnTable):
+ # Follows Wright's (1990) calculations for determining ENc scores.
+
+ def faCalcWright(aa_counts):
+ # Returns the codon homozygosity (fa) for a given "type" of AA (e.g.
+ # 2-fold degeneracy).
+ counts = [i[2] for i in aa_counts]
+ # n_aa --> number of this particular AA
+ n_aa = sum(counts)
+ # fa --> codon homozygosity
+ try:
+ fa = (((n_aa*sum([(i/float(n_aa))**2 for i in counts]))-1)/(n_aa-1))
+ except:
+ fa = 0
+ return fa
+
+ def ENcWright_by_Degen(fa_data):
+ # Same as used in Wright 1990, averages the homozygosity across all codons
+ # of a given class (e.g. 2-fold degeneracy)
+
+ # Codons without any degeneracy (e.g. ATG == M) have 100% homozygosity
+ # and provide a "base" for the ENc score
+ enc = 2
+ for k, v in fa_data.items():
+ non_zero_vals, non_zero_sum = len([i for i in v if i != 0]), sum([i for i in v if i != 0])
+ try:
+ f_aa = non_zero_sum/non_zero_vals
+ except:
+ f_aa = 1
+ enc += k/f_aa
+ return enc
+
+ # Determines the number of degenerate groups to use (i.e. whether 6-Fold
+ # degeneracy is present).
+ degen_cdns = {}
+ for k, v in cdnTable.items():
+ if v[1] not in degen_cdns.keys():
+ degen_cdns[v[1]] = [v[0]]
+ else:
+ if v[0] not in degen_cdns[v[1]]:
+ degen_cdns[v[1]] += [v[0]]
+
+ # Calculates codon homozygosity (fa) for each amino acid. Groups the
+ # resulting values based on the amino acids degeneracy (e.g. 'two-fold').
+ fa_cdns = {len(v):[] for k, v in degen_cdns.items() if 'one' not in k}
+
+ for k, v in degen_cdns.items():
+ # Skip codons lacking degeneracy
+ if 'one' in k:
+ continue
+
+ for aa in v:
+ aa_counts = [cdnTable[k] for k in cdnTable.keys() if cdnTable[k][0] == aa]
+ fa_cdns[len(v)] += [faCalcWright(aa_counts)]
+ enc_val = min(61, round(ENcWright_by_Degen(fa_cdns),4))
+ return enc_val
+
+ def SunEq5(cdnTable):
+ def calcFcf(aa_counts):
+ counts = [i[2] for i in aa_counts]
+ pseudocounts = [i+1 for i in counts]
+ na = sum(pseudocounts)
+ fcf = sum([(i/float(na))**2 for i in pseudocounts]), sum(pseudocounts)
+ return fcf
+
+ ENcWeightedPsuedo = 0
+ degen_cdns = {}
+
+ for k, v in cdnTable.items():
+ if v[1] == 'none':
+ continue
+ if v[1] not in degen_cdns.keys():
+ degen_cdns[v[1]] = [v[0]]
+ else:
+ if v[0] not in degen_cdns[v[1]]:
+ degen_cdns[v[1]] += [v[0]]
+ for k, v in degen_cdns.items():
+ fcf_nc = []
+ for aa in v:
+ aa_counts = [cdnTable[k] for k in cdnTable.keys() if cdnTable[k][0] == aa]
+ fcf_nc.append(calcFcf(aa_counts))
+ weightedENc = (len(fcf_nc) /
+ (sum([i[0]*i[1] for i in fcf_nc]) /
+ sum([i[1] for i in fcf_nc])))
+ ENcWeightedPsuedo += weightedENc
+ return round(ENcWeightedPsuedo,4)
+
+ def calcRCSU(cdnTbl):
+ rscu = {k:[v[0]] for k, v in cdnTbl.items() if v[0].isalpha()}
+ for k, v in rscu.items():
+ try:
+ aa_info = [(key, val[-1]) for key, val in cdnTbl.items() if val[0] == v[0]]
+ aa_cnts = [x[1] for x in aa_info]
+ cdn_rscu = (cdnTbl[k][-1]*len(aa_cnts))/sum(aa_cnts)
+ rscu[k] += [str(round(cdn_rscu,4))]
+ except:
+ rscu[k] += ['0.0']
+ return rscu
+
+
+class GenUtil(object):
+ """
+ "Overflow" of functions for now. Just a precaution to make the code a
+ little cleaner/easier to manage.
+
+ This class inclues means to normalize/check the user-provided genetic code,
+ which if not valid will default to the "universal" genetic code.
+
+ Similarly, This class will return the appropriate
+ codon count table and provides a function to update its values.
+ """
+ def convertGenCode(gCode):
+ # Will interpret the user provided genetic code (gcode) and checks that
+ # it is currently available for use with the NCBI/biopython
+ # supported translation tables. Default is universal.
+ # Dictionary of the possible/functional genetic codes that are supported.
+ # --- Chilodonella and condylostoma are to come!
+ transTable = {'universal':1, 'blepharisma':4,
+ 'ciliate':6, 'euplotes':10, 'mesodinium':29, 'myrionecta':29, 'peritrich':30,
+ '1':1, '4':4, '6':6, '10':10, '29':29, '30':30, 'chilo':'chilo'}
+
+ if str(gCode).lower() not in transTable:
+ print("\nWarning: Provided genetic code is not supported (yet).\n")
+ print("Currently running using the UNIVERSAL genetic code.\n\n")
+ print("Alternative genetic codes are as follows (Note: numbers "\
+ "correspond to NCBI genetic code tables):\n")
+ print('\n'.join(list(transTable.keys()))+'\n')
+ return 'Universal',1
+ else:
+ return gCode,transTable[str(gCode).lower()]
+
+ def getCDNtable(gCode):
+ # Returns the appropriate codon table to be used for the ENc calculations.
+ # Universal codon table, with 6-fold degenerate codons split
+ # into four-fold and two-fold groups.
+ universal_no6fold = {
+ 'GCT': ['A', 'four', 0], 'GCC': ['A', 'four', 0], 'GCA': ['A', 'four', 0],
+ 'GCG': ['A', 'four', 0], 'CGT': ['R', 'four', 0], 'CGC': ['R', 'four', 0],
+ 'CGG': ['R', 'four', 0], 'CGA': ['R', 'four', 0], 'AGA': ['R_', 'two', 0],
+ 'AGG': ['R_', 'two', 0], 'AAT': ['N', 'two', 0], 'AAC': ['N', 'two', 0],
+ 'GAT': ['D', 'two', 0], 'GAC': ['D', 'two', 0], 'TGT': ['C', 'two', 0],
+ 'TGC': ['C', 'two', 0], 'CAA': ['Q', 'two', 0], 'CAG': ['Q', 'two', 0],
+ 'GAA': ['E', 'two', 0], 'GAG': ['E', 'two', 0], 'GGT': ['G', 'four', 0],
+ 'GGC': ['G', 'four', 0], 'GGA': ['G', 'four', 0], 'GGG': ['G', 'four', 0],
+ 'CAT': ['H', 'two', 0], 'CAC': ['H', 'two', 0], 'ATT': ['I', 'three', 0],
+ 'ATC': ['I', 'three', 0], 'ATA': ['I', 'three', 0], 'ATG': ['M', 'one', 0],
+ 'TTA': ['L_', 'two', 0], 'TTG': ['L_', 'two', 0], 'CTT': ['L', 'four', 0],
+ 'CTC': ['L', 'four', 0], 'CTA': ['L', 'four', 0], 'CTG': ['L', 'four', 0],
+ 'AAA': ['K', 'two', 0], 'AAG': ['K', 'two', 0], 'TTT': ['F', 'two', 0],
+ 'TTC': ['F', 'two', 0], 'CCT': ['P', 'four', 0], 'CCC': ['P', 'four', 0],
+ 'CCA': ['P', 'four', 0], 'CCG': ['P', 'four', 0], 'TCT': ['S', 'four', 0],
+ 'TCC': ['S', 'four', 0], 'TCA': ['S', 'four', 0], 'TCG': ['S', 'four', 0],
+ 'AGT': ['S_', 'two', 0], 'AGC': ['S_', 'two', 0], 'ACT': ['T', 'four', 0],
+ 'ACC': ['T', 'four', 0], 'ACA': ['T', 'four', 0], 'ACG': ['T', 'four', 0],
+ 'TGG': ['W', 'one', 0], 'TAT': ['Y', 'two', 0], 'TAC': ['Y', 'two', 0],
+ 'GTT': ['V', 'four', 0], 'GTC': ['V', 'four', 0], 'GTA': ['V', 'four', 0],
+ 'GTG': ['V', 'four', 0], 'TAA': ['*', 'none', 0], 'TGA': ['*', 'none', 0],
+ 'TAG': ['*', 'none', 0], 'XXX': ['_missing', 'none', 0]}
+
+ # Universal codon table, with 6-fold degenerate codons kept
+ # whole, no splitting! Traditional Universal codon table.
+ universal_6fold = {
+ 'GCT': ['A', 'four', 0], 'GCC': ['A', 'four', 0], 'GCA': ['A', 'four', 0],
+ 'GCG': ['A', 'four', 0], 'CGT': ['R', 'six', 0], 'CGC': ['R', 'six', 0],
+ 'CGG': ['R', 'six', 0], 'CGA': ['R', 'six', 0], 'AGA': ['R', 'six', 0],
+ 'AGG': ['R', 'six', 0], 'AAT': ['N', 'two', 0], 'AAC': ['N', 'two', 0],
+ 'GAT': ['D', 'two', 0], 'GAC': ['D', 'two', 0], 'TGT': ['C', 'two', 0],
+ 'TGC': ['C', 'two', 0], 'CAA': ['Q', 'two', 0], 'CAG': ['Q', 'two', 0],
+ 'GAA': ['E', 'two', 0], 'GAG': ['E', 'two', 0], 'GGT': ['G', 'four', 0],
+ 'GGC': ['G', 'four', 0], 'GGA': ['G', 'four', 0], 'GGG': ['G', 'four', 0],
+ 'CAT': ['H', 'two', 0], 'CAC': ['H', 'two', 0], 'ATT': ['I', 'three', 0],
+ 'ATC': ['I', 'three', 0], 'ATA': ['I', 'three', 0], 'ATG': ['M', 'one', 0],
+ 'TTA': ['L', 'six', 0], 'TTG': ['L', 'six', 0], 'CTT': ['L', 'six', 0],
+ 'CTC': ['L', 'six', 0], 'CTA': ['L', 'six', 0], 'CTG': ['L', 'six', 0],
+ 'AAA': ['K', 'two', 0], 'AAG': ['K', 'two', 0], 'TTT': ['F', 'two', 0],
+ 'TTC': ['F', 'two', 0], 'CCT': ['P', 'four', 0], 'CCC': ['P', 'four', 0],
+ 'CCA': ['P', 'four', 0], 'CCG': ['P', 'four', 0], 'TCT': ['S', 'six', 0],
+ 'TCC': ['S', 'six', 0], 'TCA': ['S', 'six', 0], 'TCG': ['S', 'six', 0],
+ 'AGT': ['S', 'six', 0], 'AGC': ['S', 'six', 0], 'ACT': ['T', 'four', 0],
+ 'ACC': ['T', 'four', 0], 'ACA': ['T', 'four', 0], 'ACG': ['T', 'four', 0],
+ 'TGG': ['W', 'one', 0], 'TAT': ['Y', 'two', 0], 'TAC': ['Y', 'two', 0],
+ 'GTT': ['V', 'four', 0], 'GTC': ['V', 'four', 0], 'GTA': ['V', 'four', 0],
+ 'GTG': ['V', 'four', 0], 'TAA': ['*', 'none', 0], 'TGA': ['*', 'none', 0],
+ 'TAG': ['*', 'none', 0], 'XXX': ['_missing', 'none', 0]}
+
+ # Blepharisma (table 4) genetic code codon table, with 6-fold degenerate
+ # codons kept whole, no splitting!
+ blepharisma_6fold = {**universal_6fold,
+ 'TGA': ['W', 'two', 0], 'TGG': ['W', 'two', 0],
+ 'TAA': ['*', 'two', 0], 'TAG': ['*', 'two', 0]}
+
+ # Blepharisma (table 4) genetic code codon table, with 6-fold degenerate
+ # codons split into four-fold and two-fold groups.
+ blepharisma_no6fold = {**universal_no6fold,
+ 'TGA': ['W', 'two', 0], 'TGG': ['W', 'two', 0],
+ 'TAA': ['*', 'two', 0], 'TAG': ['*', 'two', 0]}
+
+ # Chilodonella genetic code codon table, with 6-fold degenerate
+ # codons kept whole, no splitting!
+ chilo_6fold = {**universal_6fold,
+ 'CAA': ['Q', 'four', 0], 'CAG': ['Q', 'four', 0],
+ 'TAA': ['*', 'one', 0], 'TAG': ['Q', 'four', 0],
+ 'TGA': ['Q', 'four', 0]}
+
+ # Chilodonella genetic code codon table, with 6-fold degenerate
+ # codons split into four-fold and two-fold groups.
+ # Note that this also splits four-fold degenerate codons that OUGHT to
+ # be in "different" functional categories (e.g. CAG =/= TAG)
+ chilo_no6fold = {**universal_no6fold,
+ 'TAA': ['*', 'one', 0], 'TAG': ['Q_', 'one', 0],
+ 'TGA': ['Q_', 'one', 0]}
+
+ # Ciliate (table 6) genetic code codon table, with 6-fold degenerate
+ # codons kept whole, no splitting! Traditional ciliate codon table.
+ ciliate_6fold = {**universal_6fold,
+ 'CAA': ['Q', 'four', 0], 'CAG': ['Q', 'four', 0],
+ 'TAA': ['Q', 'four', 0], 'TAG': ['Q', 'four', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ # Ciliate (table 6) genetic code codon table, with 6-fold degenerate
+ # codons split into four-fold and two-fold groups.
+ # Note that this also splits four-fold degenerate codons that OUGHT to
+ # be in "different" functional categories (e.g. CAA =/= TAA)
+ ciliate_no6fold = {**universal_no6fold,
+ 'TAA': ['Q_', 'two', 0], 'TAG': ['Q_', 'two', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ # Euplotes codon table, with 6-fold degenerate codons kept
+ # whole, no splitting! Traditional Universal codon table.
+ euplotes_6fold = {**universal_6fold,
+ 'TGA': ['C', 'three', 0], 'TGT': ['C', 'three', 0],
+ 'TGC': ['C', 'three', 0], 'TAA': ['*', 'two', 0],
+ 'TAG': ['*', 'two',0]}
+
+ # Euplotes genetic code codon table, with 6-fold degenerate codons
+ # split into four-fold and two-fold groups.
+ euplotes_no6fold = {**universal_no6fold,
+ 'TGA': ['C', 'three', 0], 'TGT': ['C', 'three', 0],
+ 'TGC': ['C', 'three', 0], 'TAA': ['*', 'two', 0],
+ 'TAG': ['*', 'two',0]}
+
+ # Mesodinium/Myrionecta (table 29) genetic code codon table, with 6-fold
+ # degenerate codons kept whole, no splitting! Traditional ciliate codon table.
+ mesodinium_6fold = {**universal_6fold,
+ 'TAA': ['Y', 'four', 0], 'TAT': ['Y', 'four', 0],
+ 'TAG': ['Y', 'four', 0], 'TAC': ['Y', 'four', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ # Mesodinium/Myrionecta (table 29) genetic code codon table, with 6-fold
+ # degenerate codons split into four-fold and two-fold groups.
+ mesodinium_no6fold = {**universal_no6fold,
+ 'TAA': ['Y', 'four', 0], 'TAT': ['Y', 'four', 0],
+ 'TAG': ['Y', 'four', 0], 'TAC': ['Y', 'four', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ # Peritrich (table 30) genetic code codon table, with 6-fold degenerate
+ # codons kept whole, no splitting! Traditional ciliate codon table.
+ peritrich_6fold = {**universal_6fold,
+ 'GAA': ['E', 'four', 0], 'GAG': ['E', 'four', 0],
+ 'TAA': ['E', 'four', 0], 'TAG': ['E', 'four', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ # Peritrich (table 30) genetic code codon table, with 6-fold degenerate
+ # codons split into four-fold and two-fold groups.
+ # Note that this also splits four-fold degenerate codons that OUGHT to
+ # be in "different" functional categories (e.g. CAA =/= TAA)
+ peritrich_no6fold = {**universal_no6fold,
+ 'TAA': ['E_', 'two', 0], 'TAG': ['E_', 'two', 0],
+ 'TGA': ['*', 'one', 0]}
+
+ cdnTableDict = {1:[universal_no6fold,universal_6fold],
+ 4:[blepharisma_no6fold, blepharisma_6fold],
+ 6:[ciliate_no6fold,ciliate_6fold],
+ 10:[euplotes_no6fold,euplotes_6fold],
+ 29:[mesodinium_no6fold,mesodinium_6fold],
+ 30:[peritrich_no6fold,peritrich_6fold],
+ 'chilodonella':[chilo_no6fold,chilo_6fold],
+ 'chilo':[chilo_no6fold,chilo_6fold]}
+ return cdnTableDict[gCode]
+
+ def mapCdns(seq, cdnTable):
+ # Updates the codon counts for a given sequence to the respective codon
+ # count table (e.g. with or without 6-fold degeneracy).
+ codons = [seq[n:n+3] for n in range(0, len(seq)-len(seq)%3, 3)]
+ amb_cdn = 0
+ for c in codons:
+ try:
+ cdnTable[c][-1] += 1
+ except:
+ amb_cdn += 1
+ if cdnTable['TCC'][1] == 'six':
+ return cdnTable, amb_cdn
+ else:
+ return cdnTable
+
+class GCeval():
+ """
+ Returns %GC values from DNA sequences of various types.
+ """
+ def gcTotal(seq):
+ # This function returns global GC content
+ return round(GC(seq), 4)
+
+ def gc1(seq):
+ # This function return the GC content of the first position of a codon
+ return round(GC(''.join([seq[n] for n in range(0, len(seq), 3)])), 4)
+
+ def gc2(seq):
+ # This function return the GC content of the second position of a codon
+ return round(GC(''.join([seq[n] for n in
+ range(1, len(seq)-len(seq[1:]) % 3, 3)])), 4)
+
+ def gc3(seq):
+ # This function return the GC content of the third position of a codon
+ return round(GC(''.join([seq[n] for n in
+ range(2, len(seq)-len(seq[2:]) % 3, 3)])), 4)
+
+ def gc3_4F(cdnTbl):
+ # # This function return the GC content of the third position of four-fold
+ # # degenerate codons
+ FrFold = round(GC(''.join([k[-1]*v[-1] for k, v in cdnTbl.items() if
+ 'one' not in v[1]])), 4)
+ return FrFold
+
+class SeqInfo(object):
+ """
+ Provides a means to harbor the data for each individual contig/gene in a
+ given fasta file.
+ This includes GC content (various types), Effective Number of codons
+ (ENc; again various calculations), Relative Synonymous Codon Usage (RSCU).
+ """
+ def __init__(self,seq,gcode='universal'):
+ self.ntd = str(seq)
+ self.gcode, self.transTable = GenUtil.convertGenCode(gcode)
+ # Dictionary of the GC-related functions/calculations
+ self.gcFuncs = {'gcOverall':GCeval.gcTotal,'gc1':GCeval.gc1,'gc2':GCeval.gc2,'gc3':GCeval.gc3}
+
+ def countCodons(self):
+ # Stores the different codon tables and updates their codon counts
+ cdnTbls = GenUtil.getCDNtable(self.transTable)
+ self.cdnCounts_6F,self.amb_cdn = GenUtil.mapCdns(self.ntd, cdnTbls[1])
+ self.cdnCounts_No6F = GenUtil.mapCdns(self.ntd, cdnTbls[0])
+
+ def ENcStats(self):
+ # Stores the various Effective Number of Codons calculations in the class
+ self.expENc = CalcCUB.expWrightENc(self.gc3)
+ self.obsENc_6F = CalcCUB.calcWrightENc(self.cdnCounts_6F)
+ self.obsENc_No6F = CalcCUB.calcWrightENc(self.cdnCounts_No6F)
+ self.SunENc_6F = CalcCUB.SunEq5(self.cdnCounts_6F)
+ self.SunENc_No6F = CalcCUB.SunEq5(self.cdnCounts_No6F)
+
+ def GCstats(self):
+ # Stores the various GC-stats in the class
+ for k, v in self.gcFuncs.items():
+ setattr(self,k,v(self.ntd))
+ self.gc4F = GCeval.gc3_4F(self.cdnCounts_No6F)
+
+
+ def RSCUstats(self):
+ self.rscu_No6Fold = CalcCUB.RSCU(self.cdnCounts_No6F)
+ self.rscu_6Fold = CalcCUB.RSCU(self.cdnCounts_6F)
+
+
+def prepFolders(outName):
+ if os.path.isdir(outName) == False:
+ os.mkdir(outName)
+ if os.path.isdir(outName+'/Plots') == False:
+ os.mkdir(outName+'/Plots')
+ if os.path.isdir(outName+'/SpreadSheets') == False:
+ os.mkdir(outName+'/SpreadSheets')
+
+
+def CalcRefFasta(fasta, gCode):
+ seqDB = {i.description:SeqInfo(i.seq, gCode) for i in SeqIO.parse(fasta,'fasta')}
+ GenCDNtable = {}
+ for k, v in seqDB.items():
+ v.countCodons()
+ v.GCstats()
+ v.ENcStats()
+ for k, v in v.cdnCounts_6F.items():
+ if k.isalpha() and k not in GenCDNtable .keys():
+ GenCDNtable[k] = [v[0],v[-1]]
+ else:
+ GenCDNtable[k][-1] += v[-1]
+ RSCU = CalcCUB.calcRCSU(GenCDNtable)
+ return seqDB, RSCU
+
+
+def WriteWrightOut(seqData, outName, comp):
+ if comp == False:
+ with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.ENc.Raw.tsv','w+') as w:
+ w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\t'
+ 'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t'
+ 'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
+ for k, v in seqData.items():
+ name = [k]
+ gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc4F)]
+ ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F),
+ str(v.SunENc_6F),str(v.SunENc_No6F)]
+ w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n')
+ else:
+ with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.CompTrans.ENc.Raw.tsv','w+') as w:
+ w.write('SequenceID\tAmbiguousCodons\tGC-Overall\tGC1\tGC2\tGC3\t'
+ 'GC3-Degen\tExpWrightENc\tObsWrightENc_6Fold\tObsWrightENc_No6Fold\t'
+ 'ObsWeightedENc_6Fold\tObsWeightedENc_No6Fold\n')
+ for k, v in seqData.items():
+ name = [k]
+ gcs = [str(v.gcOverall),str(v.gc1),str(v.gc2),str(v.gc3),str(v.gc4F)]
+ ENc = [str(v.expENc),str(v.obsENc_6F),str(v.obsENc_No6F),
+ str(v.SunENc_6F),str(v.SunENc_No6F)]
+ w.write('\t'.join(name+[str(v.amb_cdn)]+gcs+ENc)+'\n')
+
+
+def getCompFasta(fasta, gCode):
+ print(fasta)
+ stopCDNs = {'1':['TAA','TAG','TGA'], '4':['TAA','TAG'], '6':['TGA'], '10':['TAA','TAG'],
+ '29':['TGA'], '30':['TGA'], 'universal':['TAA','TAG','TGA'], 'blepharisma':['TAA','TAG'],
+ 'ciliate':['TGA'],'euplotes':['TAA','TAG'], 'mesodinium':['TGA'], 'peritrich':['TGA'],
+ 'chilo':['TAA']}
+ if gCode.lower() not in stopCDNs.keys():
+ stops = stopCDNs['1']
+ else:
+ stops = stopCDNs[gCode]
+
+ with open(fasta.replace('.fasta','.Comp.fasta'),'w+') as w:
+ for i in SeqIO.parse(fasta,'fasta'):
+ #if str(i.seq).upper().startswith('ATG') and str(i.seq).upper()[-3:] in stops:
+ #if str(i.seq).upper()[-3:] in stops:
+ if len(i.seq) % 3 == 0:
+ w.write('>'+i.description+'\n'+str(i.seq)+'\n')
+
+ return fasta.replace('.fasta','.Comp.fasta')
+
+def WriteNullENcOut(outName):
+ with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.ENc.Null.tsv','w+') as w:
+ w.write('GC3\tENc\n')
+ w.write('\n'.join(CalcCUB.nullENcGC3()))
+
+
+def WriteRSCUtbl(RSCUtbl, outName):
+ with open(outName+'/SpreadSheets/'+outName.split('/')[-1]+'.RSCU.tsv','w+') as w:
+ w.write('Codon\tAmino Acid\tRSCU\n')
+ for k,v in RSCUtbl.items():
+ w.write(k+'\t'+'\t'.join(v)+'\n')
+
+
+if __name__ == "__main__":
+ if len(sys.argv) < 2:
+ print('\nUsage:\n')
+ print('python CUB.py MyNtds.fasta MyTaxon genetic_code\n')
+ print('\nGenetic Codes:\n')
+ gcd = ['1', '4', '6', '10', '29', '30', 'universal', 'blepharisma',
+ 'ciliate','euplotes', 'mesodinium', 'peritrich','chilo']
+ print('\n'.join(gcd)+'\n')
+ sys.exit()
+ fasta = sys.argv[1]
+ try:
+ outName = sys.argv[2]
+ except:
+ print('Missing an output name. Include one, then run again!')
+ sys.exit()
+ try:
+ gCode = sys.argv[3]
+ except:
+ gCode = 'universal'
+ compFasta = getCompFasta(fasta, gCode)
+ prepFolders(outName)
+ fastaDataRaw, RSCUtbl = CalcRefFasta(fasta, gCode)
+ fastaDataComp, RSCUtbl = CalcRefFasta(compFasta, gCode)
+ WriteWrightOut(fastaDataRaw, outName, comp=False)
+ WriteWrightOut(fastaDataComp, outName, comp=True)
+ WriteNullENcOut(outName)
+ WriteRSCUtbl(RSCUtbl, outName)
+ os.system('cp '+fasta+' '+outName+'/')
+ os.system('mv '+compFasta+' '+outName+'/')
diff --git a/PTL1/Transcriptomes/Scripts/PTL1.2831.out b/PTL1/Transcriptomes/Scripts/PTL1.2831.out
new file mode 100644
index 0000000..aaee3ca
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/PTL1.2831.out
@@ -0,0 +1,31859 @@
+
+The following have been reloaded with a version change:
+ 1) GCCcore/10.2.0 => GCCcore/8.3.0
+ 2) GMP/6.2.0-GCCcore-10.2.0 => GMP/6.1.2-GCCcore-8.3.0
+ 3) Python/3.8.6-GCCcore-10.2.0 => Python/3.7.4-GCCcore-8.3.0
+ 4) SQLite/3.33.0-GCCcore-10.2.0 => SQLite/3.29.0-GCCcore-8.3.0
+ 5) Tcl/8.6.10-GCCcore-10.2.0 => Tcl/8.6.9-GCCcore-8.3.0
+ 6) XZ/5.2.5-GCCcore-10.2.0 => XZ/5.2.4-GCCcore-8.3.0
+ 7) binutils/2.35-GCCcore-10.2.0 => binutils/2.32-GCCcore-8.3.0
+ 8) bzip2/1.0.8-GCCcore-10.2.0 => bzip2/1.0.8-GCCcore-8.3.0
+ 9) libffi/3.3-GCCcore-10.2.0 => libffi/3.2.1-GCCcore-8.3.0
+ 10) libreadline/8.0-GCCcore-10.2.0 => libreadline/8.0-GCCcore-8.3.0
+ 11) ncurses/6.2-GCCcore-10.2.0 => ncurses/6.1-GCCcore-8.3.0
+ 12) zlib/1.2.11-GCCcore-10.2.0 => zlib/1.2.11-GCCcore-8.3.0
+
+
+The following have been reloaded with a version change:
+ 1) GCC/8.3.0 => GCC/10.3.0
+ 2) GCCcore/8.3.0 => GCCcore/10.3.0
+ 3) binutils/2.32-GCCcore-8.3.0 => binutils/2.36.1-GCCcore-10.3.0
+ 4) bzip2/1.0.8-GCCcore-8.3.0 => bzip2/1.0.8-GCCcore-10.3.0
+ 5) zlib/1.2.11-GCCcore-8.3.0 => zlib/1.2.11-GCCcore-10.3.0
+
+[1m
+
+Prepping [92mSr_rh_Emac_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m60195 contigs > 200[0m[1m in [36mSr_rh_Emac_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Tx01_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m142089 contigs > 200[0m[1m in [36mSr_rh_Tx01_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn13_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m150535 contigs > 200[0m[1m in [36mSr_rh_Nn13_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Sspa_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m96071 contigs > 200[0m[1m in [36mSr_rh_Sspa_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn06_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m145214 contigs > 200[0m[1m in [36mSr_rh_Nn06_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Atps_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m10253 contigs > 200[0m[1m in [36mSr_rh_Atps_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv01_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m208216 contigs > 200[0m[1m in [36mSr_rh_Bv01_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv05_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m218559 contigs > 200[0m[1m in [36mSr_rh_Bv05_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Gl03_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m251483 contigs > 200[0m[1m in [36mSr_rh_Gl03_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv04_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m224949 contigs > 200[0m[1m in [36mSr_rh_Bv04_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Gl01_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m8191 contigs > 200[0m[1m in [36mSr_rh_Gl01_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Hhir_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m55856 contigs > 200[0m[1m in [36mSr_rh_Hhir_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn02_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m138826 contigs > 200[0m[1m in [36mSr_rh_Nn02_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Slin_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m37070 contigs > 200[0m[1m in [36mSr_rh_Slin_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Emar_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m43809 contigs > 200[0m[1m in [36mSr_rh_Emar_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Calb_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m75768 contigs > 200[0m[1m in [36mSr_rh_Calb_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Rsp1_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m167000 contigs > 200[0m[1m in [36mSr_rh_Rsp1_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn09_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m221270 contigs > 200[0m[1m in [36mSr_rh_Nn09_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn10_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m140733 contigs > 200[0m[1m in [36mSr_rh_Nn10_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn01_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m172554 contigs > 200[0m[1m in [36mSr_rh_Nn01_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn12_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m136924 contigs > 200[0m[1m in [36mSr_rh_Nn12_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv03_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m228384 contigs > 200[0m[1m in [36mSr_rh_Bv03_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Hind_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m65043 contigs > 200[0m[1m in [36mSr_rh_Hind_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn04_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m312525 contigs > 200[0m[1m in [36mSr_rh_Nn04_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn08_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m198852 contigs > 200[0m[1m in [36mSr_rh_Nn08_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn07_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m172565 contigs > 200[0m[1m in [36mSr_rh_Nn07_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn11_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m129060 contigs > 200[0m[1m in [36mSr_rh_Nn11_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn14_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m152790 contigs > 200[0m[1m in [36mSr_rh_Nn14_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Gsp1_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m62212 contigs > 200[0m[1m in [36mSr_rh_Gsp1_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Halb_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m100948 contigs > 200[0m[1m in [36mSr_rh_Halb_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv06_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m143978 contigs > 200[0m[1m in [36mSr_rh_Bv06_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Gl02_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m261586 contigs > 200[0m[1m in [36mSr_rh_Gl02_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn05_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m128153 contigs > 200[0m[1m in [36mSr_rh_Nn05_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Nn03_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m131998 contigs > 200[0m[1m in [36mSr_rh_Nn03_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Esca_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m99293 contigs > 200[0m[1m in [36mSr_rh_Esca_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Usac_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m133441 contigs > 200[0m[1m in [36mSr_rh_Usac_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Bv02_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m236067 contigs > 200[0m[1m in [36mSr_rh_Bv02_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+[1m
+
+Prepping [92mSr_rh_Gspa_assembledTranscripts.fasta[0m
+[1m
+
+There are [91m22017 contigs > 200[0m[1m in [36mSr_rh_Gspa_assembledTranscripts.fasta[0m
+[1m
+
+Look for [36m/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa.200bp.fasta[0m[1m
+
+
+Next Script is: [92m2_Auto_rRNA_BvE.py[0m[1m
+(Alternatively[92m 2a_remove_rRNA.py followed by 2b_remove_Bact.py[0m[1m)
+
+[0m
+MERGE following files
+CREATE a dictionnary of sequences
+
+Error in cross-plate contamination assessment: the ten-digit code Sr_rh_Gspa is not found in the conspecific names file. Please check that this file is correct and try again.
+
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn02.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn02.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.212s]
+Masking queries... [0.336s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.137s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.097s]
+Masking reference... [0.717s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.306s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.233s]
+Building query seed array... [0.09s]
+Computing hash join... [0.113s]
+Building seed filter... [0.008s]
+Searching alignments... [0.148s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.095s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.134s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.099s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.144s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.085s]
+Computing hash join... [0.095s]
+Building seed filter... [0.008s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.214s]
+Building query seed array... [0.085s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.102s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.13s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.255s]
+Building query seed array... [0.105s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.127s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.092s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.126s]
+Deallocating buffers... [0.057s]
+Computing alignments... [1.45s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.021s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.975s
+Reported 13195 pairwise alignments, 13268 HSPs.
+13195 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.247s]
+Masking queries... [0.318s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.128s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.978s]
+Masking reference... [0.649s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.27s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.218s]
+Building query seed array... [0.101s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.324s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.104s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.278s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.097s]
+Computing hash join... [0.089s]
+Building seed filter... [0.008s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.086s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.318s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.204s]
+Building query seed array... [0.091s]
+Computing hash join... [0.087s]
+Building seed filter... [0.008s]
+Searching alignments... [0.234s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.095s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.205s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.101s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.219s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.09s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.203s]
+Deallocating buffers... [0.052s]
+Computing alignments... [2.586s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.677s
+Reported 27299 pairwise alignments, 27536 HSPs.
+27299 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/Sr_rh_Nn02_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn02_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Gspa.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Gspa.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.299s]
+Masking queries... [0.104s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.046s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.097s]
+Masking reference... [0.693s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.327s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.235s]
+Building query seed array... [0.037s]
+Computing hash join... [0.079s]
+Building seed filter... [0.005s]
+Searching alignments... [0.061s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.247s]
+Building query seed array... [0.037s]
+Computing hash join... [0.065s]
+Building seed filter... [0.004s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.255s]
+Building query seed array... [0.042s]
+Computing hash join... [0.063s]
+Building seed filter... [0.005s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.037s]
+Computing hash join... [0.062s]
+Building seed filter... [0.004s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.202s]
+Building query seed array... [0.035s]
+Computing hash join... [0.06s]
+Building seed filter... [0.004s]
+Searching alignments... [0.054s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.235s]
+Building query seed array... [0.04s]
+Computing hash join... [0.057s]
+Building seed filter... [0.004s]
+Searching alignments... [0.052s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.041s]
+Computing hash join... [0.061s]
+Building seed filter... [0.004s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.203s]
+Building query seed array... [0.036s]
+Computing hash join... [0.06s]
+Building seed filter... [0.004s]
+Searching alignments... [0.052s]
+Deallocating buffers... [0.055s]
+Computing alignments... [0.628s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.003s]
+Deallocating queries... [0.003s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 6.484s
+Reported 4770 pairwise alignments, 4832 HSPs.
+4770 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/BvE
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.299s]
+Masking queries... [0.154s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.048s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.99s]
+Masking reference... [0.788s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.273s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.22s]
+Building query seed array... [0.054s]
+Computing hash join... [0.067s]
+Building seed filter... [0.004s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.034s]
+Computing hash join... [0.058s]
+Building seed filter... [0.004s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.24s]
+Building query seed array... [0.044s]
+Computing hash join... [0.057s]
+Building seed filter... [0.005s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.039s]
+Computing hash join... [0.058s]
+Building seed filter... [0.004s]
+Searching alignments... [0.065s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.191s]
+Building query seed array... [0.032s]
+Computing hash join... [0.054s]
+Building seed filter... [0.004s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.039s]
+Computing hash join... [0.052s]
+Building seed filter... [0.005s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.045s]
+Computing hash join... [0.06s]
+Building seed filter... [0.005s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.19s]
+Building query seed array... [0.03s]
+Computing hash join... [0.052s]
+Building seed filter... [0.004s]
+Searching alignments... [0.06s]
+Deallocating buffers... [0.049s]
+Computing alignments... [0.79s]
+Deallocating reference... [0.016s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.003s]
+Deallocating queries... [0.003s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 6.567s
+Reported 9142 pairwise alignments, 9308 HSPs.
+9142 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/Sr_rh_Gspa_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Gspa_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn06.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn06.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.259s]
+Masking queries... [0.362s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.129s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.101s]
+Masking reference... [0.69s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.299s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.23s]
+Building query seed array... [0.104s]
+Computing hash join... [0.111s]
+Building seed filter... [0.007s]
+Searching alignments... [0.145s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.255s]
+Building query seed array... [0.1s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.144s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.103s]
+Computing hash join... [0.1s]
+Building seed filter... [0.006s]
+Searching alignments... [0.141s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.214s]
+Building query seed array... [0.092s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.141s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.099s]
+Computing hash join... [0.098s]
+Building seed filter... [0.008s]
+Searching alignments... [0.13s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.244s]
+Building query seed array... [0.109s]
+Computing hash join... [0.101s]
+Building seed filter... [0.008s]
+Searching alignments... [0.127s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.106s]
+Computing hash join... [0.097s]
+Building seed filter... [0.008s]
+Searching alignments... [0.137s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.102s]
+Computing hash join... [0.1s]
+Building seed filter... [0.009s]
+Searching alignments... [0.13s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.366s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.021s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.048s
+Reported 13937 pairwise alignments, 14011 HSPs.
+13937 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.265s]
+Masking queries... [0.333s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.133s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.004s]
+Masking reference... [0.644s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.272s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.22s]
+Building query seed array... [0.107s]
+Computing hash join... [0.129s]
+Building seed filter... [0.007s]
+Searching alignments... [0.357s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.231s]
+Building query seed array... [0.099s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.323s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.103s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.218s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.087s]
+Computing hash join... [0.094s]
+Building seed filter... [0.008s]
+Searching alignments... [0.312s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.198s]
+Building query seed array... [0.089s]
+Computing hash join... [0.092s]
+Building seed filter... [0.008s]
+Searching alignments... [0.251s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.099s]
+Computing hash join... [0.092s]
+Building seed filter... [0.009s]
+Searching alignments... [0.235s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.238s]
+Building query seed array... [0.107s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.234s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.091s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.226s]
+Deallocating buffers... [0.051s]
+Computing alignments... [2.637s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.998s
+Reported 29695 pairwise alignments, 29910 HSPs.
+29695 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/Sr_rh_Nn06_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn06_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv02.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv02.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.833s]
+Masking queries... [0.55s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.161s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.098s]
+Masking reference... [0.696s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.298s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.233s]
+Building query seed array... [0.127s]
+Computing hash join... [0.113s]
+Building seed filter... [0.006s]
+Searching alignments... [0.182s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.11s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.18s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.13s]
+Computing hash join... [0.101s]
+Building seed filter... [0.007s]
+Searching alignments... [0.173s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.097s]
+Computing hash join... [0.095s]
+Building seed filter... [0.007s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.101s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.154s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.114s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.158s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.115s]
+Computing hash join... [0.1s]
+Building seed filter... [0.007s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.216s]
+Building query seed array... [0.1s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.157s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.721s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.493s
+Reported 18788 pairwise alignments, 18972 HSPs.
+18788 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.836s]
+Masking queries... [0.465s]
+Building query seed set... [0.049s]
+Algorithm: Double-indexed
+Building query histograms... [0.155s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.978s]
+Masking reference... [0.644s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.282s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.122s]
+Computing hash join... [0.106s]
+Building seed filter... [0.008s]
+Searching alignments... [0.399s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.112s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.343s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.114s]
+Computing hash join... [0.09s]
+Building seed filter... [0.009s]
+Searching alignments... [0.3s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.199s]
+Building query seed array... [0.108s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.348s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.202s]
+Building query seed array... [0.1s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.293s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.111s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.252s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.13s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.245s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.101s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.246s]
+Deallocating buffers... [0.051s]
+Computing alignments... [3.276s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.017s]
+Deallocating queries... [0.023s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.717s
+Reported 38037 pairwise alignments, 38537 HSPs.
+38037 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/Sr_rh_Bv02_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv02_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Hind.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Hind.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.878s]
+Masking queries... [0.263s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.101s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.102s]
+Masking reference... [0.695s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.322s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.092s]
+Computing hash join... [0.118s]
+Building seed filter... [0.005s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.25s]
+Building query seed array... [0.08s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.079s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.107s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.23s]
+Building query seed array... [0.077s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.213s]
+Building query seed array... [0.07s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.103s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.08s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.101s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.246s]
+Building query seed array... [0.082s]
+Computing hash join... [0.09s]
+Building seed filter... [0.006s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.074s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.092s]
+Deallocating buffers... [0.059s]
+Computing alignments... [0.886s]
+Deallocating reference... [0.028s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.011s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.616s
+Reported 7467 pairwise alignments, 7480 HSPs.
+7467 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.888s]
+Masking queries... [0.252s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.114s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.998s]
+Masking reference... [0.663s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.286s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.085s]
+Computing hash join... [0.118s]
+Building seed filter... [0.006s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.082s]
+Computing hash join... [0.09s]
+Building seed filter... [0.005s]
+Searching alignments... [0.144s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.079s]
+Computing hash join... [0.087s]
+Building seed filter... [0.006s]
+Searching alignments... [0.13s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.069s]
+Computing hash join... [0.086s]
+Building seed filter... [0.005s]
+Searching alignments... [0.131s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.194s]
+Building query seed array... [0.074s]
+Computing hash join... [0.085s]
+Building seed filter... [0.005s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.078s]
+Computing hash join... [0.084s]
+Building seed filter... [0.005s]
+Searching alignments... [0.127s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.227s]
+Building query seed array... [0.081s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.118s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.191s]
+Building query seed array... [0.073s]
+Computing hash join... [0.087s]
+Building seed filter... [0.007s]
+Searching alignments... [0.111s]
+Deallocating buffers... [0.05s]
+Computing alignments... [1.503s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.009s
+Reported 14755 pairwise alignments, 14799 HSPs.
+14755 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/Sr_rh_Hind_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Hind_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn11.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn11.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.123s]
+Masking queries... [0.301s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.127s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.09s]
+Masking reference... [0.688s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.286s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.231s]
+Building query seed array... [0.102s]
+Computing hash join... [0.12s]
+Building seed filter... [0.007s]
+Searching alignments... [0.134s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.098s]
+Computing hash join... [0.096s]
+Building seed filter... [0.008s]
+Searching alignments... [0.132s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.255s]
+Building query seed array... [0.093s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.082s]
+Computing hash join... [0.096s]
+Building seed filter... [0.008s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.208s]
+Building query seed array... [0.084s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.236s]
+Building query seed array... [0.091s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.243s]
+Building query seed array... [0.086s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.111s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.082s]
+Computing hash join... [0.101s]
+Building seed filter... [0.007s]
+Searching alignments... [0.111s]
+Deallocating buffers... [0.056s]
+Computing alignments... [1.084s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.263s
+Reported 11697 pairwise alignments, 11771 HSPs.
+11697 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.128s]
+Masking queries... [0.307s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.119s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.991s]
+Masking reference... [0.636s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.269s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.216s]
+Building query seed array... [0.098s]
+Computing hash join... [0.109s]
+Building seed filter... [0.006s]
+Searching alignments... [0.295s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.229s]
+Building query seed array... [0.088s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.181s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.243s]
+Building query seed array... [0.09s]
+Computing hash join... [0.088s]
+Building seed filter... [0.008s]
+Searching alignments... [0.17s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.075s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.166s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.194s]
+Building query seed array... [0.086s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.152s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.221s]
+Building query seed array... [0.087s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.163s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.095s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.155s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.193s]
+Building query seed array... [0.085s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.151s]
+Deallocating buffers... [0.051s]
+Computing alignments... [1.964s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.254s
+Reported 25408 pairwise alignments, 25601 HSPs.
+25408 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/Sr_rh_Nn11_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn11_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv03.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv03.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.786s]
+Masking queries... [0.459s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.148s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.108s]
+Masking reference... [0.701s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.301s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.235s]
+Building query seed array... [0.115s]
+Computing hash join... [0.11s]
+Building seed filter... [0.006s]
+Searching alignments... [0.176s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.106s]
+Computing hash join... [0.095s]
+Building seed filter... [0.008s]
+Searching alignments... [0.158s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.246s]
+Building query seed array... [0.107s]
+Computing hash join... [0.097s]
+Building seed filter... [0.008s]
+Searching alignments... [0.17s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.097s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.094s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.106s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.244s]
+Building query seed array... [0.113s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.153s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.205s]
+Building query seed array... [0.091s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.149s]
+Deallocating buffers... [0.056s]
+Computing alignments... [1.651s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.02s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.134s
+Reported 18214 pairwise alignments, 18404 HSPs.
+18214 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/BvE
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.797s]
+Masking queries... [0.454s]
+Building query seed set... [0.051s]
+Algorithm: Double-indexed
+Building query histograms... [0.149s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.046s]
+Masking reference... [0.659s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.279s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.227s]
+Building query seed array... [0.107s]
+Computing hash join... [0.108s]
+Building seed filter... [0.009s]
+Searching alignments... [0.363s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.228s]
+Building query seed array... [0.108s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.313s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.107s]
+Computing hash join... [0.09s]
+Building seed filter... [0.006s]
+Searching alignments... [0.297s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.098s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.347s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.202s]
+Building query seed array... [0.105s]
+Computing hash join... [0.087s]
+Building seed filter... [0.007s]
+Searching alignments... [0.255s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.106s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.253s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.107s]
+Computing hash join... [0.088s]
+Building seed filter... [0.009s]
+Searching alignments... [0.229s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.098s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.233s]
+Deallocating buffers... [0.05s]
+Computing alignments... [3.164s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.417s
+Reported 36335 pairwise alignments, 36838 HSPs.
+36335 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/Sr_rh_Bv03_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv03_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Gsp1.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Gsp1.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.606s]
+Masking queries... [0.179s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.071s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.127s]
+Masking reference... [0.691s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.311s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.24s]
+Building query seed array... [0.068s]
+Computing hash join... [0.118s]
+Building seed filter... [0.005s]
+Searching alignments... [0.092s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.059s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.055s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.08s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.053s]
+Computing hash join... [0.082s]
+Building seed filter... [0.006s]
+Searching alignments... [0.081s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.054s]
+Computing hash join... [0.083s]
+Building seed filter... [0.005s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.233s]
+Building query seed array... [0.057s]
+Computing hash join... [0.082s]
+Building seed filter... [0.006s]
+Searching alignments... [0.078s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.246s]
+Building query seed array... [0.059s]
+Computing hash join... [0.081s]
+Building seed filter... [0.006s]
+Searching alignments... [0.073s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.203s]
+Building query seed array... [0.053s]
+Computing hash join... [0.086s]
+Building seed filter... [0.006s]
+Searching alignments... [0.073s]
+Deallocating buffers... [0.057s]
+Computing alignments... [0.674s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.007s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.525s
+Reported 6372 pairwise alignments, 6381 HSPs.
+6372 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.615s]
+Masking queries... [0.175s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.067s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.021s]
+Masking reference... [0.638s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.27s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.216s]
+Building query seed array... [0.067s]
+Computing hash join... [0.111s]
+Building seed filter... [0.005s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.059s]
+Computing hash join... [0.084s]
+Building seed filter... [0.006s]
+Searching alignments... [0.124s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.069s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.109s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.194s]
+Building query seed array... [0.054s]
+Computing hash join... [0.084s]
+Building seed filter... [0.005s]
+Searching alignments... [0.111s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.196s]
+Building query seed array... [0.052s]
+Computing hash join... [0.074s]
+Building seed filter... [0.006s]
+Searching alignments... [0.093s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.221s]
+Building query seed array... [0.054s]
+Computing hash join... [0.078s]
+Building seed filter... [0.006s]
+Searching alignments... [0.098s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.228s]
+Building query seed array... [0.053s]
+Computing hash join... [0.077s]
+Building seed filter... [0.006s]
+Searching alignments... [0.091s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.19s]
+Building query seed array... [0.052s]
+Computing hash join... [0.079s]
+Building seed filter... [0.006s]
+Searching alignments... [0.096s]
+Deallocating buffers... [0.049s]
+Computing alignments... [1.173s]
+Deallocating reference... [0.017s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.008s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.856s
+Reported 13026 pairwise alignments, 13050 HSPs.
+13026 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/Sr_rh_Gsp1_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Gsp1_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv06.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv06.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.977s]
+Masking queries... [0.29s]
+Building query seed set... [0.051s]
+Algorithm: Double-indexed
+Building query histograms... [0.086s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.09s]
+Masking reference... [0.691s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.318s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.072s]
+Computing hash join... [0.134s]
+Building seed filter... [0.006s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.242s]
+Building query seed array... [0.063s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.105s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.254s]
+Building query seed array... [0.067s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.221s]
+Building query seed array... [0.067s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.097s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.213s]
+Building query seed array... [0.059s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.089s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.251s]
+Building query seed array... [0.066s]
+Computing hash join... [0.09s]
+Building seed filter... [0.005s]
+Searching alignments... [0.085s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.243s]
+Building query seed array... [0.072s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.206s]
+Building query seed array... [0.061s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.089s]
+Deallocating buffers... [0.059s]
+Computing alignments... [0.916s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.558s
+Reported 11454 pairwise alignments, 11535 HSPs.
+11454 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0.001s]
+Opening the output file... [0s]
+Loading query sequences... [0.99s]
+Masking queries... [0.258s]
+Building query seed set... [0.048s]
+Algorithm: Double-indexed
+Building query histograms... [0.088s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.994s]
+Masking reference... [0.645s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.273s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.071s]
+Computing hash join... [0.117s]
+Building seed filter... [0.006s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.065s]
+Computing hash join... [0.093s]
+Building seed filter... [0.005s]
+Searching alignments... [0.171s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.069s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.148s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.062s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.179s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.201s]
+Building query seed array... [0.06s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.136s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.229s]
+Building query seed array... [0.068s]
+Computing hash join... [0.084s]
+Building seed filter... [0.005s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.244s]
+Building query seed array... [0.073s]
+Computing hash join... [0.09s]
+Building seed filter... [0.006s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.054s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.13s]
+Deallocating buffers... [0.05s]
+Computing alignments... [1.598s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.277s
+Reported 22234 pairwise alignments, 22429 HSPs.
+22234 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/Sr_rh_Bv06_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv06_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Gl01.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Gl01.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.043s]
+Masking queries... [0.023s]
+Building query seed set... [0.029s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.086s]
+Masking reference... [0.71s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.304s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.243s]
+Building query seed array... [0.012s]
+Computing hash join... [0.076s]
+Building seed filter... [0.004s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.011s]
+Computing hash join... [0.063s]
+Building seed filter... [0.004s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.01s]
+Computing hash join... [0.055s]
+Building seed filter... [0.004s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.205s]
+Building query seed array... [0.006s]
+Computing hash join... [0.051s]
+Building seed filter... [0.004s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.208s]
+Building query seed array... [0.009s]
+Computing hash join... [0.057s]
+Building seed filter... [0.004s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.234s]
+Building query seed array... [0.007s]
+Computing hash join... [0.055s]
+Building seed filter... [0.004s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.011s]
+Computing hash join... [0.054s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.206s]
+Building query seed array... [0.007s]
+Computing hash join... [0.057s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Deallocating buffers... [0.057s]
+Computing alignments... [0.126s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 4.935s
+Reported 901 pairwise alignments, 903 HSPs.
+901 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.026s]
+Building query seed set... [0.029s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.012s]
+Masking reference... [0.627s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.288s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.023s]
+Computing hash join... [0.053s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.231s]
+Building query seed array... [0.018s]
+Computing hash join... [0.049s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.015s]
+Computing hash join... [0.048s]
+Building seed filter... [0.004s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.202s]
+Building query seed array... [0.015s]
+Computing hash join... [0.053s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.2s]
+Building query seed array... [0.018s]
+Computing hash join... [0.05s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.016s]
+Computing hash join... [0.049s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.228s]
+Building query seed array... [0.015s]
+Computing hash join... [0.05s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.018s]
+Computing hash join... [0.049s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Deallocating buffers... [0.052s]
+Computing alignments... [0.168s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 4.846s
+Reported 2013 pairwise alignments, 2017 HSPs.
+2013 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/Sr_rh_Gl01_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Gl01_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Esca.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Esca.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.72s]
+Masking queries... [0.231s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.074s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.084s]
+Masking reference... [0.687s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.303s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.227s]
+Building query seed array... [0.07s]
+Computing hash join... [0.127s]
+Building seed filter... [0.006s]
+Searching alignments... [0.092s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.057s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.087s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.054s]
+Computing hash join... [0.081s]
+Building seed filter... [0.005s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.053s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.086s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.209s]
+Building query seed array... [0.053s]
+Computing hash join... [0.077s]
+Building seed filter... [0.004s]
+Searching alignments... [0.073s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.235s]
+Building query seed array... [0.053s]
+Computing hash join... [0.074s]
+Building seed filter... [0.005s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.262s]
+Building query seed array... [0.07s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.075s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.055s]
+Computing hash join... [0.074s]
+Building seed filter... [0.005s]
+Searching alignments... [0.073s]
+Deallocating buffers... [0.057s]
+Computing alignments... [0.777s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.008s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.742s
+Reported 8279 pairwise alignments, 8300 HSPs.
+8279 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.723s]
+Masking queries... [0.215s]
+Building query seed set... [0.043s]
+Algorithm: Double-indexed
+Building query histograms... [0.082s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.018s]
+Masking reference... [0.642s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.296s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.218s]
+Building query seed array... [0.064s]
+Computing hash join... [0.102s]
+Building seed filter... [0.006s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.056s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.137s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.054s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.054s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.136s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.194s]
+Building query seed array... [0.056s]
+Computing hash join... [0.078s]
+Building seed filter... [0.006s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.066s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.108s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.056s]
+Computing hash join... [0.075s]
+Building seed filter... [0.006s]
+Searching alignments... [0.11s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.048s]
+Computing hash join... [0.086s]
+Building seed filter... [0.005s]
+Searching alignments... [0.116s]
+Deallocating buffers... [0.049s]
+Computing alignments... [1.318s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.01s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.354s
+Reported 17266 pairwise alignments, 17309 HSPs.
+17266 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/Sr_rh_Esca_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Esca_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Calb.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Calb.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.792s]
+Masking queries... [0.208s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.082s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.109s]
+Masking reference... [0.705s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.306s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.233s]
+Building query seed array... [0.076s]
+Computing hash join... [0.131s]
+Building seed filter... [0.004s]
+Searching alignments... [0.104s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.249s]
+Building query seed array... [0.064s]
+Computing hash join... [0.107s]
+Building seed filter... [0.006s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.063s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.093s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.207s]
+Building query seed array... [0.062s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.089s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.208s]
+Building query seed array... [0.061s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.083s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.236s]
+Building query seed array... [0.063s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.083s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.242s]
+Building query seed array... [0.066s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.065s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.081s]
+Deallocating buffers... [0.056s]
+Computing alignments... [0.797s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.01s]
+Deallocating queries... [0.007s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.114s
+Reported 7719 pairwise alignments, 7754 HSPs.
+7719 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.79s]
+Masking queries... [0.213s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.086s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.004s]
+Masking reference... [0.641s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.265s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.216s]
+Building query seed array... [0.079s]
+Computing hash join... [0.118s]
+Building seed filter... [0.005s]
+Searching alignments... [0.142s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.066s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.137s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.229s]
+Building query seed array... [0.062s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.055s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.133s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.196s]
+Building query seed array... [0.055s]
+Computing hash join... [0.091s]
+Building seed filter... [0.005s]
+Searching alignments... [0.118s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.061s]
+Computing hash join... [0.089s]
+Building seed filter... [0.005s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.228s]
+Building query seed array... [0.062s]
+Computing hash join... [0.09s]
+Building seed filter... [0.005s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.191s]
+Building query seed array... [0.063s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.112s]
+Deallocating buffers... [0.05s]
+Computing alignments... [1.391s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.01s]
+Deallocating queries... [0.01s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.576s
+Reported 15220 pairwise alignments, 15279 HSPs.
+15220 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/Sr_rh_Calb_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Calb_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Emac.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Emac.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.739s]
+Masking queries... [0.202s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.086s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.109s]
+Masking reference... [0.69s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.306s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.239s]
+Building query seed array... [0.076s]
+Computing hash join... [0.133s]
+Building seed filter... [0.006s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.068s]
+Computing hash join... [0.109s]
+Building seed filter... [0.005s]
+Searching alignments... [0.097s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.257s]
+Building query seed array... [0.076s]
+Computing hash join... [0.105s]
+Building seed filter... [0.006s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.063s]
+Computing hash join... [0.1s]
+Building seed filter... [0.006s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.208s]
+Building query seed array... [0.06s]
+Computing hash join... [0.1s]
+Building seed filter... [0.006s]
+Searching alignments... [0.088s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.074s]
+Computing hash join... [0.103s]
+Building seed filter... [0.005s]
+Searching alignments... [0.087s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.243s]
+Building query seed array... [0.068s]
+Computing hash join... [0.1s]
+Building seed filter... [0.005s]
+Searching alignments... [0.086s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.207s]
+Building query seed array... [0.063s]
+Computing hash join... [0.1s]
+Building seed filter... [0.005s]
+Searching alignments... [0.083s]
+Deallocating buffers... [0.056s]
+Computing alignments... [0.768s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.009s]
+Deallocating queries... [0.007s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.096s
+Reported 6356 pairwise alignments, 6370 HSPs.
+6356 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.751s]
+Masking queries... [0.21s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.091s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.978s]
+Masking reference... [0.64s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.277s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.225s]
+Building query seed array... [0.08s]
+Computing hash join... [0.145s]
+Building seed filter... [0.005s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.065s]
+Computing hash join... [0.101s]
+Building seed filter... [0.006s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.074s]
+Computing hash join... [0.101s]
+Building seed filter... [0.006s]
+Searching alignments... [0.111s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.064s]
+Computing hash join... [0.098s]
+Building seed filter... [0.005s]
+Searching alignments... [0.11s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.194s]
+Building query seed array... [0.06s]
+Computing hash join... [0.096s]
+Building seed filter... [0.005s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.217s]
+Building query seed array... [0.072s]
+Computing hash join... [0.097s]
+Building seed filter... [0.005s]
+Searching alignments... [0.097s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.229s]
+Building query seed array... [0.073s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.189s]
+Building query seed array... [0.062s]
+Computing hash join... [0.099s]
+Building seed filter... [0.005s]
+Searching alignments... [0.099s]
+Deallocating buffers... [0.05s]
+Computing alignments... [1.187s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.011s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.282s
+Reported 12686 pairwise alignments, 12732 HSPs.
+12686 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/Sr_rh_Emac_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Emac_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn05.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn05.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.137s]
+Masking queries... [0.299s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.121s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.113s]
+Masking reference... [0.703s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.297s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.233s]
+Building query seed array... [0.092s]
+Computing hash join... [0.113s]
+Building seed filter... [0.008s]
+Searching alignments... [0.13s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.089s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.124s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.087s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.082s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.126s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.08s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.088s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.091s]
+Computing hash join... [0.097s]
+Building seed filter... [0.009s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.081s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.117s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.143s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.02s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.346s
+Reported 11705 pairwise alignments, 11759 HSPs.
+11705 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/BvE
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.144s]
+Masking queries... [0.297s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.129s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.997s]
+Masking reference... [0.638s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.27s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.108s]
+Computing hash join... [0.142s]
+Building seed filter... [0.005s]
+Searching alignments... [0.321s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.229s]
+Building query seed array... [0.086s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.265s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.09s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.264s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.203s]
+Building query seed array... [0.076s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.274s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.197s]
+Building query seed array... [0.075s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.17s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.231s]
+Building query seed array... [0.093s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.22s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.229s]
+Building query seed array... [0.095s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.203s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.079s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.157s]
+Deallocating buffers... [0.051s]
+Computing alignments... [2.168s]
+Deallocating reference... [0.017s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.011s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.967s
+Reported 25364 pairwise alignments, 25538 HSPs.
+25364 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/Sr_rh_Nn05_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn05_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn10.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn10.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.355s]
+Masking queries... [0.376s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.145s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.106s]
+Masking reference... [0.694s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.297s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.237s]
+Building query seed array... [0.115s]
+Computing hash join... [0.109s]
+Building seed filter... [0.006s]
+Searching alignments... [0.16s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.244s]
+Building query seed array... [0.106s]
+Computing hash join... [0.098s]
+Building seed filter... [0.008s]
+Searching alignments... [0.158s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.256s]
+Building query seed array... [0.11s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.104s]
+Computing hash join... [0.104s]
+Building seed filter... [0.007s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.209s]
+Building query seed array... [0.1s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.11s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.11s]
+Computing hash join... [0.102s]
+Building seed filter... [0.007s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.1s]
+Computing hash join... [0.099s]
+Building seed filter... [0.007s]
+Searching alignments... [0.139s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.734s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.675s
+Reported 14496 pairwise alignments, 14578 HSPs.
+14496 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.363s]
+Masking queries... [0.364s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.16s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.984s]
+Masking reference... [0.648s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.276s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.114s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.433s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.112s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.341s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.114s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.309s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.199s]
+Building query seed array... [0.098s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.362s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.196s]
+Building query seed array... [0.096s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.278s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.107s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.262s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.23s]
+Building query seed array... [0.115s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.247s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.104s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.254s]
+Deallocating buffers... [0.05s]
+Computing alignments... [3.031s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.018s]
+Deallocating queries... [0.019s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 12.87s
+Reported 29484 pairwise alignments, 29722 HSPs.
+29484 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/Sr_rh_Nn10_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn10_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn03.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn03.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.196s]
+Masking queries... [0.334s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.124s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.09s]
+Masking reference... [0.688s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.293s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.231s]
+Building query seed array... [0.096s]
+Computing hash join... [0.107s]
+Building seed filter... [0.008s]
+Searching alignments... [0.133s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.091s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.133s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.099s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.134s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.083s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.134s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.08s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.117s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.092s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.094s]
+Computing hash join... [0.094s]
+Building seed filter... [0.005s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.088s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.119s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.366s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.678s
+Reported 12756 pairwise alignments, 12883 HSPs.
+12756 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.195s]
+Masking queries... [0.316s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.127s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.001s]
+Masking reference... [0.637s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.267s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.218s]
+Building query seed array... [0.107s]
+Computing hash join... [0.104s]
+Building seed filter... [0.012s]
+Searching alignments... [0.298s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.1s]
+Computing hash join... [0.094s]
+Building seed filter... [0.008s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.246s]
+Building query seed array... [0.107s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.231s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.089s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.267s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.195s]
+Building query seed array... [0.082s]
+Computing hash join... [0.087s]
+Building seed filter... [0.008s]
+Searching alignments... [0.213s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.221s]
+Building query seed array... [0.092s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.188s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.101s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.184s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.201s]
+Building query seed array... [0.084s]
+Computing hash join... [0.086s]
+Building seed filter... [0.008s]
+Searching alignments... [0.19s]
+Deallocating buffers... [0.052s]
+Computing alignments... [2.409s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.289s
+Reported 26522 pairwise alignments, 26813 HSPs.
+26522 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/Sr_rh_Nn03_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn03_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Halb.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Halb.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.186s]
+Masking queries... [0.342s]
+Building query seed set... [0.066s]
+Algorithm: Double-indexed
+Building query histograms... [0.137s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.119s]
+Masking reference... [0.698s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.297s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.228s]
+Building query seed array... [0.103s]
+Computing hash join... [0.109s]
+Building seed filter... [0.006s]
+Searching alignments... [0.181s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.255s]
+Building query seed array... [0.11s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.164s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.257s]
+Building query seed array... [0.112s]
+Computing hash join... [0.095s]
+Building seed filter... [0.007s]
+Searching alignments... [0.157s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.096s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.159s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.213s]
+Building query seed array... [0.089s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.106s]
+Computing hash join... [0.092s]
+Building seed filter... [0.005s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.107s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.146s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.09s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.146s]
+Deallocating buffers... [0.057s]
+Computing alignments... [1.406s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.019s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.139s
+Reported 9580 pairwise alignments, 9606 HSPs.
+9580 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.18s]
+Masking queries... [0.34s]
+Building query seed set... [0.068s]
+Algorithm: Double-indexed
+Building query histograms... [0.138s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.984s]
+Masking reference... [0.639s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.28s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.219s]
+Building query seed array... [0.103s]
+Computing hash join... [0.112s]
+Building seed filter... [0.007s]
+Searching alignments... [0.19s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.225s]
+Building query seed array... [0.112s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.185s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.106s]
+Computing hash join... [0.089s]
+Building seed filter... [0.005s]
+Searching alignments... [0.176s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.199s]
+Building query seed array... [0.096s]
+Computing hash join... [0.087s]
+Building seed filter... [0.005s]
+Searching alignments... [0.197s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.2s]
+Building query seed array... [0.092s]
+Computing hash join... [0.085s]
+Building seed filter... [0.005s]
+Searching alignments... [0.165s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.225s]
+Building query seed array... [0.106s]
+Computing hash join... [0.086s]
+Building seed filter... [0.006s]
+Searching alignments... [0.163s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.23s]
+Building query seed array... [0.101s]
+Computing hash join... [0.084s]
+Building seed filter... [0.006s]
+Searching alignments... [0.155s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.092s]
+Computing hash join... [0.084s]
+Building seed filter... [0.01s]
+Searching alignments... [0.147s]
+Deallocating buffers... [0.05s]
+Computing alignments... [2.243s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.018s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.696s
+Reported 20722 pairwise alignments, 20823 HSPs.
+20722 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/Sr_rh_Halb_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Halb_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn08.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn08.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.103s]
+Masking queries... [0.349s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.109s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.095s]
+Masking reference... [0.693s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.288s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.23s]
+Building query seed array... [0.091s]
+Computing hash join... [0.117s]
+Building seed filter... [0.006s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.083s]
+Computing hash join... [0.097s]
+Building seed filter... [0.005s]
+Searching alignments... [0.108s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.084s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.113s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.069s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.074s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.084s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.082s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.103s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.075s]
+Computing hash join... [0.096s]
+Building seed filter... [0.005s]
+Searching alignments... [0.096s]
+Deallocating buffers... [0.057s]
+Computing alignments... [1.258s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.011s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.25s
+Reported 12050 pairwise alignments, 12165 HSPs.
+12050 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.099s]
+Masking queries... [0.286s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.126s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.98s]
+Masking reference... [0.639s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.282s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.095s]
+Computing hash join... [0.115s]
+Building seed filter... [0.006s]
+Searching alignments... [0.385s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.078s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.293s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.087s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.273s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.201s]
+Building query seed array... [0.07s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.262s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.199s]
+Building query seed array... [0.073s]
+Computing hash join... [0.094s]
+Building seed filter... [0.006s]
+Searching alignments... [0.237s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.225s]
+Building query seed array... [0.085s]
+Computing hash join... [0.086s]
+Building seed filter... [0.006s]
+Searching alignments... [0.204s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.239s]
+Building query seed array... [0.086s]
+Computing hash join... [0.089s]
+Building seed filter... [0.005s]
+Searching alignments... [0.221s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.072s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.249s]
+Deallocating buffers... [0.052s]
+Computing alignments... [2.283s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.188s
+Reported 24842 pairwise alignments, 25154 HSPs.
+24842 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/Sr_rh_Nn08_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn08_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Tx01.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Tx01.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.36s]
+Masking queries... [0.364s]
+Building query seed set... [0.057s]
+Algorithm: Double-indexed
+Building query histograms... [0.136s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.097s]
+Masking reference... [0.692s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.31s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.235s]
+Building query seed array... [0.103s]
+Computing hash join... [0.097s]
+Building seed filter... [0.005s]
+Searching alignments... [0.168s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.097s]
+Computing hash join... [0.086s]
+Building seed filter... [0.006s]
+Searching alignments... [0.144s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.254s]
+Building query seed array... [0.099s]
+Computing hash join... [0.083s]
+Building seed filter... [0.006s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.086s]
+Computing hash join... [0.084s]
+Building seed filter... [0.007s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.081s]
+Computing hash join... [0.082s]
+Building seed filter... [0.005s]
+Searching alignments... [0.124s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.1s]
+Computing hash join... [0.083s]
+Building seed filter... [0.005s]
+Searching alignments... [0.126s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.101s]
+Computing hash join... [0.082s]
+Building seed filter... [0.005s]
+Searching alignments... [0.123s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.204s]
+Building query seed array... [0.083s]
+Computing hash join... [0.081s]
+Building seed filter... [0.006s]
+Searching alignments... [0.122s]
+Deallocating buffers... [0.054s]
+Computing alignments... [1.626s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.204s
+Reported 11831 pairwise alignments, 11836 HSPs.
+11831 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.353s]
+Masking queries... [0.399s]
+Building query seed set... [0.057s]
+Algorithm: Double-indexed
+Building query histograms... [0.136s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.991s]
+Masking reference... [0.629s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.301s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.215s]
+Building query seed array... [0.098s]
+Computing hash join... [0.106s]
+Building seed filter... [0.005s]
+Searching alignments... [0.227s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.093s]
+Computing hash join... [0.078s]
+Building seed filter... [0.006s]
+Searching alignments... [0.231s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.097s]
+Computing hash join... [0.079s]
+Building seed filter... [0.006s]
+Searching alignments... [0.208s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.194s]
+Building query seed array... [0.101s]
+Computing hash join... [0.083s]
+Building seed filter... [0.006s]
+Searching alignments... [0.223s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.196s]
+Building query seed array... [0.089s]
+Computing hash join... [0.078s]
+Building seed filter... [0.006s]
+Searching alignments... [0.206s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.109s]
+Computing hash join... [0.079s]
+Building seed filter... [0.006s]
+Searching alignments... [0.194s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.235s]
+Building query seed array... [0.101s]
+Computing hash join... [0.076s]
+Building seed filter... [0.006s]
+Searching alignments... [0.184s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.089s]
+Computing hash join... [0.076s]
+Building seed filter... [0.006s]
+Searching alignments... [0.179s]
+Deallocating buffers... [0.051s]
+Computing alignments... [2.893s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.754s
+Reported 28648 pairwise alignments, 28728 HSPs.
+28648 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/Sr_rh_Tx01_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Tx01_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn07.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn07.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.584s]
+Masking queries... [0.4s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.149s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.076s]
+Masking reference... [0.7s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.299s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.239s]
+Building query seed array... [0.125s]
+Computing hash join... [0.121s]
+Building seed filter... [0.008s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.113s]
+Computing hash join... [0.102s]
+Building seed filter... [0.009s]
+Searching alignments... [0.16s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.115s]
+Computing hash join... [0.104s]
+Building seed filter... [0.007s]
+Searching alignments... [0.164s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.097s]
+Computing hash join... [0.102s]
+Building seed filter... [0.007s]
+Searching alignments... [0.166s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.105s]
+Computing hash join... [0.104s]
+Building seed filter... [0.007s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.236s]
+Building query seed array... [0.112s]
+Computing hash join... [0.101s]
+Building seed filter... [0.008s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.12s]
+Computing hash join... [0.101s]
+Building seed filter... [0.007s]
+Searching alignments... [0.146s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.097s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.142s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.725s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.019s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.006s
+Reported 16673 pairwise alignments, 16752 HSPs.
+16673 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.596s]
+Masking queries... [0.392s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.148s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.977s]
+Masking reference... [0.637s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.274s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.116s]
+Computing hash join... [0.107s]
+Building seed filter... [0.009s]
+Searching alignments... [0.422s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.114s]
+Computing hash join... [0.096s]
+Building seed filter... [0.009s]
+Searching alignments... [0.35s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.235s]
+Building query seed array... [0.118s]
+Computing hash join... [0.095s]
+Building seed filter... [0.009s]
+Searching alignments... [0.287s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.102s]
+Computing hash join... [0.095s]
+Building seed filter... [0.009s]
+Searching alignments... [0.318s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.199s]
+Building query seed array... [0.098s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.304s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.109s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.286s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.115s]
+Computing hash join... [0.096s]
+Building seed filter... [0.008s]
+Searching alignments... [0.25s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.199s]
+Building query seed array... [0.101s]
+Computing hash join... [0.095s]
+Building seed filter... [0.008s]
+Searching alignments... [0.277s]
+Deallocating buffers... [0.049s]
+Computing alignments... [3.133s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.019s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.276s
+Reported 35577 pairwise alignments, 35833 HSPs.
+35577 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/Sr_rh_Nn07_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn07_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn01.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn01.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.35s]
+Masking queries... [0.382s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.144s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.137s]
+Masking reference... [0.713s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.301s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.239s]
+Building query seed array... [0.106s]
+Computing hash join... [0.124s]
+Building seed filter... [0.009s]
+Searching alignments... [0.156s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.102s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.152s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.112s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.098s]
+Computing hash join... [0.099s]
+Building seed filter... [0.007s]
+Searching alignments... [0.153s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.102s]
+Computing hash join... [0.097s]
+Building seed filter... [0.008s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.236s]
+Building query seed array... [0.111s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.11s]
+Computing hash join... [0.1s]
+Building seed filter... [0.008s]
+Searching alignments... [0.142s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.102s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.147s]
+Deallocating buffers... [0.059s]
+Computing alignments... [1.749s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.023s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.738s
+Reported 16335 pairwise alignments, 16447 HSPs.
+16335 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.37s]
+Masking queries... [0.377s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.163s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.004s]
+Masking reference... [0.651s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.275s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.217s]
+Building query seed array... [0.111s]
+Computing hash join... [0.109s]
+Building seed filter... [0.007s]
+Searching alignments... [0.411s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.228s]
+Building query seed array... [0.105s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.346s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.106s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.337s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.093s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.366s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.202s]
+Building query seed array... [0.097s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.276s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.106s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.262s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.238s]
+Building query seed array... [0.117s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.237s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.099s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.239s]
+Deallocating buffers... [0.051s]
+Computing alignments... [3.114s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.019s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.004s
+Reported 34435 pairwise alignments, 34792 HSPs.
+34435 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/Sr_rh_Nn01_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn01_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv04.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv04.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.941s]
+Masking queries... [0.466s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.161s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.227s]
+Masking reference... [0.695s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.309s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.228s]
+Building query seed array... [0.124s]
+Computing hash join... [0.118s]
+Building seed filter... [0.007s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.115s]
+Computing hash join... [0.096s]
+Building seed filter... [0.008s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.116s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.18s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.102s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.213s]
+Building query seed array... [0.105s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.159s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.114s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.156s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.117s]
+Computing hash join... [0.095s]
+Building seed filter... [0.007s]
+Searching alignments... [0.155s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.108s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.15s]
+Deallocating buffers... [0.057s]
+Computing alignments... [1.629s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.017s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.591s
+Reported 16731 pairwise alignments, 16862 HSPs.
+16731 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.937s]
+Masking queries... [0.481s]
+Building query seed set... [0.051s]
+Algorithm: Double-indexed
+Building query histograms... [0.175s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.984s]
+Masking reference... [0.641s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.275s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.218s]
+Building query seed array... [0.129s]
+Computing hash join... [0.112s]
+Building seed filter... [0.01s]
+Searching alignments... [0.36s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.226s]
+Building query seed array... [0.114s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.31s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.116s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.265s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.108s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.322s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.197s]
+Building query seed array... [0.11s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.229s]
+Building query seed array... [0.116s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.249s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.124s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.248s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.107s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.237s]
+Deallocating buffers... [0.052s]
+Computing alignments... [3.118s]
+Deallocating reference... [0.014s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.017s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.541s
+Reported 33330 pairwise alignments, 33675 HSPs.
+33330 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/Sr_rh_Bv04_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv04_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Usac.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Usac.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.916s]
+Masking queries... [0.261s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.109s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.093s]
+Masking reference... [0.695s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.298s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.236s]
+Building query seed array... [0.087s]
+Computing hash join... [0.124s]
+Building seed filter... [0.006s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.08s]
+Computing hash join... [0.1s]
+Building seed filter... [0.007s]
+Searching alignments... [0.138s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.084s]
+Computing hash join... [0.097s]
+Building seed filter... [0.008s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.071s]
+Computing hash join... [0.095s]
+Building seed filter... [0.007s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.074s]
+Computing hash join... [0.103s]
+Building seed filter... [0.006s]
+Searching alignments... [0.127s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.235s]
+Building query seed array... [0.076s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.123s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.08s]
+Computing hash join... [0.099s]
+Building seed filter... [0.007s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.065s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.121s]
+Deallocating buffers... [0.054s]
+Computing alignments... [1.485s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.013s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.432s
+Reported 18730 pairwise alignments, 18769 HSPs.
+18730 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.923s]
+Masking queries... [0.263s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.098s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.988s]
+Masking reference... [0.64s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.269s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.087s]
+Computing hash join... [0.107s]
+Building seed filter... [0.007s]
+Searching alignments... [0.263s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.083s]
+Computing hash join... [0.1s]
+Building seed filter... [0.006s]
+Searching alignments... [0.253s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.087s]
+Computing hash join... [0.097s]
+Building seed filter... [0.008s]
+Searching alignments... [0.231s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.069s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.255s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.203s]
+Building query seed array... [0.072s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.217s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.077s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.239s]
+Building query seed array... [0.087s]
+Computing hash join... [0.097s]
+Building seed filter... [0.005s]
+Searching alignments... [0.181s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.193s]
+Building query seed array... [0.071s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.177s]
+Deallocating buffers... [0.053s]
+Computing alignments... [2.193s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.523s
+Reported 40730 pairwise alignments, 40859 HSPs.
+40730 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/Sr_rh_Usac_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Usac_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn04.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn04.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.191s]
+Masking queries... [0.615s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.201s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.266s]
+Masking reference... [0.692s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.331s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.231s]
+Building query seed array... [0.161s]
+Computing hash join... [0.135s]
+Building seed filter... [0.009s]
+Searching alignments... [0.231s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.249s]
+Building query seed array... [0.148s]
+Computing hash join... [0.111s]
+Building seed filter... [0.009s]
+Searching alignments... [0.197s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.156s]
+Computing hash join... [0.112s]
+Building seed filter... [0.009s]
+Searching alignments... [0.205s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.135s]
+Computing hash join... [0.112s]
+Building seed filter... [0.009s]
+Searching alignments... [0.207s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.136s]
+Computing hash join... [0.115s]
+Building seed filter... [0.014s]
+Searching alignments... [0.192s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.153s]
+Computing hash join... [0.12s]
+Building seed filter... [0.009s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.252s]
+Building query seed array... [0.155s]
+Computing hash join... [0.109s]
+Building seed filter... [0.008s]
+Searching alignments... [0.198s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.215s]
+Building query seed array... [0.135s]
+Computing hash join... [0.118s]
+Building seed filter... [0.008s]
+Searching alignments... [0.181s]
+Deallocating buffers... [0.059s]
+Computing alignments... [2.565s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.023s]
+Deallocating queries... [0.021s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.715s
+Reported 27246 pairwise alignments, 27470 HSPs.
+27246 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.212s]
+Masking queries... [0.606s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.199s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.006s]
+Masking reference... [0.651s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.285s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.217s]
+Building query seed array... [0.152s]
+Computing hash join... [0.111s]
+Building seed filter... [0.007s]
+Searching alignments... [0.637s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.156s]
+Computing hash join... [0.104s]
+Building seed filter... [0.01s]
+Searching alignments... [0.491s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.15s]
+Computing hash join... [0.106s]
+Building seed filter... [0.009s]
+Searching alignments... [0.405s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.194s]
+Building query seed array... [0.13s]
+Computing hash join... [0.101s]
+Building seed filter... [0.007s]
+Searching alignments... [0.545s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.198s]
+Building query seed array... [0.132s]
+Computing hash join... [0.101s]
+Building seed filter... [0.009s]
+Searching alignments... [0.449s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.151s]
+Computing hash join... [0.1s]
+Building seed filter... [0.01s]
+Searching alignments... [0.443s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.235s]
+Building query seed array... [0.153s]
+Computing hash join... [0.103s]
+Building seed filter... [0.01s]
+Searching alignments... [0.358s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.144s]
+Computing hash join... [0.103s]
+Building seed filter... [0.008s]
+Searching alignments... [0.407s]
+Deallocating buffers... [0.052s]
+Computing alignments... [4.479s]
+Deallocating reference... [0.014s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.024s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 17.183s
+Reported 56655 pairwise alignments, 57309 HSPs.
+56655 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/Sr_rh_Nn04_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn04_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Emar.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Emar.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.531s]
+Masking queries... [0.153s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.07s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.189s]
+Masking reference... [0.687s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.301s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.057s]
+Computing hash join... [0.121s]
+Building seed filter... [0.005s]
+Searching alignments... [0.079s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.054s]
+Computing hash join... [0.088s]
+Building seed filter... [0.004s]
+Searching alignments... [0.078s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.059s]
+Computing hash join... [0.085s]
+Building seed filter... [0.006s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.204s]
+Building query seed array... [0.047s]
+Computing hash join... [0.079s]
+Building seed filter... [0.006s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.206s]
+Building query seed array... [0.053s]
+Computing hash join... [0.083s]
+Building seed filter... [0.005s]
+Searching alignments... [0.075s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.059s]
+Computing hash join... [0.085s]
+Building seed filter... [0.005s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.243s]
+Building query seed array... [0.054s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.069s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.059s]
+Computing hash join... [0.087s]
+Building seed filter... [0.005s]
+Searching alignments... [0.065s]
+Deallocating buffers... [0.056s]
+Computing alignments... [0.634s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.005s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.328s
+Reported 5342 pairwise alignments, 5400 HSPs.
+5342 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.534s]
+Masking queries... [0.167s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.067s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.981s]
+Masking reference... [0.636s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.274s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.067s]
+Computing hash join... [0.105s]
+Building seed filter... [0.005s]
+Searching alignments... [0.102s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.064s]
+Computing hash join... [0.082s]
+Building seed filter... [0.005s]
+Searching alignments... [0.101s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.237s]
+Building query seed array... [0.056s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.092s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.052s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.097s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.191s]
+Building query seed array... [0.051s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.085s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.216s]
+Building query seed array... [0.057s]
+Computing hash join... [0.081s]
+Building seed filter... [0.006s]
+Searching alignments... [0.083s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.056s]
+Computing hash join... [0.08s]
+Building seed filter... [0.005s]
+Searching alignments... [0.08s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.043s]
+Computing hash join... [0.078s]
+Building seed filter... [0.005s]
+Searching alignments... [0.087s]
+Deallocating buffers... [0.051s]
+Computing alignments... [1.093s]
+Deallocating reference... [0.017s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.008s]
+Deallocating queries... [0.008s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.522s
+Reported 11056 pairwise alignments, 11214 HSPs.
+11056 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/Sr_rh_Emar_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Emar_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Rsp1.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Rsp1.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.033s]
+Masking queries... [0.559s]
+Building query seed set... [0.049s]
+Algorithm: Double-indexed
+Building query histograms... [0.094s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.11s]
+Masking reference... [0.694s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.319s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.232s]
+Building query seed array... [0.075s]
+Computing hash join... [0.125s]
+Building seed filter... [0.007s]
+Searching alignments... [0.126s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.065s]
+Computing hash join... [0.105s]
+Building seed filter... [0.005s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.075s]
+Computing hash join... [0.104s]
+Building seed filter... [0.005s]
+Searching alignments... [0.118s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.217s]
+Building query seed array... [0.077s]
+Computing hash join... [0.1s]
+Building seed filter... [0.005s]
+Searching alignments... [0.115s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.223s]
+Building query seed array... [0.063s]
+Computing hash join... [0.091s]
+Building seed filter... [0.005s]
+Searching alignments... [0.098s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.069s]
+Computing hash join... [0.097s]
+Building seed filter... [0.005s]
+Searching alignments... [0.1s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.244s]
+Building query seed array... [0.069s]
+Computing hash join... [0.092s]
+Building seed filter... [0.005s]
+Searching alignments... [0.1s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.206s]
+Building query seed array... [0.059s]
+Computing hash join... [0.091s]
+Building seed filter... [0.005s]
+Searching alignments... [0.097s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.22s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.348s
+Reported 17091 pairwise alignments, 17125 HSPs.
+17091 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.034s]
+Masking queries... [0.266s]
+Building query seed set... [0.049s]
+Algorithm: Double-indexed
+Building query histograms... [0.093s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.989s]
+Masking reference... [0.658s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.292s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.222s]
+Building query seed array... [0.079s]
+Computing hash join... [0.132s]
+Building seed filter... [0.005s]
+Searching alignments... [0.202s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.069s]
+Computing hash join... [0.1s]
+Building seed filter... [0.006s]
+Searching alignments... [0.201s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.238s]
+Building query seed array... [0.067s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.064s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.181s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.199s]
+Building query seed array... [0.058s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.065s]
+Computing hash join... [0.092s]
+Building seed filter... [0.005s]
+Searching alignments... [0.177s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.228s]
+Building query seed array... [0.065s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.154s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.194s]
+Building query seed array... [0.062s]
+Computing hash join... [0.087s]
+Building seed filter... [0.005s]
+Searching alignments... [0.154s]
+Deallocating buffers... [0.052s]
+Computing alignments... [2.101s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.112s
+Reported 36259 pairwise alignments, 36348 HSPs.
+36259 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/Sr_rh_Rsp1_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Rsp1_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Sspa.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Sspa.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.778s]
+Masking queries... [0.215s]
+Building query seed set... [0.043s]
+Algorithm: Double-indexed
+Building query histograms... [0.081s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.097s]
+Masking reference... [0.696s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.303s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.232s]
+Building query seed array... [0.068s]
+Computing hash join... [0.132s]
+Building seed filter... [0.006s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.062s]
+Computing hash join... [0.108s]
+Building seed filter... [0.006s]
+Searching alignments... [0.117s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.256s]
+Building query seed array... [0.064s]
+Computing hash join... [0.101s]
+Building seed filter... [0.006s]
+Searching alignments... [0.105s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.054s]
+Computing hash join... [0.098s]
+Building seed filter... [0.006s]
+Searching alignments... [0.107s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.219s]
+Building query seed array... [0.054s]
+Computing hash join... [0.094s]
+Building seed filter... [0.005s]
+Searching alignments... [0.1s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.068s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.256s]
+Building query seed array... [0.065s]
+Computing hash join... [0.092s]
+Building seed filter... [0.006s]
+Searching alignments... [0.093s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.206s]
+Building query seed array... [0.057s]
+Computing hash join... [0.095s]
+Building seed filter... [0.005s]
+Searching alignments... [0.098s]
+Deallocating buffers... [0.056s]
+Computing alignments... [1.085s]
+Deallocating reference... [0.019s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.008s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.486s
+Reported 10845 pairwise alignments, 10920 HSPs.
+10845 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.783s]
+Masking queries... [0.228s]
+Building query seed set... [0.043s]
+Algorithm: Double-indexed
+Building query histograms... [0.081s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.979s]
+Masking reference... [0.641s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.291s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.219s]
+Building query seed array... [0.07s]
+Computing hash join... [0.109s]
+Building seed filter... [0.005s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.058s]
+Computing hash join... [0.096s]
+Building seed filter... [0.005s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.23s]
+Building query seed array... [0.066s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.135s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.056s]
+Computing hash join... [0.093s]
+Building seed filter... [0.005s]
+Searching alignments... [0.144s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.193s]
+Building query seed array... [0.055s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.124s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.057s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.132s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.061s]
+Computing hash join... [0.087s]
+Building seed filter... [0.006s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.056s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.119s]
+Deallocating buffers... [0.05s]
+Computing alignments... [1.576s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.009s]
+Deallocating queries... [0.011s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 8.814s
+Reported 23074 pairwise alignments, 23301 HSPs.
+23074 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/Sr_rh_Sspa_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Sspa_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Hhir.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Hhir.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.628s]
+Masking queries... [0.179s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.08s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.105s]
+Masking reference... [0.806s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.304s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.241s]
+Building query seed array... [0.061s]
+Computing hash join... [0.107s]
+Building seed filter... [0.006s]
+Searching alignments... [0.111s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.243s]
+Building query seed array... [0.055s]
+Computing hash join... [0.084s]
+Building seed filter... [0.005s]
+Searching alignments... [0.079s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.056s]
+Computing hash join... [0.077s]
+Building seed filter... [0.005s]
+Searching alignments... [0.081s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.053s]
+Computing hash join... [0.078s]
+Building seed filter... [0.005s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.055s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.072s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.053s]
+Computing hash join... [0.074s]
+Building seed filter... [0.005s]
+Searching alignments... [0.081s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.057s]
+Computing hash join... [0.074s]
+Building seed filter... [0.005s]
+Searching alignments... [0.079s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.055s]
+Computing hash join... [0.077s]
+Building seed filter... [0.004s]
+Searching alignments... [0.074s]
+Deallocating buffers... [0.056s]
+Computing alignments... [0.796s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.007s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.726s
+Reported 6766 pairwise alignments, 6777 HSPs.
+6766 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.632s]
+Masking queries... [0.235s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.074s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.024s]
+Masking reference... [1.658s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.282s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.222s]
+Building query seed array... [0.067s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.054s]
+Computing hash join... [0.081s]
+Building seed filter... [0.005s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.059s]
+Computing hash join... [0.075s]
+Building seed filter... [0.005s]
+Searching alignments... [0.107s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.05s]
+Computing hash join... [0.076s]
+Building seed filter... [0.006s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.195s]
+Building query seed array... [0.054s]
+Computing hash join... [0.076s]
+Building seed filter... [0.004s]
+Searching alignments... [0.101s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.221s]
+Building query seed array... [0.054s]
+Computing hash join... [0.07s]
+Building seed filter... [0.005s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.227s]
+Building query seed array... [0.06s]
+Computing hash join... [0.072s]
+Building seed filter... [0.005s]
+Searching alignments... [0.101s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.05s]
+Computing hash join... [0.071s]
+Building seed filter... [0.005s]
+Searching alignments... [0.091s]
+Deallocating buffers... [0.053s]
+Computing alignments... [1.324s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.01s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.073s
+Reported 14202 pairwise alignments, 14244 HSPs.
+14202 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/Sr_rh_Hhir_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Hhir_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn12.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn12.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.207s]
+Masking queries... [0.31s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.142s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.123s]
+Masking reference... [0.708s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.292s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.227s]
+Building query seed array... [0.1s]
+Computing hash join... [0.109s]
+Building seed filter... [0.005s]
+Searching alignments... [0.135s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.095s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.127s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.092s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.132s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.084s]
+Computing hash join... [0.096s]
+Building seed filter... [0.005s]
+Searching alignments... [0.128s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.084s]
+Computing hash join... [0.095s]
+Building seed filter... [0.007s]
+Searching alignments... [0.119s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.092s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.116s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.251s]
+Building query seed array... [0.097s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.088s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.116s]
+Deallocating buffers... [0.056s]
+Computing alignments... [1.169s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.013s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.541s
+Reported 12180 pairwise alignments, 12261 HSPs.
+12180 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.216s]
+Masking queries... [0.327s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.124s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.989s]
+Masking reference... [0.637s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.275s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.222s]
+Building query seed array... [0.091s]
+Computing hash join... [0.096s]
+Building seed filter... [0.005s]
+Searching alignments... [0.209s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.23s]
+Building query seed array... [0.099s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.195s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.103s]
+Computing hash join... [0.089s]
+Building seed filter... [0.006s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.084s]
+Computing hash join... [0.091s]
+Building seed filter... [0.006s]
+Searching alignments... [0.179s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.196s]
+Building query seed array... [0.089s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.168s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.247s]
+Building query seed array... [0.115s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.175s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.097s]
+Computing hash join... [0.087s]
+Building seed filter... [0.007s]
+Searching alignments... [0.166s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.191s]
+Building query seed array... [0.09s]
+Computing hash join... [0.092s]
+Building seed filter... [0.007s]
+Searching alignments... [0.159s]
+Deallocating buffers... [0.053s]
+Computing alignments... [2.15s]
+Deallocating reference... [0.017s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.621s
+Reported 26508 pairwise alignments, 26714 HSPs.
+26508 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/Sr_rh_Nn12_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn12_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn14.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn14.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.174s]
+Masking queries... [0.328s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.13s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.103s]
+Masking reference... [0.708s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.315s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.238s]
+Building query seed array... [0.101s]
+Computing hash join... [0.11s]
+Building seed filter... [0.007s]
+Searching alignments... [0.135s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.239s]
+Building query seed array... [0.093s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.128s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.093s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.131s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.087s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.129s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.209s]
+Building query seed array... [0.085s]
+Computing hash join... [0.098s]
+Building seed filter... [0.006s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.249s]
+Building query seed array... [0.099s]
+Computing hash join... [0.095s]
+Building seed filter... [0.005s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.093s]
+Computing hash join... [0.098s]
+Building seed filter... [0.006s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.209s]
+Building query seed array... [0.078s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.115s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.155s]
+Deallocating reference... [0.02s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.521s
+Reported 12561 pairwise alignments, 12646 HSPs.
+12561 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.193s]
+Masking queries... [0.313s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.136s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.003s]
+Masking reference... [0.644s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.283s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.217s]
+Building query seed array... [0.093s]
+Computing hash join... [0.096s]
+Building seed filter... [0.008s]
+Searching alignments... [0.331s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.099s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.196s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.099s]
+Computing hash join... [0.087s]
+Building seed filter... [0.007s]
+Searching alignments... [0.179s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.082s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.195s]
+Building query seed array... [0.093s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.155s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.218s]
+Building query seed array... [0.097s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.097s]
+Computing hash join... [0.087s]
+Building seed filter... [0.007s]
+Searching alignments... [0.159s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.083s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.158s]
+Deallocating buffers... [0.049s]
+Computing alignments... [2.103s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.601s
+Reported 27283 pairwise alignments, 27554 HSPs.
+27283 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/Sr_rh_Nn14_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn14_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Gl02.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Gl02.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.204s]
+Masking queries... [0.607s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.22s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.093s]
+Masking reference... [0.691s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.31s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.236s]
+Building query seed array... [0.156s]
+Computing hash join... [0.138s]
+Building seed filter... [0.01s]
+Searching alignments... [0.229s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.146s]
+Computing hash join... [0.11s]
+Building seed filter... [0.012s]
+Searching alignments... [0.227s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.148s]
+Computing hash join... [0.122s]
+Building seed filter... [0.009s]
+Searching alignments... [0.228s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.133s]
+Computing hash join... [0.109s]
+Building seed filter... [0.01s]
+Searching alignments... [0.216s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.213s]
+Building query seed array... [0.142s]
+Computing hash join... [0.113s]
+Building seed filter... [0.009s]
+Searching alignments... [0.2s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.149s]
+Computing hash join... [0.113s]
+Building seed filter... [0.009s]
+Searching alignments... [0.203s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.157s]
+Computing hash join... [0.111s]
+Building seed filter... [0.009s]
+Searching alignments... [0.194s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.133s]
+Computing hash join... [0.109s]
+Building seed filter... [0.008s]
+Searching alignments... [0.192s]
+Deallocating buffers... [0.059s]
+Computing alignments... [2.363s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.024s]
+Deallocating queries... [0.024s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.428s
+Reported 23866 pairwise alignments, 23926 HSPs.
+23866 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.219s]
+Masking queries... [0.556s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.203s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.998s]
+Masking reference... [0.642s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.287s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.214s]
+Building query seed array... [0.154s]
+Computing hash join... [0.112s]
+Building seed filter... [0.01s]
+Searching alignments... [0.337s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.153s]
+Computing hash join... [0.106s]
+Building seed filter... [0.011s]
+Searching alignments... [0.315s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.235s]
+Building query seed array... [0.158s]
+Computing hash join... [0.104s]
+Building seed filter... [0.008s]
+Searching alignments... [0.305s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.222s]
+Building query seed array... [0.142s]
+Computing hash join... [0.109s]
+Building seed filter... [0.007s]
+Searching alignments... [0.315s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.135s]
+Computing hash join... [0.103s]
+Building seed filter... [0.01s]
+Searching alignments... [0.271s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.152s]
+Computing hash join... [0.105s]
+Building seed filter... [0.01s]
+Searching alignments... [0.287s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.23s]
+Building query seed array... [0.154s]
+Computing hash join... [0.109s]
+Building seed filter... [0.009s]
+Searching alignments... [0.271s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.139s]
+Computing hash join... [0.106s]
+Building seed filter... [0.01s]
+Searching alignments... [0.261s]
+Deallocating buffers... [0.049s]
+Computing alignments... [4.193s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.024s]
+Deallocating queries... [0.028s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 15.549s
+Reported 46583 pairwise alignments, 46748 HSPs.
+46583 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/Sr_rh_Gl02_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Gl02_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv05.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv05.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.826s]
+Masking queries... [0.521s]
+Building query seed set... [0.048s]
+Algorithm: Double-indexed
+Building query histograms... [0.15s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.084s]
+Masking reference... [0.692s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.299s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.236s]
+Building query seed array... [0.124s]
+Computing hash join... [0.115s]
+Building seed filter... [0.007s]
+Searching alignments... [0.182s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.242s]
+Building query seed array... [0.111s]
+Computing hash join... [0.095s]
+Building seed filter... [0.008s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.255s]
+Building query seed array... [0.113s]
+Computing hash join... [0.098s]
+Building seed filter... [0.008s]
+Searching alignments... [0.171s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.098s]
+Computing hash join... [0.097s]
+Building seed filter... [0.009s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.101s]
+Computing hash join... [0.098s]
+Building seed filter... [0.008s]
+Searching alignments... [0.163s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.108s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.247s]
+Building query seed array... [0.112s]
+Computing hash join... [0.097s]
+Building seed filter... [0.007s]
+Searching alignments... [0.152s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.098s]
+Computing hash join... [0.096s]
+Building seed filter... [0.009s]
+Searching alignments... [0.147s]
+Deallocating buffers... [0.06s]
+Computing alignments... [1.576s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.019s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.239s
+Reported 16723 pairwise alignments, 16853 HSPs.
+16723 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/BvE
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.809s]
+Masking queries... [0.438s]
+Building query seed set... [0.048s]
+Algorithm: Double-indexed
+Building query histograms... [0.148s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.987s]
+Masking reference... [0.634s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.266s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.226s]
+Building query seed array... [0.116s]
+Computing hash join... [0.108s]
+Building seed filter... [0.007s]
+Searching alignments... [0.315s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.228s]
+Building query seed array... [0.106s]
+Computing hash join... [0.088s]
+Building seed filter... [0.007s]
+Searching alignments... [0.285s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.111s]
+Computing hash join... [0.089s]
+Building seed filter... [0.008s]
+Searching alignments... [0.266s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.197s]
+Building query seed array... [0.099s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.324s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.201s]
+Building query seed array... [0.098s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.248s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.111s]
+Computing hash join... [0.09s]
+Building seed filter... [0.006s]
+Searching alignments... [0.243s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.232s]
+Building query seed array... [0.11s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.249s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.201s]
+Building query seed array... [0.1s]
+Computing hash join... [0.088s]
+Building seed filter... [0.006s]
+Searching alignments... [0.231s]
+Deallocating buffers... [0.052s]
+Computing alignments... [3.101s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.126s
+Reported 34038 pairwise alignments, 34375 HSPs.
+34038 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/Sr_rh_Bv05_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv05_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Bv01.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Bv01.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.556s]
+Masking queries... [0.392s]
+Building query seed set... [0.047s]
+Algorithm: Double-indexed
+Building query histograms... [0.126s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.102s]
+Masking reference... [0.703s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.301s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.235s]
+Building query seed array... [0.093s]
+Computing hash join... [0.113s]
+Building seed filter... [0.007s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.097s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.25s]
+Building query seed array... [0.095s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.154s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.212s]
+Building query seed array... [0.079s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.149s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.217s]
+Building query seed array... [0.081s]
+Computing hash join... [0.093s]
+Building seed filter... [0.006s]
+Searching alignments... [0.126s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.238s]
+Building query seed array... [0.09s]
+Computing hash join... [0.097s]
+Building seed filter... [0.006s]
+Searching alignments... [0.131s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.09s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.131s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.211s]
+Building query seed array... [0.082s]
+Computing hash join... [0.094s]
+Building seed filter... [0.007s]
+Searching alignments... [0.129s]
+Deallocating buffers... [0.056s]
+Computing alignments... [1.438s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.329s
+Reported 17468 pairwise alignments, 17618 HSPs.
+17468 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.559s]
+Masking queries... [0.421s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.123s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.998s]
+Masking reference... [0.638s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.275s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.222s]
+Building query seed array... [0.099s]
+Computing hash join... [0.116s]
+Building seed filter... [0.01s]
+Searching alignments... [0.318s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.237s]
+Building query seed array... [0.097s]
+Computing hash join... [0.096s]
+Building seed filter... [0.007s]
+Searching alignments... [0.276s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.238s]
+Building query seed array... [0.099s]
+Computing hash join... [0.092s]
+Building seed filter... [0.009s]
+Searching alignments... [0.286s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.202s]
+Building query seed array... [0.086s]
+Computing hash join... [0.09s]
+Building seed filter... [0.008s]
+Searching alignments... [0.309s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.199s]
+Building query seed array... [0.077s]
+Computing hash join... [0.092s]
+Building seed filter... [0.008s]
+Searching alignments... [0.244s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.086s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.207s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.093s]
+Computing hash join... [0.095s]
+Building seed filter... [0.008s]
+Searching alignments... [0.204s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.08s]
+Computing hash join... [0.093s]
+Building seed filter... [0.008s]
+Searching alignments... [0.204s]
+Deallocating buffers... [0.05s]
+Computing alignments... [2.675s]
+Deallocating reference... [0.022s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 12.237s
+Reported 35541 pairwise alignments, 35937 HSPs.
+35541 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/Sr_rh_Bv01_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Bv01_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Slin.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Slin.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.36s]
+Masking queries... [0.117s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.046s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.089s]
+Masking reference... [0.702s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.315s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.232s]
+Building query seed array... [0.055s]
+Computing hash join... [0.081s]
+Building seed filter... [0.004s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.038s]
+Computing hash join... [0.065s]
+Building seed filter... [0.005s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.253s]
+Building query seed array... [0.031s]
+Computing hash join... [0.058s]
+Building seed filter... [0.005s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.04s]
+Computing hash join... [0.056s]
+Building seed filter... [0.004s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.224s]
+Building query seed array... [0.038s]
+Computing hash join... [0.056s]
+Building seed filter... [0.004s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.233s]
+Building query seed array... [0.036s]
+Computing hash join... [0.05s]
+Building seed filter... [0.004s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.248s]
+Building query seed array... [0.044s]
+Computing hash join... [0.054s]
+Building seed filter... [0.004s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.208s]
+Building query seed array... [0.038s]
+Computing hash join... [0.053s]
+Building seed filter... [0.004s]
+Searching alignments... [0.044s]
+Deallocating buffers... [0.055s]
+Computing alignments... [0.446s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.003s]
+Deallocating queries... [0.005s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 6.344s
+Reported 3720 pairwise alignments, 3786 HSPs.
+3720 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.379s]
+Masking queries... [0.163s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.046s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.992s]
+Masking reference... [0.639s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.286s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.049s]
+Computing hash join... [0.074s]
+Building seed filter... [0.005s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.222s]
+Building query seed array... [0.036s]
+Computing hash join... [0.054s]
+Building seed filter... [0.005s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.23s]
+Building query seed array... [0.034s]
+Computing hash join... [0.052s]
+Building seed filter... [0.005s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.192s]
+Building query seed array... [0.038s]
+Computing hash join... [0.05s]
+Building seed filter... [0.004s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.191s]
+Building query seed array... [0.035s]
+Computing hash join... [0.05s]
+Building seed filter... [0.005s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.213s]
+Building query seed array... [0.039s]
+Computing hash join... [0.05s]
+Building seed filter... [0.005s]
+Searching alignments... [0.069s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.231s]
+Building query seed array... [0.036s]
+Computing hash join... [0.05s]
+Building seed filter... [0.005s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.195s]
+Building query seed array... [0.036s]
+Computing hash join... [0.051s]
+Building seed filter... [0.004s]
+Searching alignments... [0.066s]
+Deallocating buffers... [0.051s]
+Computing alignments... [0.736s]
+Deallocating reference... [0.017s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.003s]
+Deallocating queries... [0.005s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 6.473s
+Reported 8131 pairwise alignments, 8278 HSPs.
+8131 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/Sr_rh_Slin_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Slin_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Gl03.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Gl03.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.745s]
+Masking queries... [0.498s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.179s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.084s]
+Masking reference... [0.714s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.306s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.233s]
+Building query seed array... [0.138s]
+Computing hash join... [0.135s]
+Building seed filter... [0.011s]
+Searching alignments... [0.228s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.248s]
+Building query seed array... [0.133s]
+Computing hash join... [0.113s]
+Building seed filter... [0.009s]
+Searching alignments... [0.215s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.254s]
+Building query seed array... [0.138s]
+Computing hash join... [0.118s]
+Building seed filter... [0.009s]
+Searching alignments... [0.237s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.229s]
+Building query seed array... [0.127s]
+Computing hash join... [0.114s]
+Building seed filter... [0.008s]
+Searching alignments... [0.216s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.208s]
+Building query seed array... [0.116s]
+Computing hash join... [0.111s]
+Building seed filter... [0.008s]
+Searching alignments... [0.195s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.244s]
+Building query seed array... [0.128s]
+Computing hash join... [0.111s]
+Building seed filter... [0.009s]
+Searching alignments... [0.193s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.245s]
+Building query seed array... [0.13s]
+Computing hash join... [0.11s]
+Building seed filter... [0.009s]
+Searching alignments... [0.196s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.114s]
+Computing hash join... [0.111s]
+Building seed filter... [0.008s]
+Searching alignments... [0.191s]
+Deallocating buffers... [0.059s]
+Computing alignments... [2.383s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.022s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 12.681s
+Reported 24064 pairwise alignments, 24123 HSPs.
+24064 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.762s]
+Masking queries... [0.457s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.176s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.971s]
+Masking reference... [0.64s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.287s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.211s]
+Building query seed array... [0.128s]
+Computing hash join... [0.12s]
+Building seed filter... [0.009s]
+Searching alignments... [0.31s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.224s]
+Building query seed array... [0.127s]
+Computing hash join... [0.104s]
+Building seed filter... [0.01s]
+Searching alignments... [0.308s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.234s]
+Building query seed array... [0.133s]
+Computing hash join... [0.105s]
+Building seed filter... [0.009s]
+Searching alignments... [0.287s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.205s]
+Building query seed array... [0.116s]
+Computing hash join... [0.102s]
+Building seed filter... [0.008s]
+Searching alignments... [0.288s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.199s]
+Building query seed array... [0.12s]
+Computing hash join... [0.101s]
+Building seed filter... [0.008s]
+Searching alignments... [0.253s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.225s]
+Building query seed array... [0.129s]
+Computing hash join... [0.102s]
+Building seed filter... [0.009s]
+Searching alignments... [0.246s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.236s]
+Building query seed array... [0.145s]
+Computing hash join... [0.106s]
+Building seed filter... [0.009s]
+Searching alignments... [0.249s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.196s]
+Building query seed array... [0.116s]
+Computing hash join... [0.105s]
+Building seed filter... [0.009s]
+Searching alignments... [0.242s]
+Deallocating buffers... [0.05s]
+Computing alignments... [3.854s]
+Deallocating reference... [0.024s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.022s]
+Deallocating queries... [0.022s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 14.194s
+Reported 49617 pairwise alignments, 49761 HSPs.
+49617 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/Sr_rh_Gl03_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Gl03_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn09.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn09.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.803s]
+Masking queries... [0.454s]
+Building query seed set... [0.029s]
+Algorithm: Double-indexed
+Building query histograms... [0.181s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.117s]
+Masking reference... [1.661s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.319s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.238s]
+Building query seed array... [0.132s]
+Computing hash join... [0.121s]
+Building seed filter... [0.007s]
+Searching alignments... [0.188s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.136s]
+Computing hash join... [0.11s]
+Building seed filter... [0.007s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.246s]
+Building query seed array... [0.134s]
+Computing hash join... [0.106s]
+Building seed filter... [0.007s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.213s]
+Building query seed array... [0.119s]
+Computing hash join... [0.104s]
+Building seed filter... [0.007s]
+Searching alignments... [0.187s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.212s]
+Building query seed array... [0.116s]
+Computing hash join... [0.108s]
+Building seed filter... [0.008s]
+Searching alignments... [0.165s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.246s]
+Building query seed array... [0.135s]
+Computing hash join... [0.104s]
+Building seed filter... [0.007s]
+Searching alignments... [0.166s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.254s]
+Building query seed array... [0.135s]
+Computing hash join... [0.107s]
+Building seed filter... [0.008s]
+Searching alignments... [0.16s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.121s]
+Computing hash join... [0.106s]
+Building seed filter... [0.008s]
+Searching alignments... [0.157s]
+Deallocating buffers... [0.056s]
+Computing alignments... [2.04s]
+Deallocating reference... [0.026s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.02s]
+Deallocating queries... [0.021s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 12.971s
+Reported 21847 pairwise alignments, 22013 HSPs.
+21847 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.803s]
+Masking queries... [0.461s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.18s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.989s]
+Masking reference... [0.651s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.293s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.22s]
+Building query seed array... [0.15s]
+Computing hash join... [0.121s]
+Building seed filter... [0.008s]
+Searching alignments... [0.61s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.23s]
+Building query seed array... [0.136s]
+Computing hash join... [0.102s]
+Building seed filter... [0.008s]
+Searching alignments... [0.325s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.134s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.414s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.116s]
+Computing hash join... [0.101s]
+Building seed filter... [0.008s]
+Searching alignments... [0.615s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.191s]
+Building query seed array... [0.12s]
+Computing hash join... [0.1s]
+Building seed filter... [0.008s]
+Searching alignments... [0.442s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.22s]
+Building query seed array... [0.131s]
+Computing hash join... [0.103s]
+Building seed filter... [0.008s]
+Searching alignments... [0.429s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.134s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.329s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.2s]
+Building query seed array... [0.117s]
+Computing hash join... [0.099s]
+Building seed filter... [0.008s]
+Searching alignments... [0.272s]
+Deallocating buffers... [0.05s]
+Computing alignments... [3.679s]
+Deallocating reference... [0.013s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.022s]
+Deallocating queries... [0.019s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 15.337s
+Reported 44982 pairwise alignments, 45503 HSPs.
+44982 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/Sr_rh_Nn09_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn09_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Nn13.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Nn13.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.271s]
+Masking queries... [0.345s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.137s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.096s]
+Masking reference... [0.719s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.314s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.234s]
+Building query seed array... [0.1s]
+Computing hash join... [0.119s]
+Building seed filter... [0.008s]
+Searching alignments... [0.141s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.235s]
+Building query seed array... [0.095s]
+Computing hash join... [0.098s]
+Building seed filter... [0.008s]
+Searching alignments... [0.138s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.249s]
+Building query seed array... [0.098s]
+Computing hash join... [0.096s]
+Building seed filter... [0.006s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.232s]
+Building query seed array... [0.095s]
+Computing hash join... [0.098s]
+Building seed filter... [0.006s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.21s]
+Building query seed array... [0.093s]
+Computing hash join... [0.098s]
+Building seed filter... [0.007s]
+Searching alignments... [0.129s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.241s]
+Building query seed array... [0.101s]
+Computing hash join... [0.095s]
+Building seed filter... [0.006s]
+Searching alignments... [0.129s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.259s]
+Building query seed array... [0.109s]
+Computing hash join... [0.099s]
+Building seed filter... [0.007s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.21s]
+Building query seed array... [0.098s]
+Computing hash join... [0.102s]
+Building seed filter... [0.007s]
+Searching alignments... [0.124s]
+Deallocating buffers... [0.058s]
+Computing alignments... [1.314s]
+Deallocating reference... [0.018s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 9.969s
+Reported 13752 pairwise alignments, 13820 HSPs.
+13752 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.274s]
+Masking queries... [0.342s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.147s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.985s]
+Masking reference... [0.639s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.287s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.219s]
+Building query seed array... [0.101s]
+Computing hash join... [0.099s]
+Building seed filter... [0.006s]
+Searching alignments... [0.36s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.221s]
+Building query seed array... [0.1s]
+Computing hash join... [0.09s]
+Building seed filter... [0.007s]
+Searching alignments... [0.286s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.101s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.244s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.198s]
+Building query seed array... [0.091s]
+Computing hash join... [0.093s]
+Building seed filter... [0.007s]
+Searching alignments... [0.312s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.201s]
+Building query seed array... [0.089s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.189s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.227s]
+Building query seed array... [0.103s]
+Computing hash join... [0.091s]
+Building seed filter... [0.008s]
+Searching alignments... [0.191s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.233s]
+Building query seed array... [0.101s]
+Computing hash join... [0.089s]
+Building seed filter... [0.007s]
+Searching alignments... [0.19s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.194s]
+Building query seed array... [0.089s]
+Computing hash join... [0.091s]
+Building seed filter... [0.007s]
+Searching alignments... [0.182s]
+Deallocating buffers... [0.052s]
+Computing alignments... [2.506s]
+Deallocating reference... [0.016s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 11.607s
+Reported 29317 pairwise alignments, 29537 HSPs.
+29317 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/Sr_rh_Nn13_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Nn13_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+Warning: [blastn] Examining 5 or more matches is recommended
+[1m
+
+BLASTing [36mSr_rh_Atps.200bp.fasta[0m[1m against the rDNA database
+
+[0m
+[1mBinning Sequences from [36mSr_rh_Atps.200bp.fasta[0m[1m
+as rDNA OR Potentially Protein-Coding
+
+[0m
+[1m
+Look for [38;5;214mbeegfs_NorRNAseqs.fasta[0m[1m
+in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m2b_remove_Bact.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/micout.dmnd
+Sequences = 1451565
+Letters = 458122721
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.145s]
+Masking queries... [0.066s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.033s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.088s]
+Masking reference... [0.689s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.316s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.229s]
+Building query seed array... [0.034s]
+Computing hash join... [0.059s]
+Building seed filter... [0.004s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.245s]
+Building query seed array... [0.03s]
+Computing hash join... [0.044s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.259s]
+Building query seed array... [0.029s]
+Computing hash join... [0.04s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.207s]
+Building query seed array... [0.023s]
+Computing hash join... [0.042s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.207s]
+Building query seed array... [0.022s]
+Computing hash join... [0.039s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.24s]
+Building query seed array... [0.028s]
+Computing hash join... [0.038s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.242s]
+Building query seed array... [0.023s]
+Computing hash join... [0.038s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.203s]
+Building query seed array... [0.02s]
+Computing hash join... [0.039s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Deallocating buffers... [0.055s]
+Computing alignments... [0.218s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0.002s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 5.342s
+Reported 2739 pairwise alignments, 2882 HSPs.
+2739 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/BvE
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_BvsE/eukout.dmnd
+Sequences = 884771
+Letters = 428734159
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.153s]
+Masking queries... [0.058s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.032s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.988s]
+Masking reference... [0.639s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.282s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.221s]
+Building query seed array... [0.028s]
+Computing hash join... [0.039s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.223s]
+Building query seed array... [0.028s]
+Computing hash join... [0.034s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.22s]
+Building query seed array... [0.026s]
+Computing hash join... [0.035s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.189s]
+Building query seed array... [0.024s]
+Computing hash join... [0.034s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.191s]
+Building query seed array... [0.027s]
+Computing hash join... [0.037s]
+Building seed filter... [0.004s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.212s]
+Building query seed array... [0.023s]
+Computing hash join... [0.034s]
+Building seed filter... [0.004s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.226s]
+Building query seed array... [0.025s]
+Computing hash join... [0.034s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.191s]
+Building query seed array... [0.027s]
+Computing hash join... [0.035s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Deallocating buffers... [0.052s]
+Computing alignments... [0.125s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0.002s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 4.805s
+Reported 1289 pairwise alignments, 1382 HSPs.
+1289 queries aligned.
+/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/Sr_rh_Atps_NorRNAseqs.fasta
+[1m
+
+"BLAST"-ing against PROK database using DIAMOND: [36mmicout.dmnd[0m
+
+
+[1m
+
+"BLAST"-ing against EUK database using DIAMOND: [36meukout.dmnd[0m
+
+
+[1m
+Look for [36mSr_rh_Atps_WTA_EPU.fasta[0m[1m in the beegfs Folder
+
+[0m
+[1mNext Script is: [92m3_CountOGsDiamond.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.223s]
+Masking queries... [0.467s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.145s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.597s]
+Masking reference... [1.189s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.447s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.345s]
+Building query seed array... [0.103s]
+Computing hash join... [0.14s]
+Building seed filter... [0.008s]
+Searching alignments... [0.396s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.38s]
+Building query seed array... [0.099s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.39s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.375s]
+Building query seed array... [0.102s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.36s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.323s]
+Building query seed array... [0.086s]
+Computing hash join... [0.124s]
+Building seed filter... [0.009s]
+Searching alignments... [0.364s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.319s]
+Building query seed array... [0.091s]
+Computing hash join... [0.128s]
+Building seed filter... [0.011s]
+Searching alignments... [0.325s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.374s]
+Building query seed array... [0.102s]
+Computing hash join... [0.124s]
+Building seed filter... [0.008s]
+Searching alignments... [0.31s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.096s]
+Computing hash join... [0.13s]
+Building seed filter... [0.009s]
+Searching alignments... [0.332s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.086s]
+Computing hash join... [0.124s]
+Building seed filter... [0.008s]
+Searching alignments... [0.312s]
+Deallocating buffers... [0.093s]
+Computing alignments... [7.27s]
+Deallocating reference... [0.034s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.013s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 20.043s
+Reported 354463 pairwise alignments, 356676 HSPs.
+18186 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn02_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.297s]
+Masking queries... [0.103s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.046s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.611s]
+Masking reference... [1.323s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.457s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.356s]
+Building query seed array... [0.054s]
+Computing hash join... [0.119s]
+Building seed filter... [0.005s]
+Searching alignments... [0.122s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.366s]
+Building query seed array... [0.038s]
+Computing hash join... [0.088s]
+Building seed filter... [0.005s]
+Searching alignments... [0.114s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.045s]
+Computing hash join... [0.087s]
+Building seed filter... [0.006s]
+Searching alignments... [0.117s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.32s]
+Building query seed array... [0.035s]
+Computing hash join... [0.086s]
+Building seed filter... [0.005s]
+Searching alignments... [0.109s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.314s]
+Building query seed array... [0.037s]
+Computing hash join... [0.081s]
+Building seed filter... [0.005s]
+Searching alignments... [0.105s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.357s]
+Building query seed array... [0.033s]
+Computing hash join... [0.084s]
+Building seed filter... [0.005s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.372s]
+Building query seed array... [0.038s]
+Computing hash join... [0.083s]
+Building seed filter... [0.005s]
+Searching alignments... [0.1s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.309s]
+Building query seed array... [0.036s]
+Computing hash join... [0.082s]
+Building seed filter... [0.005s]
+Searching alignments... [0.097s]
+Deallocating buffers... [0.094s]
+Computing alignments... [3.364s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.002s]
+Deallocating queries... [0.003s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 12.124s
+Reported 141326 pairwise alignments, 143069 HSPs.
+7105 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Gspa_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.256s]
+Masking queries... [0.342s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.132s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.602s]
+Masking reference... [1.062s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.466s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.349s]
+Building query seed array... [0.104s]
+Computing hash join... [0.142s]
+Building seed filter... [0.008s]
+Searching alignments... [0.431s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.369s]
+Building query seed array... [0.103s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.4s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.109s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.369s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.095s]
+Computing hash join... [0.13s]
+Building seed filter... [0.009s]
+Searching alignments... [0.357s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.321s]
+Building query seed array... [0.095s]
+Computing hash join... [0.127s]
+Building seed filter... [0.009s]
+Searching alignments... [0.377s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.368s]
+Building query seed array... [0.104s]
+Computing hash join... [0.125s]
+Building seed filter... [0.008s]
+Searching alignments... [0.342s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.375s]
+Building query seed array... [0.101s]
+Computing hash join... [0.125s]
+Building seed filter... [0.009s]
+Searching alignments... [0.375s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.339s]
+Building query seed array... [0.092s]
+Computing hash join... [0.125s]
+Building seed filter... [0.011s]
+Searching alignments... [0.28s]
+Deallocating buffers... [0.096s]
+Computing alignments... [7.307s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 20.076s
+Reported 384072 pairwise alignments, 385929 HSPs.
+19812 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn06_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.862s]
+Masking queries... [0.491s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.163s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.588s]
+Masking reference... [1.043s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.442s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.343s]
+Building query seed array... [0.117s]
+Computing hash join... [0.146s]
+Building seed filter... [0.009s]
+Searching alignments... [0.495s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.107s]
+Computing hash join... [0.13s]
+Building seed filter... [0.01s]
+Searching alignments... [0.448s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.393s]
+Building query seed array... [0.123s]
+Computing hash join... [0.127s]
+Building seed filter... [0.01s]
+Searching alignments... [0.399s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.327s]
+Building query seed array... [0.109s]
+Computing hash join... [0.13s]
+Building seed filter... [0.009s]
+Searching alignments... [0.403s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.314s]
+Building query seed array... [0.1s]
+Computing hash join... [0.133s]
+Building seed filter... [0.01s]
+Searching alignments... [0.386s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.111s]
+Computing hash join... [0.121s]
+Building seed filter... [0.011s]
+Searching alignments... [0.354s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.119s]
+Computing hash join... [0.131s]
+Building seed filter... [0.011s]
+Searching alignments... [0.369s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.099s]
+Computing hash join... [0.129s]
+Building seed filter... [0.012s]
+Searching alignments... [0.33s]
+Deallocating buffers... [0.096s]
+Computing alignments... [8.467s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.026s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 22.321s
+Reported 464168 pairwise alignments, 469292 HSPs.
+24278 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv02_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.871s]
+Masking queries... [0.256s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.104s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.572s]
+Masking reference... [1.051s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.473s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.348s]
+Building query seed array... [0.083s]
+Computing hash join... [0.161s]
+Building seed filter... [0.008s]
+Searching alignments... [0.223s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.093s]
+Computing hash join... [0.126s]
+Building seed filter... [0.007s]
+Searching alignments... [0.208s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.397s]
+Building query seed array... [0.077s]
+Computing hash join... [0.122s]
+Building seed filter... [0.008s]
+Searching alignments... [0.206s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.074s]
+Computing hash join... [0.123s]
+Building seed filter... [0.007s]
+Searching alignments... [0.199s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.313s]
+Building query seed array... [0.073s]
+Computing hash join... [0.122s]
+Building seed filter... [0.008s]
+Searching alignments... [0.177s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.081s]
+Computing hash join... [0.123s]
+Building seed filter... [0.008s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.082s]
+Computing hash join... [0.123s]
+Building seed filter... [0.008s]
+Searching alignments... [0.177s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.074s]
+Computing hash join... [0.123s]
+Building seed filter... [0.008s]
+Searching alignments... [0.183s]
+Deallocating buffers... [0.095s]
+Computing alignments... [5.504s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.014s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 16.157s
+Reported 220479 pairwise alignments, 220717 HSPs.
+10997 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Hind_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.123s]
+Masking queries... [0.311s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.119s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.577s]
+Masking reference... [1.058s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.463s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.337s]
+Building query seed array... [0.083s]
+Computing hash join... [0.19s]
+Building seed filter... [0.009s]
+Searching alignments... [0.295s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.086s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.279s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.376s]
+Building query seed array... [0.089s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.082s]
+Computing hash join... [0.13s]
+Building seed filter... [0.009s]
+Searching alignments... [0.258s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.317s]
+Building query seed array... [0.079s]
+Computing hash join... [0.132s]
+Building seed filter... [0.009s]
+Searching alignments... [0.237s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.358s]
+Building query seed array... [0.086s]
+Computing hash join... [0.132s]
+Building seed filter... [0.01s]
+Searching alignments... [0.24s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.095s]
+Computing hash join... [0.137s]
+Building seed filter... [0.01s]
+Searching alignments... [0.234s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.077s]
+Computing hash join... [0.129s]
+Building seed filter... [0.01s]
+Searching alignments... [0.226s]
+Deallocating buffers... [0.094s]
+Computing alignments... [5.707s]
+Deallocating reference... [0.021s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.012s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 17.227s
+Reported 312594 pairwise alignments, 314266 HSPs.
+16742 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn11_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.782s]
+Masking queries... [0.507s]
+Building query seed set... [0.052s]
+Algorithm: Double-indexed
+Building query histograms... [0.147s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.609s]
+Masking reference... [1.153s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.451s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.348s]
+Building query seed array... [0.105s]
+Computing hash join... [0.188s]
+Building seed filter... [0.01s]
+Searching alignments... [0.432s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.374s]
+Building query seed array... [0.105s]
+Computing hash join... [0.125s]
+Building seed filter... [0.01s]
+Searching alignments... [0.387s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.376s]
+Building query seed array... [0.113s]
+Computing hash join... [0.13s]
+Building seed filter... [0.012s]
+Searching alignments... [0.375s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.099s]
+Computing hash join... [0.128s]
+Building seed filter... [0.011s]
+Searching alignments... [0.38s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.317s]
+Building query seed array... [0.092s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.357s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.105s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.342s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.377s]
+Building query seed array... [0.113s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.354s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.092s]
+Computing hash join... [0.126s]
+Building seed filter... [0.009s]
+Searching alignments... [0.333s]
+Deallocating buffers... [0.093s]
+Computing alignments... [8.04s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.025s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.697s
+Reported 442574 pairwise alignments, 448696 HSPs.
+23147 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv03_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.595s]
+Masking queries... [0.192s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.071s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.591s]
+Masking reference... [1.117s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.475s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.355s]
+Building query seed array... [0.062s]
+Computing hash join... [0.156s]
+Building seed filter... [0.006s]
+Searching alignments... [0.175s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.06s]
+Computing hash join... [0.126s]
+Building seed filter... [0.007s]
+Searching alignments... [0.169s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.059s]
+Computing hash join... [0.123s]
+Building seed filter... [0.006s]
+Searching alignments... [0.157s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.051s]
+Computing hash join... [0.121s]
+Building seed filter... [0.007s]
+Searching alignments... [0.156s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.325s]
+Building query seed array... [0.053s]
+Computing hash join... [0.111s]
+Building seed filter... [0.007s]
+Searching alignments... [0.14s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.359s]
+Building query seed array... [0.055s]
+Computing hash join... [0.111s]
+Building seed filter... [0.007s]
+Searching alignments... [0.145s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.387s]
+Building query seed array... [0.062s]
+Computing hash join... [0.116s]
+Building seed filter... [0.007s]
+Searching alignments... [0.143s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.311s]
+Building query seed array... [0.052s]
+Computing hash join... [0.118s]
+Building seed filter... [0.007s]
+Searching alignments... [0.137s]
+Deallocating buffers... [0.094s]
+Computing alignments... [3.907s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.011s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.69s
+Reported 174844 pairwise alignments, 175037 HSPs.
+9075 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Gsp1_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.979s]
+Masking queries... [0.266s]
+Building query seed set... [0.044s]
+Algorithm: Double-indexed
+Building query histograms... [0.09s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.6s]
+Masking reference... [1.105s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.466s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.334s]
+Building query seed array... [0.072s]
+Computing hash join... [0.199s]
+Building seed filter... [0.012s]
+Searching alignments... [0.239s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.373s]
+Building query seed array... [0.067s]
+Computing hash join... [0.136s]
+Building seed filter... [0.006s]
+Searching alignments... [0.217s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.398s]
+Building query seed array... [0.067s]
+Computing hash join... [0.129s]
+Building seed filter... [0.006s]
+Searching alignments... [0.203s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.318s]
+Building query seed array... [0.061s]
+Computing hash join... [0.127s]
+Building seed filter... [0.006s]
+Searching alignments... [0.218s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.057s]
+Computing hash join... [0.124s]
+Building seed filter... [0.006s]
+Searching alignments... [0.199s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.368s]
+Building query seed array... [0.067s]
+Computing hash join... [0.125s]
+Building seed filter... [0.006s]
+Searching alignments... [0.186s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.067s]
+Computing hash join... [0.121s]
+Building seed filter... [0.006s]
+Searching alignments... [0.192s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.053s]
+Computing hash join... [0.123s]
+Building seed filter... [0.006s]
+Searching alignments... [0.183s]
+Deallocating buffers... [0.094s]
+Computing alignments... [4.041s]
+Deallocating reference... [0.031s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.009s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 14.867s
+Reported 250746 pairwise alignments, 252735 HSPs.
+13330 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv06_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.044s]
+Masking queries... [0.068s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.589s]
+Masking reference... [1.063s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.447s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.352s]
+Building query seed array... [0.009s]
+Computing hash join... [0.079s]
+Building seed filter... [0.005s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.356s]
+Building query seed array... [0.007s]
+Computing hash join... [0.075s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.37s]
+Building query seed array... [0.007s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.009s]
+Computing hash join... [0.077s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.316s]
+Building query seed array... [0.01s]
+Computing hash join... [0.079s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.009s]
+Computing hash join... [0.076s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.373s]
+Building query seed array... [0.009s]
+Computing hash join... [0.079s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.323s]
+Building query seed array... [0.014s]
+Computing hash join... [0.081s]
+Building seed filter... [0.004s]
+Searching alignments... [0.035s]
+Deallocating buffers... [0.098s]
+Computing alignments... [0.344s]
+Deallocating reference... [0.03s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.513s
+Reported 25154 pairwise alignments, 25213 HSPs.
+1224 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Gl01_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.713s]
+Masking queries... [0.209s]
+Building query seed set... [0.043s]
+Algorithm: Double-indexed
+Building query histograms... [0.075s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.588s]
+Masking reference... [1.044s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.447s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.061s]
+Computing hash join... [0.15s]
+Building seed filter... [0.008s]
+Searching alignments... [0.204s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.056s]
+Computing hash join... [0.122s]
+Building seed filter... [0.008s]
+Searching alignments... [0.187s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.383s]
+Building query seed array... [0.062s]
+Computing hash join... [0.113s]
+Building seed filter... [0.007s]
+Searching alignments... [0.175s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.053s]
+Computing hash join... [0.111s]
+Building seed filter... [0.008s]
+Searching alignments... [0.181s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.324s]
+Building query seed array... [0.056s]
+Computing hash join... [0.107s]
+Building seed filter... [0.007s]
+Searching alignments... [0.169s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.06s]
+Computing hash join... [0.11s]
+Building seed filter... [0.007s]
+Searching alignments... [0.159s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.056s]
+Computing hash join... [0.107s]
+Building seed filter... [0.007s]
+Searching alignments... [0.164s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.049s]
+Computing hash join... [0.105s]
+Building seed filter... [0.007s]
+Searching alignments... [0.154s]
+Deallocating buffers... [0.095s]
+Computing alignments... [3.829s]
+Deallocating reference... [0.029s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.006s]
+Deallocating queries... [0.013s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.753s
+Reported 211705 pairwise alignments, 212271 HSPs.
+11092 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Esca_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.785s]
+Masking queries... [0.213s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.086s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.587s]
+Masking reference... [1.104s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.447s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.339s]
+Building query seed array... [0.057s]
+Computing hash join... [0.175s]
+Building seed filter... [0.007s]
+Searching alignments... [0.205s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.369s]
+Building query seed array... [0.062s]
+Computing hash join... [0.141s]
+Building seed filter... [0.009s]
+Searching alignments... [0.187s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.062s]
+Computing hash join... [0.137s]
+Building seed filter... [0.008s]
+Searching alignments... [0.175s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.058s]
+Computing hash join... [0.129s]
+Building seed filter... [0.007s]
+Searching alignments... [0.175s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.312s]
+Building query seed array... [0.059s]
+Computing hash join... [0.135s]
+Building seed filter... [0.007s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.358s]
+Building query seed array... [0.07s]
+Computing hash join... [0.132s]
+Building seed filter... [0.007s]
+Searching alignments... [0.178s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.07s]
+Computing hash join... [0.128s]
+Building seed filter... [0.008s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.318s]
+Building query seed array... [0.054s]
+Computing hash join... [0.127s]
+Building seed filter... [0.007s]
+Searching alignments... [0.155s]
+Deallocating buffers... [0.097s]
+Computing alignments... [4.221s]
+Deallocating reference... [0.031s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.01s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 14.503s
+Reported 205337 pairwise alignments, 206188 HSPs.
+10532 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Calb_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.728s]
+Masking queries... [0.252s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.088s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.582s]
+Masking reference... [1.099s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.488s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.082s]
+Computing hash join... [0.19s]
+Building seed filter... [0.005s]
+Searching alignments... [0.184s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.066s]
+Computing hash join... [0.148s]
+Building seed filter... [0.006s]
+Searching alignments... [0.177s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.071s]
+Computing hash join... [0.143s]
+Building seed filter... [0.006s]
+Searching alignments... [0.171s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.067s]
+Computing hash join... [0.142s]
+Building seed filter... [0.006s]
+Searching alignments... [0.169s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.319s]
+Building query seed array... [0.061s]
+Computing hash join... [0.137s]
+Building seed filter... [0.008s]
+Searching alignments... [0.159s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.082s]
+Computing hash join... [0.14s]
+Building seed filter... [0.008s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.081s]
+Computing hash join... [0.139s]
+Building seed filter... [0.008s]
+Searching alignments... [0.154s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.064s]
+Computing hash join... [0.137s]
+Building seed filter... [0.008s]
+Searching alignments... [0.152s]
+Deallocating buffers... [0.094s]
+Computing alignments... [3.98s]
+Deallocating reference... [0.034s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.009s]
+Deallocating queries... [0.01s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 14.357s
+Reported 186068 pairwise alignments, 186401 HSPs.
+9237 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Emac_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.138s]
+Masking queries... [0.3s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.114s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.623s]
+Masking reference... [1.064s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.476s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.352s]
+Building query seed array... [0.082s]
+Computing hash join... [0.153s]
+Building seed filter... [0.009s]
+Searching alignments... [0.389s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.364s]
+Building query seed array... [0.091s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.289s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.089s]
+Computing hash join... [0.131s]
+Building seed filter... [0.011s]
+Searching alignments... [0.326s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.323s]
+Building query seed array... [0.083s]
+Computing hash join... [0.134s]
+Building seed filter... [0.01s]
+Searching alignments... [0.317s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.081s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.251s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.088s]
+Computing hash join... [0.13s]
+Building seed filter... [0.008s]
+Searching alignments... [0.257s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.376s]
+Building query seed array... [0.091s]
+Computing hash join... [0.13s]
+Building seed filter... [0.01s]
+Searching alignments... [0.328s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.324s]
+Building query seed array... [0.086s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.238s]
+Deallocating buffers... [0.095s]
+Computing alignments... [6.416s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.013s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 18.401s
+Reported 332050 pairwise alignments, 333483 HSPs.
+17028 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn05_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.339s]
+Masking queries... [0.361s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.165s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.602s]
+Masking reference... [1.146s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.453s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.336s]
+Building query seed array... [0.121s]
+Computing hash join... [0.15s]
+Building seed filter... [0.012s]
+Searching alignments... [0.506s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.109s]
+Computing hash join... [0.128s]
+Building seed filter... [0.012s]
+Searching alignments... [0.461s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.106s]
+Computing hash join... [0.129s]
+Building seed filter... [0.01s]
+Searching alignments... [0.419s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.098s]
+Computing hash join... [0.134s]
+Building seed filter... [0.011s]
+Searching alignments... [0.4s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.103s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.389s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.107s]
+Computing hash join... [0.131s]
+Building seed filter... [0.01s]
+Searching alignments... [0.354s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.387s]
+Building query seed array... [0.11s]
+Computing hash join... [0.132s]
+Building seed filter... [0.01s]
+Searching alignments... [0.398s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.098s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.304s]
+Deallocating buffers... [0.096s]
+Computing alignments... [8.481s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.017s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.804s
+Reported 396857 pairwise alignments, 399100 HSPs.
+20167 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn10_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.203s]
+Masking queries... [0.377s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.12s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.61s]
+Masking reference... [1.157s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.439s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.099s]
+Computing hash join... [0.152s]
+Building seed filter... [0.011s]
+Searching alignments... [0.38s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.364s]
+Building query seed array... [0.093s]
+Computing hash join... [0.128s]
+Building seed filter... [0.01s]
+Searching alignments... [0.355s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.386s]
+Building query seed array... [0.105s]
+Computing hash join... [0.131s]
+Building seed filter... [0.011s]
+Searching alignments... [0.323s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.081s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.338s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.32s]
+Building query seed array... [0.087s]
+Computing hash join... [0.127s]
+Building seed filter... [0.01s]
+Searching alignments... [0.307s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.092s]
+Computing hash join... [0.127s]
+Building seed filter... [0.008s]
+Searching alignments... [0.29s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.1s]
+Computing hash join... [0.129s]
+Building seed filter... [0.008s]
+Searching alignments... [0.337s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.089s]
+Computing hash join... [0.124s]
+Building seed filter... [0.008s]
+Searching alignments... [0.287s]
+Deallocating buffers... [0.093s]
+Computing alignments... [7.075s]
+Deallocating reference... [0.039s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 19.506s
+Reported 345493 pairwise alignments, 348050 HSPs.
+17953 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn03_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.188s]
+Masking queries... [0.38s]
+Building query seed set... [0.065s]
+Algorithm: Double-indexed
+Building query histograms... [0.151s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.613s]
+Masking reference... [1.123s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.474s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.342s]
+Building query seed array... [0.102s]
+Computing hash join... [0.143s]
+Building seed filter... [0.008s]
+Searching alignments... [0.298s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.104s]
+Computing hash join... [0.122s]
+Building seed filter... [0.007s]
+Searching alignments... [0.312s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.105s]
+Computing hash join... [0.123s]
+Building seed filter... [0.007s]
+Searching alignments... [0.272s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.095s]
+Computing hash join... [0.128s]
+Building seed filter... [0.007s]
+Searching alignments... [0.279s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.326s]
+Building query seed array... [0.095s]
+Computing hash join... [0.122s]
+Building seed filter... [0.006s]
+Searching alignments... [0.241s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.359s]
+Building query seed array... [0.099s]
+Computing hash join... [0.122s]
+Building seed filter... [0.006s]
+Searching alignments... [0.244s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.375s]
+Building query seed array... [0.11s]
+Computing hash join... [0.126s]
+Building seed filter... [0.008s]
+Searching alignments... [0.26s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.325s]
+Building query seed array... [0.096s]
+Computing hash join... [0.124s]
+Building seed filter... [0.006s]
+Searching alignments... [0.232s]
+Deallocating buffers... [0.094s]
+Computing alignments... [7.456s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 19.458s
+Reported 300277 pairwise alignments, 300581 HSPs.
+14869 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Halb_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.083s]
+Masking queries... [0.305s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.115s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.605s]
+Masking reference... [1.057s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.494s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.094s]
+Computing hash join... [0.164s]
+Building seed filter... [0.008s]
+Searching alignments... [0.39s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.079s]
+Computing hash join... [0.133s]
+Building seed filter... [0.009s]
+Searching alignments... [0.362s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.377s]
+Building query seed array... [0.082s]
+Computing hash join... [0.135s]
+Building seed filter... [0.009s]
+Searching alignments... [0.325s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.077s]
+Computing hash join... [0.134s]
+Building seed filter... [0.008s]
+Searching alignments... [0.329s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.326s]
+Building query seed array... [0.073s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.333s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.38s]
+Building query seed array... [0.082s]
+Computing hash join... [0.131s]
+Building seed filter... [0.008s]
+Searching alignments... [0.28s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.094s]
+Computing hash join... [0.135s]
+Building seed filter... [0.008s]
+Searching alignments... [0.346s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.072s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.294s]
+Deallocating buffers... [0.094s]
+Computing alignments... [5.809s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.012s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 17.987s
+Reported 309767 pairwise alignments, 311870 HSPs.
+15500 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn08_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.412s]
+Masking queries... [0.368s]
+Building query seed set... [0.056s]
+Algorithm: Double-indexed
+Building query histograms... [0.131s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.596s]
+Masking reference... [1.06s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.463s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.339s]
+Building query seed array... [0.107s]
+Computing hash join... [0.139s]
+Building seed filter... [0.007s]
+Searching alignments... [0.383s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.107s]
+Computing hash join... [0.112s]
+Building seed filter... [0.009s]
+Searching alignments... [0.346s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.093s]
+Computing hash join... [0.118s]
+Building seed filter... [0.009s]
+Searching alignments... [0.316s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.083s]
+Computing hash join... [0.109s]
+Building seed filter... [0.009s]
+Searching alignments... [0.318s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.321s]
+Building query seed array... [0.09s]
+Computing hash join... [0.114s]
+Building seed filter... [0.007s]
+Searching alignments... [0.29s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.361s]
+Building query seed array... [0.098s]
+Computing hash join... [0.111s]
+Building seed filter... [0.007s]
+Searching alignments... [0.28s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.385s]
+Building query seed array... [0.102s]
+Computing hash join... [0.11s]
+Building seed filter... [0.007s]
+Searching alignments... [0.296s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.313s]
+Building query seed array... [0.084s]
+Computing hash join... [0.112s]
+Building seed filter... [0.008s]
+Searching alignments... [0.265s]
+Deallocating buffers... [0.094s]
+Computing alignments... [9.117s]
+Deallocating reference... [0.034s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.016s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.434s
+Reported 403699 pairwise alignments, 404113 HSPs.
+19985 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Tx01_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.575s]
+Masking queries... [0.392s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.149s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.587s]
+Masking reference... [1.043s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.486s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.346s]
+Building query seed array... [0.12s]
+Computing hash join... [0.15s]
+Building seed filter... [0.014s]
+Searching alignments... [0.527s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.37s]
+Building query seed array... [0.115s]
+Computing hash join... [0.135s]
+Building seed filter... [0.013s]
+Searching alignments... [0.479s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.38s]
+Building query seed array... [0.12s]
+Computing hash join... [0.134s]
+Building seed filter... [0.012s]
+Searching alignments... [0.431s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.331s]
+Building query seed array... [0.101s]
+Computing hash join... [0.128s]
+Building seed filter... [0.014s]
+Searching alignments... [0.417s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.317s]
+Building query seed array... [0.107s]
+Computing hash join... [0.131s]
+Building seed filter... [0.01s]
+Searching alignments... [0.406s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.364s]
+Building query seed array... [0.114s]
+Computing hash join... [0.134s]
+Building seed filter... [0.01s]
+Searching alignments... [0.365s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.383s]
+Building query seed array... [0.123s]
+Computing hash join... [0.132s]
+Building seed filter... [0.01s]
+Searching alignments... [0.425s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.318s]
+Building query seed array... [0.106s]
+Computing hash join... [0.135s]
+Building seed filter... [0.011s]
+Searching alignments... [0.36s]
+Deallocating buffers... [0.092s]
+Computing alignments... [8.807s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.017s]
+Deallocating queries... [0.021s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 22.588s
+Reported 468908 pairwise alignments, 470976 HSPs.
+23977 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn07_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.342s]
+Masking queries... [0.383s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.146s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.591s]
+Masking reference... [1.057s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.44s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.343s]
+Building query seed array... [0.115s]
+Computing hash join... [0.144s]
+Building seed filter... [0.009s]
+Searching alignments... [0.49s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.102s]
+Computing hash join... [0.132s]
+Building seed filter... [0.009s]
+Searching alignments... [0.489s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.381s]
+Building query seed array... [0.113s]
+Computing hash join... [0.135s]
+Building seed filter... [0.01s]
+Searching alignments... [0.43s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.321s]
+Building query seed array... [0.096s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.411s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.311s]
+Building query seed array... [0.094s]
+Computing hash join... [0.129s]
+Building seed filter... [0.008s]
+Searching alignments... [0.403s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.361s]
+Building query seed array... [0.114s]
+Computing hash join... [0.128s]
+Building seed filter... [0.009s]
+Searching alignments... [0.345s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.113s]
+Computing hash join... [0.128s]
+Building seed filter... [0.008s]
+Searching alignments... [0.421s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.099s]
+Computing hash join... [0.131s]
+Building seed filter... [0.009s]
+Searching alignments... [0.315s]
+Deallocating buffers... [0.094s]
+Computing alignments... [8.498s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.021s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.772s
+Reported 440387 pairwise alignments, 443233 HSPs.
+22715 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn01_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.925s]
+Masking queries... [0.552s]
+Building query seed set... [0.049s]
+Algorithm: Double-indexed
+Building query histograms... [0.186s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.614s]
+Masking reference... [1.056s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.463s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.343s]
+Building query seed array... [0.118s]
+Computing hash join... [0.143s]
+Building seed filter... [0.009s]
+Searching alignments... [0.433s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.113s]
+Computing hash join... [0.129s]
+Building seed filter... [0.011s]
+Searching alignments... [0.382s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.391s]
+Building query seed array... [0.118s]
+Computing hash join... [0.134s]
+Building seed filter... [0.009s]
+Searching alignments... [0.363s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.102s]
+Computing hash join... [0.131s]
+Building seed filter... [0.011s]
+Searching alignments... [0.36s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.317s]
+Building query seed array... [0.1s]
+Computing hash join... [0.128s]
+Building seed filter... [0.01s]
+Searching alignments... [0.352s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.369s]
+Building query seed array... [0.116s]
+Computing hash join... [0.126s]
+Building seed filter... [0.01s]
+Searching alignments... [0.341s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.377s]
+Building query seed array... [0.116s]
+Computing hash join... [0.134s]
+Building seed filter... [0.01s]
+Searching alignments... [0.347s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.101s]
+Computing hash join... [0.13s]
+Building seed filter... [0.011s]
+Searching alignments... [0.317s]
+Deallocating buffers... [0.092s]
+Computing alignments... [7.998s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.028s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.772s
+Reported 405956 pairwise alignments, 409986 HSPs.
+21474 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv04_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.92s]
+Masking queries... [0.256s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.103s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.588s]
+Masking reference... [1.071s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.443s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.345s]
+Building query seed array... [0.076s]
+Computing hash join... [0.177s]
+Building seed filter... [0.008s]
+Searching alignments... [0.377s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.07s]
+Computing hash join... [0.134s]
+Building seed filter... [0.009s]
+Searching alignments... [0.331s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.086s]
+Computing hash join... [0.135s]
+Building seed filter... [0.01s]
+Searching alignments... [0.342s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.322s]
+Building query seed array... [0.074s]
+Computing hash join... [0.132s]
+Building seed filter... [0.009s]
+Searching alignments... [0.342s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.319s]
+Building query seed array... [0.073s]
+Computing hash join... [0.135s]
+Building seed filter... [0.008s]
+Searching alignments... [0.334s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.08s]
+Computing hash join... [0.133s]
+Building seed filter... [0.008s]
+Searching alignments... [0.282s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.385s]
+Building query seed array... [0.087s]
+Computing hash join... [0.139s]
+Building seed filter... [0.008s]
+Searching alignments... [0.267s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.071s]
+Computing hash join... [0.135s]
+Building seed filter... [0.009s]
+Searching alignments... [0.29s]
+Deallocating buffers... [0.093s]
+Computing alignments... [7.134s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.011s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 18.906s
+Reported 537338 pairwise alignments, 538184 HSPs.
+28139 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Usac_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.187s]
+Masking queries... [0.538s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.206s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.604s]
+Masking reference... [1.049s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.445s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.356s]
+Building query seed array... [0.154s]
+Computing hash join... [0.154s]
+Building seed filter... [0.011s]
+Searching alignments... [0.751s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.364s]
+Building query seed array... [0.147s]
+Computing hash join... [0.136s]
+Building seed filter... [0.01s]
+Searching alignments... [0.686s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.385s]
+Building query seed array... [0.153s]
+Computing hash join... [0.144s]
+Building seed filter... [0.01s]
+Searching alignments... [0.603s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.313s]
+Building query seed array... [0.141s]
+Computing hash join... [0.15s]
+Building seed filter... [0.011s]
+Searching alignments... [0.608s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.323s]
+Building query seed array... [0.136s]
+Computing hash join... [0.144s]
+Building seed filter... [0.012s]
+Searching alignments... [0.609s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.147s]
+Computing hash join... [0.141s]
+Building seed filter... [0.012s]
+Searching alignments... [0.534s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.161s]
+Computing hash join... [0.142s]
+Building seed filter... [0.011s]
+Searching alignments... [0.625s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.133s]
+Computing hash join... [0.14s]
+Building seed filter... [0.01s]
+Searching alignments... [0.512s]
+Deallocating buffers... [0.091s]
+Computing alignments... [12.551s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.024s]
+Deallocating queries... [0.028s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 28.989s
+Reported 725553 pairwise alignments, 730001 HSPs.
+36674 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn04_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.543s]
+Masking queries... [0.171s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.07s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.594s]
+Masking reference... [1.056s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.483s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.353s]
+Building query seed array... [0.07s]
+Computing hash join... [0.157s]
+Building seed filter... [0.005s]
+Searching alignments... [0.158s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.36s]
+Building query seed array... [0.05s]
+Computing hash join... [0.126s]
+Building seed filter... [0.006s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.383s]
+Building query seed array... [0.059s]
+Computing hash join... [0.118s]
+Building seed filter... [0.008s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.054s]
+Computing hash join... [0.115s]
+Building seed filter... [0.007s]
+Searching alignments... [0.143s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.318s]
+Building query seed array... [0.05s]
+Computing hash join... [0.108s]
+Building seed filter... [0.006s]
+Searching alignments... [0.128s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.057s]
+Computing hash join... [0.117s]
+Building seed filter... [0.007s]
+Searching alignments... [0.141s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.061s]
+Computing hash join... [0.11s]
+Building seed filter... [0.006s]
+Searching alignments... [0.131s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.326s]
+Building query seed array... [0.057s]
+Computing hash join... [0.112s]
+Building seed filter... [0.006s]
+Searching alignments... [0.126s]
+Deallocating buffers... [0.095s]
+Computing alignments... [3.851s]
+Deallocating reference... [0.025s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.008s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 13.385s
+Reported 158063 pairwise alignments, 159384 HSPs.
+7943 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Emar_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.032s]
+Masking queries... [0.268s]
+Building query seed set... [0.04s]
+Algorithm: Double-indexed
+Building query histograms... [0.088s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.609s]
+Masking reference... [1.222s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.44s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.074s]
+Computing hash join... [0.172s]
+Building seed filter... [0.008s]
+Searching alignments... [0.338s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.361s]
+Building query seed array... [0.068s]
+Computing hash join... [0.149s]
+Building seed filter... [0.007s]
+Searching alignments... [0.291s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.064s]
+Computing hash join... [0.136s]
+Building seed filter... [0.007s]
+Searching alignments... [0.279s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.379s]
+Building query seed array... [0.064s]
+Computing hash join... [0.136s]
+Building seed filter... [0.007s]
+Searching alignments... [0.269s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.316s]
+Building query seed array... [0.056s]
+Computing hash join... [0.133s]
+Building seed filter... [0.006s]
+Searching alignments... [0.239s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.364s]
+Building query seed array... [0.065s]
+Computing hash join... [0.128s]
+Building seed filter... [0.007s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.068s]
+Computing hash join... [0.134s]
+Building seed filter... [0.007s]
+Searching alignments... [0.252s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.054s]
+Computing hash join... [0.131s]
+Building seed filter... [0.007s]
+Searching alignments... [0.232s]
+Deallocating buffers... [0.093s]
+Computing alignments... [5.993s]
+Deallocating reference... [0.035s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.008s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 17.572s
+Reported 461440 pairwise alignments, 462438 HSPs.
+23164 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Rsp1_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.744s]
+Masking queries... [0.211s]
+Building query seed set... [0.041s]
+Algorithm: Double-indexed
+Building query histograms... [0.079s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.602s]
+Masking reference... [1.042s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.478s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.348s]
+Building query seed array... [0.057s]
+Computing hash join... [0.167s]
+Building seed filter... [0.007s]
+Searching alignments... [0.237s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.367s]
+Building query seed array... [0.062s]
+Computing hash join... [0.137s]
+Building seed filter... [0.006s]
+Searching alignments... [0.222s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.383s]
+Building query seed array... [0.064s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.214s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.057s]
+Computing hash join... [0.132s]
+Building seed filter... [0.007s]
+Searching alignments... [0.204s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.316s]
+Building query seed array... [0.054s]
+Computing hash join... [0.127s]
+Building seed filter... [0.006s]
+Searching alignments... [0.187s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.059s]
+Computing hash join... [0.129s]
+Building seed filter... [0.006s]
+Searching alignments... [0.19s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.063s]
+Computing hash join... [0.128s]
+Building seed filter... [0.008s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.322s]
+Building query seed array... [0.059s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.181s]
+Deallocating buffers... [0.092s]
+Computing alignments... [4.925s]
+Deallocating reference... [0.032s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.011s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 15.334s
+Reported 287405 pairwise alignments, 289878 HSPs.
+15066 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Sspa_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.639s]
+Masking queries... [0.176s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.083s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.592s]
+Masking reference... [1.04s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.482s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.344s]
+Building query seed array... [0.07s]
+Computing hash join... [0.161s]
+Building seed filter... [0.005s]
+Searching alignments... [0.179s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.371s]
+Building query seed array... [0.053s]
+Computing hash join... [0.117s]
+Building seed filter... [0.007s]
+Searching alignments... [0.169s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.388s]
+Building query seed array... [0.062s]
+Computing hash join... [0.11s]
+Building seed filter... [0.006s]
+Searching alignments... [0.16s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.051s]
+Computing hash join... [0.116s]
+Building seed filter... [0.006s]
+Searching alignments... [0.162s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.321s]
+Building query seed array... [0.051s]
+Computing hash join... [0.105s]
+Building seed filter... [0.006s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.056s]
+Computing hash join... [0.107s]
+Building seed filter... [0.007s]
+Searching alignments... [0.146s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.375s]
+Building query seed array... [0.059s]
+Computing hash join... [0.105s]
+Building seed filter... [0.007s]
+Searching alignments... [0.153s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.047s]
+Computing hash join... [0.106s]
+Building seed filter... [0.007s]
+Searching alignments... [0.142s]
+Deallocating buffers... [0.094s]
+Computing alignments... [4.475s]
+Deallocating reference... [0.023s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.007s]
+Deallocating queries... [0.008s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 14.192s
+Reported 208347 pairwise alignments, 208875 HSPs.
+10555 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Hhir_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.196s]
+Masking queries... [0.331s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.12s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.595s]
+Masking reference... [1.25s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.458s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.341s]
+Building query seed array... [0.1s]
+Computing hash join... [0.146s]
+Building seed filter... [0.011s]
+Searching alignments... [0.309s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.365s]
+Building query seed array... [0.104s]
+Computing hash join... [0.137s]
+Building seed filter... [0.012s]
+Searching alignments... [0.298s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.377s]
+Building query seed array... [0.099s]
+Computing hash join... [0.128s]
+Building seed filter... [0.01s]
+Searching alignments... [0.287s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.32s]
+Building query seed array... [0.088s]
+Computing hash join... [0.134s]
+Building seed filter... [0.009s]
+Searching alignments... [0.274s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.316s]
+Building query seed array... [0.088s]
+Computing hash join... [0.126s]
+Building seed filter... [0.009s]
+Searching alignments... [0.249s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.1s]
+Computing hash join... [0.129s]
+Building seed filter... [0.011s]
+Searching alignments... [0.263s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.38s]
+Building query seed array... [0.094s]
+Computing hash join... [0.128s]
+Building seed filter... [0.01s]
+Searching alignments... [0.252s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.324s]
+Building query seed array... [0.092s]
+Computing hash join... [0.129s]
+Building seed filter... [0.01s]
+Searching alignments... [0.244s]
+Deallocating buffers... [0.097s]
+Computing alignments... [6.423s]
+Deallocating reference... [0.041s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.013s]
+Deallocating queries... [0.015s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 18.487s
+Reported 329599 pairwise alignments, 331231 HSPs.
+17423 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn12_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.186s]
+Masking queries... [0.323s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.122s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.602s]
+Masking reference... [1.068s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.484s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.344s]
+Building query seed array... [0.089s]
+Computing hash join... [0.151s]
+Building seed filter... [0.01s]
+Searching alignments... [0.392s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.087s]
+Computing hash join... [0.126s]
+Building seed filter... [0.011s]
+Searching alignments... [0.275s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.09s]
+Computing hash join... [0.132s]
+Building seed filter... [0.01s]
+Searching alignments... [0.271s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.322s]
+Building query seed array... [0.087s]
+Computing hash join... [0.128s]
+Building seed filter... [0.011s]
+Searching alignments... [0.261s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.081s]
+Computing hash join... [0.126s]
+Building seed filter... [0.009s]
+Searching alignments... [0.235s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.092s]
+Computing hash join... [0.124s]
+Building seed filter... [0.008s]
+Searching alignments... [0.253s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.376s]
+Building query seed array... [0.092s]
+Computing hash join... [0.127s]
+Building seed filter... [0.008s]
+Searching alignments... [0.243s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.321s]
+Building query seed array... [0.107s]
+Computing hash join... [0.125s]
+Building seed filter... [0.011s]
+Searching alignments... [0.225s]
+Deallocating buffers... [0.099s]
+Computing alignments... [6.156s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.014s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 17.975s
+Reported 330365 pairwise alignments, 332323 HSPs.
+17441 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn14_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [2.193s]
+Masking queries... [0.553s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.214s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.618s]
+Masking reference... [1.063s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.459s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.359s]
+Building query seed array... [0.158s]
+Computing hash join... [0.155s]
+Building seed filter... [0.01s]
+Searching alignments... [0.505s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.361s]
+Building query seed array... [0.15s]
+Computing hash join... [0.144s]
+Building seed filter... [0.011s]
+Searching alignments... [0.476s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.151s]
+Computing hash join... [0.148s]
+Building seed filter... [0.01s]
+Searching alignments... [0.448s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.13s]
+Computing hash join... [0.142s]
+Building seed filter... [0.011s]
+Searching alignments... [0.445s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.32s]
+Building query seed array... [0.133s]
+Computing hash join... [0.145s]
+Building seed filter... [0.011s]
+Searching alignments... [0.394s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.366s]
+Building query seed array... [0.15s]
+Computing hash join... [0.146s]
+Building seed filter... [0.012s]
+Searching alignments... [0.422s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.402s]
+Building query seed array... [0.16s]
+Computing hash join... [0.141s]
+Building seed filter... [0.01s]
+Searching alignments... [0.4s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.313s]
+Building query seed array... [0.136s]
+Computing hash join... [0.141s]
+Building seed filter... [0.012s]
+Searching alignments... [0.386s]
+Deallocating buffers... [0.097s]
+Computing alignments... [12.415s]
+Deallocating reference... [0.038s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.021s]
+Deallocating queries... [0.029s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 27.503s
+Reported 604291 pairwise alignments, 606168 HSPs.
+31505 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Gl02_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.803s]
+Masking queries... [0.507s]
+Building query seed set... [0.05s]
+Algorithm: Double-indexed
+Building query histograms... [0.156s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.612s]
+Masking reference... [1.068s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.449s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.344s]
+Building query seed array... [0.101s]
+Computing hash join... [0.247s]
+Building seed filter... [0.01s]
+Searching alignments... [0.398s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.371s]
+Building query seed array... [0.11s]
+Computing hash join... [0.124s]
+Building seed filter... [0.009s]
+Searching alignments... [0.389s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.396s]
+Building query seed array... [0.112s]
+Computing hash join... [0.133s]
+Building seed filter... [0.01s]
+Searching alignments... [0.365s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.315s]
+Building query seed array... [0.098s]
+Computing hash join... [0.13s]
+Building seed filter... [0.01s]
+Searching alignments... [0.363s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.102s]
+Computing hash join... [0.132s]
+Building seed filter... [0.01s]
+Searching alignments... [0.341s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.371s]
+Building query seed array... [0.11s]
+Computing hash join... [0.13s]
+Building seed filter... [0.01s]
+Searching alignments... [0.321s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.112s]
+Computing hash join... [0.13s]
+Building seed filter... [0.01s]
+Searching alignments... [0.35s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.32s]
+Building query seed array... [0.1s]
+Computing hash join... [0.127s]
+Building seed filter... [0.01s]
+Searching alignments... [0.311s]
+Deallocating buffers... [0.093s]
+Computing alignments... [7.788s]
+Deallocating reference... [0.037s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.015s]
+Deallocating queries... [0.024s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 21.37s
+Reported 412048 pairwise alignments, 415577 HSPs.
+21731 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv05_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.542s]
+Masking queries... [0.379s]
+Building query seed set... [0.049s]
+Algorithm: Double-indexed
+Building query histograms... [0.123s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.582s]
+Masking reference... [1.08s]
+Initializing temporary storage... [0.013s]
+Building reference histograms... [0.476s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.355s]
+Building query seed array... [0.099s]
+Computing hash join... [0.177s]
+Building seed filter... [0.011s]
+Searching alignments... [0.378s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.087s]
+Computing hash join... [0.13s]
+Building seed filter... [0.009s]
+Searching alignments... [0.354s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.38s]
+Building query seed array... [0.093s]
+Computing hash join... [0.133s]
+Building seed filter... [0.011s]
+Searching alignments... [0.338s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.323s]
+Building query seed array... [0.089s]
+Computing hash join... [0.134s]
+Building seed filter... [0.009s]
+Searching alignments... [0.344s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.321s]
+Building query seed array... [0.084s]
+Computing hash join... [0.13s]
+Building seed filter... [0.008s]
+Searching alignments... [0.317s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.36s]
+Building query seed array... [0.112s]
+Computing hash join... [0.139s]
+Building seed filter... [0.008s]
+Searching alignments... [0.297s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.382s]
+Building query seed array... [0.09s]
+Computing hash join... [0.133s]
+Building seed filter... [0.008s]
+Searching alignments... [0.324s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.085s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.281s]
+Deallocating buffers... [0.092s]
+Computing alignments... [6.871s]
+Deallocating reference... [0.038s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.011s]
+Deallocating queries... [0.02s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 19.663s
+Reported 426635 pairwise alignments, 430735 HSPs.
+22250 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Bv01_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.369s]
+Masking queries... [0.107s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.046s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.619s]
+Masking reference... [1.097s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.461s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.353s]
+Building query seed array... [0.043s]
+Computing hash join... [0.116s]
+Building seed filter... [0.006s]
+Searching alignments... [0.109s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.357s]
+Building query seed array... [0.034s]
+Computing hash join... [0.087s]
+Building seed filter... [0.006s]
+Searching alignments... [0.119s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.396s]
+Building query seed array... [0.04s]
+Computing hash join... [0.076s]
+Building seed filter... [0.005s]
+Searching alignments... [0.104s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.033s]
+Computing hash join... [0.077s]
+Building seed filter... [0.005s]
+Searching alignments... [0.107s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.317s]
+Building query seed array... [0.04s]
+Computing hash join... [0.078s]
+Building seed filter... [0.006s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.357s]
+Building query seed array... [0.035s]
+Computing hash join... [0.077s]
+Building seed filter... [0.005s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.371s]
+Building query seed array... [0.037s]
+Computing hash join... [0.077s]
+Building seed filter... [0.006s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.315s]
+Building query seed array... [0.038s]
+Computing hash join... [0.075s]
+Building seed filter... [0.005s]
+Searching alignments... [0.089s]
+Deallocating buffers... [0.091s]
+Computing alignments... [2.255s]
+Deallocating reference... [0.027s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.003s]
+Deallocating queries... [0.007s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 10.778s
+Reported 119039 pairwise alignments, 121169 HSPs.
+5832 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Slin_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.775s]
+Masking queries... [0.471s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.174s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.598s]
+Masking reference... [1.039s]
+Initializing temporary storage... [0.012s]
+Building reference histograms... [0.468s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.351s]
+Building query seed array... [0.136s]
+Computing hash join... [0.16s]
+Building seed filter... [0.012s]
+Searching alignments... [0.495s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.372s]
+Building query seed array... [0.129s]
+Computing hash join... [0.145s]
+Building seed filter... [0.01s]
+Searching alignments... [0.481s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.378s]
+Building query seed array... [0.129s]
+Computing hash join... [0.144s]
+Building seed filter... [0.012s]
+Searching alignments... [0.451s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.315s]
+Building query seed array... [0.119s]
+Computing hash join... [0.144s]
+Building seed filter... [0.013s]
+Searching alignments... [0.441s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.321s]
+Building query seed array... [0.114s]
+Computing hash join... [0.145s]
+Building seed filter... [0.012s]
+Searching alignments... [0.386s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.136s]
+Computing hash join... [0.151s]
+Building seed filter... [0.013s]
+Searching alignments... [0.388s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.139s]
+Computing hash join... [0.144s]
+Building seed filter... [0.014s]
+Searching alignments... [0.389s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.126s]
+Computing hash join... [0.149s]
+Building seed filter... [0.012s]
+Searching alignments... [0.364s]
+Deallocating buffers... [0.095s]
+Computing alignments... [11.681s]
+Deallocating reference... [0.036s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.021s]
+Deallocating queries... [0.028s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 25.969s
+Reported 640067 pairwise alignments, 641506 HSPs.
+32752 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Gl03_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.801s]
+Masking queries... [0.495s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.18s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.586s]
+Masking reference... [1.057s]
+Initializing temporary storage... [0.013s]
+Building reference histograms... [0.47s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.345s]
+Building query seed array... [0.135s]
+Computing hash join... [0.166s]
+Building seed filter... [0.01s]
+Searching alignments... [0.68s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.371s]
+Building query seed array... [0.136s]
+Computing hash join... [0.14s]
+Building seed filter... [0.012s]
+Searching alignments... [0.5s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.383s]
+Building query seed array... [0.142s]
+Computing hash join... [0.139s]
+Building seed filter... [0.01s]
+Searching alignments... [0.596s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.317s]
+Building query seed array... [0.127s]
+Computing hash join... [0.144s]
+Building seed filter... [0.01s]
+Searching alignments... [0.585s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.315s]
+Building query seed array... [0.118s]
+Computing hash join... [0.139s]
+Building seed filter... [0.01s]
+Searching alignments... [0.566s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.363s]
+Building query seed array... [0.133s]
+Computing hash join... [0.139s]
+Building seed filter... [0.01s]
+Searching alignments... [0.462s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.379s]
+Building query seed array... [0.133s]
+Computing hash join... [0.143s]
+Building seed filter... [0.011s]
+Searching alignments... [0.587s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.316s]
+Building query seed array... [0.116s]
+Computing hash join... [0.138s]
+Building seed filter... [0.011s]
+Searching alignments... [0.379s]
+Deallocating buffers... [0.095s]
+Computing alignments... [10.458s]
+Deallocating reference... [0.034s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.021s]
+Deallocating queries... [0.018s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 25.722s
+Reported 592579 pairwise alignments, 596988 HSPs.
+30042 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn09_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [1.276s]
+Masking queries... [0.366s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.132s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.59s]
+Masking reference... [1.132s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.465s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.352s]
+Building query seed array... [0.11s]
+Computing hash join... [0.147s]
+Building seed filter... [0.008s]
+Searching alignments... [0.452s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.362s]
+Building query seed array... [0.108s]
+Computing hash join... [0.131s]
+Building seed filter... [0.008s]
+Searching alignments... [0.364s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.375s]
+Building query seed array... [0.102s]
+Computing hash join... [0.13s]
+Building seed filter... [0.008s]
+Searching alignments... [0.328s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.319s]
+Building query seed array... [0.103s]
+Computing hash join... [0.132s]
+Building seed filter... [0.008s]
+Searching alignments... [0.4s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.327s]
+Building query seed array... [0.092s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.283s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.368s]
+Building query seed array... [0.102s]
+Computing hash join... [0.125s]
+Building seed filter... [0.009s]
+Searching alignments... [0.303s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.377s]
+Building query seed array... [0.112s]
+Computing hash join... [0.129s]
+Building seed filter... [0.009s]
+Searching alignments... [0.33s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.318s]
+Building query seed array... [0.092s]
+Computing hash join... [0.127s]
+Building seed filter... [0.009s]
+Searching alignments... [0.276s]
+Deallocating buffers... [0.093s]
+Computing alignments... [7.313s]
+Deallocating reference... [0.039s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.016s]
+Deallocating queries... [0.019s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 19.997s
+Reported 381006 pairwise alignments, 382593 HSPs.
+19632 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Nn13_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/DiamondOG
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = ../Databases/db_OG/Hook-6.5.dmnd
+Sequences = 1512043
+Letters = 714797884
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.152s]
+Masking queries... [0.062s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.032s]
+Allocating buffers... [0s]
+Loading reference sequences... [1.616s]
+Masking reference... [1.285s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.457s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.351s]
+Building query seed array... [0.028s]
+Computing hash join... [0.069s]
+Building seed filter... [0.004s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.357s]
+Building query seed array... [0.024s]
+Computing hash join... [0.058s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.37s]
+Building query seed array... [0.022s]
+Computing hash join... [0.054s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.32s]
+Building query seed array... [0.029s]
+Computing hash join... [0.056s]
+Building seed filter... [0.004s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.313s]
+Building query seed array... [0.027s]
+Computing hash join... [0.054s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.358s]
+Building query seed array... [0.026s]
+Computing hash join... [0.056s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.374s]
+Building query seed array... [0.023s]
+Computing hash join... [0.05s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.314s]
+Building query seed array... [0.025s]
+Computing hash join... [0.052s]
+Building seed filter... [0.004s]
+Searching alignments... [0.029s]
+Deallocating buffers... [0.092s]
+Computing alignments... [0.366s]
+Deallocating reference... [0.03s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0.001s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 7.863s
+Reported 22784 pairwise alignments, 23612 HSPs.
+1572 queries aligned.
+[1m
+Starting to "BLAST" against OG databases[0m
+[1m
+
+"BLAST"-ing against OG database using DIAMOND: [36mHook-6.5.dmnd[0m
+
+
+[1m[95m
+
+Processing OG-database results to keep only the BEST match for each transcript
+
+[0m
+[1m[95mUpdating Fasta File Sequence Names with their BEST OG hits
+
+[0m
+[1m
+Look for [36mSr_rh_Atps_WTA_EPUWTA_EPU.fasta[0m[1m in the ../beegfs/ Folder
+
+[0m
+[1mNext Script is: [92m4_InFrameStopFreq.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.024s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.009s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.012s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.046s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.052s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.462s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.89s
+Reported 14977 pairwise alignments, 14985 HSPs.
+14977 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.026s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.103s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.071s]
+Building query seed array... [0.019s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.068s]
+Building query seed array... [0.024s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.024s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.058s]
+Building query seed array... [0.021s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.053s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.021s]
+Computing hash join... [0.008s]
+Building seed filter... [0.005s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.052s]
+Deallocating buffers... [0.011s]
+Computing alignments... [0.475s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.101s
+Reported 14970 pairwise alignments, 14978 HSPs.
+14970 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.023s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.066s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.019s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.056s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.471s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.991s
+Reported 14951 pairwise alignments, 14957 HSPs.
+14951 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn02_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.015s]
+Masking queries... [0.022s]
+Building query seed set... [0.026s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.153s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.183s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.369s
+Reported 5809 pairwise alignments, 5814 HSPs.
+5809 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.015s]
+Masking queries... [0.017s]
+Building query seed set... [0.019s]
+Algorithm: Double-indexed
+Building query histograms... [0.008s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.103s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.065s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.066s]
+Building query seed array... [0.015s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.059s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.01s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.183s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.378s
+Reported 5801 pairwise alignments, 5806 HSPs.
+5801 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.015s]
+Masking queries... [0.02s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.108s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.018s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.01s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.184s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.354s
+Reported 5802 pairwise alignments, 5807 HSPs.
+5802 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Gspa_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.026s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.108s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.067s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.024s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.02s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.025s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.452s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.912s
+Reported 16011 pairwise alignments, 16017 HSPs.
+16011 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.067s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.009s]
+Computing hash join... [0.018s]
+Building seed filter... [0.004s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.04s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.041s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.046s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.452s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.802s
+Reported 15989 pairwise alignments, 15994 HSPs.
+15989 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.023s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.069s]
+Building query seed array... [0.018s]
+Computing hash join... [0.018s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.005s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.451s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.823s
+Reported 16009 pairwise alignments, 16014 HSPs.
+16009 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn06_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.031s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.021s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.121s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.069s]
+Building query seed array... [0.028s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.022s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.066s]
+Building query seed array... [0.023s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.473s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.944s
+Reported 19508 pairwise alignments, 19511 HSPs.
+19508 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.025s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.02s]
+Computing hash join... [0.018s]
+Building seed filter... [0.003s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.024s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.077s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.024s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.064s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.025s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.481s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.992s
+Reported 19456 pairwise alignments, 19460 HSPs.
+19456 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.026s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.048s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.471s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.796s
+Reported 19448 pairwise alignments, 19452 HSPs.
+19448 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv02_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.022s]
+Masking queries... [0.024s]
+Building query seed set... [0.025s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.145s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.052s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.062s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.012s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.29s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.596s
+Reported 9114 pairwise alignments, 9130 HSPs.
+9114 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.025s]
+Masking queries... [0.025s]
+Building query seed set... [0.025s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.06s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.068s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.288s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.586s
+Reported 9086 pairwise alignments, 9105 HSPs.
+9086 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.025s]
+Masking queries... [0.024s]
+Building query seed set... [0.026s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.111s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.018s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.282s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.536s
+Reported 9098 pairwise alignments, 9119 HSPs.
+9098 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Hind_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.022s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.145s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.016s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.065s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.02s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.052s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.339s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.721s
+Reported 13395 pairwise alignments, 13400 HSPs.
+13395 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.024s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.009s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.047s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.011s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.037s]
+Building query seed array... [0.009s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.038s]
+Building query seed array... [0.009s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.35s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.588s
+Reported 13387 pairwise alignments, 13390 HSPs.
+13387 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.025s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.005s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.021s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.356s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.724s
+Reported 13378 pairwise alignments, 13382 HSPs.
+13378 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn11_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.025s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.014s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.024s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.019s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.448s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.832s
+Reported 18677 pairwise alignments, 18682 HSPs.
+18677 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.025s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.145s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.022s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.026s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.022s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.463s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.88s
+Reported 18645 pairwise alignments, 18651 HSPs.
+18645 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.026s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.021s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.066s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.021s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.023s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.064s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.457s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.926s
+Reported 18616 pairwise alignments, 18622 HSPs.
+18616 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv03_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.017s]
+Masking queries... [0.019s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.008s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.005s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.065s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.248s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.483s
+Reported 7264 pairwise alignments, 7269 HSPs.
+7264 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.018s]
+Masking queries... [0.022s]
+Building query seed set... [0.024s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.145s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.013s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.25s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.505s
+Reported 7257 pairwise alignments, 7263 HSPs.
+7257 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.017s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.052s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.244s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.462s
+Reported 7266 pairwise alignments, 7272 HSPs.
+7266 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Gsp1_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.021s]
+Building query seed set... [0.019s]
+Algorithm: Double-indexed
+Building query histograms... [0.008s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.064s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.256s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.523s
+Reported 10678 pairwise alignments, 10680 HSPs.
+10678 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.024s]
+Masking queries... [0.024s]
+Building query seed set... [0.023s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.006s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.016s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.257s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.54s
+Reported 10650 pairwise alignments, 10652 HSPs.
+10650 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.02s]
+Masking queries... [0.02s]
+Building query seed set... [0.028s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.053s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.265s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.55s
+Reported 10635 pairwise alignments, 10637 HSPs.
+10635 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv06_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.001s]
+Masking queries... [0.015s]
+Building query seed set... [0.003s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.119s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.006s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.006s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.011s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.009s]
+Computing hash join... [0.01s]
+Building seed filter... [0.007s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.008s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.008s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.009s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.008s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.054s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.1s
+Reported 1110 pairwise alignments, 1110 HSPs.
+1110 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.001s]
+Masking queries... [0.014s]
+Building query seed set... [0.002s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.155s]
+Masking reference... [0.133s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.067s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.006s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.005s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.053s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.135s
+Reported 1110 pairwise alignments, 1110 HSPs.
+1110 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.003s]
+Masking queries... [0.013s]
+Building query seed set... [0.003s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.109s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.006s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.062s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.007s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.055s]
+Building query seed array... [0.009s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.011s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.009s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.01s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.009s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.056s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.139s
+Reported 1110 pairwise alignments, 1110 HSPs.
+1110 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Gl01_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.018s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.008s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.066s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.013s]
+Computing hash join... [0.015s]
+Building seed filter... [0.006s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.055s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.232s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.506s
+Reported 8949 pairwise alignments, 8950 HSPs.
+8949 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.022s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.008s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.068s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.242s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.483s
+Reported 8938 pairwise alignments, 8939 HSPs.
+8938 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.017s]
+Building query seed set... [0.02s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.066s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.064s]
+Building query seed array... [0.021s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.005s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.238s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.497s
+Reported 8940 pairwise alignments, 8941 HSPs.
+8940 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Esca_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.021s]
+Masking queries... [0.025s]
+Building query seed set... [0.024s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.277s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.541s
+Reported 8489 pairwise alignments, 8494 HSPs.
+8489 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.03s]
+Masking queries... [0.024s]
+Building query seed set... [0.025s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.014s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.012s]
+Computing alignments... [0.28s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.575s
+Reported 8457 pairwise alignments, 8463 HSPs.
+8457 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.021s]
+Building query seed set... [0.025s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.111s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.015s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.271s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.522s
+Reported 8493 pairwise alignments, 8499 HSPs.
+8493 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Calb_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.021s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.155s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.065s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.005s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.019s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.243s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.499s
+Reported 7656 pairwise alignments, 7658 HSPs.
+7656 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.025s]
+Masking queries... [0.021s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.245s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.459s
+Reported 7627 pairwise alignments, 7629 HSPs.
+7627 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.024s]
+Masking queries... [0.02s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.054s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.243s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.525s
+Reported 7662 pairwise alignments, 7664 HSPs.
+7662 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Emac_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.032s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.015s]
+Computing hash join... [0.019s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.019s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.02s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.373s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.759s
+Reported 13827 pairwise alignments, 13830 HSPs.
+13827 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.027s]
+Masking queries... [0.024s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.102s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.067s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.023s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.02s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.383s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.757s
+Reported 13833 pairwise alignments, 13835 HSPs.
+13833 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.027s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.114s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.074s]
+Building query seed array... [0.023s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.021s]
+Computing hash join... [0.014s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.059s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.024s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.058s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.378s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.822s
+Reported 13823 pairwise alignments, 13825 HSPs.
+13823 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn05_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.028s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.017s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.023s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.023s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.54s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.997s
+Reported 16657 pairwise alignments, 16661 HSPs.
+16657 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.037s]
+Building query seed set... [0.044s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.02s]
+Computing hash join... [0.012s]
+Building seed filter... [0.007s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.014s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.536s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.985s
+Reported 16447 pairwise alignments, 16451 HSPs.
+16447 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.025s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.019s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.056s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.025s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.027s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.062s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.023s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.023s]
+Computing hash join... [0.008s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.534s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.049s
+Reported 16439 pairwise alignments, 16443 HSPs.
+16439 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn10_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.026s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.017s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.409s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.746s
+Reported 14708 pairwise alignments, 14710 HSPs.
+14708 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.025s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.016s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.02s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.422s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.804s
+Reported 14686 pairwise alignments, 14687 HSPs.
+14686 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.03s]
+Masking queries... [0.032s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.067s]
+Building query seed array... [0.022s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.024s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.419s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.822s
+Reported 14707 pairwise alignments, 14709 HSPs.
+14707 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn03_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.103s]
+Building query seed set... [0.027s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.02s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.013s]
+Computing hash join... [0.006s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.023s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.02s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.019s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.014s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.406s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.813s
+Reported 12458 pairwise alignments, 12469 HSPs.
+12458 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.027s]
+Building query seed set... [0.027s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.067s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.017s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.016s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.019s]
+Computing hash join... [0.008s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.022s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.412s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.745s
+Reported 12438 pairwise alignments, 12449 HSPs.
+12438 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.026s]
+Building query seed set... [0.028s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.108s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.02s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.057s]
+Building query seed array... [0.02s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.016s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.018s]
+Computing hash join... [0.006s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.4s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.78s
+Reported 12459 pairwise alignments, 12473 HSPs.
+12459 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Halb_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.023s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.014s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.067s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.043s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.064s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.376s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.834s
+Reported 13085 pairwise alignments, 13089 HSPs.
+13085 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.022s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.045s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.062s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.057s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.133s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.068s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.067s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.378s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.875s
+Reported 13082 pairwise alignments, 13085 HSPs.
+13082 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.022s]
+Masking queries... [0.024s]
+Building query seed set... [0.023s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.011s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.119s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.379s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.802s
+Reported 13075 pairwise alignments, 13079 HSPs.
+13075 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn08_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.032s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.056s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.062s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.013s]
+Computing hash join... [0.006s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.011s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.012s]
+Computing hash join... [0.006s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.012s]
+Computing hash join... [0.006s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.018s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.011s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.496s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.894s
+Reported 16992 pairwise alignments, 17022 HSPs.
+16992 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.025s]
+Building query seed set... [0.027s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.054s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.013s]
+Computing hash join... [0.008s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.01s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.011s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.498s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.821s
+Reported 16995 pairwise alignments, 17026 HSPs.
+16995 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.027s]
+Building query seed set... [0.028s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.053s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.011s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.013s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.011s]
+Computing hash join... [0.007s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.012s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.497s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.825s
+Reported 17008 pairwise alignments, 17039 HSPs.
+17008 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Tx01_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.05s]
+Masking queries... [0.034s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.122s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.013s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.04s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.042s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.041s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.514s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.903s
+Reported 19505 pairwise alignments, 19510 HSPs.
+19505 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.043s]
+Masking queries... [0.038s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.144s]
+Masking reference... [0.114s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.021s]
+Computing hash join... [0.016s]
+Building seed filter... [0.004s]
+Searching alignments... [0.064s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.062s]
+Building query seed array... [0.022s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.074s]
+Building query seed array... [0.026s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.066s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.023s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.061s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.532s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.098s
+Reported 19471 pairwise alignments, 19474 HSPs.
+19471 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.04s]
+Masking queries... [0.026s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.052s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.061s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.021s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.52s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.964s
+Reported 19449 pairwise alignments, 19453 HSPs.
+19449 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn07_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.026s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.01s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.062s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.045s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.04s]
+Building query seed array... [0.009s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.515s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.892s
+Reported 18653 pairwise alignments, 18661 HSPs.
+18653 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.044s]
+Masking queries... [0.03s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.115s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.053s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.005s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.527s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.96s
+Reported 18645 pairwise alignments, 18655 HSPs.
+18645 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.028s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.006s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.043s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.046s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.005s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.012s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.038s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.525s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.873s
+Reported 18646 pairwise alignments, 18653 HSPs.
+18646 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn01_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.025s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.052s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.027s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.058s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.449s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.88s
+Reported 17205 pairwise alignments, 17208 HSPs.
+17205 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.034s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.103s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.016s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.064s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.454s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.876s
+Reported 17102 pairwise alignments, 17107 HSPs.
+17102 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.042s]
+Masking queries... [0.026s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.153s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.009s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.46s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.785s
+Reported 17052 pairwise alignments, 17057 HSPs.
+17052 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv04_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.028s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.051s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.037s]
+Building query seed array... [0.008s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.037s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.422s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.742s
+Reported 23370 pairwise alignments, 23380 HSPs.
+23370 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.048s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.009s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.008s]
+Building seed filter... [0.005s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.048s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.032s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.425s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.818s
+Reported 23332 pairwise alignments, 23344 HSPs.
+23332 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.037s]
+Masking queries... [0.03s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.111s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.046s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.423s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.842s
+Reported 23363 pairwise alignments, 23372 HSPs.
+23363 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Usac_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.05s]
+Masking queries... [0.032s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.056s]
+Building query seed array... [0.013s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.064s]
+Building query seed array... [0.02s]
+Computing hash join... [0.013s]
+Building seed filter... [0.005s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.014s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.041s]
+Building query seed array... [0.015s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.04s]
+Building query seed array... [0.014s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.748s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.291s
+Reported 30410 pairwise alignments, 30414 HSPs.
+30410 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.052s]
+Masking queries... [0.032s]
+Building query seed set... [0.042s]
+Algorithm: Double-indexed
+Building query histograms... [0.022s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.146s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.056s]
+Building query seed array... [0.015s]
+Computing hash join... [0.019s]
+Building seed filter... [0.006s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.053s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.013s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.04s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Deallocating buffers... [0.011s]
+Computing alignments... [0.75s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.273s
+Reported 30044 pairwise alignments, 30046 HSPs.
+30044 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.048s]
+Masking queries... [0.033s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.056s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.072s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.052s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.009s]
+Building seed filter... [0.004s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.744s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.247s
+Reported 30358 pairwise alignments, 30361 HSPs.
+30358 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn04_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.015s]
+Masking queries... [0.021s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.153s]
+Masking reference... [0.109s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.006s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.05s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.232s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.437s
+Reported 6507 pairwise alignments, 6514 HSPs.
+6507 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.017s]
+Masking queries... [0.021s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.113s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.241s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.437s
+Reported 6501 pairwise alignments, 6504 HSPs.
+6501 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.018s]
+Masking queries... [0.02s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.145s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.023s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.238s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.418s
+Reported 6510 pairwise alignments, 6515 HSPs.
+6510 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Emar_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.027s]
+Masking queries... [0.025s]
+Building query seed set... [0.03s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.015s]
+Computing hash join... [0.015s]
+Building seed filter... [0.004s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.367s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.744s
+Reported 19529 pairwise alignments, 19530 HSPs.
+19529 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.022s]
+Building query seed set... [0.029s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.013s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.023s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.06s]
+Building query seed array... [0.019s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.375s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.776s
+Reported 19648 pairwise alignments, 19649 HSPs.
+19648 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.025s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.015s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.374s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.739s
+Reported 19425 pairwise alignments, 19428 HSPs.
+19425 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Rsp1_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.025s]
+Masking queries... [0.023s]
+Building query seed set... [0.026s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.159s]
+Masking reference... [0.103s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.284s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.579s
+Reported 11921 pairwise alignments, 11926 HSPs.
+11921 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.019s]
+Building query seed set... [0.026s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.162s]
+Masking reference... [0.108s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.015s]
+Computing hash join... [0.021s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.021s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.284s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.578s
+Reported 11920 pairwise alignments, 11925 HSPs.
+11920 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.023s]
+Masking queries... [0.023s]
+Building query seed set... [0.026s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.16s]
+Masking reference... [0.114s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.07s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.285s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.562s
+Reported 11928 pairwise alignments, 11933 HSPs.
+11928 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Sspa_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.022s]
+Masking queries... [0.023s]
+Building query seed set... [0.024s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.155s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.064s]
+Building query seed array... [0.017s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.056s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.265s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.554s
+Reported 8536 pairwise alignments, 8540 HSPs.
+8536 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.023s]
+Masking queries... [0.024s]
+Building query seed set... [0.027s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.171s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.045s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.019s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.009s]
+Building seed filter... [0.006s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.074s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.266s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.547s
+Reported 8521 pairwise alignments, 8526 HSPs.
+8521 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0.001s]
+Opening the output file... [0s]
+Loading query sequences... [0.024s]
+Masking queries... [0.023s]
+Building query seed set... [0.025s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.154s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.276s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.501s
+Reported 8540 pairwise alignments, 8546 HSPs.
+8540 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Hhir_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.031s]
+Masking queries... [0.024s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.16s]
+Masking reference... [0.11s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.068s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.02s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.064s]
+Building query seed array... [0.024s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.054s]
+Building query seed array... [0.023s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.065s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.389s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.831s
+Reported 14131 pairwise alignments, 14135 HSPs.
+14131 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0.001s]
+Opening the output file... [0s]
+Loading query sequences... [0.038s]
+Masking queries... [0.034s]
+Building query seed set... [0.038s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.176s]
+Masking reference... [0.103s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.02s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.39s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.849s
+Reported 14101 pairwise alignments, 14103 HSPs.
+14101 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.023s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.176s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.022s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.063s]
+Building query seed array... [0.022s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.024s]
+Computing hash join... [0.012s]
+Building seed filter... [0.005s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.399s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.842s
+Reported 14108 pairwise alignments, 14110 HSPs.
+14108 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn12_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.029s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.165s]
+Masking reference... [0.114s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.053s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.018s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.066s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.058s]
+Building query seed array... [0.022s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.35s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.759s
+Reported 13993 pairwise alignments, 13999 HSPs.
+13993 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.026s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.162s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.053s]
+Building query seed array... [0.015s]
+Computing hash join... [0.018s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.063s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.371s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.711s
+Reported 13983 pairwise alignments, 13987 HSPs.
+13983 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.023s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.156s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.019s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.019s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.367s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.693s
+Reported 13981 pairwise alignments, 13986 HSPs.
+13981 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn14_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.053s]
+Masking queries... [0.038s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.013s]
+Computing hash join... [0.019s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.015s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.04s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.036s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.647s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.04s
+Reported 25265 pairwise alignments, 25285 HSPs.
+25265 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.059s]
+Masking queries... [0.031s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.026s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.018s]
+Computing hash join... [0.016s]
+Building seed filter... [0.004s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.048s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.043s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.044s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.666s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.084s
+Reported 25226 pairwise alignments, 25252 HSPs.
+25226 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.057s]
+Masking queries... [0.031s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.024s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.15s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.021s]
+Computing hash join... [0.02s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.044s]
+Building query seed array... [0.014s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.016s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.668s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.088s
+Reported 25233 pairwise alignments, 25260 HSPs.
+25233 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Gl02_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.034s]
+Masking queries... [0.027s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.022s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.158s]
+Masking reference... [0.11s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.053s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.06s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.006s]
+Computing alignments... [0.45s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.76s
+Reported 17375 pairwise alignments, 17379 HSPs.
+17375 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.037s]
+Masking queries... [0.024s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.011s]
+Computing hash join... [0.017s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.042s]
+Building query seed array... [0.009s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.042s]
+Building query seed array... [0.011s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.01s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.465s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.773s
+Reported 17358 pairwise alignments, 17365 HSPs.
+17358 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.025s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.061s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.055s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.013s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.012s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.022s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.47s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.846s
+Reported 17328 pairwise alignments, 17333 HSPs.
+17328 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv05_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.027s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.069s]
+Building query seed array... [0.017s]
+Computing hash join... [0.016s]
+Building seed filter... [0.004s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.018s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.017s]
+Computing hash join... [0.01s]
+Building seed filter... [0.005s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.053s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.389s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.774s
+Reported 17843 pairwise alignments, 17846 HSPs.
+17843 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.023s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.153s]
+Masking reference... [0.105s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.02s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.049s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.048s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0.006s]
+Computing alignments... [0.394s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.719s
+Reported 17817 pairwise alignments, 17820 HSPs.
+17817 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.029s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.161s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.054s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.015s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.068s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.022s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.059s]
+Building query seed array... [0.026s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.058s]
+Building query seed array... [0.021s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.394s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.838s
+Reported 17794 pairwise alignments, 17797 HSPs.
+17794 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Bv01_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.01s]
+Masking queries... [0.018s]
+Building query seed set... [0.012s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.155s]
+Masking reference... [0.122s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.066s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.056s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.011s]
+Computing hash join... [0.013s]
+Building seed filter... [0.006s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.177s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.345s
+Reported 4888 pairwise alignments, 4891 HSPs.
+4888 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.01s]
+Masking queries... [0.016s]
+Building query seed set... [0.011s]
+Algorithm: Double-indexed
+Building query histograms... [0.005s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.163s]
+Masking reference... [0.126s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.063s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.063s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.012s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.012s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.014s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.008s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.176s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.367s
+Reported 4897 pairwise alignments, 4900 HSPs.
+4897 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.018s]
+Masking queries... [0.018s]
+Building query seed set... [0.012s]
+Algorithm: Double-indexed
+Building query histograms... [0.005s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.155s]
+Masking reference... [0.114s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.055s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.057s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.056s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.01s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.012s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.011s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.012s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.009s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.053s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.013s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.175s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.345s
+Reported 4885 pairwise alignments, 4889 HSPs.
+4885 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Slin_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.046s]
+Masking queries... [0.035s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.022s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.156s]
+Masking reference... [0.112s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.06s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.058s]
+Building query seed array... [0.016s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.069s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.016s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.045s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.044s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Deallocating buffers... [0.011s]
+Computing alignments... [0.661s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.164s
+Reported 26876 pairwise alignments, 26884 HSPs.
+26876 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.06s]
+Masking queries... [0.035s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.021s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.148s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.052s]
+Building query seed array... [0.014s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.046s]
+Building query seed array... [0.017s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.036s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.68s]
+Deallocating reference... [0.002s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.156s
+Reported 26862 pairwise alignments, 26870 HSPs.
+26862 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.054s]
+Masking queries... [0.031s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.157s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.065s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.066s]
+Building query seed array... [0.015s]
+Computing hash join... [0.013s]
+Building seed filter... [0.004s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.014s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.046s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.044s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.042s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Deallocating buffers... [0.01s]
+Computing alignments... [0.671s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.192s
+Reported 26880 pairwise alignments, 26889 HSPs.
+26880 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Gl03_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.04s]
+Masking queries... [0.032s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.113s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.058s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.023s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.021s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.019s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.022s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.049s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.02s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.022s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.048s]
+Building query seed array... [0.021s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.644s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.178s
+Reported 24415 pairwise alignments, 24421 HSPs.
+24415 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.059s]
+Masking queries... [0.03s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.018s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.156s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.062s]
+Building query seed array... [0.014s]
+Computing hash join... [0.016s]
+Building seed filter... [0.003s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.051s]
+Building query seed array... [0.015s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.013s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.052s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.045s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.017s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.016s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.654s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.161s
+Reported 24409 pairwise alignments, 24417 HSPs.
+24409 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.059s]
+Masking queries... [0.029s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.151s]
+Masking reference... [0.106s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.06s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.019s]
+Computing hash join... [0.013s]
+Building seed filter... [0.006s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.051s]
+Building query seed array... [0.013s]
+Computing hash join... [0.013s]
+Building seed filter... [0.005s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.013s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.039s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.043s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.047s]
+Building query seed array... [0.013s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.047s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.012s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.643s]
+Deallocating reference... [0.005s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.112s
+Reported 24403 pairwise alignments, 24408 HSPs.
+24403 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn09_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.03s]
+Masking queries... [0.029s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.147s]
+Masking reference... [0.115s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.018s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.059s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.015s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.051s]
+Building query seed array... [0.018s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.049s]
+Building query seed array... [0.019s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.018s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.044s]
+Building query seed array... [0.016s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.019s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.42s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.79s
+Reported 15965 pairwise alignments, 15969 HSPs.
+15965 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13
+Opening the database... [0.002s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.037s]
+Masking queries... [0.024s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.149s]
+Masking reference... [0.107s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.011s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.047s]
+Building query seed array... [0.011s]
+Computing hash join... [0.009s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.043s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.042s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.054s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.05s]
+Building query seed array... [0.015s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.041s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0.009s]
+Computing alignments... [0.428s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.723s
+Reported 15949 pairwise alignments, 15952 HSPs.
+15949 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.025s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.144s]
+Masking reference... [0.117s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.063s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.068s]
+Building query seed array... [0.012s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.058s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.058s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.052s]
+Building query seed array... [0.008s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.05s]
+Building query seed array... [0.016s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.055s]
+Building query seed array... [0.014s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.046s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.414s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.797s
+Reported 15941 pairwise alignments, 15945 HSPs.
+15941 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Nn13_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13 Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.005s]
+Masking queries... [0.01s]
+Building query seed set... [0.005s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.153s]
+Masking reference... [0.104s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.056s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.065s]
+Building query seed array... [0.011s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.065s]
+Building query seed array... [0.009s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.013s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.006s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.009s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.003s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.061s]
+Building query seed array... [0.01s]
+Computing hash join... [0.011s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.013s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.014s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Deallocating buffers... [0.007s]
+Computing alignments... [0.042s]
+Deallocating reference... [0.008s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.11s
+Reported 706 pairwise alignments, 706 HSPs.
+706 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.002s]
+Masking queries... [0.012s]
+Building query seed set... [0.004s]
+Algorithm: Double-indexed
+Building query histograms... [0.003s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.108s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.057s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.061s]
+Building query seed array... [0.011s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.057s]
+Building query seed array... [0.01s]
+Computing hash join... [0.015s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.057s]
+Building query seed array... [0.011s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.05s]
+Building query seed array... [0.008s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.048s]
+Building query seed array... [0.007s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.06s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.056s]
+Building query seed array... [0.01s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.057s]
+Building query seed array... [0.009s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Deallocating buffers... [0.008s]
+Computing alignments... [0.042s]
+Deallocating reference... [0.004s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.098s
+Reported 700 pairwise alignments, 700 HSPs.
+700 queries aligned.
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 1
+Reference = ../Databases/db_StopFreq/RepEukProts.dmnd
+Sequences = 156593
+Letters = 61953133
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.002s]
+Masking queries... [0.012s]
+Building query seed set... [0.003s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.152s]
+Masking reference... [0.117s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.059s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.064s]
+Building query seed array... [0.011s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.055s]
+Building query seed array... [0.01s]
+Computing hash join... [0.014s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.054s]
+Building query seed array... [0.009s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.047s]
+Building query seed array... [0.011s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.001s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.047s]
+Building query seed array... [0.012s]
+Computing hash join... [0.012s]
+Building seed filter... [0.007s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.052s]
+Building query seed array... [0.01s]
+Computing hash join... [0.01s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.053s]
+Building query seed array... [0.01s]
+Computing hash join... [0.012s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.049s]
+Building query seed array... [0.01s]
+Computing hash join... [0.013s]
+Building seed filter... [0.003s]
+Searching alignments... [0.002s]
+Deallocating buffers... [0.011s]
+Computing alignments... [0.038s]
+Deallocating reference... [0.003s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.088s
+Reported 709 pairwise alignments, 709 HSPs.
+709 queries aligned.
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+Identifying ORFs in the Fasta file based on the output of 3_CountOGsDiamond.py
+[0m
+[1m
+
+Translating DNA using[91m TAA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TGA[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Translating DNA using[91m TAG[0m[1m as the sole STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TGA [0m[1mas only STOP codon
+[0m
+[1m
+
+Writing FASTA files with ORF and Protein sequences with[91m TAG [0m[1mas only STOP codon
+[0m
+[1m
+
+Gathering Sequence information from FASTA and TSV files
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TGA[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAG[0m[1m is the only STOP
+[0m
+[1m
+Collecting in-frame stop codon information when[91m TAA[0m[1m is the only STOP
+[0m
+[1m
+Look for [36mSr_rh_Atps_WTA_EPU.Renamed_StopCodonStats.tsv[0m[1m in the /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps Folder
+
+[0m
+[1mNext Script is: [92m5_GCodeTranslate.py
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn02_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn02_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn02_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn02_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn02_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn02 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Gspa_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Gspa_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Gspa_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Gspa_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Gspa_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Gspa Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn06_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn06_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn06_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn06_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn06_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn06 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv02_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv02_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv02_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv02_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv02_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv02 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Hind_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Hind_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Hind_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Hind_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Hind_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Hind Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn11_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn11_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn11_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn11_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn11_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn11 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv03_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv03_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv03_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv03_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv03_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv03 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Gsp1_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Gsp1_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Gsp1_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Gsp1_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Gsp1_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Gsp1 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv06_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv06_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv06_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv06_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv06_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv06 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Gl01_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Gl01_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Gl01_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Gl01_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Gl01_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Gl01 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Esca_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Esca_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Esca_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Esca_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Esca_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Esca Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Calb_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Calb_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Calb_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Calb_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Calb_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Calb Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Emac_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Emac_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Emac_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Emac_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Emac_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Emac Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn05_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn05_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn05_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn05_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn05_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn05 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn10_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn10_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn10_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn10_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn10_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn10 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn03_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn03_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn03_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn03_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn03_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn03 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Halb_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Halb_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Halb_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Halb_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Halb_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Halb Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn08_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn08_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn08_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn08_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn08_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn08 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Tx01_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Tx01_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Tx01_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Tx01_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Tx01_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Tx01 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn07_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn07_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn07_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn07_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn07_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn07 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn01_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn01_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn01_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn01_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn01_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn01 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv04_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv04_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv04_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv04_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv04_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv04 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Usac_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Usac_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Usac_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Usac_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Usac_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Usac Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn04_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn04_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn04_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn04_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn04_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn04 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Emar_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Emar_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Emar_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Emar_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Emar_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Emar Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Rsp1_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Rsp1_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Rsp1_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Rsp1_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Rsp1_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Rsp1 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Sspa_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Sspa_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Sspa_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Sspa_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Sspa_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Sspa Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Hhir_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Hhir_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Hhir_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Hhir_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Hhir_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Hhir Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn12_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn12_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn12_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn12_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn12_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn12 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn14_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn14_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn14_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn14_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn14_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn14 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Gl02_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Gl02_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Gl02_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Gl02_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Gl02_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Gl02 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv05_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv05_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv05_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv05_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv05_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv05 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Bv01_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Bv01_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Bv01_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Bv01_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Bv01_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Bv01 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Slin_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Slin_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Slin_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Slin_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Slin_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Slin Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Gl03_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Gl03_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Gl03_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Gl03_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Gl03_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Gl03 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn09_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn09_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn09_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn09_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn09_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn09 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Nn13_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Nn13_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Nn13_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Nn13_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Nn13_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Nn13 Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+/gridapps/software/Biopython/1.75-foss-2019b-Python-3.7.4/lib/python3.7/site-packages/Bio/Seq.py:2748: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
+ BiopythonWarning)
+[1m
+
+Grabbing useful info from the [38;5;214mSr_rh_Atps_WTA_EPU.Renamed.fasta[0m[1m Fasta File
+and from the [38;5;214mSr_rh_Atps_WTA_EPU.Renamed_allOGCleanresults.tsv[0m[1m OG-Assignment Spreadsheet[0m
+[1m
+
+Extracting [94mORFs[0m[1m from the transcriptomic data-set
+
+[0m
+[1m
+
+Translating [94mORFs[0m[1m from using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Writing FASTA file with [94mTranslated ORF[0m[1m sequences using the [36mUniversal genetic code[0m
+[1m
+
+Look for [36mSr_rh_Atps_WTA_EPU.Renamed_Universal_NTD.ORF.fasta[0m[1m,
+[36mSr_rh_Atps_WTA_EPU.Renamed_Universal_AA.ORF.fasta[0m[1m, and
+[36mSr_rh_Atps_WTA_EPU.Renamed_Universal_allOGCleanresults.tsv[0m[1m,
+which are in the [38;5;214mSr_rh_Atps Folder[0m
+[1m
+
+Next Script is: [92m6_FilterPartials.py[0m[1m in the [94mFinalizeTranscripts Folder[0m[1m
+with a copy of the outputs of this script!
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/Original/Concatenated/Sr_rh_Rsp1.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.024s]
+Masking sequences... [0.024s]
+Writing sequences... [0.008s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = bab6450592789937ae623d8d5a857e95
+Processed 23164 sequences, 4715295 letters.
+Total time = 0.063s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Rsp1/Original/Concatenated/Sr_rh_Rsp1.AA.Concatenated.dmnd
+Sequences = 23164
+Letters = 4715295
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.032s]
+Masking queries... [0.022s]
+Building query seed set... [0.03s]
+Algorithm: Double-indexed
+Building query histograms... [0.011s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.014s]
+Masking reference... [0.014s]
+Initializing temporary storage... [0.008s]
+Building reference histograms... [0.011s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.017s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.021s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.015s]
+Building query seed array... [0.018s]
+Computing hash join... [0.004s]
+Building seed filter... [0.006s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.052s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.02s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.02s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.023s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.049s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.529s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.449s
+Reported 213997 pairwise alignments, 214009 HSPs.
+20278 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Rsp1[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Rsp1
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Rsp1
+
+[0m
+[1mThere were [96m23164[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m402[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m23164[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1460[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3886 Unique ORFs[0m[1m for [96mSr_rh_Rsp1
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/Original/Concatenated/Sr_rh_Gspa.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.015s]
+Masking sequences... [0.022s]
+Writing sequences... [0.005s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = a6c8290dedcc9f8988a2173a11da18c7
+Processed 7105 sequences, 3003718 letters.
+Total time = 0.048s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gspa/Original/Concatenated/Sr_rh_Gspa.AA.Concatenated.dmnd
+Sequences = 7105
+Letters = 3003718
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.021s]
+Masking queries... [0.022s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.011s]
+Masking reference... [0.012s]
+Initializing temporary storage... [0.008s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.012s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.008s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.007s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.01s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.016s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.014s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.007s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.008s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.016s]
+Deallocating buffers... [0s]
+Computing alignments... [0.163s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.688s
+Reported 21465 pairwise alignments, 21479 HSPs.
+4188 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Gspa[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Gspa
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Gspa
+
+[0m
+[1mThere were [96m7105[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m403[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m7105[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m247[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3885 Unique ORFs[0m[1m for [96mSr_rh_Gspa
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/Original/Concatenated/Sr_rh_Bv06.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.025s]
+Masking sequences... [0.025s]
+Writing sequences... [0.006s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0.001s]
+Database hash = 0d69e46f38fb37d85dde5e9893f95811
+Processed 13330 sequences, 3179706 letters.
+Total time = 0.064s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv06/Original/Concatenated/Sr_rh_Bv06.AA.Concatenated.dmnd
+Sequences = 13330
+Letters = 3179706
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.019s]
+Masking queries... [0.02s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.01s]
+Masking reference... [0.013s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.01s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.015s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.01s]
+Building query seed array... [0.007s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.013s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.013s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0s]
+Computing alignments... [0.354s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.974s
+Reported 118156 pairwise alignments, 118180 HSPs.
+10897 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv06[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv06
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv06
+
+[0m
+[1mThere were [96m13330[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m247[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m13330[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m708[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3447 Unique ORFs[0m[1m for [96mSr_rh_Bv06
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/Original/Concatenated/Sr_rh_Bv05.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.034s]
+Masking sequences... [0.032s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0.001s]
+Database hash = f232a8887cb0b9a70c7d1734930dc141
+Processed 21731 sequences, 6537985 letters.
+Total time = 0.084s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv05/Original/Concatenated/Sr_rh_Bv05.AA.Concatenated.dmnd
+Sequences = 21731
+Letters = 6537985
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.046s]
+Masking queries... [0.03s]
+Building query seed set... [0.037s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.02s]
+Masking reference... [0.019s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.017s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.011s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.08s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.017s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.064s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.01s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.009s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.053s]
+Deallocating buffers... [0s]
+Computing alignments... [1.01s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.041s
+Reported 247684 pairwise alignments, 247700 HSPs.
+18611 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv05[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv05
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv05
+
+[0m
+[1mThere were [96m21731[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m985[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m21731[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1186[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4673 Unique ORFs[0m[1m for [96mSr_rh_Bv05
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/Original/Concatenated/Sr_rh_Hhir.AA.Concatenated.fasta
+Opening the database file... [0.001s]
+Loading sequences... [0.029s]
+Masking sequences... [0.025s]
+Writing sequences... [0.007s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 428316e31713e49d2d7dce86c739ac6d
+Processed 10555 sequences, 4383683 letters.
+Total time = 0.067s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hhir/Original/Concatenated/Sr_rh_Hhir.AA.Concatenated.dmnd
+Sequences = 10555
+Letters = 4383683
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.021s]
+Building query seed set... [0.028s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.011s]
+Masking reference... [0.015s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.013s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.015s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.035s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.012s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.012s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.013s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.019s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Deallocating buffers... [0s]
+Computing alignments... [0.348s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.045s
+Reported 74899 pairwise alignments, 74902 HSPs.
+8134 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Hhir[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Hhir
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Hhir
+
+[0m
+[1mThere were [96m10555[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m539[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m10555[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m276[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3796 Unique ORFs[0m[1m for [96mSr_rh_Hhir
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/Original/Concatenated/Sr_rh_Usac.AA.Concatenated.fasta
+Opening the database file... [0.003s]
+Loading sequences... [0.04s]
+Masking sequences... [0.03s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 8b58851e74ea699eb4d51c09aeec1dbf
+Processed 28139 sequences, 6273041 letters.
+Total time = 0.088s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Usac/Original/Concatenated/Sr_rh_Usac.AA.Concatenated.dmnd
+Sequences = 28139
+Letters = 6273041
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.04s]
+Masking queries... [0.029s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.019s]
+Masking reference... [0.021s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.013s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.02s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.006s]
+Searching alignments... [0.075s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.054s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.011s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.054s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.009s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.053s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.045s]
+Deallocating buffers... [0s]
+Computing alignments... [0.662s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.57s
+Reported 254805 pairwise alignments, 254821 HSPs.
+22199 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Usac[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Usac
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Usac
+
+[0m
+[1mThere were [96m28139[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m552[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m28139[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m2668[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5891 Unique ORFs[0m[1m for [96mSr_rh_Usac
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/Original/Concatenated/Sr_rh_Nn12.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.027s]
+Masking sequences... [0.025s]
+Writing sequences... [0.008s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = e7d4a4c31fbd8f98b96b01981ecc8606
+Processed 17423 sequences, 5488596 letters.
+Total time = 0.067s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn12/Original/Concatenated/Sr_rh_Nn12.AA.Concatenated.dmnd
+Sequences = 17423
+Letters = 5488596
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.023s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.018s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.012s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.054s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.021s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.02s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.044s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.559s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.461s
+Reported 130509 pairwise alignments, 130513 HSPs.
+13655 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn12[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn12
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn12
+
+[0m
+[1mThere were [96m17423[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m714[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m17423[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1428[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4918 Unique ORFs[0m[1m for [96mSr_rh_Nn12
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/Original/Concatenated/Sr_rh_Nn11.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.025s]
+Masking sequences... [0.027s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = ce23face356f3db46ecedaa798ad5aef
+Processed 16742 sequences, 5190604 letters.
+Total time = 0.068s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn11/Original/Concatenated/Sr_rh_Nn11.AA.Concatenated.dmnd
+Sequences = 16742
+Letters = 5190604
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.023s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.016s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.011s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.014s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.017s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.043s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.019s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.037s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.034s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.033s]
+Deallocating buffers... [0s]
+Computing alignments... [0.486s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.293s
+Reported 118397 pairwise alignments, 118399 HSPs.
+12869 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn11[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn11
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn11
+
+[0m
+[1mThere were [96m16742[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m605[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m16742[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1489[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4851 Unique ORFs[0m[1m for [96mSr_rh_Nn11
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/Original/Concatenated/Sr_rh_Emac.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.019s]
+Masking sequences... [0.021s]
+Writing sequences... [0.005s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0.001s]
+Database hash = 64cf2a04524c8e16fd6656e71370d508
+Processed 9237 sequences, 3633229 letters.
+Total time = 0.051s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emac/Original/Concatenated/Sr_rh_Emac.AA.Concatenated.dmnd
+Sequences = 9237
+Letters = 3633229
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.023s]
+Masking queries... [0.021s]
+Building query seed set... [0.022s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.009s]
+Masking reference... [0.013s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.011s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.013s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.007s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.011s]
+Building query seed array... [0.011s]
+Computing hash join... [0.004s]
+Building seed filter... [0.006s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.005s]
+Building seed filter... [0.007s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0s]
+Computing alignments... [0.293s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.903s
+Reported 63591 pairwise alignments, 63591 HSPs.
+7137 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Emac[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Emac
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Emac
+
+[0m
+[1mThere were [96m9237[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m832[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m9237[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m279[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3032 Unique ORFs[0m[1m for [96mSr_rh_Emac
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/Original/Concatenated/Sr_rh_Nn07.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.039s]
+Masking sequences... [0.032s]
+Writing sequences... [0.012s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0.001s]
+Database hash = 8244245367c3ffdbc45bb090b15f7b05
+Processed 23977 sequences, 7324212 letters.
+Total time = 0.092s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn07/Original/Concatenated/Sr_rh_Nn07.AA.Concatenated.dmnd
+Sequences = 23977
+Letters = 7324212
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.05s]
+Masking queries... [0.027s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.022s]
+Masking reference... [0.022s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.018s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.012s]
+Computing hash join... [0.005s]
+Building seed filter... [0.007s]
+Searching alignments... [0.214s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.005s]
+Searching alignments... [0.153s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.147s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.135s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.161s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.126s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.136s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.015s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.128s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.08s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.825s
+Reported 245593 pairwise alignments, 245597 HSPs.
+19882 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn07[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn07
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn07
+
+[0m
+[1mThere were [96m23977[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m2660[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m23977[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1830[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5510 Unique ORFs[0m[1m for [96mSr_rh_Nn07
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/Original/Concatenated/Sr_rh_Nn13.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.033s]
+Masking sequences... [0.028s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 6284262dc2b368563c66830b2de682fe
+Processed 19632 sequences, 6226238 letters.
+Total time = 0.077s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn13/Original/Concatenated/Sr_rh_Nn13.AA.Concatenated.dmnd
+Sequences = 19632
+Letters = 6226238
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.027s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.016s]
+Masking reference... [0.019s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.013s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.014s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.092s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.013s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.012s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.072s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.009s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.011s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.01s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.009s]
+Building query seed array... [0.009s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.059s]
+Deallocating buffers... [0s]
+Computing alignments... [0.711s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.702s
+Reported 167005 pairwise alignments, 167007 HSPs.
+15814 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn13[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn13
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn13
+
+[0m
+[1mThere were [96m19632[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1170[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m19632[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1617[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5105 Unique ORFs[0m[1m for [96mSr_rh_Nn13
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/Original/Concatenated/Sr_rh_Hind.AA.Concatenated.fasta
+Opening the database file... [0.001s]
+Loading sequences... [0.023s]
+Masking sequences... [0.024s]
+Writing sequences... [0.007s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 31071ed620ecc09074d6eef75556a9f9
+Processed 10997 sequences, 4801737 letters.
+Total time = 0.059s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Hind/Original/Concatenated/Sr_rh_Hind.AA.Concatenated.dmnd
+Sequences = 10997
+Letters = 4801737
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.026s]
+Masking queries... [0.021s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.012s]
+Masking reference... [0.016s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.048s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.039s]
+Deallocating buffers... [0s]
+Computing alignments... [0.412s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.221s
+Reported 85965 pairwise alignments, 86115 HSPs.
+9226 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Hind[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Hind
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Hind
+
+[0m
+[1mThere were [96m10997[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1346[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m10997[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m307[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m2768 Unique ORFs[0m[1m for [96mSr_rh_Hind
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/Original/Concatenated/Sr_rh_Slin.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.016s]
+Masking sequences... [0.016s]
+Writing sequences... [0.003s]
+Hashing sequences... [0s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = eb21f94236c55caa57cea789977257e5
+Processed 5832 sequences, 1943459 letters.
+Total time = 0.04s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Slin/Original/Concatenated/Sr_rh_Slin.AA.Concatenated.dmnd
+Sequences = 5832
+Letters = 1943459
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.017s]
+Masking queries... [0.015s]
+Building query seed set... [0.012s]
+Algorithm: Double-indexed
+Building query histograms... [0.005s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.007s]
+Masking reference... [0.009s]
+Initializing temporary storage... [0.008s]
+Building reference histograms... [0.004s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.01s]
+Building query seed array... [0.011s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.009s]
+Building query seed array... [0.011s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.019s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.012s]
+Building query seed array... [0.008s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.017s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.008s]
+Building query seed array... [0.008s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.018s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.009s]
+Building query seed array... [0.009s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.015s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.009s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.015s]
+Deallocating buffers... [0s]
+Computing alignments... [0.144s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.621s
+Reported 32543 pairwise alignments, 32545 HSPs.
+3816 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Slin[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Slin
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Slin
+
+[0m
+[1mThere were [96m5832[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m441[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m5832[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m279[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m2566 Unique ORFs[0m[1m for [96mSr_rh_Slin
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/Original/Concatenated/Sr_rh_Atps.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.002s]
+Masking sequences... [0.011s]
+Writing sequences... [0s]
+Hashing sequences... [0s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 032e18933d35f2dcdbd89f8365a0e29b
+Processed 1572 sequences, 304954 letters.
+Total time = 0.018s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Atps/Original/Concatenated/Sr_rh_Atps.AA.Concatenated.dmnd
+Sequences = 1572
+Letters = 304954
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.002s]
+Masking queries... [0.009s]
+Building query seed set... [0.003s]
+Algorithm: Double-indexed
+Building query histograms... [0.003s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.001s]
+Masking reference... [0.004s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.003s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.014s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.007s]
+Computing hash join... [0.002s]
+Building seed filter... [0.005s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.007s]
+Building query seed array... [0.004s]
+Computing hash join... [0.001s]
+Building seed filter... [0.003s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.007s]
+Building query seed array... [0.006s]
+Computing hash join... [0.002s]
+Building seed filter... [0.005s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.006s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.013s]
+Building query seed array... [0.007s]
+Computing hash join... [0.001s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.007s]
+Building query seed array... [0.006s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.006s]
+Building query seed array... [0.003s]
+Computing hash join... [0.001s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Deallocating buffers... [0s]
+Computing alignments... [0.031s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.307s
+Reported 2855 pairwise alignments, 2855 HSPs.
+490 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Atps[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Atps
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Atps
+
+[0m
+[1mThere were [96m1572[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m39[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m1572[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m119[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m1065 Unique ORFs[0m[1m for [96mSr_rh_Atps
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/Original/Concatenated/Sr_rh_Calb.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.026s]
+Masking sequences... [0.024s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.003s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = c31e6238b80f6551ff9fba31e8253bf7
+Processed 10532 sequences, 3924177 letters.
+Total time = 0.067s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Calb/Original/Concatenated/Sr_rh_Calb.AA.Concatenated.dmnd
+Sequences = 10532
+Letters = 3924177
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.022s]
+Masking queries... [0.024s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.01s]
+Masking reference... [0.013s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.012s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.012s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.013s]
+Building query seed array... [0.016s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.013s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0s]
+Computing alignments... [0.38s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.027s
+Reported 89461 pairwise alignments, 89467 HSPs.
+8205 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Calb[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Calb
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Calb
+
+[0m
+[1mThere were [96m10532[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m339[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m10532[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m350[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3460 Unique ORFs[0m[1m for [96mSr_rh_Calb
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/Original/Concatenated/Sr_rh_Gsp1.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.018s]
+Masking sequences... [0.021s]
+Writing sequences... [0.005s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = e29604468b49ff25602af34bf175d55b
+Processed 9075 sequences, 3395806 letters.
+Total time = 0.049s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gsp1/Original/Concatenated/Sr_rh_Gsp1.AA.Concatenated.dmnd
+Sequences = 9075
+Letters = 3395806
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.018s]
+Masking queries... [0.021s]
+Building query seed set... [0.023s]
+Algorithm: Double-indexed
+Building query histograms... [0.009s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.01s]
+Masking reference... [0.013s]
+Initializing temporary storage... [0.008s]
+Building reference histograms... [0.006s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.031s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.015s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.008s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.009s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.012s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.02s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.007s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Deallocating buffers... [0s]
+Computing alignments... [0.272s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.859s
+Reported 57494 pairwise alignments, 57495 HSPs.
+6675 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Gsp1[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Gsp1
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Gsp1
+
+[0m
+[1mThere were [96m9075[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m410[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m9075[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m386[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3393 Unique ORFs[0m[1m for [96mSr_rh_Gsp1
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/Original/Concatenated/Sr_rh_Nn08.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.022s]
+Masking sequences... [0.026s]
+Writing sequences... [0.007s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 5aaed5bdda45faa3943131907b7845d5
+Processed 15500 sequences, 3990841 letters.
+Total time = 0.062s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn08/Original/Concatenated/Sr_rh_Nn08.AA.Concatenated.dmnd
+Sequences = 15500
+Letters = 3990841
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.024s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.017s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.015s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.158s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.023s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.124s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.022s]
+Building query seed array... [0.016s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.113s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.109s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.017s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.102s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.021s]
+Building query seed array... [0.012s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.101s]
+Deallocating buffers... [0s]
+Computing alignments... [0.615s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.065s
+Reported 166114 pairwise alignments, 166116 HSPs.
+12320 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn08[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn08
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn08
+
+[0m
+[1mThere were [96m15500[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m2616[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m15500[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1059[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4023 Unique ORFs[0m[1m for [96mSr_rh_Nn08
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/Original/Concatenated/Sr_rh_Nn04.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.048s]
+Masking sequences... [0.037s]
+Writing sequences... [0.015s]
+Hashing sequences... [0.004s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 95f78e5fe98e9036e94658c2ba4f58da
+Processed 36674 sequences, 9173466 letters.
+Total time = 0.11s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn04/Original/Concatenated/Sr_rh_Nn04.AA.Concatenated.dmnd
+Sequences = 36674
+Letters = 9173466
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.049s]
+Masking queries... [0.034s]
+Building query seed set... [0.039s]
+Algorithm: Double-indexed
+Building query histograms... [0.021s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.025s]
+Masking reference... [0.029s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.018s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.019s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.483s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.022s]
+Building query seed array... [0.016s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.347s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.025s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.375s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.021s]
+Building query seed array... [0.013s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.345s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.02s]
+Building query seed array... [0.011s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.347s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.023s]
+Building query seed array... [0.016s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.298s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.026s]
+Building query seed array... [0.02s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.307s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.02s]
+Building query seed array... [0.011s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.29s]
+Deallocating buffers... [0.002s]
+Computing alignments... [1.939s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 5.355s
+Reported 475363 pairwise alignments, 475381 HSPs.
+31089 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn04[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn04
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn04
+
+[0m
+[1mThere were [96m36674[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m7073[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m36674[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m3043[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m6419 Unique ORFs[0m[1m for [96mSr_rh_Nn04
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/Original/Concatenated/Sr_rh_Bv01.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.027s]
+Masking sequences... [0.027s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 32762a5b753a4aa6704d518df14f98b0
+Processed 22250 sequences, 5423683 letters.
+Total time = 0.07s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv01/Original/Concatenated/Sr_rh_Bv01.AA.Concatenated.dmnd
+Sequences = 22250
+Letters = 5423683
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.026s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.017s]
+Masking reference... [0.016s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.011s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.02s]
+Building query seed array... [0.018s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.05s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.047s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.046s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.017s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.045s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.016s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.044s]
+Deallocating buffers... [0s]
+Computing alignments... [0.694s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.582s
+Reported 210419 pairwise alignments, 210421 HSPs.
+17900 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv01[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv01
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv01
+
+[0m
+[1mThere were [96m22250[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m925[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m22250[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1761[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5198 Unique ORFs[0m[1m for [96mSr_rh_Bv01
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/Original/Concatenated/Sr_rh_Nn05.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.026s]
+Masking sequences... [0.031s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 53344b07d607f88908ffa47877c05848
+Processed 17028 sequences, 5371066 letters.
+Total time = 0.073s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn05/Original/Concatenated/Sr_rh_Nn05.AA.Concatenated.dmnd
+Sequences = 17028
+Letters = 5371066
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.028s]
+Masking queries... [0.026s]
+Building query seed set... [0.032s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.013s]
+Masking reference... [0.019s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.017s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.015s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.064s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.022s]
+Building query seed array... [0.025s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.065s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.056s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.053s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.021s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.018s]
+Building query seed array... [0.02s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.053s]
+Deallocating buffers... [0s]
+Computing alignments... [0.573s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.605s
+Reported 136247 pairwise alignments, 136251 HSPs.
+13401 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn05[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn05
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn05
+
+[0m
+[1mThere were [96m17028[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1026[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m17028[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1409[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4799 Unique ORFs[0m[1m for [96mSr_rh_Nn05
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/Original/Concatenated/Sr_rh_Gl03.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.052s]
+Masking sequences... [0.051s]
+Writing sequences... [0.016s]
+Hashing sequences... [0.003s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 8c5853401a6b05601e71e4bc98b8ba39
+Processed 32752 sequences, 10207231 letters.
+Total time = 0.128s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl03/Original/Concatenated/Sr_rh_Gl03.AA.Concatenated.dmnd
+Sequences = 32752
+Letters = 10207231
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.059s]
+Masking queries... [0.036s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.022s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.028s]
+Masking reference... [0.025s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.019s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.026s]
+Building query seed array... [0.016s]
+Computing hash join... [0.007s]
+Building seed filter... [0.004s]
+Searching alignments... [0.1s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.021s]
+Building query seed array... [0.014s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.09s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.015s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.015s]
+Building query seed array... [0.017s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.082s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.015s]
+Building query seed array... [0.015s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.019s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.07s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.022s]
+Building query seed array... [0.018s]
+Computing hash join... [0.005s]
+Building seed filter... [0.005s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.014s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.067s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.422s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.681s
+Reported 371577 pairwise alignments, 371643 HSPs.
+30596 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Gl03[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Gl03
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Gl03
+
+[0m
+[1mThere were [96m32752[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m835[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m32752[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1335[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4863 Unique ORFs[0m[1m for [96mSr_rh_Gl03
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/Original/Concatenated/Sr_rh_Emar.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.016s]
+Masking sequences... [0.022s]
+Writing sequences... [0.005s]
+Hashing sequences... [0s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 0377bff5727d8ea0665197857dd36934
+Processed 7943 sequences, 3401675 letters.
+Total time = 0.048s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Emar/Original/Concatenated/Sr_rh_Emar.AA.Concatenated.dmnd
+Sequences = 7943
+Letters = 3401675
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.017s]
+Masking queries... [0.019s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.009s]
+Masking reference... [0.017s]
+Initializing temporary storage... [0.008s]
+Building reference histograms... [0.009s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.03s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.006s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.029s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.012s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.011s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.024s]
+Deallocating buffers... [0s]
+Computing alignments... [0.248s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.847s
+Reported 45208 pairwise alignments, 45211 HSPs.
+5967 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Emar[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Emar
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Emar
+
+[0m
+[1mThere were [96m7943[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m828[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m7943[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m195[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3036 Unique ORFs[0m[1m for [96mSr_rh_Emar
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/Original/Concatenated/Sr_rh_Nn02.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.028s]
+Masking sequences... [0.026s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = fafb09591ab6392c934e41fce1e5cc78
+Processed 18186 sequences, 5834132 letters.
+Total time = 0.07s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn02/Original/Concatenated/Sr_rh_Nn02.AA.Concatenated.dmnd
+Sequences = 18186
+Letters = 5834132
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.024s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.017s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.01s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.021s]
+Building query seed array... [0.018s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.183s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.026s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.121s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.025s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.125s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.026s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.112s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.021s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.142s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.027s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.12s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.023s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.16s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.025s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.147s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.831s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.506s
+Reported 179318 pairwise alignments, 179321 HSPs.
+14504 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn02[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn02
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn02
+
+[0m
+[1mThere were [96m18186[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1966[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m18186[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1352[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4670 Unique ORFs[0m[1m for [96mSr_rh_Nn02
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/Original/Concatenated/Sr_rh_Nn10.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.035s]
+Masking sequences... [0.032s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 2c8f05bd448e81fa11fb1f390a5a1b16
+Processed 20167 sequences, 6887392 letters.
+Total time = 0.085s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn10/Original/Concatenated/Sr_rh_Nn10.AA.Concatenated.dmnd
+Sequences = 20167
+Letters = 6887392
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.04s]
+Masking queries... [0.025s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.022s]
+Masking reference... [0.021s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.015s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.02s]
+Building query seed array... [0.011s]
+Computing hash join... [0.004s]
+Building seed filter... [0.005s]
+Searching alignments... [0.213s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.021s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.171s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.017s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.164s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.017s]
+Building query seed array... [0.009s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.156s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.01s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.151s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.128s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.174s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.019s]
+Building query seed array... [0.011s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.14s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.167s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.983s
+Reported 236210 pairwise alignments, 236216 HSPs.
+16852 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn10[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn10
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn10
+
+[0m
+[1mThere were [96m20167[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m2853[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m20167[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1214[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4580 Unique ORFs[0m[1m for [96mSr_rh_Nn10
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/Original/Concatenated/Sr_rh_Nn03.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.035s]
+Masking sequences... [0.028s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 103564f9e7dd2f1f2bec1ec8db24c811
+Processed 17953 sequences, 5742700 letters.
+Total time = 0.079s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn03/Original/Concatenated/Sr_rh_Nn03.AA.Concatenated.dmnd
+Sequences = 17953
+Letters = 5742700
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.031s]
+Masking queries... [0.026s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.013s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.016s]
+Masking reference... [0.017s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.012s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.022s]
+Building query seed array... [0.017s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.095s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.02s]
+Building query seed array... [0.024s]
+Computing hash join... [0.004s]
+Building seed filter... [0.007s]
+Searching alignments... [0.079s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.024s]
+Building query seed array... [0.023s]
+Computing hash join... [0.005s]
+Building seed filter... [0.007s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.076s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.065s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.061s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.075s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.021s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.068s]
+Deallocating buffers... [0s]
+Computing alignments... [0.684s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.832s
+Reported 154410 pairwise alignments, 154413 HSPs.
+14138 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn03[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn03
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn03
+
+[0m
+[1mThere were [96m17953[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1458[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m17953[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1522[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4771 Unique ORFs[0m[1m for [96mSr_rh_Nn03
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/Original/Concatenated/Sr_rh_Nn06.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.032s]
+Masking sequences... [0.029s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 9d688130f29a63e4d67352cdb9f99ac1
+Processed 19812 sequences, 6063731 letters.
+Total time = 0.077s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn06/Original/Concatenated/Sr_rh_Nn06.AA.Concatenated.dmnd
+Sequences = 19812
+Letters = 6063731
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.032s]
+Masking queries... [0.029s]
+Building query seed set... [0.035s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.02s]
+Masking reference... [0.018s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.011s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.139s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.017s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.103s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.102s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.012s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.09s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.01s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.107s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.093s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.081s]
+Deallocating buffers... [0s]
+Computing alignments... [0.802s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.059s
+Reported 193966 pairwise alignments, 193972 HSPs.
+16000 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn06[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn06
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn06
+
+[0m
+[1mThere were [96m19812[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1949[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m19812[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1501[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4947 Unique ORFs[0m[1m for [96mSr_rh_Nn06
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/Original/Concatenated/Sr_rh_Bv02.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.034s]
+Masking sequences... [0.029s]
+Writing sequences... [0.011s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 96b1fdedb1bc7f9735f8d6a9c060b359
+Processed 24278 sequences, 6856585 letters.
+Total time = 0.081s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv02/Original/Concatenated/Sr_rh_Bv02.AA.Concatenated.dmnd
+Sequences = 24278
+Letters = 6856585
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.047s]
+Masking queries... [0.031s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.02s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.021s]
+Masking reference... [0.02s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.01s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.016s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.088s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.024s]
+Building query seed array... [0.027s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.077s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.071s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.019s]
+Building query seed array... [0.026s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.014s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.066s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.023s]
+Building query seed array... [0.02s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.062s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.02s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.06s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.018s]
+Building query seed array... [0.02s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.058s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.001s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.159s
+Reported 274535 pairwise alignments, 274572 HSPs.
+20473 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv02[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv02
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv02
+
+[0m
+[1mThere were [96m24278[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1366[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m24278[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1535[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5142 Unique ORFs[0m[1m for [96mSr_rh_Bv02
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/Original/Concatenated/Sr_rh_Gl02.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.055s]
+Masking sequences... [0.042s]
+Writing sequences... [0.017s]
+Hashing sequences... [0.003s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 9fd3ebe1fc02a1cc4b69bb7b2be9a35d
+Processed 31505 sequences, 11021837 letters.
+Total time = 0.123s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl02/Original/Concatenated/Sr_rh_Gl02.AA.Concatenated.dmnd
+Sequences = 31505
+Letters = 11021837
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.057s]
+Masking queries... [0.034s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.021s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.028s]
+Masking reference... [0.028s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.02s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.026s]
+Building query seed array... [0.019s]
+Computing hash join... [0.008s]
+Building seed filter... [0.003s]
+Searching alignments... [0.108s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.017s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.017s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.08s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.014s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.089s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.012s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.081s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.013s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.076s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.014s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.016s]
+Computing hash join... [0.006s]
+Building seed filter... [0.004s]
+Searching alignments... [0.078s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.574s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.849s
+Reported 351084 pairwise alignments, 351138 HSPs.
+29361 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Gl02[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Gl02
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Gl02
+
+[0m
+[1mThere were [96m31505[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m925[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m31505[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1258[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4912 Unique ORFs[0m[1m for [96mSr_rh_Gl02
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/Original/Concatenated/Sr_rh_Esca.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.018s]
+Masking sequences... [0.125s]
+Writing sequences... [0.005s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = a6ba9de57b7334a769b88bd0f22acf5b
+Processed 11092 sequences, 3356704 letters.
+Total time = 0.154s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Esca/Original/Concatenated/Sr_rh_Esca.AA.Concatenated.dmnd
+Sequences = 11092
+Letters = 3356704
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.021s]
+Masking queries... [0.021s]
+Building query seed set... [0.021s]
+Algorithm: Double-indexed
+Building query histograms... [0.01s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.012s]
+Masking reference... [0.013s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.007s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.036s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.013s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.01s]
+Building query seed array... [0.013s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.01s]
+Building query seed array... [0.012s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.011s]
+Building query seed array... [0.009s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.021s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.011s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.022s]
+Deallocating buffers... [0s]
+Computing alignments... [0.27s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.867s
+Reported 80939 pairwise alignments, 80941 HSPs.
+8644 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Esca[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Esca
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Esca
+
+[0m
+[1mThere were [96m11092[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m697[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m11092[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m491[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3480 Unique ORFs[0m[1m for [96mSr_rh_Esca
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/Original/Concatenated/Sr_rh_Bv03.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.032s]
+Masking sequences... [0.028s]
+Writing sequences... [0.011s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 7d2fb8d327ed29a308fc6adf9481fe27
+Processed 23147 sequences, 6331934 letters.
+Total time = 0.079s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv03/Original/Concatenated/Sr_rh_Bv03.AA.Concatenated.dmnd
+Sequences = 23147
+Letters = 6331934
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.033s]
+Masking queries... [0.026s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.019s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.017s]
+Masking reference... [0.02s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.012s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.018s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.084s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.074s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.07s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.018s]
+Building query seed array... [0.021s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.067s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.021s]
+Building query seed array... [0.021s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.058s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.019s]
+Building query seed array... [0.019s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.059s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.952s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.056s
+Reported 269959 pairwise alignments, 269963 HSPs.
+19405 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv03[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv03
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv03
+
+[0m
+[1mThere were [96m23147[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1552[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m23147[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1372[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5015 Unique ORFs[0m[1m for [96mSr_rh_Bv03
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/Original/Concatenated/Sr_rh_Sspa.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.026s]
+Masking sequences... [0.025s]
+Writing sequences... [0.007s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 73ca9ebb7bc1f11c92eff313afe8d09e
+Processed 15066 sequences, 4394283 letters.
+Total time = 0.064s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Sspa/Original/Concatenated/Sr_rh_Sspa.AA.Concatenated.dmnd
+Sequences = 15066
+Letters = 4394283
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.025s]
+Masking queries... [0.022s]
+Building query seed set... [0.031s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.017s]
+Initializing temporary storage... [0.011s]
+Building reference histograms... [0.012s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.017s]
+Building query seed array... [0.023s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.032s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.012s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.028s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.027s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.011s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.024s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.011s]
+Building query seed array... [0.013s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.025s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.026s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.023s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.027s]
+Deallocating buffers... [0s]
+Computing alignments... [0.306s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.987s
+Reported 81557 pairwise alignments, 81557 HSPs.
+11553 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Sspa[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Sspa
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Sspa
+
+[0m
+[1mThere were [96m15066[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m934[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m15066[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m955[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5007 Unique ORFs[0m[1m for [96mSr_rh_Sspa
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/Original/Concatenated/Sr_rh_Halb.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.028s]
+Masking sequences... [0.027s]
+Writing sequences... [0.009s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = be446b493c85f79b57f24c5868ac0c4c
+Processed 14869 sequences, 6087712 letters.
+Total time = 0.071s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Halb/Original/Concatenated/Sr_rh_Halb.AA.Concatenated.dmnd
+Sequences = 14869
+Letters = 6087712
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.029s]
+Masking queries... [0.024s]
+Building query seed set... [0.027s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.015s]
+Masking reference... [0.018s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.013s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.086s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.075s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.017s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.062s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.065s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.022s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.059s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.014s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.02s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.062s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.056s]
+Deallocating buffers... [0s]
+Computing alignments... [0.649s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.682s
+Reported 153389 pairwise alignments, 153474 HSPs.
+13522 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Halb[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Halb
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Halb
+
+[0m
+[1mThere were [96m14869[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m3233[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m14869[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m309[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m2652 Unique ORFs[0m[1m for [96mSr_rh_Halb
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/Original/Concatenated/Sr_rh_Bv04.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.033s]
+Masking sequences... [0.03s]
+Writing sequences... [0.011s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 7d1e6c82caa1170cabd2b9c12a903852
+Processed 21474 sequences, 6727927 letters.
+Total time = 0.082s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Bv04/Original/Concatenated/Sr_rh_Bv04.AA.Concatenated.dmnd
+Sequences = 21474
+Letters = 6727927
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.04s]
+Masking queries... [0.03s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.016s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.018s]
+Masking reference... [0.021s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.014s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.018s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.081s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.027s]
+Building query seed array... [0.02s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.07s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.02s]
+Building query seed array... [0.021s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.068s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.017s]
+Building query seed array... [0.019s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.057s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.018s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.063s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.019s]
+Building query seed array... [0.022s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.072s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.019s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.051s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.015s]
+Building query seed array... [0.018s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.055s]
+Deallocating buffers... [0s]
+Computing alignments... [1.096s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.197s
+Reported 262985 pairwise alignments, 263041 HSPs.
+18915 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Bv04[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Bv04
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Bv04
+
+[0m
+[1mThere were [96m21474[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m1156[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m21474[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m848[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4346 Unique ORFs[0m[1m for [96mSr_rh_Bv04
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/Original/Concatenated/Sr_rh_Nn01.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.034s]
+Masking sequences... [0.031s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = d53a7002a89335cfb90dd79e5cf900d7
+Processed 22715 sequences, 6753119 letters.
+Total time = 0.083s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn01/Original/Concatenated/Sr_rh_Nn01.AA.Concatenated.dmnd
+Sequences = 22715
+Letters = 6753119
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.036s]
+Masking queries... [0.029s]
+Building query seed set... [0.036s]
+Algorithm: Double-indexed
+Building query histograms... [0.014s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.019s]
+Masking reference... [0.02s]
+Initializing temporary storage... [0.01s]
+Building reference histograms... [0.013s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.012s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.214s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.022s]
+Building query seed array... [0.014s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.154s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.018s]
+Building query seed array... [0.016s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.173s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.018s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.15s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.016s]
+Building query seed array... [0.013s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.149s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.014s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.123s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.142s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.014s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.132s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.996s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.749s
+Reported 234923 pairwise alignments, 234933 HSPs.
+18619 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn01[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn01
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn01
+
+[0m
+[1mThere were [96m22715[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m2722[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m22715[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1826[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5092 Unique ORFs[0m[1m for [96mSr_rh_Nn01
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/Original/Concatenated/Sr_rh_Tx01.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.035s]
+Masking sequences... [0.03s]
+Writing sequences... [0.011s]
+Hashing sequences... [0.002s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 5c42afa531e715892722c3aab558955f
+Processed 19985 sequences, 6911292 letters.
+Total time = 0.084s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Tx01/Original/Concatenated/Sr_rh_Tx01.AA.Concatenated.dmnd
+Sequences = 19985
+Letters = 6911292
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.035s]
+Masking queries... [0.027s]
+Building query seed set... [0.029s]
+Algorithm: Double-indexed
+Building query histograms... [0.015s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.019s]
+Masking reference... [0.02s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.014s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.018s]
+Building query seed array... [0.01s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.123s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.104s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.015s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.099s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.096s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.094s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.013s]
+Building query seed array... [0.011s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.088s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.014s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.098s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.013s]
+Building query seed array... [0.012s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.099s]
+Deallocating buffers... [0.001s]
+Computing alignments... [0.886s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 2.149s
+Reported 249989 pairwise alignments, 250001 HSPs.
+18701 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Tx01[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Tx01
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Tx01
+
+[0m
+[1mThere were [96m19985[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m5250[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m19985[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m353[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m3027 Unique ORFs[0m[1m for [96mSr_rh_Tx01
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/Original/Concatenated/Sr_rh_Nn09.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.043s]
+Masking sequences... [0.034s]
+Writing sequences... [0.014s]
+Hashing sequences... [0.003s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 442d2660d19d6736d72315a56ba66c98
+Processed 30042 sequences, 8360487 letters.
+Total time = 0.1s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn09/Original/Concatenated/Sr_rh_Nn09.AA.Concatenated.dmnd
+Sequences = 30042
+Letters = 8360487
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.055s]
+Masking queries... [0.036s]
+Building query seed set... [0.034s]
+Algorithm: Double-indexed
+Building query histograms... [0.022s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.023s]
+Masking reference... [0.023s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.016s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.023s]
+Building query seed array... [0.016s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.342s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.018s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.283s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.019s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.298s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.02s]
+Building query seed array... [0.016s]
+Computing hash join... [0.005s]
+Building seed filter... [0.003s]
+Searching alignments... [0.243s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.019s]
+Building query seed array... [0.012s]
+Computing hash join... [0.005s]
+Building seed filter... [0.004s]
+Searching alignments... [0.269s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.023s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.225s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.021s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.251s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.022s]
+Building query seed array... [0.012s]
+Computing hash join... [0.004s]
+Building seed filter... [0.004s]
+Searching alignments... [0.239s]
+Deallocating buffers... [0.001s]
+Computing alignments... [1.535s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0.001s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 4.28s
+Reported 355048 pairwise alignments, 355055 HSPs.
+25203 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn09[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn09
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn09
+
+[0m
+[1mThere were [96m30042[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m4549[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m30042[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m2368[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m5956 Unique ORFs[0m[1m for [96mSr_rh_Nn09
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/Original/Concatenated/Sr_rh_Gl01.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.003s]
+Masking sequences... [0.016s]
+Writing sequences... [0s]
+Hashing sequences... [0s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 527bc5ca7392445b7844cb181d0620f1
+Processed 1224 sequences, 170624 letters.
+Total time = 0.023s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Gl01/Original/Concatenated/Sr_rh_Gl01.AA.Concatenated.dmnd
+Sequences = 1224
+Letters = 170624
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.001s]
+Masking queries... [0.014s]
+Building query seed set... [0.004s]
+Algorithm: Double-indexed
+Building query histograms... [0.002s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.001s]
+Masking reference... [0.007s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.003s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.013s]
+Building query seed array... [0.014s]
+Computing hash join... [0.002s]
+Building seed filter... [0.007s]
+Searching alignments... [0.007s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.008s]
+Building query seed array... [0.004s]
+Computing hash join... [0.002s]
+Building seed filter... [0.004s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.007s]
+Computing hash join... [0.003s]
+Building seed filter... [0.005s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.009s]
+Building query seed array... [0.009s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.005s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.011s]
+Building query seed array... [0.005s]
+Computing hash join... [0.001s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.011s]
+Building query seed array... [0.008s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.007s]
+Building query seed array... [0.006s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.009s]
+Building query seed array... [0.006s]
+Computing hash join... [0.002s]
+Building seed filter... [0.003s]
+Searching alignments... [0.004s]
+Deallocating buffers... [0s]
+Computing alignments... [0.036s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0.001s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 0.331s
+Reported 4157 pairwise alignments, 4157 HSPs.
+594 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Gl01[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Gl01
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Gl01
+
+[0m
+[1mThere were [96m1224[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m32[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m1224[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m44[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m667 Unique ORFs[0m[1m for [96mSr_rh_Gl01
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 64
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Database file: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/Original/Concatenated/Sr_rh_Nn14.AA.Concatenated.fasta
+Opening the database file... [0.002s]
+Loading sequences... [0.028s]
+Masking sequences... [0.027s]
+Writing sequences... [0.01s]
+Hashing sequences... [0.001s]
+Loading sequences... [0s]
+Writing trailer... [0s]
+Closing the input file... [0s]
+Closing the database file... [0s]
+Database hash = 2cefd71c2b2dfc7c97c47bb5141899b8
+Processed 17441 sequences, 5176642 letters.
+Total time = 0.071s
+diamond v0.9.30.131 (C) Max Planck Society for the Advancement of Science
+Documentation, support and updates available at http://www.diamondsearch.org
+
+#CPU threads: 60
+Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1)
+Temporary directory: /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/Original/Concatenated/SpreadSheets
+Opening the database... [0.001s]
+#Target sequences to report alignments for: 25
+Reference = /beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams//Output/Sr_rh_Nn14/Original/Concatenated/Sr_rh_Nn14.AA.Concatenated.dmnd
+Sequences = 17441
+Letters = 5176642
+Block size = 2000000000
+Opening the input file... [0s]
+Opening the output file... [0s]
+Loading query sequences... [0.027s]
+Masking queries... [0.025s]
+Building query seed set... [0.033s]
+Algorithm: Double-indexed
+Building query histograms... [0.012s]
+Allocating buffers... [0s]
+Loading reference sequences... [0.014s]
+Masking reference... [0.017s]
+Initializing temporary storage... [0.009s]
+Building reference histograms... [0.015s]
+Allocating buffers... [0s]
+Processing query block 0, reference block 0, shape 0, index chunk 0.
+Building reference seed array... [0.021s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.055s]
+Processing query block 0, reference block 0, shape 0, index chunk 1.
+Building reference seed array... [0.014s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 0, index chunk 2.
+Building reference seed array... [0.015s]
+Building query seed array... [0.015s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.052s]
+Processing query block 0, reference block 0, shape 0, index chunk 3.
+Building reference seed array... [0.019s]
+Building query seed array... [0.017s]
+Computing hash join... [0.004s]
+Building seed filter... [0.003s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 0.
+Building reference seed array... [0.014s]
+Building query seed array... [0.02s]
+Computing hash join... [0.004s]
+Building seed filter... [0.005s]
+Searching alignments... [0.042s]
+Processing query block 0, reference block 0, shape 1, index chunk 1.
+Building reference seed array... [0.016s]
+Building query seed array... [0.017s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.038s]
+Processing query block 0, reference block 0, shape 1, index chunk 2.
+Building reference seed array... [0.016s]
+Building query seed array... [0.018s]
+Computing hash join... [0.003s]
+Building seed filter... [0.004s]
+Searching alignments... [0.04s]
+Processing query block 0, reference block 0, shape 1, index chunk 3.
+Building reference seed array... [0.017s]
+Building query seed array... [0.016s]
+Computing hash join... [0.003s]
+Building seed filter... [0.003s]
+Searching alignments... [0.041s]
+Deallocating buffers... [0s]
+Computing alignments... [0.496s]
+Deallocating reference... [0s]
+Loading reference sequences... [0s]
+Deallocating buffers... [0s]
+Deallocating queries... [0s]
+Loading query sequences... [0s]
+Closing the input file... [0s]
+Closing the output file... [0s]
+Closing the database file... [0s]
+Deallocating taxonomy... [0s]
+Total time = 1.358s
+Reported 124839 pairwise alignments, 124844 HSPs.
+13517 queries aligned.
+[1m
+
+Merging Transcriptome data together.[0m
+[1m
+
+Binning ALL [38;5;214mNucleotide ORFs[0m[1m for [92mSr_rh_Nn14[0m[1m at 98% identity.
+
+[0m
+[1m
+
+Removing Partial [95mORFs[0m[1m with >98% Nucleotide Identity over >70% of
+their length when compared to more complete [95mORFs [0m[1mfrom: [96mSr_rh_Nn14
+
+[0m
+[1mRemoving Abnormally Short (70% length) OR Long (200% length)[95m ORFs[0m[1m
+compared to typical [38;5;214mGene Family [0m[1mmember length for: [96mSr_rh_Nn14
+
+[0m
+[1mThere were [96m17441[0m[1m[95m ORFs [0m[1moriginally, with [38;5;214m663[0m[1m Partial [95mORFs[0m[1m that
+were [91m100% Identical[0m[1m to larger[95m ORFs.
+
+[0m
+[1mOf the [96m17441[0m[1m original[95m ORFs[0m[1m, [38;5;214m0[0m[1m are [95mPartial ORFs [0m[1m(e.g. [91m> 98%[0m[1m
+NUCLEOTIDE identity) to larger[95m ORFs[0m[1m with [38;5;214m1588[0m[1m additional[95m ORFs
+[0m[1mthat were either [91mTOO LONG or SHORT.
+
+[0m
+[1mOverall, there are [92m4906 Unique ORFs[0m[1m for [96mSr_rh_Nn14
+[0m
+[1m
+Next Script is: [92m6b_update_cov_post_removepartials.py
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Esca[0m[1m's files with the following 10-character
+code: [96mSr_rh_Esca[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Esca_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Esca[0m[1m files can be
+found in the [91mSr_rh_Esca[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn05[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn05[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn05_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn05[0m[1m files can be
+found in the [91mSr_rh_Nn05[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv04[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv04[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv04_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv04[0m[1m files can be
+found in the [91mSr_rh_Bv04[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn10[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn10[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn10_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn10[0m[1m files can be
+found in the [91mSr_rh_Nn10[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv03[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv03[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv03_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv03[0m[1m files can be
+found in the [91mSr_rh_Bv03[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn14[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn14[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn14_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn14[0m[1m files can be
+found in the [91mSr_rh_Nn14[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn03[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn03[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn03_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn03[0m[1m files can be
+found in the [91mSr_rh_Nn03[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv02[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv02[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv02_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv02[0m[1m files can be
+found in the [91mSr_rh_Bv02[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn07[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn07[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn07_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn07[0m[1m files can be
+found in the [91mSr_rh_Nn07[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Hhir[0m[1m's files with the following 10-character
+code: [96mSr_rh_Hhir[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Hhir_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Hhir[0m[1m files can be
+found in the [91mSr_rh_Hhir[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Gl01[0m[1m's files with the following 10-character
+code: [96mSr_rh_Gl01[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Gl01_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Gl01[0m[1m files can be
+found in the [91mSr_rh_Gl01[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Gsp1[0m[1m's files with the following 10-character
+code: [96mSr_rh_Gsp1[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Gsp1_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Gsp1[0m[1m files can be
+found in the [91mSr_rh_Gsp1[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Rsp1[0m[1m's files with the following 10-character
+code: [96mSr_rh_Rsp1[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Rsp1_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Rsp1[0m[1m files can be
+found in the [91mSr_rh_Rsp1[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Calb[0m[1m's files with the following 10-character
+code: [96mSr_rh_Calb[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Calb_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Calb[0m[1m files can be
+found in the [91mSr_rh_Calb[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn09[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn09[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn09_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn09[0m[1m files can be
+found in the [91mSr_rh_Nn09[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn08[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn08[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn08_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn08[0m[1m files can be
+found in the [91mSr_rh_Nn08[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn01[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn01[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn01_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn01[0m[1m files can be
+found in the [91mSr_rh_Nn01[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv06[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv06[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv06_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv06[0m[1m files can be
+found in the [91mSr_rh_Bv06[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn02[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn02[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn02_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn02[0m[1m files can be
+found in the [91mSr_rh_Nn02[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv05[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv05[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv05_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv05[0m[1m files can be
+found in the [91mSr_rh_Bv05[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Sspa[0m[1m's files with the following 10-character
+code: [96mSr_rh_Sspa[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Sspa_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Sspa[0m[1m files can be
+found in the [91mSr_rh_Sspa[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Hind[0m[1m's files with the following 10-character
+code: [96mSr_rh_Hind[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Hind_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Hind[0m[1m files can be
+found in the [91mSr_rh_Hind[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn12[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn12[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn12_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn12[0m[1m files can be
+found in the [91mSr_rh_Nn12[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Gspa[0m[1m's files with the following 10-character
+code: [96mSr_rh_Gspa[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Gspa_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Gspa[0m[1m files can be
+found in the [91mSr_rh_Gspa[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Bv01[0m[1m's files with the following 10-character
+code: [96mSr_rh_Bv01[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Bv01_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Bv01[0m[1m files can be
+found in the [91mSr_rh_Bv01[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Tx01[0m[1m's files with the following 10-character
+code: [96mSr_rh_Tx01[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Tx01_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Tx01[0m[1m files can be
+found in the [91mSr_rh_Tx01[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn06[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn06[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn06_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn06[0m[1m files can be
+found in the [91mSr_rh_Nn06[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn04[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn04[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn04_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn04[0m[1m files can be
+found in the [91mSr_rh_Nn04[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Gl02[0m[1m's files with the following 10-character
+code: [96mSr_rh_Gl02[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Gl02_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Gl02[0m[1m files can be
+found in the [91mSr_rh_Gl02[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Slin[0m[1m's files with the following 10-character
+code: [96mSr_rh_Slin[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Slin_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Slin[0m[1m files can be
+found in the [91mSr_rh_Slin[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Emar[0m[1m's files with the following 10-character
+code: [96mSr_rh_Emar[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Emar_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Emar[0m[1m files can be
+found in the [91mSr_rh_Emar[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn13[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn13[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn13_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn13[0m[1m files can be
+found in the [91mSr_rh_Nn13[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Emac[0m[1m's files with the following 10-character
+code: [96mSr_rh_Emac[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Emac_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Emac[0m[1m files can be
+found in the [91mSr_rh_Emac[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Halb[0m[1m's files with the following 10-character
+code: [96mSr_rh_Halb[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Halb_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Halb[0m[1m files can be
+found in the [91mSr_rh_Halb[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Atps[0m[1m's files with the following 10-character
+code: [96mSr_rh_Atps[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Atps_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Atps[0m[1m files can be
+found in the [91mSr_rh_Atps[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Nn11[0m[1m's files with the following 10-character
+code: [96mSr_rh_Nn11[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Nn11_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Nn11[0m[1m files can be
+found in the [91mSr_rh_Nn11[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Gl03[0m[1m's files with the following 10-character
+code: [96mSr_rh_Gl03[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Gl03_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Gl03[0m[1m files can be
+found in the [91mSr_rh_Gl03[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+[1m
+
+Renaming [38;5;214mSr_rh_Usac[0m[1m's files with the following 10-character
+code: [96mSr_rh_Usac[0m
+
+[1m
+Renaming Translated (Protein) [95mORFs
+[0m
+[1m
+Renaming Nucleotide [95mORFs
+[0m
+[1m
+Updating CDS Names in the Spreadsheet[0m
+[1m
+
+Converting [38;5;214mSr_rh_Usac_Filtered.UC.Final.AA.ORF.fasta[0m[1m to XML format
+[0m
+[1m
+There is no next script! The final [38;5;214mSr_rh_Usac[0m[1m files can be
+found in the [91mSr_rh_Usac[0m[1m and [91mReadyToGo folders[0m[1m and are ready
+for the KatzLab Phylogenomic Tree-Building Steps!
+
+[0m
+Traceback (most recent call last):
+ File "8_SummaryStats.py", line 8, in
+ import matplotlib.pyplot as plt
+ModuleNotFoundError: No module named 'matplotlib'
+
+Running script 1...
+
+
+Running script 2...
+
+
+Running script 3...
+
+
+Running script 4...
+
+
+Running script 5...
+
+
+Running script 6...
+
+
+Running script 7...
+
diff --git a/PTL1/Transcriptomes/Scripts/UnexpexctedShortStuffBlameXyrus.txt b/PTL1/Transcriptomes/Scripts/UnexpexctedShortStuffBlameXyrus.txt
new file mode 100644
index 0000000..4ce2676
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/UnexpexctedShortStuffBlameXyrus.txt
@@ -0,0 +1,143 @@
+Contig_204_Len5938_Cov7976_P_OG6_102770
+Contig_3323_Len1201_Cov3_U_OG6_148486
+Contig_313_Len4904_Cov3_E_OG6_101730
+Contig_3269_Len1219_Cov2_U_OG6_102957
+Contig_9180_Len427_Cov1_P_OG6_100774
+Contig_4698_Len874_Cov1_U_OG6_111564
+Contig_6408_Len634_Cov2_U_OG6_102446
+Contig_667_Len3323_Cov11_U_OG6_116443
+Contig_2271_Len1620_Cov1_E_OG6_101536
+Contig_4504_Len909_Cov11_P_OG6_101629
+Contig_333_Len4757_Cov12241_P_OG6_102770
+Contig_811_Len2973_Cov4_U_OG6_116443
+Contig_4707_Len871_Cov7779_P_OG6_102770
+Contig_5488_Len751_Cov2_U_OG6_103872
+Contig_317_Len4879_Cov6_E_OG6_107629
+Contig_5624_Len732_Cov1_U_OG6_100648
+Contig_1895_Len1829_Cov9_U_OG6_107629
+Contig_6636_Len610_Cov1_P_OG6_100598
+Contig_4338_Len944_Cov2_U_OG6_118109
+Contig_3061_Len1290_Cov2_P_OG6_105259
+Contig_786_Len3043_Cov3_E_OG6_101725
+Contig_4267_Len958_Cov2_U_OG6_107629
+Contig_157_Len6644_Cov11_E_OG6_102358
+Contig_24_Len10475_Cov4_E_OG6_106943
+Contig_145_Len6822_Cov9_U_OG6_145244
+Contig_536_Len3701_Cov3_E_OG6_103917
+Contig_421_Len4239_Cov31_P_OG6_102198
+Contig_2102_Len1703_Cov4_E_OG6_102675
+Contig_40_Len9764_Cov77_E_OG6_105576
+Contig_4490_Len912_Cov1_P_OG6_106264
+Contig_6491_Len626_Cov2_P_OG6_100328
+Contig_7231_Len557_Cov1_U_OG6_107629
+Contig_756_Len3094_Cov12165_P_OG6_102770
+Contig_3009_Len1307_Cov13_U_OG6_116443
+Contig_4049_Len1006_Cov3_U_OG6_103879
+Contig_426_Len4213_Cov26_U_OG6_108411
+Contig_5227_Len788_Cov1_P_OG6_100289
+Contig_701_Len3225_Cov2_P_OG6_106492
+Contig_4905_Len840_Cov2_P_OG6_115036
+Contig_28_Len10287_Cov699_E_OG6_100777
+Contig_117_Len7490_Cov12_E_OG6_102035
+Contig_748_Len3109_Cov7889_P_OG6_102770
+Contig_3013_Len1306_Cov6_U_OG6_116443
+Contig_5988_Len682_Cov2_U_OG6_107629
+Contig_2349_Len1580_Cov1_P_OG6_124813
+Contig_349_Len4667_Cov4_U_OG6_116443
+Contig_841_Len2909_Cov21_E_OG6_107629
+Contig_8720_Len444_Cov1_P_OG6_115892
+Contig_2350_Len1578_Cov8_U_OG6_107629
+Contig_7003_Len576_Cov3_P_OG6_115725
+Contig_8605_Len452_Cov1_U_OG6_107629
+Contig_3057_Len1292_Cov6_U_OG6_102073
+Contig_168_Len6512_Cov4_E_OG6_102446
+Contig_3018_Len1303_Cov9938_P_OG6_102770
+Contig_3148_Len1260_Cov6057_P_OG6_102770
+Contig_2866_Len1358_Cov8209_P_OG6_102770
+Contig_1129_Len2472_Cov5_E_OG6_100425
+Contig_4087_Len998_Cov2_E_OG6_102109
+Contig_9116_Len429_Cov2_E_OG6_100420
+Contig_2878_Len1356_Cov2_E_OG6_102565
+Contig_1436_Len2164_Cov2_U_OG6_121413
+Contig_125_Len7242_Cov67_U_OG6_105015
+Contig_4250_Len962_Cov4_U_OG6_107629
+Contig_9689_Len411_Cov1_P_OG6_110848
+Contig_488_Len3892_Cov12068_P_OG6_102770
+Contig_5963_Len686_Cov1_P_OG6_101423
+Contig_5913_Len692_Cov3_U_OG6_116443
+Contig_1768_Len1907_Cov2_P_OG6_106950
+Contig_1477_Len2126_Cov2_P_OG6_104145
+Contig_7577_Len529_Cov1_E_OG6_116443
+Contig_9982_Len402_Cov2_P_OG6_104843
+Contig_373_Len4515_Cov26_U_OG6_108411
+Contig_4656_Len883_Cov2_E_OG6_102774
+Contig_3145_Len1262_Cov2_P_OG6_110223
+Contig_5222_Len788_Cov2_E_OG6_116443
+Contig_6139_Len665_Cov1_P_OG6_129320
+Contig_987_Len2641_Cov4_E_OG6_103026
+Contig_213_Len5837_Cov11847_P_OG6_102770
+Contig_5568_Len739_Cov1_E_OG6_102109
+Contig_3238_Len1232_Cov5_U_OG6_116443
+Contig_1549_Len2061_Cov3_E_OG6_102774
+Contig_3274_Len1217_Cov2_E_OG6_107629
+Contig_6478_Len627_Cov4_U_OG6_107219
+Contig_1710_Len1945_Cov2_P_OG6_101690
+Contig_172_Len6427_Cov11653_P_OG6_102770
+Contig_2759_Len1398_Cov2_U_OG6_102446
+Contig_4836_Len848_Cov10167_E_OG6_101051
+Contig_665_Len3326_Cov6_E_OG6_103961
+Contig_7896_Len504_Cov1_U_OG6_116443
+Contig_6369_Len640_Cov2_U_OG6_107629
+Contig_218_Len5773_Cov12260_P_OG6_102770
+Contig_250_Len5432_Cov11_U_OG6_102109
+Contig_1503_Len2102_Cov2_P_OG6_104631
+Contig_1781_Len1898_Cov4_E_OG6_103110
+Contig_7718_Len517_Cov4_U_OG6_107629
+Contig_2524_Len1486_Cov10283_U_OG6_102770
+Contig_207_Len5911_Cov4_P_OG6_104171
+Contig_1989_Len1770_Cov9572_P_OG6_102770
+Contig_6893_Len587_Cov1_P_OG6_103083
+Contig_1403_Len2189_Cov6_E_OG6_100617
+Contig_4699_Len873_Cov2_U_OG6_102109
+Contig_7520_Len533_Cov1_P_OG6_103438
+Contig_115_Len7578_Cov15_U_OG6_107629
+Contig_1732_Len1931_Cov2_E_OG6_101536
+Contig_6482_Len627_Cov1_P_OG6_101673
+Contig_849_Len2894_Cov3_U_OG6_116443
+Contig_3913_Len1037_Cov5_U_OG6_107629
+Contig_9808_Len408_Cov1_P_OG6_113435
+Contig_439_Len4172_Cov3_E_OG6_107629
+Contig_749_Len3109_Cov7_U_OG6_101143
+Contig_376_Len4497_Cov28_E_OG6_116443
+Contig_1579_Len2041_Cov3_E_OG6_103026
+Contig_787_Len3042_Cov8_U_OG6_101143
+Contig_4099_Len996_Cov1_U_OG6_105091
+Contig_8084_Len489_Cov1_P_OG6_101427
+Contig_2431_Len1534_Cov37_E_OG6_101143
+Contig_110_Len7741_Cov24_U_OG6_101172
+Contig_4412_Len930_Cov1_P_OG6_101345
+Contig_7241_Len556_Cov1_E_OG6_107629
+Contig_574_Len3608_Cov16_P_OG6_107278
+Contig_739_Len3127_Cov4_E_OG6_102109
+Contig_858_Len2877_Cov9661_P_OG6_102770
+Contig_3857_Len1055_Cov1_U_OG6_100774
+Contig_7308_Len551_Cov1_P_OG6_100463
+Contig_61_Len9077_Cov26_E_OG6_101172
+Contig_5256_Len784_Cov1_U_OG6_107629
+Contig_6823_Len592_Cov1_E_OG6_100210
+Contig_2634_Len1443_Cov2_U_OG6_102109
+Contig_2511_Len1491_Cov2_P_OG6_118575
+Contig_3656_Len1108_Cov2_P_OG6_106027
+Contig_7423_Len542_Cov1_U_OG6_132867
+Contig_889_Len2819_Cov18_U_OG6_116443
+Contig_5665_Len726_Cov1_E_OG6_100769
+Contig_3821_Len1064_Cov2_P_OG6_100469
+Contig_6635_Len610_Cov1_P_OG6_100578
+Contig_573_Len3614_Cov53_U_OG6_102121
+Contig_7211_Len558_Cov3_U_OG6_101143
+Contig_1293_Len2294_Cov87_E_OG6_106711
+Contig_131_Len7117_Cov11286_P_OG6_102770
+Contig_5544_Len742_Cov1_P_OG6_111848
+Contig_806_Len2987_Cov21_E_OG6_103192
+Contig_219_Len5773_Cov12245_P_OG6_102770
+Contig_136_Len7040_Cov8_U_OG6_100080
diff --git a/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-37.pyc b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-37.pyc
new file mode 100644
index 0000000..1927e55
Binary files /dev/null and b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-37.pyc differ
diff --git a/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-38.pyc b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-38.pyc
new file mode 100644
index 0000000..80437ee
Binary files /dev/null and b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-38.pyc differ
diff --git a/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-39.pyc b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-39.pyc
new file mode 100644
index 0000000..dc18356
Binary files /dev/null and b/PTL1/Transcriptomes/Scripts/__pycache__/CUB.cpython-39.pyc differ
diff --git a/PTL1/Transcriptomes/Scripts/scratch.py b/PTL1/Transcriptomes/Scripts/scratch.py
new file mode 100644
index 0000000..6eee0b3
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/scratch.py
@@ -0,0 +1,7 @@
+import re
+
+
+og = 'OG6_123456'
+
+ogv = og.split(re.split('OG.{1}_', og)[1])[0][-4:]
+print(ogv, re.split('OG.{1}_', og)[1])
\ No newline at end of file
diff --git a/PTL1/Transcriptomes/Scripts/wrapper.py b/PTL1/Transcriptomes/Scripts/wrapper.py
new file mode 100644
index 0000000..16ebf6b
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/wrapper.py
@@ -0,0 +1,261 @@
+#Dependencies
+import os, sys, re
+import shutil
+import argparse
+
+
+def get_args():
+
+ parser = argparse.ArgumentParser(
+ prog = 'PhyloToL v6.0 Part 1 for Transcriptomes',
+ description = "Updated January 19th, 2023 by Auden Cote-L'Heureux. Link to GitHub: https://github.com/AudenCote/PhyloToL_v6.0"
+ )
+
+ parser.add_argument('-s', '--script', default = -1, type = int, choices = { 1, 2, 3, 4, 5, 6, 7 }, help = 'Script to run if you are only running one script')
+ parser.add_argument('-n', '--conspecific_names', type = str, help = 'A .txt or .tsv file with two tab-separated columns; the first should have 10 digit codes, the second species or other identifying names. This is used to determine which sequences to remove (only between "species") in cross-plate contamination assessment')
+ parser.add_argument('-1', '--first_script', default = -1, type = int, choices = { 1, 2, 3, 4, 5, 6 }, help = 'First script to run')
+ parser.add_argument('-2', '--last_script', default = -1, type = int, choices = { 2, 3, 4, 5, 6, 7 }, help = 'First script to run')
+ parser.add_argument('-a', '--assembled_transcripts', type = str, help = 'Path to a folder of assembled transcripts, assembled by rnaSPAdes. Each assembled transcript file name should start with a unique 10 digit code, and end in "_assembledTranscripts.fasta", E.g. Op_me_hsap_assembledTranscripts.fasta')
+ parser.add_argument('-o', '--output', default = '../', type = str, help = 'An "Output" folder will be created at this directory to contain all output files. By default this folder will be created at the parent directory of the Scripts folder')
+ parser.add_argument('-x', '--xplate_contam', action = 'store_true', help = 'Run cross-plate contamination removal (includes all files)')
+ parser.add_argument('-g', '--genetic_code', type = str, help = 'If all of your taxa use the same genetic code, you may enter it here (to be used in script 5). Alternatively, if you need to use a variety of genetic codes but know which codes to use, you may fill give here the path to a .txt or .tsv with two tab-separated columns, the first with the ten-digit codes and the second column with the corresponding genetics codes. Otherwise, stop at script 4 and fill in "gcode_output.tsv" before running script 5')
+ parser.add_argument('-min', '--minlen', type = int, default = 200, help = 'Minimum transcript length')
+ parser.add_argument('-max', '--maxlen', type = int, default = 12000, help = 'Maximum transcript length')
+ parser.add_argument('-d', '--databases', type = str, default = '../Databases', help = 'Path to databases folder')
+
+ return parser.parse_args()
+
+
+#running the first script on all the bare files
+def script_one(args, ten_digit_codes):
+ for file in os.listdir(args.assembled_transcripts):
+ if file[10:] == '_assembledTranscripts.fasta' and file[:10] in ten_digit_codes:
+ os.system('python 1a_ContigFiltStats.py --input_file ' + args.assembled_transcripts + '/' + file + ' --output_file ' + args.output + '/Output/' + file[:10] + ' --minLen ' + str(args.minlen) + ' --maxLen ' + str(args.maxlen) + ' --spades') #SPADES ARGUMENT??
+
+ if args.xplate_contam:
+ os.system('python 1b_XSpeciesContaminationAgnes.py ' + args.output + '/Output/XlaneBleeding ' + str(args.minlen) + ' ' + args.conspecific_names)
+
+
+def script_two(args):
+
+ for folder in os.listdir(args.output + '/Output/'):
+ if os.path.isfile(args.output + '/Output/' + folder + '/SizeFiltered/' + folder + '.' + str(args.minlen) + 'bp.fasta'):
+ os.system('python 2a_remove_rRNA.py --input_file ' + args.output + '/Output/' + folder + '/SizeFiltered/' + folder + '.' + str(args.minlen) + 'bp.fasta --databases ' + args.databases)
+
+ fasta_withBact = args.output + '/Output/' + folder + '/' + folder + '_NorRNAseqs.fasta'
+ os.system('python 2b_remove_Bact.py --input_file ' + fasta_withBact + ' --databases ' + args.databases)
+
+#NEED TO SORT OUT FILE NAMES ETC. BELOW HERE
+
+#running the third script
+def script_three(args):
+
+ for folder in os.listdir(args.output + '/Output'):
+ if os.path.isfile(args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.fasta'):
+ os.system('python 3_CountOGsDiamond.py --input_file ' + args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.fasta --evalue 1e-15 --databases ' + args.databases)
+
+
+#running the fourth script
+def script_four(args):
+ for folder in os.listdir(args.output + '/Output'):
+ if os.path.isfile(args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed.fasta'):
+ os.system('python 4_InFrameStopFreq.py --input_file ' + args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed.fasta --databases ' + args.databases)
+
+ #putting all of the gcode summaries produced by fourth script into a spreadsheet
+ gcode_info = []
+ for folder in os.listdir(args.output + '/Output'):
+ if os.path.isfile(args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed_StopCodonStats.tsv'):
+ with open(args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed_StopCodonStats.tsv') as f:
+ for line in f:
+ line_sep = line.split('\t')
+ if line_sep[0] == 'Summary':
+ gcode_info.append([folder, line_sep[6], line_sep[7], line_sep[8][:-1]])
+
+ valid_codes = ['bleph','blepharisma','chilo','chilodonella','condy', 'condylostoma','none','eup','euplotes','peritrich','vorticella','ciliate','universal','taa','tag','tga','mesodinium']
+
+ stop = False
+ gcode_file = { }
+ if args.genetic_code.endswith('.txt') or args.genetic_code.endswith('.tsv'):
+ if os.path.isfile(args.genetic_code):
+ for line in open(args.genetic_code):
+ try:
+ if line.split('\t')[1].strip().lower() in valid_codes:
+ gcode_file.update({ line.split('\t')[0] : line.split('\t')[1].strip() })
+ else:
+ print('Genetic code ERROR -- ' + line.split('\t')[1].strip() + ' is not a valid genetic code. Please fill out the "gcode_output.tsv" file and continue with script 5.')
+ except IndexError:
+ print('\nGenetic code ERROR -- it looks like you tried to enter a .txt/.tsv file, but it is improperly formatted. Stopping after script 4; you may fill out the file gcode_output.tsv and continue with script 5.\n')
+ stop = True
+ else:
+ print('\nGenetic code ERROR -- it looks like you tried to enter a .txt/.tsv file, but it could not be found. Stopping after script 4; you may fill out the file gcode_output.tsv and continue with script 5.\n')
+ stop = True
+
+ with open(args.output + '/Output/gcode_output.tsv', 'w') as g:
+ g.writelines('10 Digit Code\tIn-frame TAG Density\tIn-frame TGA Density\tIn-frame TAA Density\tGenetic Code\n')
+ for row in gcode_info:
+ if args.genetic_code == None:
+ g.writelines(row[0] + '\t' + row[1] + '\t' + row[2] + '\t' + row[3] + '\t\n')
+ elif args.genetic_code.lower() in valid_codes:
+ g.writelines(row[0] + '\t' + row[1] + '\t' + row[2] + '\t' + row[3] + '\t' + args.genetic_code + '\n')
+ elif args.genetic_code.endswith('.txt') or args.genetic_code.endswith('.tsv'):
+ try:
+ g.writelines(row[0] + '\t' + row[1] + '\t' + row[2] + '\t' + row[3]+ '\t' + gcode_file[row[0]] + '\n')
+ except KeyError:
+ g.writelines(row[0] + '\t' + row[1] + '\t' + row[2] + '\t' + row[3]+ '\t' + 'Universal' + '\n')
+ print('\nDefaulting to Universal genetic code for taxon ' + row[0] + '\n')
+ #print('\nGenetic code ERROR -- it looks like you tried to enter a .txt/.tsv file, but a taxon is missing. Stopping after script 4; you may fill out the file gcode_output.tsv and continue with script 5.\n')
+ #stop = True
+ else:
+ stop = True
+
+ if stop or args.genetic_code == None:
+ print('\nStopping after script 4 because genetic code information is incomplete. Please fill out the file "gcode_output.tsv" and continue with script 5.\n')
+ exit()
+
+
+def script_five(args):
+
+ valid_codes = ['bleph','blepharisma','chilo','chilodonella','condy', 'condylostoma','none','eup','euplotes','peritrich','vorticella','ciliate','universal','taa','tag','tga','mesodinium']
+
+ lines = [line.strip().split('\t') for line in open(args.output + '/Output/gcode_output.tsv', 'r')]
+ with open(args.output + '/Output/gcode_output.tsv', 'r') as g:
+ for folder in os.listdir(args.output + '/Output'):
+ if os.path.isfile(args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed.fasta'):
+ for line in lines:
+ if line[0] == folder and line[-1].lower() in valid_codes:
+ os.system('python 5_GCodeTranslate.py --input_file ' + args.output + '/Output/' + folder + '/' + folder + '_WTA_EPU.Renamed.fasta --genetic_code ' + line[-1])
+ elif line[-1].lower() not in valid_codes and line[-1] != 'Genetic Code':
+ print('\n' + line[-1] + ' is not a valid genetic code. Skipping taxon ' + folder + '.\n')
+
+
+def script_six(args):
+
+ prefixes = []
+ for file in os.listdir(args.output + '/Output'):
+ if file.endswith('_AA.ORF.fasta'):
+ prefixes.append(file[:10])
+
+ unique_prefixes = list(dict.fromkeys(prefixes))
+
+ hook_fasta = ''
+ for file in os.listdir(args.databases + '/db_OG'):
+ if file.split('.')[-1] in ('fasta', 'fas', 'fa', 'faa'):
+ hook_fasta = args.databases + '/db_OG/' + file
+
+ if hook_fasta == '':
+ print('\nNo .fasta file could be found containing Hook sequences. This should be supplied along with the .dmnd-formatted database file in the Databases/db_OG folder. Quitting before script 6.\n')
+
+ for prefix in unique_prefixes:
+ os.system('python 6_FilterPartials.py --file_prefix ' + args.output + '/Output/' + prefix + ' --hook_fasta ' + hook_fasta)
+
+ for prefix in unique_prefixes:
+ os.system('python 6b_update_cov_post_removepartials.py ' + args.output + '/Output/' + prefix)
+
+
+def script_seven(args):
+
+ for file in os.listdir(args.output + '/Output/ToRename'):
+ if '.AA.ORF.fasta' in file:
+ os.system('python 7_FinalizeName.py --input_file ' + args.output + '/Output/ToRename/' + file + ' --name ' + file[:10])
+
+ os.mkdir(args.output + '/Output/Intermediate')
+
+ for file in os.listdir(args.output + '/Output'):
+ if file != 'ReadyToGo' and file != 'Intermediate':
+ os.system('mv ' + args.output + '/Output/' + file + ' ' + args.output + '/Output/Intermediate')
+
+ os.system('python 8_SummaryStats.py -i ' + args.output + '/Output -d ' + args.databases)
+
+
+if __name__ == "__main__":
+
+ args = get_args()
+
+ if (args.first_script == 1 or args.script == 1) and (args.assembled_transcripts == None or not os.path.isdir(args.assembled_transcripts)):
+ print('\nERROR: If starting at the first script, a valid path to a folder of assembled transcript files (which must end in .fasta, .fa, or .fna) should be input using the --assembled_transcripts argument')
+ quit()
+
+ if args.genetic_code == None and args.script == -1:
+ if args.first_script < 5 and args.last_script >= 5:
+ print('\nERROR: You cannot run script 5 without giving a genetic code! If all of the taxa in the run use the same genetic code, then use the --genetic_code argument (e.g. -g Universal). Otherwise, stop after script 4, fill out the spreadsheet called "gcode_translate.tsv," and then run scripts 5-7. If this does not make sense, please ask for help.')
+ quit()
+
+ ten_digit_codes = []
+ if args.first_script == 1 or args.script == 1:
+ for file in os.listdir(args.assembled_transcripts):
+ if file[10:] == '_assembledTranscripts.fasta':
+ ten_digit_codes.append(file[:10])
+ else:
+ if not os.path.isdir(args.output + '/Output'):
+ print('\nERROR: A folder called "Output" is not found at the given output path. Enter the correct path for --output or start from script 1.\n')
+ quit()
+
+ if(len(ten_digit_codes) > len(list(dict.fromkeys(ten_digit_codes)))):
+ print('\nERROR: Duplicate 10-digit codes are not allowed.\n')
+ quit()
+
+ for code in ten_digit_codes:
+ for c, char in enumerate(code):
+ if (c != 2 and c != 5 and char not in 'qwertyuiopasdfghjklzxcvbnmQWERTYUIOPASDFGHJKLZXCVBNM1234567890') or ((c == 2 or c == 5) and char != '_'):
+ print('\nERROR: ' + code + ' is an invalid 10-digit code sample identifier. It must of the format Op_me_hsap (Homo sapiens for example). Please ask for help if this does not make sense.\n')
+ quit()
+
+ if os.path.isdir(args.output + '/Output') and (args.first_script == 1 or args.script == 1):
+ print('\nERROR: An "Output" folder already exists at the given path. Please delete or rename this folder and try again.\n')
+ quit()
+ elif os.path.isdir(args.output + '/Output/Intermediate'):
+ print('\nIt looks like this run is already complete. Try deleting/renaming the Output folder and try again.\n')
+ quit()
+ elif not os.path.isdir(args.output + '/Output'):
+ os.mkdir(args.output + '/Output')
+
+ scripts = [0, script_one, script_two, script_three, script_four, script_five, script_six, script_seven]
+
+ if args.script == -1:
+ if args.first_script < args.last_script:
+ for i in range(1 + args.last_script - args.first_script):
+ print('\nRunning script ' + str(i + args.first_script) + '...\n')
+ if i + args.first_script == 1:
+ if len(ten_digit_codes) == 0:
+ print('\nNo properly-named assembled transcripts files found.\n')
+ quit()
+ else:
+ scripts[i + args.first_script](args, ten_digit_codes)
+ else:
+ scripts[i + args.first_script](args)
+ else:
+ print('\nERROR: Invalid script combination: the first script must be less than the last script. If you want to use only once script, use the --script argument.\n')
+ quit()
+ else:
+ if args.script == 1:
+ if len(ten_digit_codes) == 0:
+ print('\nNo properly-named assembled transcripts files found.\n')
+ quit()
+ else:
+ scripts[args.script](args, ten_digit_codes)
+ else:
+ scripts[args.script](args)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/PTL1/Transcriptomes/Scripts/wrapper_submit.sh b/PTL1/Transcriptomes/Scripts/wrapper_submit.sh
new file mode 100644
index 0000000..ed90f2f
--- /dev/null
+++ b/PTL1/Transcriptomes/Scripts/wrapper_submit.sh
@@ -0,0 +1,29 @@
+#!/bin/bash
+#
+#SBATCH --job-name=PTL1_GBF
+#SBATCH --output=PTL1.%j.out # Stdout (%j expands to jobId)
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --ntasks-per-node=64 ##change to number of srun when running multiple instances
+#SBATCH --mem=160G
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=YOUREMAIL@smith.edu
+
+module purge #Cleans up any loaded modules
+module use /gridapps/modules/all #make sure module locations is loaded
+
+module load slurm
+module load tqdm
+module load Biopython/1.75-foss-2019b-Python-3.7.4
+module load BLAST+/2.9.0-gompi-2019b
+module load DIAMOND/0.9.30-GCC-8.3.0
+module load VSEARCH/2.21.1-GCC-10.3.0
+
+parent='/beegfs/fast/katzlab/becky/PTL1/Transcriptomes/Forams/'
+
+srun -D ${parent}Scripts python3 ${parent}Scripts/wrapper.py -1 1 -2 7 -x --assembled_transcripts ${parent}AssembledTranscripts -o ${parent} -n ${parent}Conspecific.txt --genetic_code Universal &
+#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 2 -2 7 -x --assembled_transcripts ${parent}Plate4/Assembled_Transcripts -o ${parent}Plate4 -n ${parent}Plate4/Conspecific.txt --genetic_code ${parent}Plate4/Gcodes.txt &
+#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 2 -2 7 -x --assembled_transcripts ${parent}Plate7/Assembled_Transcripts -o ${parent}Plate7 -n ${parent}Plate7/Conspecific.txt --genetic_code ${parent}Plate7/Gcodes.txt &
+#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 1 -2 7 -x --assembled_transcripts ${parent}Plate11/Assembled_Transcripts -o ${parent}Plate11 -n ${parent}Plate11/Conspecific.txt --genetic_code ${parent}Plate11/Gcodes.txt &
+#srun -D ${parent}HQ/Scripts python3 ${parent}HQ/Scripts/wrapper.py -1 2 -2 7 -x --assembled_transcripts ${parent}Plate18/Assembled_Transcripts -o ${parent}Plate18 -n ${parent}Plate18/Conspecific.txt --genetic_code ${parent}Plate18/Gcodes.txt &
+wait