YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 12:10:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updated preguidance with no logger dependency

Browse Source
This commit is contained in:
Godwin Ani 2023-12-04 14:54:57 -05:00 committed by GitHub
parent a15ba2402d
commit b466a30a96
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 38 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

83
PTL2/Scripts/preguidance.py
View File

@ -1,5 +1,4 @@
import os, sys, re import os, sys, re
from logger import Logger
from Bio import SeqIO from Bio import SeqIO
@ -8,53 +7,71 @@ def run(params):
try: try:
ogs = list(dict.fromkeys([line.strip() for line in open(params.gf_list)])) ogs = list(dict.fromkeys([line.strip() for line in open(params.gf_list)]))
except (FileNotFoundError, TypeError) as e: except (FileNotFoundError, TypeError) as e:
Logger.Error('Unable to read GF list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e)) print('\nERROR: Unable to read GF list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e) + '\n')
exit()
try: try:
taxa = list(dict.fromkeys([line.strip() for line in open(params.taxon_list)])) taxa = list(dict.fromkeys([line.strip() for line in open(params.taxon_list)]))
except (FileNotFoundError, TypeError) as e: except (FileNotFoundError, TypeError) as e:
Logger.Error('Unable to read taxon list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e)) print('\nERROR: Unable to read taxon list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e) + '\n')
exit()
if params.sim_taxa != None:
try: try:
sim_taxa = list(dict.fromkeys([line.strip() for line in open(params.sim_taxa)])) sim_taxa = list(dict.fromkeys([line.strip() for line in open(params.sim_taxa)]))
except (FileNotFoundError, TypeError) as e: except (FileNotFoundError, TypeError) as e:
Logger.Error('Unable to read similarity taxa list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e)) print('\nERROR: Unable to read similarity taxa list file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e) + '\n')
exit()
else:
sim_taxa = 'all'
if params.blacklist != None:
try: try:
blacklist_seqs = list(dict.fromkeys([line.strip() for line in open(params.blacklist)])) blacklist_seqs = list(dict.fromkeys([line.strip() for line in open(params.blacklist)]))
except (FileNotFoundError, TypeError) as e: except (FileNotFoundError, TypeError) as e:
print('\nUnable to read blacklist file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e)) print('\nERROR: Unable to read blacklist file. Please make sure that the path is correct and that the file is formatted correctly.\n\n' + str(e) + '\n')
exit()
else:
blacklist_seqs = []
if not os.path.isdir(params.data): if not os.path.isdir(params.data):
Logger.Error(Logger.Error('Input amino-acid data files not found. Please make sure that the given path (--data) is correct.')) print('\nInput amino-acid data files not found. Please make sure that the given path (--data) is correct.\n')
aa_files = [f for f in os.listdir(params.data) if f[:10] in taxa if f.endswith('.faa') or f.endswith('.fa') or f.endswith('.fasta')] aa_files = [f for f in os.listdir(params.data) if f[:10] in taxa if f.endswith('.faa') or f.endswith('.fa') or f.endswith('.fasta')]
missing_taxa = [tax for tax in taxa if tax not in [f[:10] for f in aa_files]] missing_taxa = [tax for tax in taxa if tax not in [f[:10] for f in aa_files]]
if(len(missing_taxa) > 0): if(len(missing_taxa) > 0):
Logger.Warning('The following taxa in the taxon list are missing amino-acid files in ' + params.data + ':\n' + '\n'.join(['\t' + t for t in missing_taxa])) print('\nWARNING: The following taxa in the taxon list are missing amino-acid files in ' + params.data + ':\n' + '\n'.join(['\t' + t for t in missing_taxa]) + '\n')
os.mkdir(params.output + '/Output/Intermediate/SF_Diamond') os.mkdir(params.output + '/Output/Intermediate/SF_Diamond')
removed_file = open(params.output + '/Output/Pre-Guidance/SimFilter_removed.txt', 'w') removed_file = open(params.output + '/Output/Pre-Guidance/SimFilter_removed.txt', 'w')
for og in ogs: for og in ogs:
Logger.Message('Processing ' + og) print('\nProcessing ' + og + '\n')
with open(params.output + '/Output/Pre-Guidance/' + og + '_preguidance.faa', 'w') as preguidance_file: with open(params.output + '/Output/Pre-Guidance/' + og + '_preguidance.fasta', 'w') as preguidance_file:
for taxon_file in aa_files: for taxon_file in aa_files:
recs = [] recs = []
for rec in sorted([rec for rec in SeqIO.parse(params.data + '/' + taxon_file, 'fasta') if rec.id[-10:] == og and rec.id not in blacklist_seqs and params.og_identifier in rec.id], key=lambda x: -len(x.seq)): for rec in sorted([rec for rec in SeqIO.parse(params.data + '/' + taxon_file, 'fasta') if rec.id[-10:] == og and rec.id not in blacklist_seqs and params.og_identifier in rec.id], key=lambda x: -len(x.seq)):
if(rec.id == rec.description): if(rec.id == rec.description):
recs.append(rec) recs.append(rec)
else: else:
Logger.Warning('\tThe sequence ID ' + rec.description + ' is invalid. Please make sure that sequence IDs contain no spaces, tabs, etc. This sequence is being excluded.') print('\n\tThe sequence ID ' + rec.description + ' is invalid. Please make sure that sequence IDs contain no spaces, tabs, etc. This sequence is being excluded.\n')
if sim_taxa == 'all':
use_taxon = True
else:
if taxon_file[:10] in sim_taxa:
use_taxon = True
else:
use_taxon = False
masters = []; removed = 0; flag = 0; cycle = 0 masters = []; removed = 0; flag = 0; cycle = 0
if params.similarity_filter and taxon_file[:10] in sim_taxa: if params.similarity_filter and use_taxon:
if len(recs) > 1: if len(recs) > 1:
while flag == 0: while flag == 0:
master_file_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_master_' + str(cycle) master_file_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_master_' + str(cycle)
query_file_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_queries_' + str(cycle) + '.faa' query_file_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_queries_' + str(cycle) + '.fasta'
diamond_out_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_diamond_results_' + str(cycle) + '.tsv' diamond_out_name = params.output + '/Output/Intermediate/SF_Diamond/' + og + '_' + taxon_file[:10] + '_diamond_results_' + str(cycle) + '.tsv'
open(master_file_name + '.faa', 'w').write('>' + recs[0].id + '\n' + str(recs[0].seq) + '\n\n') open(master_file_name + '.faa', 'w').write('>' + recs[0].id + '\n' + str(recs[0].seq) + '\n\n')
@ -85,7 +102,7 @@ def run(params):
for item in recs_to_remove: for item in recs_to_remove:
removed_file.write(f"{item}\n") removed_file.write(f"{item}\n")
Logger.Message('\t' + str(removed) + ' sequence(s) removed by the similarity filter (' + str(cycle + 1) + ' iterations) from ' + taxon_file[:10]) print('\n\t' + str(removed) + ' sequence(s) removed by the similarity filter (' + str(cycle + 1) + ' iterations) from ' + taxon_file[:10] + '\n')
for rec in recs + masters: for rec in recs + masters:
preguidance_file.write('>' + rec.id + '\n' + str(rec.seq) + '\n\n') preguidance_file.write('>' + rec.id + '\n' + str(rec.seq) + '\n\n')
@ -95,43 +112,3 @@ def run(params):
if(not params.keep_temp): if(not params.keep_temp):
os.system('rm -r ' + params.output + '/Output/Intermediate/SF_Diamond') os.system('rm -r ' + params.output + '/Output/Intermediate/SF_Diamond')