YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2026-02-10 21:10:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

Updating header in 2a_Identify_rRNA.py

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2024-01-16 12:11:57 -05:00 committed by GitHub
parent 229bd77cca
commit d90e67c266
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
PTL1/Transcriptomes/Scripts/2a_Identify_rRNA.py
View File

@ -1,29 +1,13 @@
#!/usr/bin/env python3.5 # Last updated 8/18/2017
##__Updated__: 18_08_2017 # This script is intended to identify and isolate SSU/LSU sequences by BLASTn-ing
##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com # all length-filtered assembled transcripts against a reference database.
##__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 ##
## ##
##########################################################################################
# You must run Script 1a before this step. Optionally, you may also have run Script 1b.
# Before running this script, ensure that you have a properly formatted rRNA reference
# BLAST database in the Databases/db_BvsE/SSULSUdb folder.
#Dependencies
import argparse, os, sys import argparse, os, sys
from argparse import RawTextHelpFormatter,SUPPRESS from argparse import RawTextHelpFormatter,SUPPRESS
from Bio import SeqIO from Bio import SeqIO
@ -198,25 +182,6 @@ def remove_rDNA(args, rRNA_folder):
no_SSULSU += 1 no_SSULSU += 1
return str(with_SSULSU), str(no_SSULSU) 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 --------------------------------### ###-------------------------------- Next Script Message --------------------------------###
@ -251,9 +216,7 @@ def main():
code, rRNA_folder = prep_folders(args) code, rRNA_folder = prep_folders(args)
with_SSULSU, no_SSULSU = remove_rDNA(args, rRNA_folder) with_SSULSU, no_SSULSU = remove_rDNA(args, rRNA_folder)
#update_log(args, with_SSULSU, no_SSULSU)
clean_up(args) clean_up(args)
next_script(args) next_script(args)