31 lines
1.2 KiB
Python
31 lines
1.2 KiB
Python
|
#!/usr/bin/env python3
|
||
|
|
import argparse, os, re, sys
|
||
|
|
usage = '''
|
||
|
|
Synopsis:
|
||
|
|
|
||
|
|
map_fasta_ids genome.all.id.map genome.all.transcripts.fasta
|
||
|
|
|
||
|
|
Description:
|
||
|
|
|
||
|
|
This script takes a id map file and changes the name of the ID in a
|
||
|
|
fasta file.
|
||
|
|
'''
|
||
|
|
parser=argparse.ArgumentParser(add_help=False, usage=usage)
|
||
|
|
parser.add_argument('--help', action='store_true'); parser.add_argument('map_file', nargs='?'); parser.add_argument('fasta_file', nargs='?')
|
||
|
|
args=parser.parse_args()
|
||
|
|
if args.help or not args.map_file or not args.fasta_file: sys.exit(usage)
|
||
|
|
mapping={}
|
||
|
|
with open(args.map_file, encoding='utf-8', errors='replace') as fh:
|
||
|
|
for line in fh:
|
||
|
|
f=line.split()
|
||
|
|
if len(f)>=2: mapping[f[0]]=f[1]
|
||
|
|
with open(args.fasta_file, encoding='utf-8', errors='replace') as fh: lines=fh.readlines()
|
||
|
|
os.unlink(args.fasta_file)
|
||
|
|
with open(args.fasta_file,'w') as out:
|
||
|
|
for line in lines:
|
||
|
|
if line.startswith('>'):
|
||
|
|
m=re.match(r'^>(\S+)', line); old=m.group(1) if m else ''
|
||
|
|
if old in mapping: line=re.sub(r'^>'+re.escape(old), '>'+mapping[old], line)
|
||
|
|
else: print(f"WARNING: No mapping available for {old}", file=sys.stderr)
|
||
|
|
out.write(line)
|