parse_breseq.py

#!/usr/bin/env python
import sys

'''
Parses through multiple breseq files and prints a tab delimited file with all
mutations listed according to the respective files they were found in.

Usage: parse_breseq.py <breseq1.txt> <breseq2.txt> ...

Note: breseq files are generated by copying ALL text on breseq "index.html" pages
and saving in text format. Simply CTRL+A, CTRL+C on webpage and CTRL+V into text document.
Formatting must be precise!

Output format:
evidence	seq id	position	mutation	annotation	gene	description	<in_file1?> <in_file2?> ...
'''

file_list = sys.argv[1:]

lines_by_file = {}
all_lines = []
for file in file_list:
	lines_by_file[file] = []
	file_handle = open(file)	
	for i, line in enumerate(file_handle.readlines()):
		if i <= 5:
			continue
		elif line.strip().split() == []:
			break
		lines_by_file[file].append('\t'.join(line.strip().split(' \t')))
		all_lines.append('\t'.join(line.strip().split(' \t')))


line_set = set(all_lines)
files_by_line = {}
for file in file_list:
	for line in lines_by_file[file]:
		if line not in files_by_line:
			files_by_line[line]=[file]
		else:
			files_by_line[line].append(file)

sys.stdout.write('evidence\tseq id\tposition\tmutation\tannotation\tgene\tdescription\t{0}\n'.format('\t'.join(file_list)))
for line in files_by_line:
	print_line = line
	for query_file in file_list:
		if query_file in files_by_line[line]:
			print_line += '\t1'
		else:
			print_line += '\t0'
	print_line += '\n'
	sys.stdout.write(print_line)