Created
October 17, 2016 16:04
-
-
Save suqingdong/4834553fe6f741d88aff16fe22f4a81c to your computer and use it in GitHub Desktop.
generate sample_info according info.txt, pn and disease
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
#-*- coding: utf-8 -*- | |
def get_sample_info(infofile, pn, disease): | |
header = '#B1\n#FamilyID\tSampleID\tSex\tNormal/Patient\tPN' | |
if disease: | |
header += '\tDisease' | |
header += '\n' | |
with open('sample_info', 'w') as out: | |
out.write(header) | |
with open(infofile) as f: | |
for eachline in f: | |
if len(eachline) > 1: | |
familyid = eachline.rstrip().split('\t')[0] or '.' | |
sampleid = eachline.rstrip().split('\t')[2] | |
sex = eachline.rstrip().split('\t')[4] | |
nop = eachline.rstrip().split('\t')[6] | |
line = '{}\t{}\t{}\t{}\t{}'.format(familyid, sampleid, sex, nop, pn) | |
if disease: | |
line = line + '\t' + disease | |
line += '\n' | |
out.write(line) | |
if __name__ == '__main__': | |
import sys | |
if len(sys.argv) < 3: | |
print "Usage: {} <info.txt> <pn> [disease]".format(sys.argv[0]) | |
exit(1) | |
if len(sys.argv) == 4: | |
disease = sys.argv[3] | |
else: | |
disease = None | |
get_sample_info(sys.argv[1], sys.argv[2], disease) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment