Created
April 26, 2016 09:21
-
-
Save arundurvasula/3e3241ab4ae8877781654a4af4f86d4f to your computer and use it in GitHub Desktop.
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
import gzip | |
import csv | |
import argparse | |
import sys | |
parser = argparse.ArgumentParser(description="A script that makes a haploid vcf diploid. Expects a whole genome VCF.") | |
parser.add_argument("-v", "--vcf", action="store", required=True, help="Input VCF file. Should be a multisample, whole genome VCF from Shore with haploid calls.") | |
parser.add_argument("-o", "--out", action="store", required=True, help="Output filename") | |
parser.add_argument("-g", "--gzip", action="store_true", required=False, help="Set if the VCF is gzipped.") | |
args = parser.parse_args() | |
vcf_in = args.vcf | |
out_name = args.out | |
if args.gzip: | |
opener = gzip.open | |
else: | |
opener = open | |
with opener(vcf_in, 'r') as tsvin: | |
tsvin = csv.reader(tsvin, delimiter='\t') | |
vcf_out = csv.writer(open(out_name, 'w'), delimiter='\t', lineterminator="\n") | |
for row in tsvin: | |
if any('##' in strings for strings in row): | |
continue | |
if any('#CHROM' in strings for strings in row): | |
vcf_out.writerow(["##fileformat=VCFv4.0"]) | |
vcf_out.writerow(row) | |
continue | |
chrom,pos,id,ref,alt,qual,filter,info,format=row[0:9] | |
if chrom=='23': | |
chrom='X' | |
# elif chrom=='24': | |
# chrom='Y' | |
else: | |
continue | |
out = [chrom,pos,id,ref,alt,qual,filter,info,format] + row[9:] | |
vcf_out.writerow(out) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment