Created
June 11, 2015 21:01
-
-
Save philippbayer/ee424b4e76e6d6e7a71c to your computer and use it in GitHub Desktop.
getting 1000 genomes data with tabix and python
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
urls={"1":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr1.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"10":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr10.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"11":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr11.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"12":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr12.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"13":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr13.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"14":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr14.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"15":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr15.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"16":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr16.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"17":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr17.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"18":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr18.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"19":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr19.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"2":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr2.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"20":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr20.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"21":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr21.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"22":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr22.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"3":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr3.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"4":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr4.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"5":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr5.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"6":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr6.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"7":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr7.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"8":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr8.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz", | |
"9":"ftp://ftp-trace.ncbi.nih.gov/1000genomes/ftp/release/20130502/ALL.chr9.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz"} | |
chroms = {} | |
for l in open("your_plink_file.map"): | |
ll = l.rstrip().split("\t") | |
chrom, pos = ll[0], ll[-1] | |
if chrom in chroms: | |
chroms[chrom].append("%s:%s-%s"%(chrom, pos, pos)) | |
else: | |
chroms[chrom] = ["%s:%s-%s"%(chrom, pos, pos)] | |
import os | |
for chrom in chroms: | |
print "getting %s SNPS for chromosome %s" %(len(chroms[chrom]), chrom) | |
command = "./tabix-0.2.6/tabix -fh %s %s | grep -v SV > %s.vcf" %(urls[chrom], " ".join(chroms[chrom]), chrom) | |
os.popen(command) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment