sh 从gt_hmm生成断点基因型

Posted 2021-05-07

cat <(cut -f 1,2 gt_hmm_fill.tsv) <(cut -f 1,3 gt_hmm_fill.tsv) |\
grep -v 'chrom' |\
sort -k1,1 -k2,2n |\
uniq > breakpoint_sites.tsv
bgzip breakpoint_sites.tsv -c > breakpoint_sites.tsv.gz && tabix -s1 -b2 -e2 breakpoint_sites.tsv.gz

bcftools view -T breakpoint_sites.tsv.gz -m 2 -M 2 gt_hmm.vcf.gz |\
bcftools query -f '[%CHROM\t%POS\t%SAMPLE\t%GT\n]' |\
awk  -v OFS='\t' '''
        {   
            gsub("0/0", "0", $0);
            gsub("1/1", "1", $0);
            gsub("./.","", $0);
            $3;
            print
        }''' | gzip > breakpoint_gts.tsv.gz