sv_to_gt.sh

REGIONS="$1" # e.g. svim_ambiguous_regions.txt
METHOD="$2" # e.g. svim
VCF_FILE="$3" # $FILTERED_VCFS/svim_sorted_filtered.vcf.gz
vcf="$(zgrep -v '^#' "$VCF_FILE")"
line_num=0
while read -r line;
do
    ((line_num++))
    genotypes="$line_num"
    svs=$(echo "$line" | grep "'$METHOD[[:alnum:]._-]*'" -o | tr -d "\'")
    [ -z "$svs" ] && continue # if no svim svs are found in that line
    sv_cnt=0
    while read -r sv;
    do
        [ $sv_cnt -eq 0 ] && genotypes=$(getpos "$sv")
        ((sv_cnt++))
        genotypes="$genotypes $(echo "$vcf" |
            awk -F'\t' -v "SV=$sv" '$3~SV {split($10,a,":");print a[1], $6}')"
    done <<< "$svs"
    echo "$genotypes"
done < "$REGIONS"