Last active
June 8, 2016 18:24
-
-
Save pontikos/c4755938b509e1f2aaea365b442f939f to your computer and use it in GitHub Desktop.
Check that your VCFs are not truncated.
This file contains hidden or 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
# chrom sizes in hg19 | |
declare -A sizes | |
sizes["chr1"]=249250621 | |
sizes["chr2"]=243199373 | |
sizes["chr3"]=198022430 | |
sizes["chr4"]=191154276 | |
sizes["chr5"]=180915260 | |
sizes["chr6"]=171115067 | |
sizes["chr7"]=159138663 | |
sizes["chrX"]=155270560 | |
sizes["chr8"]=146364022 | |
sizes["chr9"]=141213431 | |
sizes["chr10"]=135534747 | |
sizes["chr11"]=135006516 | |
sizes["chr12"]=133851895 | |
sizes["chr13"]=115169878 | |
sizes["chr14"]=107349540 | |
sizes["chr15"]=102531392 | |
sizes["chr16"]=90354753 | |
sizes["chr17"]=81195210 | |
sizes["chr18"]=78077248 | |
sizes["chr20"]=63025520 | |
sizes["chrY"]=59373566 | |
sizes["chr19"]=59128983 | |
sizes["chr22"]=51304566 | |
sizes["chr21"]=48129895 | |
# get 10M from the end | |
for chr in `seq 1 22` X | |
do | |
x=`echo *chr${chr}.*vcf.gz.tbi` | |
if [ -s $x ] | |
then | |
pos=`expr ${sizes["chr${chr}"]} - 10000000` | |
last_pos=`tabix ${x%.tbi} ${chr}:${pos} | awk '{print $2}' | tail -n1` | |
if [[ ${last_pos} == "" ]] | |
then | |
echo ${x%.tbi} may be truncated | |
else | |
echo ${x%.tbi}, last_pos:${last_pos}, chrom_size: ${sizes["chr${chr}"]}, remaining `expr ${sizes["chr${chr}"]} - ${last_pos}` | |
fi | |
else | |
echo $x does not exist | |
fi | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment