e6e4ac7f750c6e2894752ef008325efee95ae6fc angie Wed Jun 16 17:47:08 2021 -0700 Added vcfSamples function (grab VCF sample names from #CHROM header line, print one name per line) diff --git src/hg/utils/otto/sarscov2phylo/util.sh src/hg/utils/otto/sarscov2phylo/util.sh index 1373dbb..8d5182c 100755 --- src/hg/utils/otto/sarscov2phylo/util.sh +++ src/hg/utils/otto/sarscov2phylo/util.sh @@ -49,15 +49,25 @@ | sed -re 's@ \| @ \|@; s@ $@@; s@[:,]@ @g; s@ @ @g; s@[()]@@g;' \ | sed -re 's@ \|@\t@;' # Got rid of this: s/ ([^|])/_\1/g; } export -f cleanGenbank cleanCncb () { sed -re "s@^BetaCoV/@@; s@^hCoV-19/@@; s@^SARS-CoV-2/@@; s@^human/@@; s@ *\| *@\t@;" } export -f cleanCncb +vcfSamples () { + set +o pipefail + xcat $1 \ + | head \ + | grep ^#CHROM \ + | sed -re 's/\t/\n/g;' \ + | tail -n+10 + set -o pipefail +} +export -f vcfSamples