56405fd76d2760549a7fe511384e534f240ac79e angie Wed Mar 3 18:45:30 2021 -0800 Clean up a bit when done. diff --git src/hg/utils/otto/sarscov2phylo/getNcbi.sh src/hg/utils/otto/sarscov2phylo/getNcbi.sh index bfc5d26..39d03ea 100755 --- src/hg/utils/otto/sarscov2phylo/getNcbi.sh +++ src/hg/utils/otto/sarscov2phylo/getNcbi.sh @@ -69,15 +69,19 @@ $scriptDir/gbMetadataAddBioSample.pl gb.bioSample.tab ncbi_dataset.tsv \ > ncbi_dataset.plusBioSample.tsv # Make a file for joining collection date with ID: tawk '$3 != "" {print $1, $3;}' ncbi_dataset.plusBioSample.tsv \ | sort > gbToDate # Replace FASTA headers with reconstructed names from enhanced metadata. time cleanGenbank < ncbi_dataset/data/genomic.fna \ | $scriptDir/fixNcbiFastaNames.pl ncbi_dataset.plusBioSample.tsv \ | xz -T 50 \ > genbank.fa.xz rm -f $ottoDir/ncbi.latest ln -s ncbi.$today $ottoDir/ncbi.latest + +# Clean up +rm -r ncbi_dataset +nice xz all.bioSample.* &