df04c1f66cdd6895471998c6d9c70b1a413f7d4e angie Sat Mar 12 20:33:25 2022 -0800 Use new --include-nt option when generating taxonium protobufs. Also watch out for EPI_ISL as part of GenBank name. diff --git src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh index 659623d..5fa1334 100755 --- src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh +++ src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh @@ -134,22 +134,23 @@ $dir/public.plusGisaid.latest.metadata.tsv.gz ln -sf `pwd`/hgPhyloPlace.plusGisaid.description.txt $dir/public.plusGisaid.latest.version.txt ln -sf `pwd`/epiToPublic.latest $dir/ done # Make Taxodium-formatted protobuf for display zcat /hive/data/genomes/wuhCor1/goldenPath/bigZips/genes/ncbiGenes.gtf.gz \ | grep -v '"ORF1a"' > ncbiGenes.gtf zcat /hive/data/genomes/wuhCor1/wuhCor1.fa.gz > wuhCor1.fa zcat gisaidAndPublic.$today.metadata.tsv.gz > metadata.tmp.tsv time $matUtils extract -i gisaidAndPublic.$today.masked.pb \ -f wuhCor1.fa \ -g ncbiGenes.gtf \ -M metadata.tmp.tsv \ --extra-fields pango_lineage_usher \ + --include-nt \ --write-taxodium gisaidAndPublic.$today.masked.taxodium.pb rm metadata.tmp.tsv wuhCor1.fa gzip -f gisaidAndPublic.$today.masked.taxodium.pb $scriptDir/extractPublicTree.sh $today grep skipping annotate*