23036e8b97ae73f56eeee54d68a7668d4881e77b
angie
  Mon Jan 9 18:00:29 2023 -0800
Don't make old taxodium/v1 protobuf anymore, everyone has moved on to taxonium/v2.  Make names file for big tree so hgPhyloPlace doesn't have to read in protobuf to get names for matching uploaded names/IDs.

diff --git src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
index 47bac66..0c09743 100755
--- src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
+++ src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
@@ -84,81 +84,63 @@
 tail -n+2 clade-paths.public \
 | grep -E '^[A-Za-z]' \
 | cut -f 1,3 > lineageToPath.public
 
 
 cncbDate=$(ls -l $cncbDir | sed -re 's/.*cncb\.([0-9]{4}-[0-9][0-9]-[0-9][0-9]).*/\1/')
 echo "sarscov2phylo release 13-11-20; NCBI and COG-UK sequences downloaded $today; CNCB sequences downloaded $cncbDate" \
     > version.txt
 
 $matUtils extract -i public-$today.all.masked.pb -u samples.public.$today
 sampleCountComma=$(echo $(wc -l < samples.public.$today) \
                    | sed -re 's/([0-9]+)([0-9]{3})$/\1,\2/; s/([0-9]+)([0-9]{3},[0-9]{3})$/\1,\2/;')
 echo "$sampleCountComma genomes from GenBank, COG-UK and CNCB ($today); sarscov2phylo 13-11-20 tree with newer sequences added by UShER" \
     > hgPhyloPlace.description.txt
 
-# Make Taxonium V1-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 public-$today.metadata.tsv.gz > metadata.tmp.tsv
-time $matUtils extract -i public-$today.all.masked.pb \
-    -f wuhCor1.fa \
-    -g ncbiGenes.gtf \
-    -M metadata.tmp.tsv \
-    --extra-fields pango_lineage_usher \
-    --include-nt \
-    --write-taxodium public-$today.all.masked.taxodium.pb
-rm metadata.tmp.tsv wuhCor1.fa
-gzip -f public-$today.all.masked.taxodium.pb
-
 # Make Taxonium V2 .jsonl.gz protobuf for display
 usher_to_taxonium --input public-$today.all.masked.pb \
     --metadata public-$today.metadata.tsv.gz \
     --genbank ~angie/github/taxonium/taxoniumtools/test_data/hu1.gb \
     --columns genbank_accession,country,date,pangolin_lineage,pango_lineage_usher \
     --clade_types=nextstrain,pango \
     --name_internal_nodes \
     --title "$today tree with sequences from GISAID, INSDC, COG-UK and CNCB" \
     --output public-$today.all.masked.taxonium.jsonl.gz
 
 # Link to public trees download directory hierarchy
 archiveRoot=/hive/users/angie/publicTrees
 read y m d < <(echo $today | sed -re 's/-/ /g')
 archive=$archiveRoot/$y/$m/$d
 mkdir -p $archive
 gzip -c public-$today.all.nwk > $archive/public-$today.all.nwk.gz
 ln -f `pwd`/public-$today.all.masked.{pb,vcf.gz} $archive/
 gzip -c public-$today.all.masked.pb > $archive/public-$today.all.masked.pb.gz
 ln -f `pwd`/public-$today.metadata.tsv.gz $archive/
 gzip -c public-$today.all.masked.nextclade.pangolin.pb \
     > $archive/public-$today.all.masked.nextclade.pangolin.pb.gz
 gzip -c lineageToPublicName > $archive/lineageToPublicName.tsv.gz
 gzip -c cladeToPublicName > $archive/cladeToPublicName.tsv.gz
 ln -f `pwd`/hgPhyloPlace.description.txt $archive/public-$today.version.txt
-ln -f `pwd`/public-$today.all.masked.taxodium.pb.gz $archive/
 ln -f `pwd`/public-$today.all.masked.taxonium.jsonl.gz $archive/
 
 # Update 'latest' in $archiveRoot
 ln -f $archive/public-$today.all.nwk.gz $archiveRoot/public-latest.all.nwk.gz
 ln -f $archive/public-$today.all.masked.pb $archiveRoot/public-latest.all.masked.pb
 ln -f $archive/public-$today.all.masked.pb.gz $archiveRoot/public-latest.all.masked.pb.gz
 ln -f $archive/public-$today.all.masked.vcf.gz $archiveRoot/public-latest.all.masked.vcf.gz
 ln -f $archive/public-$today.metadata.tsv.gz $archiveRoot/public-latest.metadata.tsv.gz
 ln -f $archive/public-$today.version.txt $archiveRoot/public-latest.version.txt
-ln -f $archive/public-$today.all.masked.taxodium.pb.gz \
-    $archiveRoot/public-latest.all.masked.taxodium.pb.gz
 ln -f $archive/public-$today.all.masked.taxonium.jsonl.gz \
     $archiveRoot/public-latest.all.masked.taxonium.jsonl.gz
 
 # Update hgdownload-test link for archive
 mkdir -p /usr/local/apache/htdocs-hgdownload/goldenPath/wuhCor1/UShER_SARS-CoV-2/$y/$m
 ln -sf $archive /usr/local/apache/htdocs-hgdownload/goldenPath/wuhCor1/UShER_SARS-CoV-2/$y/$m
 
 # Update links to latest public protobuf and metadata in hgwdev cgi-bin directories
 pigz -p 8 -c samples.public.$today > samples.public.$today.gz
 for dir in /usr/local/apache/cgi-bin{-angie,-beta,}/hgPhyloPlaceData/wuhCor1; do
     ln -sf `pwd`/public-$today.all.masked.pb $dir/public-latest.all.masked.pb
     ln -sf `pwd`/public-$today.metadata.tsv.gz $dir/public-latest.metadata.tsv.gz
     ln -sf `pwd`/hgPhyloPlace.description.txt $dir/public-latest.version.txt
     ln -sf `pwd`/samples.public.$today.gz $dir/public-latest.names.gz
 done