e931fd3e5fdab83eeb110b2450a0f365eff170e2
angie
  Mon Oct 4 17:04:17 2021 -0700
Omit ORF1a from taxodium amino acid annotations (redundant with ORF1ab).  Add optional baseProtobuf arg to updateCombinedTree.sh / makeNewMaskedVcf.sh to start with a custom protobuf (e.g. optimized) instead of eyesterday's protobuf.

diff --git src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
index dd6e7e7..055389f 100755
--- src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
+++ src/hg/utils/otto/sarscov2phylo/extractPublicTree.sh
@@ -87,31 +87,32 @@
 
 rm public-$today.all.masked.pb
 ln -f public-$today.all.masked.nextclade.pangolin.pb public-$today.all.masked.pb
 
 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 Taxodium-formatted protobuf for display
-zcat /hive/data/genomes/wuhCor1/goldenPath/bigZips/genes/ncbiGenes.gtf.gz > ncbiGenes.gtf
+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 \
     --write-taxodium public-$today.all.masked.taxodium.pb
 rm metadata.tmp.tsv wuhCor1.fa
 gzip -f public-$today.all.masked.taxodium.pb
 
 # 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