efdf71bc99d33cb9fc9327b8b8e05244dab81e08
angie
  Fri Aug 28 08:29:52 2026 -0700
Scan the tree for split lineages, excluding some highly recurrent mutations.

diff --git src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh
index 61bb0df9542..cc6299d94b1 100755
--- src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh
+++ src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh
@@ -1,16 +1,18 @@
 #!/bin/bash
+source ~/.bashrc
+conda activate bte
 set -beEu -x -o pipefail
 
 #	Do not modify this script, modify the source tree copy:
 #	kent/src/hg/utils/otto/sarscov2phylo/updateCombinedTree.sh
 
 usage() {
     echo "usage: $0 prevDate today problematicSitesVcf [baseProtobuf]"
     echo "This assumes that ncbi.latest and cogUk.latest links/directories have been updated."
 }
 
 if (( $# != 3 && $# != 4 )); then
   usage
   exit 1
 fi
 
@@ -184,33 +186,30 @@
 # Extract Omicron-only tree for faster searches
 $matUtils extract -i gisaidAndPublic.$today.masked.pb.gz -c B.1.1.529 \
     -o gisaidAndPublic.$today.masked.omicron.pb.gz \
     -u samples.$today.omicron
 pigz -f -p 8 samples.$today.omicron
 ssh hgwdev ln -sf $(pwd)/gisaidAndPublic.$today.masked.omicron.pb.gz \
     /gbdb/wuhCor1/hgPhyloPlaceData/public.plusGisaid.latest.masked.omicron.pb.gz
 sampleCountComma=$(echo $(zcat samples.$today.omicron.gz | wc -l) \
                    | sed -re 's/([0-9]+)([0-9]{3})$/\1,\2/; s/([0-9]+)([0-9]{3},[0-9]{3})$/\1,\2/;')
 echo "$sampleCountComma Omicron genomes from GISAID, GenBank, COG-UK and CNCB ($today); sarscov2phylo 13-11-20 tree with newer sequences added by UShER" \
     > hgPhyloPlace.plusGisaid.omicron.description.txt
 ssh hgwdev ln -sf $(pwd)/hgPhyloPlace.plusGisaid.omicron.description.txt \
     /gbdb/wuhCor1/hgPhyloPlaceData/public.plusGisaid.latest.omicron.version.txt
 
 # Extract recent-only tree (samples from the past year plus samples within radius 5 of those) for faster searches
-set +x
-conda activate bte
-set -x
 python $scriptDir/find_recent_samples.py -i gisaidAndPublic.$today.metadata.tsv.gz -n 365 -o recent_samples.txt
 python $scriptDir/prune_to_radius.py -i gisaidAndPublic.$today.masked.pb.gz -l recent_samples.txt -r 5 \
        -o samples.$today.recent
 $matUtils extract -i gisaidAndPublic.$today.masked.pb.gz \
     -s samples.$today.recent \
     -o gisaidAndPublic.$today.masked.recent.pb.gz
 pigz -f -p 8 samples.$today.recent
 ssh hgwdev ln -sf $(pwd)/gisaidAndPublic.$today.masked.recent.pb.gz \
     /gbdb/wuhCor1/hgPhyloPlaceData/public.plusGisaid.latest.masked.recent.pb.gz
 sampleCountComma=$(echo $(zcat samples.$today.recent.gz | wc -l) \
                    | sed -re 's/([0-9]+)([0-9]{3})$/\1,\2/; s/([0-9]+)([0-9]{3},[0-9]{3})$/\1,\2/;')
 echo "$sampleCountComma recent genomes from GISAID, GenBank, COG-UK and CNCB ($today); sarscov2phylo 13-11-20 tree with newer sequences added by UShER" \
     > hgPhyloPlace.plusGisaid.recent.description.txt
 ssh hgwdev ln -sf $(pwd)/hgPhyloPlace.plusGisaid.recent.description.txt \
     /gbdb/wuhCor1/hgPhyloPlaceData/public.plusGisaid.latest.recent.version.txt
@@ -237,19 +236,26 @@
 done
 
 # Make Taxonium v2 protobuf for display
 usher_to_taxonium --input gisaidAndPublic.$today.masked.pb.gz \
     --metadata gisaidAndPublic.$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 "$today tree with sequences from GISAID, INSDC, COG-UK and CNCB" \
     --output gisaidAndPublic.$today.masked.taxonium.jsonl.gz \
     >& utt.log &
 
 $scriptDir/extractPublicTree.sh $today $prevDate
 
+# Scan for split lineages
+time python ~/kent/src/hg/utils/otto/sarscov2phylo/find_split_lineages.py \
+     -i gisaidAndPublic.$today.masked.pb.gz \
+     -e G22599C,G22927T,T22928C,A23598G \
+     -p pruneForSplitLineages \
+     > split_lineages.txt
+
 set +o pipefail
 grep skipping annotate* | cat
 
 # Clean up