a501a677b1027e7103b547e54b0e2ee286ca09e7
angie
  Fri Mar 5 15:39:35 2021 -0800
Make getNcbi.sh more efficient: fetch only new IDs from BioSample; run nextclade and pangolin only on new sequences.

diff --git src/hg/utils/otto/sarscov2phylo/updatePublic.sh src/hg/utils/otto/sarscov2phylo/updatePublic.sh
index 19b36e1..bd7710f 100755
--- src/hg/utils/otto/sarscov2phylo/updatePublic.sh
+++ src/hg/utils/otto/sarscov2phylo/updatePublic.sh
@@ -23,26 +23,23 @@
 today=$(date +%F)
 scriptDir=$(dirname "${BASH_SOURCE[0]}")
 
 $scriptDir/gisaidFromChunks.sh
 
 cogUkDir=$ottoDir/cogUk.$today
 mkdir -p $cogUkDir
 cd $cogUkDir
 $scriptDir/getCogUk.sh >& getCogUk.log
 
 ncbiDir=$ottoDir/ncbi.$today
 mkdir -p $ncbiDir
 cd $ncbiDir
 $scriptDir/getNcbi.sh >& getNcbi.log
 
-$scriptDir/nextcladeNcbi.sh &
-$scriptDir/pangolinNcbi.sh
-
 $scriptDir/updateIdMapping.sh $gisaidDir/{metadata_batch_$today.tsv.gz,sequences_batch_$today.fa.xz}
 
 buildDir=$ottoDir/$today
 mkdir -p $buildDir
 cd $buildDir
 $scriptDir/updatePublicTree.sh $prevDate $problematicSitesVcf >& updatePublicTree.log
 
 cat hgPhyloPlace.description.txt