f1b5392d9fb6337cf2e2f9d55484a2950ebb3b37 angie Tue Nov 14 17:10:21 2023 -0800 CNCB is now updating daily. diff --git src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh index 69f2a00..f0c19be 100755 --- src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh +++ src/hg/utils/otto/sarscov2phylo/updateIdMapping.sh @@ -15,32 +15,31 @@ nextmeta=$1 nextfasta=$2 scriptDir=$(dirname "${BASH_SOURCE[0]}") source $scriptDir/util.sh today=$(date +%F) ottoDir=/hive/data/outside/otto/sarscov2phylo mapScriptDir=~angie/chris_ncov # Should use a better location than this... installDir=/hive/users/angie/gisaid ncbiDir=$ottoDir/ncbi.$today cogUkDir=$ottoDir/cogUk.$today -# Last time I checked, CNCB had not updated since September, just keep using what we have -cncbDir=$ottoDir/cncb.latest +cncbDir=$ottoDir/cncb.$today # Set up input files for Chris's scripts to map GISAID <--> public sequences cd $mapScriptDir rm -rf input/$today mkdir input/$today cd input/$today ln -sf $cncbDir/cncb.nonGenBank.fasta.xz . ln -sf $ncbiDir/genbank.fa.xz . ln -sf $cogUkDir/cog_all.fasta.xz . ln -sf $nextfasta . xcat $nextmeta | tail -n+2 | cut -f1,3 | uniq > seqToEpi cd $mapScriptDir time ./build.sh -t $today