f7003f9a6744e9c1d0ec6cef2226a1035d2b2b06 jcasper Wed Jul 15 22:08:51 2026 -0700 TrackDb and makedoc for UCSC Genes version of GENCODE V50, refs #37395 diff --git src/hg/makeDb/doc/ucscGenes/hg38.gencodeV50.sh src/hg/makeDb/doc/ucscGenes/hg38.gencodeV50.sh new file mode 100644 index 00000000000..785e38bf9e5 --- /dev/null +++ src/hg/makeDb/doc/ucscGenes/hg38.gencodeV50.sh @@ -0,0 +1,37 @@ +export db=hg38 +export GENCODE_VERSION=V50 +export PREV_GENCODE_VERSION=V49 +screen -S knownGene${GENCODE_VERSION} +mkdir /hive/data/genomes/$db/bed/gencode$GENCODE_VERSION/build +cd /hive/data/genomes/$db/bed/gencode$GENCODE_VERSION/build +PATH=$HOME/kent/src/hg/utils/otto/knownGene":$PATH" +cp /hive/data/genomes/${db}/bed/gencode${PREV_GENCODE_VERSION}/build/buildEnv.sh buildEnv.sh + +# edit buildEnv.sh +. buildEnv.sh + +cp ${oldGeneDir}/${PREV_GENCODE_VERSION}.files.txt . +cp ${oldGeneDir}/${PREV_GENCODE_VERSION}.tables.txt . + +hgsql ${oldKnownDb} -Ne "show tables" > ${oldKnownDb}.tables.txt +diff <(sort ${PREV_GENCODE_VERSION}.tables.txt) <(sort ${oldKnownDb}.tables.txt) +# no difference + +buildKnown.sh & + +# Continue with the steps to load the tables into the database. + +# After that's done, then can do the myGene2 knownTo (hasn't been integrated because it needs +# manual gene list fetch). +#myGene2 +mkdir $dir/myGene2 +cd $dir/myGene2 + +# copy list of genes to a file from https://mygene2.org/MyGene2/genes +awk '{print $1}' thatfile | sort > genes.lst +hgsql knownGene${GENCODE_VERSION} -Ne "select geneSymbol, kgId from kgXref" | sort > ids.txt +join -t $'\t' genes.lst ids.txt | tawk '{print $2,$1}' | sort > knownToMyGene2.txt +hgLoadSqlTab knownGene${GENCODE_VERSION} knownToMyGene2 ~/kent/src/hg/lib/knownTo.sql knownToMyGene2.txt + +# make sure the track and html for knownGene${PREV_GENCODE_VERSION} is preserved in +# knownGeneArchive.