4e0ed5b2547fe5c4305c6bd4d9336c4800ae0276
jcasper
  Wed Mar 6 10:41:33 2024 -0800
Commit of files for knownGeneV45 build, refs #32414

diff --git src/hg/makeDb/doc/ucscGenes/hg38.gencodeV45.sh src/hg/makeDb/doc/ucscGenes/hg38.gencodeV45.sh
new file mode 100644
index 0000000..7228638
--- /dev/null
+++ src/hg/makeDb/doc/ucscGenes/hg38.gencodeV45.sh
@@ -0,0 +1,33 @@
+export db=hg38
+export GENCODE_VERSION=V44
+export PREV_GENCODE_VERSION=V43
+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
+
+# NB: Had to manually construct the files.txt file; it was missing.
+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 &
+
+# 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 hg38 -Ne "select geneSymbol, kgId from kgXref" | sort > ids.txt
+join -t $'\t' genes.lst  ids.txt | tawk '{print $2,$1}' | sort > knownToMyGene2.txt
+hgLoadSqlTab $db knownToMyGene2 ~/kent/src/hg/lib/knownTo.sql knownToMyGene2.txt