2d78f7651d5a78740cf16d032e2fc702a3e24342
jcasper
  Mon Sep 29 00:11:16 2025 -0700
knownGeneV49 makedoc, refs #36169

diff --git src/hg/makeDb/doc/ucscGenes/hg38.gencodeV49.sh src/hg/makeDb/doc/ucscGenes/hg38.gencodeV49.sh
new file mode 100644
index 00000000000..bae4a6e7292
--- /dev/null
+++ src/hg/makeDb/doc/ucscGenes/hg38.gencodeV49.sh
@@ -0,0 +1,37 @@
+export db=hg38
+export GENCODE_VERSION=V49
+export PREV_GENCODE_VERSION=V48
+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 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 $db knownToMyGene2 ~/kent/src/hg/lib/knownTo.sql knownToMyGene2.txt
+
+# make sure the track and html for knownGene${PREV_GENCODE_VERSION} is preserved in
+# knownGeneArchive.