f8e605d52fb7a05d5c5b19d3d6a14e7e554c0a0a
markd
  Sat Sep 25 13:59:34 2021 -0700
change ensembl to ucsc names (programs, files, variables) to be gencode to ucsc, as gencode does not actually use ensembl names, it use ENCODE, which uses UCSC for primary assembly and GenBank access or other sequences

diff --git src/hg/makeDb/outside/gencode/gencodeLoad.mk src/hg/makeDb/outside/gencode/gencodeLoad.mk
index 54b3387..1bbcb21 100644
--- src/hg/makeDb/outside/gencode/gencodeLoad.mk
+++ src/hg/makeDb/outside/gencode/gencodeLoad.mk
@@ -89,40 +89,40 @@
 rel = V${ver}
 releaseUrl = ${baseUrl}/${gencodeOrg}/${ftpReleaseSubdir}
 dataDir = data
 relDir = ${dataDir}/release_${ver}
 annotationGff = ${relDir}/gencode.v${ver}.${annGffTypeName}.gff3.gz
 pseudo2WayGff = ${relDir}/gencode.v${ver}.2wayconspseudos.gff3.gz
 polyAGff = ${relDir}/gencode.v${ver}.polyAs.gff3.gz
 
 ccdsBinDir = ~markd/compbio/ccds/ccds2/output/bin/$(mach)/opt
 gencodeMakeTracks = ${ccdsBinDir}/gencodeMakeTracks
 gencodeMakeAttrs = ${ccdsBinDir}/gencodeMakeAttrs
 gencodeExonSupportToTable = ${ccdsBinDir}/gencodeExonSupportToTable
 gencodeGxfToGenePred = ${ccdsBinDir}/gencodeGxfToGenePred
 gencodePolyaGxfToGenePred = ${ccdsBinDir}/gencodePolyaGxfToGenePred
 gencodeGxfToAttrs = ${ccdsBinDir}/gencodeGxfToAttrs
-ensToUcscMkLift = ${HOME}/kent/src/hg/makeDb/outside/gencode/bin/ensToUcscMkLift
+buildGencodeToUcscLift = ${HOME}/kent/src/hg/makeDb/outside/gencode/bin/buildGencodeToUcscLift
 gencodeBackMapMetadataIds = ${ccdsBinDir}/gencodeBackMapMetadataIds
 encodeAutoSqlDir = ${HOME}/kent/src/hg/lib/encode
 
 ##
 # intermediate data not loaded into tracks
 ##
 gencodeGp = ${dataDir}/gencode.gp
 gencodeTsv = ${dataDir}/gencode.tsv
-ensemblToUcscChain = ${dataDir}/ensemblToUcsc.chain
+gencodeToUcscChain = ${dataDir}/gencodeToUcsc.chain
 
 # flag indicating fetch was done
 fetchDone = ${relDir}/done
 
 ##
 # track and table data
 ##
 tableDir = tables
 tablePre = wgEncodeGencode
 
 # subset track and pattern for generate genePred and track names for each subset
 # obtained from gencode.v*.annotation.level_1_2.gtf, gencode.v*.annotation.level_3.gtf
 tableBasic = ${tablePre}Basic${rel}
 tableBasicGp = ${tableDir}/${tableBasic}.gp
 
@@ -270,76 +270,76 @@
 	@mkdir -p $(dir $@)
 	${gencodeMakeTracks}  $$(echo $* | tr A-Z a-z) ${gencodeGp} ${gencodeTsv} $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 ${tableTagTab}: ${tableAttrsTab}
 ${tableAttrsTab}: ${gencodeGp} ${gencodeTsv}
 	@mkdir -p $(dir $@)
 	${gencodeMakeAttrs} ${gencodeGp} ${gencodeTsv} $@.${tmpExt} ${tableTagTab}
 	mv -f $@.${tmpExt} $@
 
 ${table2WayConsPseudoGp}: ${pseudo2WayGff}
 	@mkdir -p $(dir $@)
 	gff3ToGenePred -allowMinimalGenes $< $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
-${tablePolyAGp}: ${polyAGff} ${ensemblToUcscChain}
+${tablePolyAGp}: ${polyAGff} ${gencodeToUcscChain}
 	@mkdir -p $(dir $@)
-	${gencodePolyaGxfToGenePred} $< ${ensemblToUcscChain} $@.${tmpExt}
+	${gencodePolyaGxfToGenePred} $< ${gencodeToUcscChain} $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 ${tableUniProtTab}: ${tableSwissProtMeta} ${tableTrEMBLMeta} ${gencodeTsv}
 	@mkdir -p $(dir $@)
 	((${metaFilterCmdGz} ${tableSwissProtMeta} | tawk '{print $$0,"SwissProt"}') && (${metaFilterCmdGz}  ${tableTrEMBLMeta} | tawk '{print $$0,"TrEMBL"}')) | sort -k 1,1 > $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
-${ensemblToUcscChain}:
+${gencodeToUcscChain}:
 	@mkdir -p $(dir $@)
-	${ensToUcscMkLift} ${db} $@.${tmpExt}
+	${buildGencodeToUcscLift} ${db} $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 # other tab files, just copy to name following convention to make load rules
 # work
 ifeq (${isBackmap}, yes)
    metaFilterCmd = ${gencodeBackMapMetadataIds} ${gencodeTsv} ${targetGencodeTsv}
    metaFilterCmdGz = ${metaFilterCmd}
    metaFilterDepend = ${gencodeTsv} ${targetGencodeTsv}
 else
    metaFilterCmd = cat
    metaFilterCmdGz = zcat
    metaFilterDepend = ${gencodeTsv}
 endif
 define copyMetadataTabGz
 mkdir -p $(dir $@)
 ${metaFilterCmdGz} $< > $@.${tmpExt}
 mv -f $@.${tmpExt} $@
 endef
 define copyMetadataTab
 mkdir -p $(dir $@)
 ${metaFilterCmd} $< > $@.${tmpExt}
 mv -f $@.${tmpExt} $@
 endef
 
 ${tableGeneSourceTab}: ${tableGeneSourceMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 ${tableTranscriptSourceTab}: ${tableTranscriptSourceMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 ${tableTranscriptSupportTab}: ${tableTranscriptSupportMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
-${tableExonSupportTab}: ${tableExonSupportMeta} ${ensemblToUcscChain} ${metaFilterDepend}
+${tableExonSupportTab}: ${tableExonSupportMeta} ${gencodeToUcscChain} ${metaFilterDepend}
 	@mkdir -p $(dir $@)
-	${gencodeExonSupportToTable} ${tableExonSupportMeta} ${ensemblToUcscChain} $@.${tmpExt}
+	${gencodeExonSupportToTable} ${tableExonSupportMeta} ${gencodeToUcscChain} $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 ${tableGeneSymbolTab}: ${tableGeneSymbolMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 ${tablePdbTab}: ${tablePdbMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 ${tablePubMedTab}: ${tablePubMedMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 ${tableRefSeqTab}: ${tableRefSeqMeta} ${metaFilterDepend}
 	${copyMetadataTabGz}
 
 ${tableTranscriptionSupportLevelTab}: ${tableTranscriptionSupportLevelData}
 	mkdir -p $(dir $@)
 	cp $< $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
@@ -349,33 +349,33 @@
 	zcat $< | tawk '{print $$1,$$2-1,$$3,$$4,$$5-1,$$6,$$7,$$8}' | sort -k 4,4 -k 5,5n > $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 ${tableAnnotationRemarkTab}: ${tableAnnotationRemarkMeta} ${metaFilterDepend}
 	@mkdir -p $(dir $@)
 	${metaFilterCmdGz} $<  | tawk '{print $$1,gensub("\\\\n|\\\\","","g",$$2)}' | sort -k 1,1 > $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 # drop ENSTR entries that are a hack to support PAR sequences in GTF
 ${tableEntrezGeneTab}: ${tableEntrezGeneMeta} ${metaFilterDepend}
 	@mkdir -p $(dir $@)
 	zcat $< | tawk '$$1!~/^ENSTR/' | sort -k 1,1 | ${metaFilterCmd} /dev/stdin > $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 ##
 # intermediate data for ensembl/havana, not loaded into databases
 ##
-${gencodeGp}: ${annotationGff} ${ensemblToUcscChain}
+${gencodeGp}: ${annotationGff} ${gencodeToUcscChain}
 	@mkdir -p $(dir $@)
-	${gencodeGxfToGenePred} ${db} ${annotationGff} ${ensemblToUcscChain} $@.${tmpExt}
+	${gencodeGxfToGenePred} ${db} ${annotationGff} ${gencodeToUcscChain} $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 ${tableTranscriptionSupportLevelData}: ${metaFilterDepend}
 	touch $@
 ${gencodeTsv}: ${annotationGff}
 	@mkdir -p $(dir $@)
 	${gencodeGxfToAttrs} --keepGoing ${annotationGff} $@.${tmpExt} --tslTabOut=${tableTranscriptionSupportLevelData}.${tmpExt}
 	mv -f ${tableTranscriptionSupportLevelData}.${tmpExt} ${tableTranscriptionSupportLevelData}
 	mv -f $@.${tmpExt} $@
 
 ${targetGencodeTsv}:
 	@mkdir -p $(dir $@)
 	hgsql ${db}  -e 'select * from wgEncodeGencodeAttrsV${backmapTargetVer}' > $@.${tmpExt}
 	mv -f $@.${tmpExt} $@