bd0945ac583598387ea83c8b3c20593bd934b06a
markd
  Sat Sep 25 16:29:23 2021 -0700
reload V38 with new changes

diff --git src/hg/makeDb/outside/gencode/gencodeLoad.mk src/hg/makeDb/outside/gencode/gencodeLoad.mk
index 1bbcb21..a4580e1 100644
--- src/hg/makeDb/outside/gencode/gencodeLoad.mk
+++ src/hg/makeDb/outside/gencode/gencodeLoad.mk
@@ -36,54 +36,58 @@
 #preRelease = yes
 db = hg38
 #db = hg19
 #db = mm39
 #db = mm10
 ifeq (${db},mm10)
     grcRefAssembly = GRCm38
     verBase = M25
     prevVer = M24
     backmapTargetVer = M25
     ver = ${verBase}lift37
     gencodeOrg = Gencode_mouse
     ftpReleaseSubdir = release_${verBase}/GRCm38_mapping
     annGffTypeName = chr_patch_hapl_scaff.annotation
     isBackmap = yes
+    asmReptUrl = https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/635/GCF_000001635.26_GRCm38.p6/GCF_000001635.26_GRCm38.p6_assembly_report.txt
 else ifeq (${db},mm39)
     grcRefAssembly = GRCm39
     ver = M27
     prevVer = M26
     gencodeOrg = Gencode_mouse
     ftpReleaseSubdir = release_${ver}
     annGffTypeName = chr_patch_hapl_scaff.annotation
+    asmReptUrl = https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/635/GCF_000001635.27_GRCm39/GCF_000001635.27_GRCm39_assembly_report.txt
 else ifeq (${db},hg38)
     grcRefAssembly = GRCh38
     ver = 38
     prevVer = 37
     gencodeOrg = Gencode_human
     ftpReleaseSubdir = release_${ver}
     annGffTypeName = chr_patch_hapl_scaff.annotation
+    asmReptUrl = https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_assembly_report.txt
 else ifeq (${db},hg19)
     grcRefAssembly = GRCh37
     verBase = 38
     ver = ${verBase}lift37
     prevVer = 37lift37
     backmapTargetVer = 19
     ftpReleaseSubdir = release_${verBase}/GRCh37_mapping
     gencodeOrg = Gencode_human
     annGffTypeName = annotation
     isBackmap = yes
+    asmReptUrl = https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/001/405/GCF_000001405.39_GRCh38.p13/GCF_000001405.39_GRCh38.p13_assembly_report.txt
 else
     $(error unimplement genome database: ${db})
 endif
 # END EDIT THESE EACH RELEASE
 
 
 ifeq (${preRelease},yes)
     # pre-release
     baseUrl = ftp://ftp.ebi.ac.uk/pub/databases/havana/gencode_pre
 else
     # official release
     baseUrl = ftp://ftp.ebi.ac.uk/pub/databases/gencode
 endif
 
 rel = V${ver}
@@ -99,30 +103,31 @@
 gencodeMakeAttrs = ${ccdsBinDir}/gencodeMakeAttrs
 gencodeExonSupportToTable = ${ccdsBinDir}/gencodeExonSupportToTable
 gencodeGxfToGenePred = ${ccdsBinDir}/gencodeGxfToGenePred
 gencodePolyaGxfToGenePred = ${ccdsBinDir}/gencodePolyaGxfToGenePred
 gencodeGxfToAttrs = ${ccdsBinDir}/gencodeGxfToAttrs
 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
 gencodeToUcscChain = ${dataDir}/gencodeToUcsc.chain
+asmRept = ${dataDir}/$(notdir asmReptUrl)
 
 # 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
 
@@ -280,33 +285,38 @@
 ${table2WayConsPseudoGp}: ${pseudo2WayGff}
 	@mkdir -p $(dir $@)
 	gff3ToGenePred -allowMinimalGenes $< $@.${tmpExt}
 	mv -f $@.${tmpExt} $@
 
 ${tablePolyAGp}: ${polyAGff} ${gencodeToUcscChain}
 	@mkdir -p $(dir $@)
 	${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} $@
 
-${gencodeToUcscChain}:
+${gencodeToUcscChain}: ${asmRept}
 	@mkdir -p $(dir $@)
-	${buildGencodeToUcscLift} ${db} $@.${tmpExt}
+	${buildGencodeToUcscLift} ${db} ${asmRept} $@.${tmpExt}
+	mv -f $@.${tmpExt} $@
+
+${asmRept}:
+	@mkdir -p $(dir $@)
+	wget -nv -O $@.${tmpExt} ${asmReptUrl}
 	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 $@)