4440223fad68a002964802e0ecf3b1b94cb28503 markd Sat Nov 16 10:11:29 2019 -0800 import of gencode V33 prerelase diff --git src/hg/makeDb/doc/hg38/gencode.txt src/hg/makeDb/doc/hg38/gencode.txt index 44448a1..5eeea9b 100644 --- src/hg/makeDb/doc/hg38/gencode.txt +++ src/hg/makeDb/doc/hg38/gencode.txt @@ -1,565 +1,609 @@ ######################################################################### 2014-08-11: import of UCSC GENCODE group processing of GENCODE V20 (markd) # download files mkdir -p /hive/data/genomes/hg38/bed/gencodeV20/data cd /hive/data/genomes/hg38/bed/gencodeV20 # download gencode release cd data wget -nv -r -np ftp://ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_20 mv ftp.sanger.ac.uk/pub/gencode/Gencode_human/release_20 . rm -rf ftp.sanger.ac.uk cd .. # create Makefile from previous one. cp /hive/data/genomes/hg19/bed/gencodeV19/Makefile . # build and load tables (time nice make -j 10) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. make cmpRelease >gencode-cmp.tsv ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. ## Important to make sure filter attrs.transcriptType matches current set ## figured out with select distinct transcriptType from wgEncodeGencodeAttrsV20 order by transcriptType; cd kent/src/hg/makeDb/trackDb cp human/hg38/wgEncodeGencodeV18.ra human/hg38/wgEncodeGencodeV20.ra cp human/hg38/wgEncodeGencodeV18.html human/hg38/wgEncodeGencodeV20.html # edit these plus human/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV20.ra in reverse order with previous # tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. ### IMPORTANT: make sure that hgTracks/gencodeTracks.c registers ### track handler for this version of gencode: registerTrackHandler("wgEncodeGencodeV20", gencodeGeneMethods); # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed cd /hive/data/genomes/hg38/bed/gencodeV20 make joinerCheck # output in check/joiner.out ######################################################################### 2014-10-16: import of UCSC GENCODE group processing of GENCODE V21 (markd) # download files mkdir -p /hive/data/genomes/hg38/bed/gencodeV21/data cd /hive/data/genomes/hg38/bed/gencodeV21 # create Makefile from previous one. # WARNING: next build start with hg/makeDb/outside/gencode/gencodeLoad.mk cp /hive/data/genomes/hg38/bed/gencodeV20/Makefile . # download, build and load tables (time nice make -j 10) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. make cmpRelease >gencode-cmp.tsv ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. ## Important to make sure filter attrs.transcriptType matches current set ## figured out with select distinct transcriptType from wgEncodeGencodeAttrsV21 order by transcriptType; cd kent/src/hg/makeDb/trackDb cp human/hg38/wgEncodeGencodeV18.ra human/hg38/wgEncodeGencodeV21.ra cp human/hg38/wgEncodeGencodeV18.html human/hg38/wgEncodeGencodeV21.html # edit these plus human/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV21.ra in reverse order with previous # tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. ### IMPORTANT: make sure that hgTracks/gencodeTracks.c registers ### track handler for this version of gencode: registerTrackHandler("wgEncodeGencodeV21", gencodeGeneMethods); # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed cd /hive/data/genomes/hg38/bed/gencodeV21 make joinerCheck # output in check/joiner.out ######################################################################### 2015-03-13: import of UCSC GENCODE group processing of GENCODE V22 (markd) # download files mkdir -p /hive/data/genomes/hg38/bed/gencodeV22 cd /hive/data/genomes/hg38/bed/gencodeV22 # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set # release and transcript support versions # download, build and load tables (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk cmpRelease >gencode-cmp.tsv ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. ## Important to make sure filter attrs.transcriptType matches current set ## figured out with select distinct transcriptType from wgEncodeGencodeAttrsV22 order by transcriptType; cd kent/src/hg/makeDb/trackDb cp human/hg38/wgEncodeGencodeV18.ra human/hg38/wgEncodeGencodeV22.ra cp human/hg38/wgEncodeGencodeV18.html human/hg38/wgEncodeGencodeV22.html # edit these plus human/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV22.ra in reverse order with previous # tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed # output in check/joiner.out cd /hive/data/genomes/hg38/bed/gencodeV22 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck ######################################################################### 2015-10-02: import of UCSC GENCODE group processing of GENCODE V23 (markd) # download files mkdir -p /hive/data/genomes/hg38/bed/gencodeV23 cd /hive/data/genomes/hg38/bed/gencodeV23 # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set # release and transcript support versions # download, build and load tables (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk cmpRelease >gencode-cmp.tsv ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. ## Important to make sure filter attrs.transcriptType matches current set ## figured out with select distinct transcriptType from wgEncodeGencodeAttrsV23 order by transcriptType; cd kent/src/hg/makeDb/trackDb cp human/hg38/wgEncodeGencodeV22.ra human/hg38/wgEncodeGencodeV23.ra cp human/hg38/wgEncodeGencodeV22.html human/hg38/wgEncodeGencodeV23.html # edit these plus human/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV23.ra tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed # output in check/joiner.out cd /hive/data/genomes/hg38/bed/gencodeV23 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck ######################################################################### 2015-12-08: import of UCSC GENCODE group processing of GENCODE V24 (markd) # download files mkdir -p /hive/data/genomes/hg38/bed/gencodeV24 cd /hive/data/genomes/hg38/bed/gencodeV24 # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set # release and transcript support versions # download, build and load tables (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense (results in gencode-cmp.tsv) make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk cmpRelease ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. Follow instructiuons in ra file to ensure ## filters are correct. cd kent/src/hg/makeDb/trackDb cp human/hg38/wgEncodeGencodeV23.ra human/hg38/wgEncodeGencodeV24.ra cp human/hg38/wgEncodeGencodeV23.html human/hg38/wgEncodeGencodeV24.html # edit these plus human/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV24.ra tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed # output in check/joiner.out ### NOT DONE SINCE TRACK NOT BEING PUSHED cd /hive/data/genomes/hg38/bed/gencodeV24 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck ######################################################################### 2016-07-23: import of UCSC GENCODE group processing of GENCODE V25 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV25 pushd /hive/data/genomes/hg38/bed/gencodeV25 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv ## Copy and update trackDb files from previous release. ## Change version and use lower priority so it sorts to top of ## super track page. Follow instructions in ra file to ensure ## filters are correct. cd kent/src/hg/makeDb/trackDb cp mouse/hg38/wgEncodeGencodeVM9.ra mouse/hg38/wgEncodeGencodeV25.ra cp mouse/hg38/wgEncodeGencodeVM9.html mouse/hg38/wgEncodeGencodeV25.html # edit these plus mouse/hg38/trackDb.wgEncode.ra # - set priorities in wgEncodeGencodeV25.ra tracks so newest shows up first # priority - set to previous version priority minus 0.001 # searchPriority - set each to previous minus 0.001 # - make current track default to pack and hide previous [ONLY if it's going to be pushed] # superTrack wgEncodeGencodeSuper pack # - Update wgEncodeGencodeSuper.html to describe new release and to # pick up other updates. [ONLY if it's going to be pushed] # update all.joiner and validate # look for the last section `begin Gencode V??' in all.joiner # and copy and update version # repeat this until happy, editing minCheck as needed # output in check/joiner.out cd /hive/data/genomes/hg38/bed/gencodeV25 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck ######################################################################### 2017-04-16: import of UCSC GENCODE group processing of GENCODE V26 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV26 pushd /hive/data/genomes/hg38/bed/gencodeV26 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 26 88 'March 2017' # edit human/hg38/trackDb.wgEncode.ra to add new .ra file include make DBS=hg38 # Update human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit all.joiner to add ~/tmp/gencodeV26.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV26 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2017-09-14: import of UCSC GENCODE group processing of GENCODE V27 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV27 pushd /hive/data/genomes/hg38/bed/gencodeV27 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 27 90 'Aug 2017' # Update human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.wgEncode.ra to add new .ra file include make DBS=hg38 # edit all.joiner to add ~/tmp/gencodeV27.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV27 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2018-03-07: update UCSC GENCODE V27 to include protein id (for VAI) and fix PAR tag # save existing data, move a mkdir -p prev/pre-proteinId mv data/gencode.tab prev/pre-proteinId/ mv tables/wgEncodeGencodeAttrsV27.tab tables/wgEncodeGencodeTagV27.tab prev/pre-proteinId/ mv loaded/wgEncodeGencodeAttrsV27.tab.loaded loaded/wgEncodeGencodeTagV27.tab.loaded prev/pre-proteinId/ # rebuild, getting protein ids. make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk loadTables >&prot-ids.log # 2018-03-19: update search to include protein id cd kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 27 90 'Aug 2017' ######################################################################### 2018-04-11: import of UCSC GENCODE group processing of GENCODE V28 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV28 pushd /hive/data/genomes/hg38/bed/gencodeV28 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 28 92 'Apr 2018' # Update human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.wgEncode.ra to add new .ra file include make DBS=hg38 # edit all.joiner to add ~/tmp/gencodeV28.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV28 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2018-09-05: import of UCSC GENCODE group processing of GENCODE V29 (markd) 2018-11-09 this was the prerelease and the /hive/data/genomes/hg38/bed/gencodeV29 was renamed to /hive/data/genomes/hg38/bed/gencodeV29.pre when the full release was downloaded. # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # This is a pre-release from # ftp://ftp.ebi.ac.uk/pub/databases/havana/gencode_pre/Gencode_human/release_29/ # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV29 pushd /hive/data/genomes/hg38/bed/gencodeV29 # pre-release contained invalid biotype, fix for now mv gencode.v29.chr_patch_hapl_scaff.annotation.gtf.gz gencode.v29.chr_patch_hapl_scaff.annotation.orig.gtf.gz zcat gencode.v29.chr_patch_hapl_scaff.annotation.orig.gtf.gz | sed -e 's/"lincrna"/"lincRNA"/g' | gzip -c> gencode.v29.chr_patch_hapl_scaff.annotation.gtf.gz (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd ~/kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 29 94 'Sept 2018' # Edit human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.wgEncode.ra to add new .ra file include make DBS=hg38 # edit all.joiner to add ~/tmp/gencodeV29.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV29 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2018-11-09: import of UCSC GENCODE group processing of GENCODE V29 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV29 pushd /hive/data/genomes/hg38/bed/gencodeV29 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd ~/kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 29 94 'Oct 2018' # Edit human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.wgEncode.ra to add new .ra file include make DBS=hg38 # edit all.joiner to add ~/tmp/gencodeV29.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV29 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2019-04-08: import of UCSC GENCODE group processing of GENCODE V30 (markd) # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV30 pushd /hive/data/genomes/hg38/bed/gencodeV30 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd ~/kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 30 96 'Apr 2019' # Edit human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.gencode.ra to add new .ra file include make DBS=hg38 ## only if being pushed to RR: # edit all.joiner to add ~/tmp/gencodeV30.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV30 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ######################################################################### 2019-07-03: import of UCSC GENCODE group processing of GENCODE V31 (markd) # Replaced import of pre-release # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV31a pushd /hive/data/genomes/hg38/bed/gencodeV31 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd ~/kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 31 97 'June 2019' # Edit human/hg38/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg38/trackDb.gencode.ra to add new .ra file include make DBS=hg38 ## only if being pushed to RR: # edit all.joiner to add ~/tmp/gencodeV31.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV31 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all # if pushing public, add ticket and MARK QA READY ######################################################################### 2019-08-30: import of UCSC GENCODE group processing of GENCODE V32 (markd) # PRE-RELEASE # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions # download, build and load tables mkdir -p /hive/data/genomes/hg38/bed/gencodeV32 pushd /hive/data/genomes/hg38/bed/gencodeV32 (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& # compare tables from previous release to see if number changed makes # sense. Results are in gencode-cmp.tsv # generate trackDb and joiner blurb pushd ~/kent/src/hg/makeDb/trackDb ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 32 98 'Sept 2019' # If being pushed public, update 'Release Notes' in # human/hg38/wgEncodeGencodeSuper.html # edit human/hg38/trackDb.gencode.ra to add new .ra file include make DBS=hg38 ## only if being pushed to RR: # edit all.joiner to add ~/tmp/gencodeV32.joiner # verify with: pushd /hive/data/genomes/hg38/bed/gencodeV32 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all # if pushing public: add ticket and MARK QA READY 2019-08-30: repeat above for final release mv /hive/data/genomes/hg38/bed/gencodeV32 /hive/data/genomes/hg38/bed/gencodeV32pre # redo do above imports for t in tables/* ; do cmp ../gencodeV32pre/$t $t ; done Changes: wgEncodeGencode2wayConsPseudoV32.gp wgEncodeGencodeAttrsV32.tab wgEncodeGencodePolyaV32.gp wgEncodeGencodeTagV32.tab only attrs and maybe tags matter to hgGene gencode mkdir pre-diffs diff ../gencodeV32pre/tables/wgEncodeGencodeAttrsV32.tab tables/wgEncodeGencodeAttrsV32.tab >pre-diffs/wgEncodeGencodeAttrsV32.diff diff ../gencodeV32pre/tables/wgEncodeGencodeTagV32.tab tables/wgEncodeGencodeTagV32.tab >pre-diffs/wgEncodeGencodeTagV32.diff # wgEncodeGencodeAttrsV32: experimental conformation level changed on a few pseudogenes # wgEncodeGencodeTagV32: pseudo_consens changed on a few pseudogenes. ######################################################################### +2019-11-15: import of UCSC GENCODE group processing of GENCODE V32 (markd) + # PRE-RELEASE + # edit hg/makeDb/outside/gencode/gencodeLoad.mk to set release and ensembl versions + + # download, build and load tables + mkdir -p /hive/data/genomes/hg38/bed/gencodeV33 + pushd /hive/data/genomes/hg38/bed/gencodeV33 + + (time nice make -j 10 -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk) >&build.1.out& + + # compare tables from previous release to see if number changed makes + # sense. Results are in gencode-cmp.tsv + + # generate trackDb and joiner blurb + pushd ~/kent/src/hg/makeDb/trackDb + ../../makeDb/outside/gencode/gencodeGenerateTrackDbs hg38 33 40 'Nov 2019' + + # If being pushed public, update 'Release Notes' in + # human/hg38/wgEncodeGencodeSuper.html + + # edit human/hg38/trackDb.gencode.ra to add new .ra file include + make DBS=hg38 + + ## only if being pushed to RR: + # edit all.joiner to add ~/tmp/gencodeV33.joiner + # verify with: + pushd /hive/data/genomes/hg38/bed/gencodeV33 + make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck + + # commit all + +######################################################################### + +if fgrep Error: check/joiner.out ; then false; else true; fi +Error: 6 of 20572 elements (0.029%) of hg38.wgEncodeGencodePseudoGeneV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2645 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +Error: 857 of 226969 elements (0.378%) of hg38.wgEncodeGencodeCompV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2640 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +Error: 703 of 100360 elements (0.700%) of hg38.wgEncodeGencodeBasicV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2635 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +Error: 703 of 100360 elements (0.700%) of hg38.wgEncodeGencodeBasicV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2635 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +Error: 857 of 226969 elements (0.378%) of hg38.wgEncodeGencodeCompV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2640 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +Error: 6 of 20572 elements (0.029%) of hg38.wgEncodeGencodePseudoGeneV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2645 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +make: *** [joinerCheck] Error 1 + +Error: 857 of 226969 elements (0.378%) of hg38.wgEncodeGencodeCompV33.name are not in key wgEncodeGencodeAttrsV33.transcriptId line 2640 of /cluster/home/markd/kent/src/hg/makeDb/schema/all.joiner +hgsql hg38 -Ne 'select name from wgEncodeGencodeCompV33 where name not in (select transcriptId from wgEncodeGencodeAttrsV33)' >~/tmp/comp.ids