48e9d70521d7c9a5ee6bb8057b222d4afcd0658f hiram Thu Sep 10 18:19:37 2020 -0700 browser complete QA Ready refs #22271 diff --git src/hg/makeDb/doc/mm39/initialBuild.txt src/hg/makeDb/doc/mm39/initialBuild.txt index 4c18312..2e80032 100644 --- src/hg/makeDb/doc/mm39/initialBuild.txt +++ src/hg/makeDb/doc/mm39/initialBuild.txt @@ -486,52 +486,52 @@ cd /hive/data/genomes/mm39/bed/tandemDups time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -twoBit=/hive/data/genomes/mm39/mm39.unmasked.2bit mm39) \ > do.log 2>&1 & # real 440m10.886s # one job in pairedEnds needs more memory: time ./runOne 29 20000 chrY tmp/chrY.bed.gz # real 28m57.353s # continuing time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -continue=collapsePairedEnds \ -twoBit=/hive/data/genomes/mm39/mm39.unmasked.2bit mm39) \ > collapsePairedEnds.log 2>&1 & -XXX - running - Thu Jul 30 09:19:46 PDT 2020 + # real 3m23.138s cat fb.mm39.tandemDups.txt - # 155315479 bases of 3044872214 (5.101%) in intersection + # 66584052 bases of 2728222451 (2.441%) in intersection bigBedInfo mm39.tandemDups.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 13 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 -# itemCount: 2,822,307 -# primaryDataSize: 72,710,994 -# primaryIndexSize: 292,560 +# itemCount: 858,983 +# primaryDataSize: 22,513,298 +# primaryIndexSize: 62,976 # zoomLevels: 9 -# chromCount: 5335 -# basesCovered: 1,635,503,835 -# meanDepth (of bases covered): 14.396921 +# chromCount: 57 +# basesCovered: 1,408,031,925 +# meanDepth (of bases covered): 5.083425 # minDepth: 1.000000 -# maxDepth: 381.000000 -# std of depth: 29.341113 +# maxDepth: 240.000000 +# std of depth: 8.811752 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (DONE - 2020-07-27 - Hiram) # construct idKeys for the genbank sequence mkdir /hive/data/genomes/mm39/genbank/idKeys cd /hive/data/genomes/mm39/genbank/idKeys faToTwoBit ../GCA_*m39_genomic.fna.gz mm39.genbank.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/mm39.genbank.2bit genbankMm39) > do.log 2>&1 & # real 0m45.317s cat genbankMm39.keySignature.txt # 804f78d880a5a7f049c472046b563601 @@ -793,60 +793,67 @@ # completed before rmsk was done, to finish: featureBits -countGaps mm39 rmsk windowmaskerSdust 2> fb.mm39.rmsk.windowmaskerSdust.txt cat fb.mm39.rmsk.windowmaskerSdust.txt # 753903955 bases of 2728222451 (27.634%) in intersection time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -continue=cleanup -dbHost=hgwdev mm39) > cleanup.log 2>&1 # real 1m7.841s ########################################################################## # cpgIslands - (DONE - 2020-07-30 - Hiram) mkdir /hive/data/genomes/mm39/bed/cpgIslands cd /hive/data/genomes/mm39/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku mm39) > do.log 2>&1 -XXX - running - Thu Jul 30 09:20:26 PDT 2020 - # real 3m29.034s + # real 3m28.053s cat fb.mm39.cpgIslandExt.txt - # 47618882 bases of 2481941580 (1.919%) in intersection + # 10571422 bases of 2654624157 (0.398%) in intersection ############################################################################## # genscan - (DONE - 2020-07-30 - Hiram) mkdir /hive/data/genomes/mm39/bed/genscan cd /hive/data/genomes/mm39/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku mm39) > do.log 2>&1 -XXX - running - Thu Jul 30 09:20:55 PDT 2020 # real 8m19.775s - # two jobs broken: -./runGsBig2M.csh chr22 000 gtf/000/chr22.gtf pep/000/chr22.pep subopt/000/chr22.bed & -./runGsBig2M.csh chr34 000 gtf/000/chr34.gtf pep/000/chr34.pep subopt/000/chr34.bed -wait - # real 14m27.845s + # one job broken: +./runGsBig2M.csh chr10 000 gtf/000/chr10.gtf pep/000/chr10.pep subopt/000/chr10.bed + # real 34m35.712s + # continuing time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -continue=makeBed -bigClusterHub=ku mm39) > makeBed.log 2>&1 # real 0m45.365s cat fb.mm39.genscan.txt - # 57650331 bases of 2481941580 (2.323%) in intersection + # 55445747 bases of 2654624157 (2.089%) in intersection cat fb.mm39.genscanSubopt.txt - # 50129491 bases of 2481941580 (2.020%) in intersection + # 57607700 bases of 2654624157 (2.170%) in intersection + +######################################################################### +# ncbiGene (WORKING - 2020-07-30 - Hiram) + + mkdir /hive/data/genomes/mm39/bed/xenoRefGene + cd /hive/data/genomes/mm39/bed/xenoRefGene + + time (~/kent/src/hg/utils/automation/doXenoRefGene.pl -buildDir=`pwd` \ + -bigClusterHub=ku -workhorse=hgwdev -dbHost=hgwdev mm39) > do.log 2>&1 & + # real 67m18.015s ######################################################################### # Create kluster run files (DONE - 2020-07-30 - Hiram) # numerator is mm39 gapless bases "real" as reported by: featureBits -noRandom -noHap mm39 gap # 73490654 bases of 2649940489 (2.773%) in intersection # ^^^ # denominator is hg19 gapless bases as reported by: # featureBits -noRandom -noHap hg19 gap # 234344806 bases of 2861349177 (8.190%) in intersection # 1024 is threshold used for human -repMatch: calc \( 2649940489 / 2861349177 \) \* 1024 # ( 2649940489 / 2861349177 ) * 1024 = 948.342510 @@ -917,134 +924,91 @@ # 1 430000 # 1 522000 # use gap size of 5000 to construct a lift file: gapToLift -allowBridged -verbose=2 -minGap=5000 mm39 \ jkStuff/mm39.5Kgaps.lft -bedFile=jkStuff/mm39.5Kgaps.bed wc -l jkStuff/mm39.5Kgaps* # 176 jkStuff/mm39.5Kgaps.bed # 176 jkStuff/mm39.5Kgaps.lft # to see the gaps used: bedInvert.pl chrom.sizes jkStuff/mm39.5Kgaps.bed \ | cut -f4 | sort -n | uniq -c | less ######################################################################## -# lastz/chain/net swap human/hg38 (TBD - 2020-04-10 - Hiram) - - # original alignment - cd /hive/data/genomes/hg38/bed/lastzMm39.2020-04-02 - - cat fb.hg38.chainMm39Link.txt - # 1549397508 bases of 3110768607 (49.808%) in intersection - cat fb.hg38.chainSynMm39Link.txt - # 1488468205 bases of 3110768607 (47.849%) in intersection - - time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ - hg38 mm39) > rbest.log 2>&1 & - # real 310m32.196s - - cat fb.hg38.chainRBest.Mm39.txt - # 1425406620 bases of 3110768607 (45.822%) in intersection - - # and for the swap: +# lastz/chain/net swap human/hg38 (DONE - 2020-08-18 - Hiram) + + # alignment on hg38: + cd /hive/data/genomes/hg38/bed/lastzMm39.2020-08-17 + sed -e 's/^/ # /;' fb.hg38.chainMm39Link.txt + # 966592868 bases of 3110768607 (31.072%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynMm39Link.txt + # 913448433 bases of 3110768607 (29.364%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainRBest.Mm39.txt + # 891660271 bases of 3110768607 (28.664%) in intersection + + # and the swap mkdir /hive/data/genomes/mm39/bed/blastz.hg38.swap cd /hive/data/genomes/mm39/bed/blastz.hg38.swap - time (doBlastzChainNet.pl -verbose=2 \ - /hive/data/genomes/hg38/bed/lastzMm39.2020-04-02/DEF \ - -swap -chainMinScore=3000 -chainLinearGap=medium \ - -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ - -syntenicNet) > swap.log 2>&1 - # real 99m10.990s + /hive/data/genomes/hg38/bed/lastzMm39.2020-08-17/DEF \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -swap -syntenicNet) > swap.log 2>&1 + # real 47m57.164s - cat fb.mm39.chainHg38Link.txt - # 1493209286 bases of 2481941580 (60.163%) in intersection - cat fb.mm39.chainSynHg38Link.txt - # 1448164376 bases of 2481941580 (58.348%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainHg38Link.txt + # 939000954 bases of 2654624157 (35.372%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainSynHg38Link.txt + # 891050480 bases of 2654624157 (33.566%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ mm39 hg38) > rbest.log 2>&1 & # real 257m59.713s - cat fb.mm39.chainRBest.Hg38.txt - # 1425296830 bases of 2481941580 (57.427%) in intersection - -########################################################################### -# lastz/chain/net swap mouse/mm10 (TBD - 2020-04-20 - Hiram) - - # original alignment - cat fb.mm10.chainMm39Link.txt - # 777883731 bases of 2652783500 (29.323%) in intersection - cat fb.mm10.chainSynMm39Link.txt - # 736602602 bases of 2652783500 (27.767%) in intersection - - time (doRecipBest.pl -load -workhorse=hgwdev mm10 mm39 \ - -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & - # real 219m16.168s - - cat fb.mm10.chainRBest.Mm39.txt - # 741307883 bases of 2652783500 (27.945%) in intersection - - mkdir /hive/data/genomes/mm39/bed/blastz.mm10.swap - cd /hive/data/genomes/mm39/bed/blastz.mm10.swap - time (doBlastzChainNet.pl -verbose=2 \ - /hive/data/genomes/mm10/bed/lastzMm39.2020-04-02/DEF \ - -swap -syntenicNet \ - -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ - -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & - # real 50m20.639s - - cat fb.mm39.chainMm10Link.txt - # 772902855 bases of 2481941580 (31.141%) in intersection - cat fb.mm39.chainSynMm10Link.txt - # 737924732 bases of 2481941580 (29.732%) in intersection - - time (doRecipBest.pl -load -workhorse=hgwdev mm39 mm10 \ - -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & - # real 173m38.016s - - cat fb.mm39.chainRBest.Mm10.txt - # 740357755 bases of 2481941580 (29.830%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainRBest.Hg38.txt + # 893176796 bases of 2654624157 (33.646%) in intersection ############################################################################## # GENBANK AUTO UPDATE (DONE - 2020-07-30 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Mus musculus 581990 4871398 37663 # Mus musculus albula 4 0 0 # Mus musculus bactrianus 4 0 0 # Mus musculus brevirostris 2 0 0 # Mus musculus castaneus 28 2 0 # Mus musculus domesticus 1703 70 0 # Mus musculus kobuvirus 2 0 0 # Mus musculus molossinus 38 0 0 # Mus musculus musculus 71 4 0 # Mus musculus musculus x M. m. castaneus 1 0 0 # Mus musculus papillomavirus type 1 10 0 0 # Mus musculus picornavirus 3 0 0 # Mus musculus wagneri 2 0 0 # edit etc/genbank.conf to add mm39 just after mm10 # mm39 - (house mouse - GCA_000001635.9 - GRCm39) mm39.serverGenome = /hive/data/genomes/mm39/mm39.2bit mm39.ooc = /hive/data/genomes/mm39/jkStuff/mm39.11.ooc mm39.lift = /hive/data/genomes/mm39/jkStuff/mm39.5Kgaps.lft +mm39.perChromTables = no mm39.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} mm39.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} mm39.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} mm39.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} mm39.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} mm39.downloadDir = mm39 mm39.refseq.mrna.xeno.load = yes mm39.refseq.mrna.xeno.loadDesc = yes mm39.genbank.mrna.xeno.load = yes mm39.genbank.mrna.blatTargetDb = yes mm39.upstreamGeneTbl = refGene # mm39.mgc = yes # mm39.orfeome = yes # mm39.ccds.buildId = 21 # mm39.upstreamMaf = multiz60way /hive/data/genomes/mm39/bed/multiz60way/species.list @@ -1143,191 +1107,237 @@ -query2Bit=/hive/data/genomes/mm10/mm10.2bit \ -querySizes=/hive/data/genomes/mm10/chrom.sizes \ -ooc=/hive/data/genomes/mm39/jkStuff/mm39.11.ooc \ mm39 mm10 time (doSameSpeciesLiftOver.pl -verbose=2 \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -query2Bit=/hive/data/genomes/mm10/mm10.2bit \ -querySizes=/hive/data/genomes/mm10/chrom.sizes \ -ooc=/hive/data/genomes/mm39/jkStuff/mm39.11.ooc \ mm39 mm10) > doLiftOverToMm10.log 2>&1 # real 257m18.898s # see if the liftOver menus function in the browser from mm39 to mm10 ############################################################################## -# BLATSERVERS ENTRY (TBD - 2020-04-02 - Hiram) +# BLATSERVERS ENTRY (DONE - 2020-09-10 - Hiram) # After getting a blat server assigned by the Blat Server Gods, ssh hgwdev hgsql -e 'INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ - VALUES ("mm39", "blat1b", "17904", "1", "0"); \ + VALUES ("mm39", "blat1a", "17904", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ - VALUES ("mm39", "blat1b", "17905", "0", "1");' \ + VALUES ("mm39", "blat1a", "17905", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ -## reset default position to gene: CDH2 upon recommendation from Kerstin -## (TBD - 2020-06-22 - Hiram) +## reset default position to same as mm10 default via blat of DNA +## (DONE - 2020-09-10 - Hiram) +chr12:56,741,761-56,761,390 ssh hgwdev - hgsql -e 'update dbDb set defaultPos="chr7:60683331-61003907" + hgsql -e 'update dbDb set defaultPos="chr12:56741761-56761390" where name="mm39";' hgcentraltest ############################################################################## # crispr whole genome (DONE - 2020-07-30 - Hiram) mkdir /hive/data/genomes/mm39/bed/crisprAll cd /hive/data/genomes/mm39/bed/crisprAll # the large shoulder argument will cause the entire genome to be scanned # this takes a while for a new genome to get the bwa indexing done time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 -stop=ranges \ mm39 augustusGene -shoulder=250000000 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) >> ranges.log 2>&1 -XXX - running - Thu Jul 30 10:12:03 PDT 2020 - # real 1m16.539s + # real 62m2.060s - failed on 'genscan' genes + # real 1m16.884s - rerun on 'augustusGene' time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ - -continue=guides -stop=specScores mm39 genscan \ + -continue=guides -stop=specScores mm39 augustusGene \ -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > specScores.log 2>&1 # real 6558m26.295s cat guides/run.time | sed -e 's/^/# /;' # Completed: 100 of 100 jobs -# CPU time in finished jobs: 11979s 199.66m 3.33h 0.14d 0.000 y -# IO & Wait Time: 251s 4.18m 0.07h 0.00d 0.000 y -# Average job time: 122s 2.04m 0.03h 0.00d -# Longest finished job: 289s 4.82m 0.08h 0.00d -# Submission to last job: 303s 5.05m 0.08h 0.00d +# CPU time in finished jobs: 13031s 217.19m 3.62h 0.15d 0.000 y +# IO & Wait Time: 299s 4.98m 0.08h 0.00d 0.000 y +# Average job time: 133s 2.22m 0.04h 0.00d +# Longest finished job: 920s 15.33m 0.26h 0.01d +# Submission to last job: 935s 15.58m 0.26h 0.01d cat specScores/run.time | sed -e 's/^/# /;' -# Completed: 3096565 of 3096565 jobs -# CPU time in finished jobs: 263946983s 4399116.38m 73318.61h 3054.94d 8.370 y -# IO & Wait Time: 17766691s 296111.52m 4935.19h 205.63d 0.563 y -# Average job time: 91s 1.52m 0.03h 0.00d -# Longest finished job: 851s 14.18m 0.24h 0.01d -# Submission to last job: 324649s 5410.82m 90.18h 3.76d +# Completed: 2947790 of 2947790 jobs +# CPU time in finished jobs: 247411142s 4123519.03m 68725.32h 2863.55d 7.845 y +# IO & Wait Time: 0s 0.00m 0.00h 0.00d 0.000 y +# Average job time: 82s 1.37m 0.02h 0.00d +# Longest finished job: 353s 5.88m 0.10h 0.00d +# Submission to last job: 561467s 9357.78m 155.96h 6.50d -# # Number of specScores: 233102255 + +# Number of specScores: 220274834 ### remember to get back to hgwdev to run this time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ - -continue=effScores -stop=load mm39 genscan \ + -continue=effScores -stop=load mm39 augustusGene \ -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > load.log 2>&1 - # real 932m13.229s + # real 1615m13.200s cat effScores/run.time | sed -e 's/^/# /;' -# Completed: 25662 of 25662 jobs -# CPU time in finished jobs: 12763858s 212730.96m 3545.52h 147.73d 0.405 y -# IO & Wait Time: 144123s 2402.05m 40.03h 1.67d 0.005 y -# Average job time: 503s 8.38m 0.14h 0.01d -# Longest finished job: 4091s 68.18m 1.14h 0.05d -# Submission to last job: 15067s 251.12m 4.19h 0.17d +# Completed: 27714 of 27714 jobs +# CPU time in finished jobs: 13108172s 218469.53m 3641.16h 151.71d 0.416 y +# IO & Wait Time: 52457s 874.29m 14.57h 0.61d 0.002 y +# Average job time: 475s 7.91m 0.13h 0.01d +# Longest finished job: 2486s 41.43m 0.69h 0.03d +# Submission to last job: 44334s 738.90m 12.31h 0.51d cat offTargets/run.time | sed -e 's/^/# /;' -# Completed: 154829 of 154829 jobs -# CPU time in finished jobs: 1805712s 30095.20m 501.59h 20.90d 0.057 y -# IO & Wait Time: 3128264s 52137.73m 868.96h 36.21d 0.099 y -# Average job time: 32s 0.53m 0.01h 0.00d -# Longest finished job: 273s 4.55m 0.08h 0.00d -# Submission to last job: 5337s 88.95m 1.48h 0.06d +# Completed: 147390 of 147390 jobs +# CPU time in finished jobs: 2280286s 38004.77m 633.41h 26.39d 0.072 y +# IO & Wait Time: 505943s 8432.38m 140.54h 5.86d 0.016 y +# Average job time: 19s 0.32m 0.01h 0.00d +# Longest finished job: 36s 0.60m 0.01h 0.00d +# Submission to last job: 13489s 224.82m 3.75h 0.16d + + bigBedInfo crispr.bb | sed -e 's/^/# /;' +# version: 4 +# fieldCount: 22 +# hasHeaderExtension: yes +# isCompressed: yes +# isSwapped: 0 +# extraIndexCount: 0 +# itemCount: 276,331,386 +# primaryDataSize: 12,229,621,910 +# primaryIndexSize: 17,345,476 +# zoomLevels: 10 +# chromCount: 33 +# basesCovered: 2,179,930,088 +# meanDepth (of bases covered): 2.915516 +# minDepth: 1.000000 +# maxDepth: 32.000000 +# std of depth: 1.944181 ######################################################################### # all.joiner update, downloads and in pushQ - (WORKING - 2019-11-20 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # verify all the business is done for release ~/kent/src/hg/utils/automation/verifyBrowser.pl mm39 -# 66 tables in database mm39 - Dog, Canis lupus familiaris -# verified 55 tables in database mm39, 11 extra tables, 14 optional tables +# 65 tables in database mm39 - Mouse, Mus musculus +# verified 45 tables in database mm39, 20 extra tables, 8 optional tables # chainNetRBestHg38 3 optional tables -# chainNetRBestMm10 3 optional tables # chainNetSynHg38 3 optional tables -# chainNetSynMm10 3 optional tables # gapOverlap 1 optional tables # tandemDups 1 optional tables -# 1 chainCanFam3 - extra table -# 2 chainCanFam3Link - extra table -# 3 chainRBestCanFam3 - extra table -# 4 chainRBestCanFam3Link - extra table +# 1 chainCalJac4 - extra table +# 2 chainCalJac4Link - extra table +# 3 chainCanFam5 - extra table +# 4 chainCanFam5Link - extra table # . . . etc . . . -# 8 crisprAllTargets - extra table -# 9 netCanFam3 - extra table -# 10 netRBestCanFam3 - extra table -# 11 netSynCanFam3 - extra table -# 13 genbank tables found -# verified 28 required tables, 1 missing tables -# 1 ucscToRefSeq - missing table +# 17 netRBestCalJac4 - extra table +# 18 netRBestCanFam5 - extra table +# 19 netSynCalJac4 - extra table +# 20 netSynCanFam5 - extra table +# 12 genbank tables found +# verified 25 required tables, 4 missing tables +# 1 chainMm10 - missing table +# 2 chainMm10Link - missing table +# 3 netMm10 - missing table +# 4 ucscToRefSeq - missing table +# missing mm10.chainMm39 +# missing mm10.chainMm39Link +# missing mm10.netMm39 # hg38 chainNet to mm39 found 3 required tables -# mm10 chainNet to mm39 found 3 required tables # hg38 chainNet RBest and syntenic to mm39 found 6 optional tables -# mm10 chainNet RBest and syntenic to mm39 found 3 optional tables # liftOver to previous versions: 1, from previous versions: 1 +# blatServers: mm39 blat1a 17905 0 1 mm39 blat1a 17904 1 0 # fixup all.joiner until this is a clean output joinerCheck -database=mm39 -tableCoverage all.joiner joinerCheck -database=mm39 -times all.joiner joinerCheck -database=mm39 -keys all.joiner # when clean, check in: git commit -m 'adding rules for mm39 refs #22271' all.joiner git push # run up a 'make alpha' in hg/hgTables to get this all.joiner file # into the hgwdev/genome-test system cd /hive/data/genomes/mm39 - time (makeDownloads.pl mm39) > downloads.log 2>&1 + time (makeDownloads.pl -noChromFiles mm39) > downloads.log 2>&1 # real 16m11.233s + # going to make a chromosomes directory and perChrom tar image to + # be compatible with mm10 + mkdir /hive/data/genomes/mm39/goldenPath/chromosomes + cd /hive/data/genomes/mm39/goldenPath/chromosomes + time zcat ../bigZips/mm39.fa.gz | faSplit byname stdin ./ + # real 0m28.876s + tar tar cvzf ../bigZips/mm39.chromFa.tar.gz *.fa + time gzip *.fa + # real 9m17.575s + time md5sum *.fa.gz > md5sum.txt + # real 0m4.835s + # add a README.txt file to this directory, copy from mm10 + mkdir /usr/local/apache/htdocs-hgdownload/goldenPath/mm39/chromosomes + ln -s `pwd`/* \ + /usr/local/apache/htdocs-hgdownload/goldenPath/mm39/chromosomes/ + cd ../bigZips + ln -s `pwd`/mm39.chromFa.tar.gz \ + /usr/local/apache/htdocs-hgdownload/goldenPath/mm39/bigZips/ + + + + cd .. + md5sum mm39.chromFa.tar.gz >> md5sum.txt + # add comments about these items to README.txt # now ready for pushQ entry mkdir /hive/data/genomes/mm39/pushQ cd /hive/data/genomes/mm39/pushQ time ($HOME/kent/src/hg/utils/automation/makePushQSql.pl -redmineList mm39) > mm39.pushQ.sql 2> stderr.out - # real 15m2.385s + # real 10m44.233s # remove the tandemDups and gapOverlap from the file list: sed -i -e "/tandemDups/d" redmine.mm39.table.list sed -i -e "/Tandem Dups/d" redmine.mm39.releaseLog.txt sed -i -e "/gapOverlap/d" redmine.mm39.table.list sed -i -e "/Gap Overlaps/d" redmine.mm39.releaseLog.txt # check for errors in stderr.out, some are OK, e.g.: # WARNING: mm39 does not have ucscToRefSeq # WARNING: hgwdev does not have /gbdb/mm39/ncbiRefSeq/ncbiRefSeqVersion.txt # WARNING: hgwdev does not have /gbdb/mm39/ncbiRefSeq/ncbiRefSeqOther.bb # WARNING: hgwdev does not have /gbdb/mm39/ncbiRefSeq/ncbiRefSeqOther.ix # WARNING: hgwdev does not have /gbdb/mm39/ncbiRefSeq/ncbiRefSeqOther.ixx # WARNING: hgwdev does not have /gbdb/mm39/ncbiRefSeq/seqNcbiRefSeq.rna.fa # WARNING: mm39 does not have seq # WARNING: mm39 does not have extFile # verify the file list does correctly match to files cat redmine.mm39.file.list | while read L do eval ls $L > /dev/null done # should be silent, missing files will show as errors # verify database tables, how many to expect: wc -l redmine.mm39.table.list - # 52 redmine.mm39.table.list + # 45 redmine.mm39.table.list - # how many actual: awk -F'.' '{printf "hgsql -N %s -e '"'"'show table status like \"%s\";'"'"'\n", $1, $2}' redmine.mm39.table.list | sh | wc -l - # 52 + # 45 # would be a smaller number actual if some were missing # add the path names to the listing files in the redmine issue # in the three appropriate entry boxes: # /hive/data/genomes/mm39/pushQ/redmine.mm39.file.list # /hive/data/genomes/mm39/pushQ/redmine.mm39.releaseLog.txt # /hive/data/genomes/mm39/pushQ/redmine.mm39.table.list #########################################################################