180734e3da31c25fecc1583231a29885abc1d18b hiram Thu Sep 17 12:00:59 2020 -0700 pretty close to done refs #24074 diff --git src/hg/makeDb/doc/calJac4/initialBuild.txt src/hg/makeDb/doc/calJac4/initialBuild.txt index a5f59e7..6944e16 100644 --- src/hg/makeDb/doc/calJac4/initialBuild.txt +++ src/hg/makeDb/doc/calJac4/initialBuild.txt @@ -118,30 +118,42 @@ refseq/*_assembly_report.txt > calJac4.config.ra # fix commonName: commonName White-tufted-ear marmoset to: commonName Marmoset # fix orderKey: orderKey 23305 to orderKey 13093 # fix bioSample: ncbiBioSample notFound to ncbiBioSample SAMN12783337 +Should have fixed the commonName from: +commonName White-tufted-ear marmoset +to +commonName Marmoset + +To make it match the other calJac assemblies. To fix later: + +hgsql -e 'select genome from dbDb where name="calJac4";' hgcentraltest +hgsql -e 'update dbDb set genome="Marmoset" where name="calJac4";' hgcentraltest +hgsql -e 'select genome from dbDb where name="calJac4";' hgcentraltest + + # see also: https://www.ncbi.nlm.nih.gov/biosample/?term=SAMN12783337 # compare with previous version to see if it is sane: diff calJac4.config.ra ../calJac3/calJac3.config.ra # verify it really does look sane cat calJac4.config.ra # config parameters for makeGenomeDb.pl: db calJac4 clade mammal genomeCladePriority 35 scientificName Callithrix jacchus commonName White-tufted-ear marmoset assemblyDate May 2020 assemblyLabel McDonnell Genome Institute at Washington University @@ -301,46 +313,30 @@ # Q3 55834.000000 # average 100548.682540 # min 13.000000 # max 1000000.000000 # count 378 # total 38007402.000000 # standard deviation 237103.349286 # the 2bit sequence has 2 more gaps and 41 more bases in gap: # count 380 # total 38007443.000000 # the gaps file defined 1 more gap at 40 bases: # count 379 # total 38007442.000000 -XXX - TBD - Wed Sep 2 07:44:09 PDT 2020 - - # survey gap types from gap file - # the gaps file defines 23 more gaps than the AGP files, - # the gaps file defines 13 more gaps but 54 less bases than the sequence - # note the 'unknown' types (== 23 gaps) - zgrep -v "^#" ../refseq/*gaps* | cut -f5,6 | sort | uniq -c \ - | sed -e 's/^/# /;' -# 15 between_scaffolds na -# 22 centromere na -# 1 unknown inferred_from_sequence -# 341 within_scaffold map - - # the single 'unknown' gap is the 40 base gap that is not in the AGP files - zgrep "unknown" ../refseq/*gaps* - # NC_048406.1 8006927 8006966 40 unknown inferred_from_sequence # survey of AGP types of gaps: # beware, can also be type U in col 5, doesn't happen here: awk '$5 == "U"' *.agp (no output) awk '$5 == "N"' *.agp | awk '{print $7,$NF}' | sort | uniq -c \ | sed -e 's/^/# /;' # 22 centromere na # 15 contig na # 341 scaffold map # name equivalences in the assembly_report file: grep -v "^#" \ ../refseq/G*_1.1_assembly_report.txt \ | awk '{printf "%s\t%s\n", $1,$5}' | sort > ncbi.assembly.genbank.equivalence grep -v "^#" \ @@ -364,140 +360,119 @@ # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db calJac4.config.ra) > db.log 2>&1 # real 15m10.248s # check in the trackDb files created in TemporaryTrackDbCheckout/ # and add calJac4 to trackDb/makefile refs #24074 # fixing up the images reference to calJac4.jpg # temporary symlink until masked sequence is available cd /hive/data/genomes/calJac4 ln -s `pwd`/calJac4.unmasked.2bit /gbdb/calJac4/calJac4.2bit ############################################################################# -# verify gap table vs NCBI gap file (TBD - 2020-07-27 - Hiram) +# verify gap table vs NCBI gap file (DONE - 2020-09-17 - Hiram) mkdir /hive/data/genomes/calJac4/bed/gap cd /hive/data/genomes/calJac4/bed/gap zgrep -v "^#" ../../refseq/G*_gaps.txt.gz \ | awk '{printf "%s\t%d\t%d\t%s_%s\n", $1,$2-1,$3,$5,$6}' \ | sort -k1,1 -k2,2n > refseq.gap.bed # type survey: cut -f4 *.bed | sort | uniq -c | sed -e 's/^/# /;' -# 60 between_scaffolds_na -# 20 centromere_na -# 21 short_arm_na -# 42 telomere_na -# 4 unknown_inferred_from_sequence -# 19 unknown_unspecified -# 5 within_scaffold_align_genus -# 36 within_scaffold_map -# 96 within_scaffold_paired-ends -# 44 within_scaffold_unspecified +# 15 between_scaffolds_na +# 22 centromere_na +# 1 unknown_inferred_from_sequence +# 341 within_scaffold_map + # how much defined by NCBI: awk '{print $3-$2}' *.bed | ave stdin | grep -w total - # total 73600614.000000 + # total 38007442.000000 # how much in the gap table: hgsql -e 'select * from gap;' calJac4 | awk '{print $4-$3}' \ | ave stdin | grep -w total - # total 73598294.000000 - - # an extra 2320 bases marked in the gap file - # Compare to mm10: - hgsql -e 'select * from gap;' mm10 | awk '{print $4-$3}' \ - | ave stdin | sed -e 's/^/# /;' -# Q1 100.000000 -# median 838.000000 -# Q3 50000.000000 -# average 113665.609898 -# min 0.000000 -# max 2890000.000000 -# count 687 -# total 78088274.000000 -# standard deviation 485103.795880 + # total 38007402.000000 - hgsql -e 'select * from gap;' calJac4 | awk '{print $4-$3}' \ - | ave stdin | sed -e 's/^/# /;' -# Q1 1357.000000 -# median 50000.000000 -# Q3 100000.000000 -# average 226456.289231 -# min 0.000000 -# max 2890000.000000 -# count 325 -# total 73598294.000000 -# standard deviation 687212.981441 + # gap table type survey: + hgsql -N -e 'select type from gap;' calJac4 \ + | sort | uniq -c | sed -e 's/^/ #/;' + # 22 centromere + # 15 contig + # 341 scaffold + # the one extra definition at 40 bases in the NCBI gap file is the unknown: + grep unknown *.bed + # NC_048406.1 8006926 8006966 unknown_inferred_from_sequence ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/cpgIslandsUnmasked cd /hive/data/genomes/calJac4/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/calJac4/calJac4.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku calJac4) > do.log 2>&1 -XXX - running - Wed Sep 2 10:08:50 PDT 2020 - # real 3m30.591s + # real 3m43.555s cat fb.calJac4.cpgIslandExtUnmasked.txt - # 56535294 bases of 2481941580 (2.278%) in intersection + # 26183576 bases of 2859817025 (0.916%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/cytoBand cd /hive/data/genomes/calJac4/bed/cytoBand makeCytoBandIdeo.csh calJac4 ############################################################################# # run up idKeys files for chromAlias/ncbiRefSeq (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/idKeys cd /hive/data/genomes/calJac4/bed/idKeys time (doIdKeys.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit \ -buildDir=`pwd` calJac4) > do.log 2>&1 & # real 1m55.340s cat calJac4.keySignature.txt # 01e329dd4e2641908a563b4ff1c8b648 ############################################################################# # gapOverlap (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/gapOverlap cd /hive/data/genomes/calJac4/bed/gapOverlap time (doGapOverlap.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4 ) \ > do.log 2>&1 & - # XXX empty result ?? did it run in 54 seconds ? # real 0m54.302s - # there is one only: - wc -l bed.tab - # 1 bed.tab - cut -f2- bed.tab -chr6 47663669 47714277 chr6:47663670-47714277 304 + 47663669 47714277 0 2 304,304 0,50304 + # there were not very many gaps, it only had to do one job and blat + # found nothing. + # this result does not exist: cat fb.calJac4.gapOverlap.txt # 608 bases of 2728222451 (0.000%) in intersection + # manually finish off since it quit in the load step + doGapOverlap.pl -continue=cleanup \ + -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4 + ############################################################################# # tandemDups (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/tandemDups cd /hive/data/genomes/calJac4/bed/tandemDups time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4) \ > do.log 2>&1 & # real 193m21.761s cat fb.calJac4.tandemDups.txt # 80358205 bases of 2897824427 (2.773%) in intersection bigBedInfo calJac4.tandemDups.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 13 @@ -812,51 +787,53 @@ mkdir /hive/data/genomes/calJac4/bed/cpgIslands cd /hive/data/genomes/calJac4/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku calJac4) > do.log 2>&1 # real 3m28.053s cat fb.calJac4.cpgIslandExt.txt # 10571422 bases of 2654624157 (0.398%) in intersection ############################################################################## # genscan - (DONE - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/genscan cd /hive/data/genomes/calJac4/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku calJac4) > do.log 2>&1 -XXX - running - Thu Sep 3 11:46:01 PDT 2020 - # real 8m19.775s + # real 73m39.179s - # one job broken: -./runGsBig2M.csh chr10 000 gtf/000/chr10.gtf pep/000/chr10.pep subopt/000/chr10.bed - # real 34m35.712s + # two jobs broken: +./runGsBig2M.csh chr22 000 gtf/000/chr22.gtf pep/000/chr22.pep subopt/000/chr22.bed & +./runGsBig2M.csh chr4 000 gtf/000/chr4.gtf pep/000/chr4.pep subopt/000/chr4.bed +wait + # real 56m30.462s # continuing time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -continue=makeBed -bigClusterHub=ku calJac4) > makeBed.log 2>&1 - # real 0m45.365s + # real 1m1.807s cat fb.calJac4.genscan.txt - # 55445747 bases of 2654624157 (2.089%) in intersection + # 56416049 bases of 2859817025 (1.973%) in intersection cat fb.calJac4.genscanSubopt.txt - # 57607700 bases of 2654624157 (2.170%) in intersection + # 54809849 bases of 2859817025 (1.917%) in intersection ######################################################################### # ncbiGene (TBD - 2020-09-03 - Hiram) + # don't need to do this on GCF/RefSeq assemblies, they have RefSeq genes mkdir /hive/data/genomes/calJac4/bed/xenoRefGene cd /hive/data/genomes/calJac4/bed/xenoRefGene time (~/kent/src/hg/utils/automation/doXenoRefGene.pl -buildDir=`pwd` \ -bigClusterHub=ku -workhorse=hgwdev -dbHost=hgwdev calJac4) > do.log 2>&1 & # real 67m18.015s ######################################################################### # Create kluster run files (DONE - 2020-09-03 - Hiram) # numerator is calJac4 gapless bases "real" as reported by: featureBits -noRandom -noHap calJac4 gap # 36757259 bases of 2793460667 (1.316%) in intersection # ^^^ @@ -904,106 +881,99 @@ # forget the non-bridged of size 100, use 50,000 and allow bridged # use gap size of 50000 to construct a lift file: gapToLift -allowBridged -verbose=2 -minGap=50000 calJac4 \ jkStuff/calJac4.gaps.lft -bedFile=jkStuff/calJac4.gaps.bed wc -l jkStuff/calJac4.gaps*. # 1073 jkStuff/calJac4.gaps.bed # 1073 jkStuff/calJac4.gaps.lft # to see the gaps sizes used: bedInvert.pl chrom.sizes jkStuff/calJac4.gaps.bed \ | cut -f4 | sort -n | uniq -c | less ######################################################################## -# lastz/chain/net swap human/hg38 (TBD - 2020-04-10 - Hiram) +# lastz/chain/net swap human/hg38 (DONE - 2020-04-10 - Hiram) # original alignment - cd /hive/data/genomes/hg38/bed/lastzCalJac4.2020-04-02 + cd /hive/data/genomes/hg38/bed/lastzCalJac4.2020-08-03 cat fb.hg38.chainCalJac4Link.txt - # 1549397508 bases of 3110768607 (49.808%) in intersection + # 2338614467 bases of 3110768607 (75.178%) in intersection cat fb.hg38.chainSynCalJac4Link.txt - # 1488468205 bases of 3110768607 (47.849%) in intersection - - time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ - hg38 calJac4) > rbest.log 2>&1 & - # real 310m32.196s - + # 2261509186 bases of 3110768607 (72.699%) in intersection cat fb.hg38.chainRBest.CalJac4.txt - # 1425406620 bases of 3110768607 (45.822%) in intersection + # 2146650109 bases of 3110768607 (69.007%) in intersection # and for the swap: mkdir /hive/data/genomes/calJac4/bed/blastz.hg38.swap cd /hive/data/genomes/calJac4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ - /hive/data/genomes/hg38/bed/lastzCalJac4.2020-04-02/DEF \ + /hive/data/genomes/hg38/bed/lastzCalJac4.2020-08-03/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 - # real 99m10.990s + # real 105m30.938s cat fb.calJac4.chainHg38Link.txt - # 1493209286 bases of 2481941580 (60.163%) in intersection + # 2256668215 bases of 2859817025 (78.910%) in intersection cat fb.calJac4.chainSynHg38Link.txt - # 1448164376 bases of 2481941580 (58.348%) in intersection + # 2183912419 bases of 2859817025 (76.365%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ calJac4 hg38) > rbest.log 2>&1 & - # real 257m59.713s + # real 467m22.590s cat fb.calJac4.chainRBest.Hg38.txt - # 1425296830 bases of 2481941580 (57.427%) in intersection + # 2147250913 bases of 2859817025 (75.084%) in intersection -########################################################################### -# lastz/chain/net swap mouse/mm10 (TBD - 2020-04-20 - Hiram) +############################################################################ +# lastz/chain/net swap mouse/mm10 (DONE - 2020-08-03 - Hiram) # original alignment + cd /hive/data/genomes/mm10/bed/lastzCalJac4.2020-08-03 + cat fb.mm10.chainCalJac4Link.txt - # 777883731 bases of 2652783500 (29.323%) in intersection + # 877278264 bases of 2652783500 (33.070%) in intersection cat fb.mm10.chainSynCalJac4Link.txt - # 736602602 bases of 2652783500 (27.767%) in intersection - - time (doRecipBest.pl -load -workhorse=hgwdev mm10 calJac4 \ - -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & - # real 219m16.168s - + # 830868888 bases of 2652783500 (31.321%) in intersection cat fb.mm10.chainRBest.CalJac4.txt - # 741307883 bases of 2652783500 (27.945%) in intersection + # 835445771 bases of 2652783500 (31.493%) in intersection mkdir /hive/data/genomes/calJac4/bed/blastz.mm10.swap cd /hive/data/genomes/calJac4/bed/blastz.mm10.swap + time (doBlastzChainNet.pl -verbose=2 \ - /hive/data/genomes/mm10/bed/lastzCalJac4.2020-04-02/DEF \ + /hive/data/genomes/mm10/bed/lastzCalJac4.2020-08-03/DEF \ -swap -syntenicNet \ - -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & - # real 50m20.639s + # real 51m16.400s cat fb.calJac4.chainMm10Link.txt - # 772902855 bases of 2481941580 (31.141%) in intersection + # 882506277 bases of 2859817025 (30.859%) in intersection cat fb.calJac4.chainSynMm10Link.txt - # 737924732 bases of 2481941580 (29.732%) in intersection + # 831171319 bases of 2859817025 (29.064%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev calJac4 mm10 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & - # real 173m38.016s + # real 308m53.845s cat fb.calJac4.chainRBest.Mm10.txt - # 740357755 bases of 2481941580 (29.830%) in intersection + # 833789913 bases of 2859817025 (29.155%) in intersection ############################################################################## # GENBANK AUTO UPDATE (DONE - 2020-09-03 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Callithrix geoffroyi 7 0 0 # Callithrix jacchus 1607 292992 221 # Callithrix kuhlii 1 0 0 # Callithrix penicillata 1 0 0 # Callithrix pygmaea 5 0 0 # Callithrix sp. 4 0 0 @@ -1041,213 +1011,188 @@ make etc-update # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add calJac4 to: # etc/hgwdev.dbs etc/align.dbs git commit -m "Added calJac4 - marmoset refs #24074" etc/hgwdev.dbs etc/align.dbs git push make etc-update # wait a few days for genbank magic to take place, the tracks will # appear ############################################################################# -# augustus gene track (TBD - 2020-09-03 - Hiram) +# augustus gene track (DONE - 2020-09-04 - Hiram) mkdir /hive/data/genomes/calJac4/bed/augustus cd /hive/data/genomes/calJac4/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev calJac4) > do.log 2>&1 - # real 119m8.866s + # real 119m49.652s cat fb.calJac4.augustusGene.txt - # 49120541 bases of 2654624157 (1.850%) in intersection + # 56033149 bases of 2859817025 (1.959%) in intersection ######################################################################### -# ncbiRefSeq (TBD - 2019-11-20 - Hiram) - ### XXX ### Not available on GCA/genbank assemblies +# ncbiRefSeq (DONE - 2020-09-17 - Hiram) mkdir /hive/data/genomes/calJac4/bed/ncbiRefSeq cd /hive/data/genomes/calJac4/bed/ncbiRefSeq - # running step wise just to be careful - time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ - -bigClusterHub=ku -dbHost=hgwdev \ - -stop=download -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ - refseq vertebrate_mammalian Gorilla_gorilla \ - GCA_008122165.1_Kamilah_GGO_v0 calJac4) > download.log 2>&1 - # real 1m37.523s - - time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ - -continue=process -bigClusterHub=ku -dbHost=hgwdev \ - -stop=process -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ - refseq vertebrate_mammalian Gorilla_gorilla \ - GCF_008122165.1_Kamilah_GGO_v0 calJac4) > process.log 2>&1 - # real 2m9.450s time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ - -continue=load -bigClusterHub=ku -dbHost=hgwdev \ - -stop=load -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ - refseq vertebrate_mammalian Gorilla_gorilla \ - GCF_008122165.1_Kamilah_GGO_v0 calJac4) > load.log 2>&1 - # real 0m21.982s + -bigClusterHub=ku -dbHost=hgwdev \ + -fileServer=hgwdev -smallClusterHub=hgwdev -workhorse=hgwdev \ + GCF_009663435.1_Callithrix_jacchus_cj1700_1.1 calJac4) > do.log 2>&1 & cat fb.ncbiRefSeq.calJac4.txt - # 74279781 bases of 2999027915 (2.477%) in intersection + # 102754440 bases of 2859817025 (3.593%) in intersection - # add: include ../../refSeqComposite.ra alpha - # to the gorilla/calJac4/trackDb.ra to turn on the track in the browser + # add: include ../../refSeqComposite.ra + # to the marmoset/calJac4/trackDb.ra to turn on the track in the browser - # XXX 2019-11-20 - ready for this after genbank runs + # XXX 2020-09-17 - ready for this after genbank runs featureBits -enrichment calJac4 refGene ncbiRefSeq # refGene 0.402%, ncbiRefSeq 3.148%, both 0.402%, cover 99.90%, enrich 31.73x featureBits -enrichment calJac4 ncbiRefSeq refGene # ncbiRefSeq 3.148%, refGene 0.402%, both 0.402%, cover 12.76%, enrich 31.73x featureBits -enrichment calJac4 ncbiRefSeqCurated refGene # ncbiRefSeqCurated 0.401%, refGene 0.402%, both 0.400%, cover 99.66%, enrich 247.79x featureBits -enrichment calJac4 refGene ncbiRefSeqCurated # refGene 0.402%, ncbiRefSeqCurated 0.401%, both 0.400%, cover 99.33%, enrich 247.79x ############################################################################## -# LIFTOVER TO mm10 (TBD - 2020-09-03 - Hiram) +# LIFTOVER TO calJac3 (DONE - 2020-09-04 - Hiram) ssh hgwdev - mkdir /hive/data/genomes/calJac4/bed/blat.mm10.2020-09-03 - cd /hive/data/genomes/calJac4/bed/blat.mm10.2020-09-03 + mkdir /hive/data/genomes/calJac4/bed/blat.calJac3.2020-09-04 + cd /hive/data/genomes/calJac4/bed/blat.calJac3.2020-09-04 doSameSpeciesLiftOver.pl -verbose=2 \ -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ - -query2Bit=/hive/data/genomes/mm10/mm10.2bit \ - -querySizes=/hive/data/genomes/mm10/chrom.sizes \ + -query2Bit=/hive/data/genomes/calJac3/calJac3.2bit \ + -querySizes=/hive/data/genomes/calJac3/chrom.sizes \ -ooc=/hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc \ - calJac4 mm10 + calJac4 calJac3 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 \ + -query2Bit=/hive/data/genomes/calJac3/calJac3.2bit \ + -querySizes=/hive/data/genomes/calJac3/chrom.sizes \ -ooc=/hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc \ - calJac4 mm10) > doLiftOverToMm10.log 2>&1 - # real 257m18.898s + calJac4 calJac3) > doLiftOverToCalJac4.log 2>&1 + # real 248m51.413s - # see if the liftOver menus function in the browser from calJac4 to mm10 + # see if the liftOver menus function in the browser from calJac4 to calJac3 ############################################################################## -# BLATSERVERS ENTRY (TBD - 2020-04-02 - Hiram) -# request sent 2020-08-17 +# BLATSERVERS ENTRY (DONE - 2020-09-04 - 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 ("calJac4", "blat1b", "17904", "1", "0"); \ + VALUES ("calJac4", "blat1a", "17902", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ - VALUES ("calJac4", "blat1b", "17905", "0", "1");' \ + VALUES ("calJac4", "blat1a", "17903", "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 calJac3 via blat of the protein from there +## (DONE - 2020-09-17 - Hiram) ssh hgwdev - hgsql -e 'update dbDb set defaultPos="chr7:60683331-61003907" + hgsql -e 'update dbDb set defaultPos="chr15:67061035-67077513" where name="calJac4";' hgcentraltest ############################################################################## -# crispr whole genome (TBD - 2020-09-03 - Hiram) +# crispr whole genome (DONE - 2020-09-04 -> 2020-09-10 - Hiram) mkdir /hive/data/genomes/calJac4/bed/crisprAll cd /hive/data/genomes/calJac4/bed/crisprAll + # need to have augustus genes done. This will not work with genscan + # 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 \ calJac4 augustusGene -shoulder=250000000 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) >> ranges.log 2>&1 - # real 62m2.060s - failed on 'genscan' genes - # real 1m16.884s - rerun on 'augustusGene' + # real 73m51.391s time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ - -continue=guides -stop=specScores calJac4 augustusGene \ + -continue=guides -stop=load calJac4 augustusGene \ -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > specScores.log 2>&1 - # real 6558m26.295s + # real 7968m4.344s cat guides/run.time | sed -e 's/^/# /;' # Completed: 100 of 100 jobs -# 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 +# CPU time in finished jobs: 12157s 202.62m 3.38h 0.14d 0.000 y +# IO & Wait Time: 252s 4.20m 0.07h 0.00d 0.000 y +# Average job time: 124s 2.07m 0.03h 0.00d +# Longest finished job: 505s 8.42m 0.14h 0.01d +# Submission to last job: 517s 8.62m 0.14h 0.01d cat specScores/run.time | sed -e 's/^/# /;' -# 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 +# Completed: 3085907 of 3085907 jobs +# CPU time in finished jobs: 294759806s 4912663.43m 81877.72h 3411.57d 9.347 y +# IO & Wait Time: 6938403s 115640.05m 1927.33h 80.31d 0.220 y +# Average job time: 98s 1.63m 0.03h 0.00d +# Longest finished job: 372s 6.20m 0.10h 0.00d +# Submission to last job: 324356s 5405.93m 90.10h 3.75d - -# 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 calJac4 augustusGene \ - -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ - -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ - -workhorse=hgwdev) > load.log 2>&1 - # real 1615m13.200s + grep "Number of specScores" specScores.log +# Number of specScores: 230996937 cat effScores/run.time | sed -e 's/^/# /;' -# 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 +# Completed: 28837 of 28837 jobs +# CPU time in finished jobs: 14627399s 243789.98m 4063.17h 169.30d 0.464 y +# IO & Wait Time: 527816s 8796.94m 146.62h 6.11d 0.017 y +# Average job time: 526s 8.76m 0.15h 0.01d +# Longest finished job: 1466s 24.43m 0.41h 0.02d +# Submission to last job: 32001s 533.35m 8.89h 0.37d cat offTargets/run.time | sed -e 's/^/# /;' -# 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 +# Completed: 154296 of 154296 jobs +# CPU time in finished jobs: 2640432s 44007.20m 733.45h 30.56d 0.084 y +# IO & Wait Time: 986281s 16438.02m 273.97h 11.42d 0.031 y +# Average job time: 24s 0.39m 0.01h 0.00d +# Longest finished job: 49s 0.82m 0.01h 0.00d +# Submission to last job: 12302s 205.03m 3.42h 0.14d 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 +# itemCount: 287,101,022 +# primaryDataSize: 12,714,904,685 +# primaryIndexSize: 18,017,884 # zoomLevels: 10 -# chromCount: 33 -# basesCovered: 2,179,930,088 -# meanDepth (of bases covered): 2.915516 +# chromCount: 34 +# basesCovered: 2,272,744,456 +# meanDepth (of bases covered): 2.905440 # minDepth: 1.000000 -# maxDepth: 32.000000 -# std of depth: 1.944181 +# maxDepth: 29.000000 +# std of depth: 1.956870 ######################################################################### # 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 calJac4 # 66 tables in database calJac4 - Dog, Canis lupus familiaris # verified 55 tables in database calJac4, 11 extra tables, 14 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