f630e910fa3bf0edff8347bd8c914606318c041e hiram Mon Sep 9 10:02:02 2019 -0700 liftOver to rheMac10 refs #23771 diff --git src/hg/makeDb/doc/rheMac8/initialBuild.txt src/hg/makeDb/doc/rheMac8/initialBuild.txt index cea828b..84ffd60 100644 --- src/hg/makeDb/doc/rheMac8/initialBuild.txt +++ src/hg/makeDb/doc/rheMac8/initialBuild.txt @@ -1,570 +1,588 @@ # for emacs: -*- mode: sh; -*- # This file describes browser build for the rheMac8 # Rhesus - Macaca mulatta # Assembly Name: Mmul_8.0.1 # Organism name: Macaca mulatta # Taxid: 9544 # Submitter: Baylor College of Medicine Genome Sequencing Center # Date: 2015-11-30 # BioSample: SAMN02981228 # Assembly type: haploid # Release type: major # Assembly level: Chromosome # Genome representation: full # GenBank Assembly Accession: GCA_000772875.3 (latest) # RefSeq Assembly Accession: GCF_000772875.2 (species-representative latest) # RefSeq Assembly and GenBank Assemblies Identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000772885.3 GCF_000772885.2 Primary Assembly ## GCF_000005875.1 non-nuclear ############################################################################# # fetch sequence from new style download directory (DONE - 2016-01-08 - Hiram) mkdir -p /hive/data/genomes/rheMac8/refseq cd /hive/data/genomes/rheMac8/refseq export asmName="GCF_000772875.2_Mmul_8.0.1" export asmType="refseq" export D="vertebrate_mammalian/Macaca_mulatta/latest_assembly_versions/${asmName}" rsync -a -P -L \ rsync://ftp.ncbi.nlm.nih.gov/genomes/${asmType}/${D}/ ./ # measure what we have here: faSize *genomic.fna.gz # 3236224332 bases (94132579 N's 3142091753 real 1857179349 upper # 1284912404 lower) in 284728 sequences in 1 files # Total size: mean 11366.0 sd 1223261.8 min 116 (NW_014950235.1) # max 225584828 (NC_027893.1) median 941 # %39.70 masked total, %40.89 masked real # check for duplicate sequences: mkdir /hive/data/genomes/rheMac8/ucsc cd /hive/data/genomes/rheMac8/ucsc faToTwoBit ../refseq/GCF_000772875.2_Mmul_8.0.1_genomic.fna.gz refseq.2bit # real 1m32.684s twoBitDup refseq.2bit # no output is a good result rm refseq.2bit ############################################################################# # fixup to UCSC naming scheme (DONE - 2016-01-29 - Hiram) mkdir /hive/data/genomes/rheMac8/ucsc cd /hive/data/genomes/rheMac8/ucsc time ~/kent/src/hg/utils/automation/ucscCompositeAgp.pl \ ../refseq/*_assembly_structure/Primary_Assembly NC_027904.1 12 NC_027902.1 10 NC_027913.1 X NC_027897.1 5 NC_027903.1 11 NC_027896.1 4 NC_027901.1 9 NC_027912.1 20 NC_027898.1 6 NC_027899.1 7 NC_027905.1 13 NC_027907.1 15 NC_027911.1 19 NC_027906.1 14 NC_027914.1 Y NC_027910.1 18 NC_027909.1 17 NC_027908.1 16 NC_027900.1 8 NC_027895.1 3 NC_027894.1 2 NC_027893.1 1 real 0m42.032s time ~/kent/src/hg/utils/automation/unplacedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # real 0m8.257s zcat \ ../refseq/*_assembly_structure/non-nuclear/assem*/AGP/chrMT.comp.agp.gz \ | grep -v "^#" | sed -e 's/^NC_005943.1/chrM/;' > chrM.agp zcat ../refseq/*_assembly_structure/non-nuclear/assem*/FASTA/*.fna.gz \ | sed -e 's/^>.*/>chrM/;' > chrM.fa # verify nothing lost compared to genbank: faSize *.fa # 3236224332 bases (94132579 N's 3142091753 real 3142091753 upper # 0 lower) in 284728 sequences in 24 files # Total size: mean 11366.0 sd 1223261.8 min 116 (chrUn_NW_014950235v1) # max 225584828 (chr1) median 941 # %0.00 masked total, %0.00 masked real # same totals as above: (except for masking) # 3236224332 bases (94132579 N's 3142091753 real 1857179349 upper # 1284912404 lower) in 284728 sequences in 1 files ############################################################################# # Initial database build (DONE - 2016-01-29 - Hiram) cd /hive/data/genomes/rheMac8 printf "%s" \ # Config parameters for makeGenomeDb.pl: db rheMac8 clade primate genomeCladePriority 15 scientificName Macaca mulatta commonName rhesus assemblyDate Nov. 2015 assemblyLabel Baylor College of Medicine Genome Sequencing Center assemblyShortLabel BCM Mmul_8.0.1 orderKey 18411 # chrM GCF_000005875.1 included in assembly # mitoAcc NC_005943.1 mitoAcc none fastaFiles /hive/data/genomes/rheMac8/ucsc/*.fa agpFiles /hive/data/genomes/rheMac8/ucsc/*.agp # qualFiles none dbDbSpeciesDir rhesus photoCreditURL http://www.wakehealth.edu/Faculty/Kaplan-Jay-R.htm # photoCreditURL http://caplab.yale.edu/ # http://www.ncbi.nlm.nih.gov/sutils/static/GP_IMAGE/rhesus.jpg # photoCreditName Dr. Laurie Santos photoCreditName J.R. Kaplan ncbiGenomeId 215 ncbiAssemblyId 2715158 ncbiAssemblyName Mmul_8.0.1 ncbiBioProject 12537 genBankAccessionID GCF_000772875.2 taxId 9544' > rheMac8.config.ra # verify sequence and AGP are OK: time makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp rheMac8.config.ra > agp.log 2>&1 # real 4m50.591s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db rheMac8.config.ra) > db.log 2>&1 # real 30m6.878s # check in the trackDb files created and add to trackDb/makefile ######################################################################### # ucscToINSDC table/track (DONE - 2016-02-05 - Hiram) # fixup the translateNames.sh file from rn6 work to use the new # genbank structure (copied over from rn6/bed/ucscToINSDC) mkdir /hive/data/genomes/rheMac8/bed/ucscToINSDC cd /hive/data/genomes/rheMac8/bed/ucscToINSDC # find accession for chrM grep chrM ../../rheMac8.agp # chrM 1 16564 1 O NC_005943.1 1 16564 + # use that accession here: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../refseq/GCF_*structure/Primary_Assembly NC_005943.1 awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > name.coordinate.tab join name.coordinate.tab ucscToINSDC.txt | tr '[ ]' '[\t]' \ > ucscToINSDC.bed # should be same line counts throughout: wc -l * # 284728 name.coordinate.tab # 284728 ucscToINSDC.bed # 284728 ucscToINSDC.txt cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1 # 20 # use the 16 in this sed sed -e "s/21/20/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab rheMac8 ucscToINSDC stdin ucscToINSDC.bed checkTableCoords rheMac8 # should cover %100 entirely: featureBits -countGaps rheMac8 ucscToINSDC # 3236224332 bases of 3236224332 (100.000%) in intersection ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2016-02-05 - Hiram) hgsql -N -e "select frag from gold;" rheMac8 | sort | head -1 AC205186.3 hgsql -N -e "select frag from gold;" rheMac8 | sort | tail -2 JSUE03348490.1 NC_005943.1 # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" rheMac8 | wc -l # 348580 hgsql -N -e "select frag from gold;" rheMac8 \ | egrep -e '[AJN][CS][U2_][E0-9][0-9]+(\.[0-9]+)?' | wc -l # 348580 hgsql -N -e "select frag from gold;" rheMac8 \ | egrep -v -e '[AJN][CS][U2_][E0-9][0-9]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/rheMac8/trackDb.ra searchTable gold shortCircuit 1 termRegex [AJN][CS][U2_][E0-9][0-9]+(\.[0-9]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box ######################################################################### ########################################################################## # running repeat masker (DONE - 2016-01-29 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/repeatMasker cd /hive/data/genomes/rheMac8/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku rheMac8) > do.log 2>&1 # real 481m50.689s # broken cluster run due to sick machines, no real problem, it # completed, continuing: time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -continue=cat -smallClusterHub=ku rheMac8) > cat.log 2>&1 # real 61m1.143s cat faSize.rmsk.txt # 3236224332 bases (94132579 N's 3142091753 real 1436601310 upper # 1705490443 lower) in 284728 sequences in 1 files # Total size: mean 11366.0 sd 1223261.8 min 116 (chrUn_NW_014950235v1) # max 225584828 (chr1) median 941 # %52.70 masked total, %54.28 masked real egrep -i "versi|relea" do.log # RepeatMasker version open-4.0.5 # January 31 2015 (open-4-0-5) version of RepeatMasker # CC RELEASE 20140131; time featureBits -countGaps rheMac8 rmsk # 1705908888 bases of 3236224332 (52.713%) in intersection # real 2m52.924s # why is it different than the faSize above ? # because rmsk masks out some N's as well as bases, the count above # separates out the N's from the bases, it doesn't show lower case N's # faster way to get the same result: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' rheMac8 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 1705908888.000000 # real 0m39.734s ########################################################################## # running simple repeat (DONE - 2016-01-29 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/simpleRepeat cd /hive/data/genomes/rheMac8/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ rheMac8) > do.log 2>&1 # real 140m2.826s cat fb.simpleRepeat # 298982788 bases of 3142093174 (9.515%) in intersection # add to rmsk after it is done: cd /hive/data/genomes/rheMac8 twoBitMask rheMac8.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed rheMac8.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa rheMac8.2bit stdout | faSize stdin > faSize.rheMac8.2bit.txt cat faSize.rheMac8.2bit.txt # 3236224332 bases (94132579 N's 3142091753 real 1434869663 upper # 1707222090 lower) in 284728 sequences in 1 files # Total size: mean 11366.0 sd 1223261.8 min 116 (chrUn_NW_014950235v1) # max 225584828 (chr1) median 941 # %52.75 masked total, %54.33 masked real rm /gbdb/rheMac8/rheMac8.2bit ln -s `pwd`/rheMac8.2bit /gbdb/rheMac8/rheMac8.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2016-02-10 - Hiram) ssh hgwdev mkdir /cluster/data/rheMac8/bed/microsat cd /cluster/data/rheMac8/bed/microsat awk '($5==2 || $5==3) && $6 >= 15 && $8 == 100 && $9 == 0 {printf("%s\t%s\t%s\t%dx%s\n", $1, $2, $3, $6, $16);}' \ ../simpleRepeat/simpleRepeat.bed > microsat.bed hgLoadBed rheMac8 microsat microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2016-02-02 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/windowMasker cd /hive/data/genomes/rheMac8/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev rheMac8) > do.log 2>&1 # real 665m37.329s # Masking statistics cat faSize.rheMac8.cleanWMSdust.txt # 3236224332 bases (94132579 N's 3142091753 real 1839176720 upper # 1302915033 lower) in 284728 sequences in 1 files # Total size: mean 11366.0 sd 1223261.8 min 116 (chrUn_NW_014950235v1) # max 225584828 (chr1) median 941 # %40.26 masked total, %41.47 masked real cat fb.rheMac8.rmsk.windowmaskerSdust.txt # 1061810183 bases of 3236224332 (32.810%) in intersection ########################################################################## # cpgIslands - (DONE - 2016-02-04 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/cpgIslands cd /hive/data/genomes/rheMac8/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku rheMac8) > do.log 2>&1 # real 45m39.560s cat fb.rheMac8.cpgIslandExt.txt # 21989740 bases of 3142093174 (0.700%) in intersection ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2016-01-29 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/cpgIslandsUnmasked cd /hive/data/genomes/rheMac8/bed/cpgIslandsUnmasked # run stepwise so the loading can be done in a different table time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/rheMac8/rheMac8.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku rheMac8) > do.log 2>&1 # real 60m39.280s cat fb.rheMac8.cpgIslandExtUnmasked.txt # 41820506 bases of 3142093174 (1.331%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2016-01-29 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/cytoBand cd /hive/data/genomes/rheMac8/bed/cytoBand makeCytoBandIdeo.csh rheMac8 ######################################################################### # genscan - (DONE - 2016-02-04 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/genscan cd /hive/data/genomes/rheMac8/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku rheMac8) > do.log 2>&1 # real 65m53.319s # two broken, run with window size 2,000,000 to finish, then continue: time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -continue=makeBed -bigClusterHub=ku rheMac8) > makeBed.log 2>&1 # real 21m55.093s cat fb.rheMac8.genscan.txt # 54559229 bases of 3142093174 (1.736%) in intersection cat fb.rheMac8.genscanSubopt.txt # 52580737 bases of 3142093174 (1.673%) in intersection ######################################################################## # Create kluster run files (DONE - 2016-02-03 - Hiram) # numerator is rheMac8 gapless bases "real" as reported by: featureBits -noRandom -noHap rheMac8 gap # 72500454 bases of 2763479500 (2.624%) 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 \( 2763479500 / 2861349177 \) \* 1024 # ( 2763479500 / 2861349177 ) * 1024 = 988.975072 # ==> use -repMatch=900 according to size scaled down from 1024 for human. # and rounded down to nearest 50 cd /hive/data/genomes/rheMac8 blat rheMac8.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/rheMac8.11.ooc \ -repMatch=900 # Wrote 43065 overused 11-mers to jkStuff/rheMac8.11.ooc # check non-bridged gaps to see what the typical size is: hgsql -N \ -e 'select * from gap where bridge="no" order by size;' rheMac8 \ | sort -k7,7nr | ave -col=7 stdin # most non-bridged gaps have size = 100 # decide on a minimum gap for this break, use either 100 or 5000 will # generate 13387 liftOver rows, but if use 6000, only got 11703 rows. # so use 100 here to get more liftOver row. gapToLift -verbose=2 -minGap=100 rheMac8 jkStuff/nonBridged.lft \ -bedFile=jkStuff/nonBridged.bed ######################################################################## # GENBANK AUTO UPDATE (DONE - 2016-02-03,10 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt # Macaca mulatta 378586 60372 5778 # edit etc/genbank.conf to add rheMac8 just before rheMac2 # rheMac8 Macaca mulatta (rhesus) rheMac8.serverGenome = /hive/data/genomes/rheMac8/rheMac8.2bit rheMac8.clusterGenome = /hive/data/genomes/rheMac8/rheMac8.2bit rheMac8.ooc = /hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc rheMac8.lift = /hive/data/genomes/rheMac8/jkStuff/rheMac8.nonBridged.lft rheMac8.perChromTables = no rheMac8.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} rheMac8.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} rheMac8.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} rheMac8.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} rheMac8.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} rheMac8.genbank.est.xeno.pslCDnaFilter = ${finished.genbank.est.xeno.pslCDnaFilter} rheMac8.downloadDir = rheMac8 rheMac8.genbank.mrna.xeno.load = yes rheMac8.refseq.mrna.native.load = yes rheMac8.refseq.mrna.xeno.load = yes rheMac8.upstreamGeneTbl = refGene git commit -m "Added rheMac8; refs #16744" etc/genbank.conf git push # update /cluster/data/genbank/: make etc-update screen # control this business with a screen since it takes a while cd /cluster/data/genbank time ./bin/gbAlignStep -initial rheMac8 # logFile: var/build/logs/2016.02.04-11:28:59.rheMac8.initalign.log # real 2229m7.259s # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.rheMac8 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad rheMac8 # logFile: var/dbload/hgwdev/logs/2016.02.09-14:37:59.rheMac8.dbload.log # real 205m12.078s # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add rheMac8 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m "Added rheMac8 - Rhesus refs #16744" etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################# # augustus gene track (DONE - 2016-02-05 - Hiram) mkdir /hive/data/genomes/rheMac8/bed/augustus cd /hive/data/genomes/rheMac8/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev rheMac8) > do.log 2>&1 # real 95m5.905s cat fb.rheMac8.augustusGene.txt # 49244982 bases of 3142093174 (1.567%) in intersection ######################################################################### # LIFTOVER TO rheMac3 (DONE - 2016-02-05 - Hiram) ssh hgwdev mkdir /hive/data/genomes/rheMac8/bed/blat.rheMac3.2016-02-05 cd /hive/data/genomes/rheMac8/bed/blat.rheMac3.2016-02-05 doSameSpeciesLiftOver.pl -verbose=2 \ -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ rheMac8 rheMac3 time (doSameSpeciesLiftOver.pl -verbose=2 \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ rheMac8 rheMac3) > doLiftOverToRheMac3.log 2>&1 # real 1015m0.435s # see if the liftOver menus function in the browser from rheMac8 to Mac3 ######################################################################### # LIFTOVER TO rheMac2 (DONE - 2016-02-05 - Hiram) ssh hgwdev mkdir /hive/data/genomes/rheMac8/bed/blat.rheMac2.2016-02-05 cd /hive/data/genomes/rheMac8/bed/blat.rheMac2.2016-02-05 doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ rheMac8 rheMac2 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ rheMac8 rheMac2) > doLiftOverToRheMac2.log 2>&1 # real 873m23.446s # failed cluster run, continuing with chain: time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ -continue=chain rheMac8 rheMac2) > chain.log 2>&1 # real 31m30.389s # see if the liftOver menus function in the browser from rheMac8 to Mac2 ########################################################################## # BLATSERVERS ENTRY (DONE - 2016-03-21 - 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 ("rheMac8", "blat1b", "17860", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("rheMac8", "blat1b", "17861", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to rheMac3 position (DONE - 2016-02-09 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr14:63580522-63594072" where name="rheMac8";' hgcentraltest ######################################################################### # all.joiner update, downloads and in pushQ - (TBD 2014-10-21 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until this is a clean output joinerCheck -database=rheMac8 -tableCoverage all.joiner joinerCheck -database=rheMac8 -times all.joiner joinerCheck -database=rheMac8 -keys all.joiner cd /hive/data/genomes/rheMac8 time (makeDownloads.pl rheMac8) > downloads.log 2>&1 # real 27m1.207s # now ready for pushQ entry mkdir /hive/data/genomes/rheMac8/pushQ cd /hive/data/genomes/rheMac8/pushQ time makePushQSql.pl rheMac8 > rheMac8.pushQ.sql 2> stderr.out # real 5m51.393s # check for errors in stderr.out, some are OK, e.g.: # WARNING: hgwdev does not have /gbdb/rheMac8/wib/gc5Base.wib # WARNING: hgwdev does not have /gbdb/rheMac8/wib/quality.wib # WARNING: hgwdev does not have /gbdb/rheMac8/bbi/quality.bw # WARNING: rheMac8 does not have seq # WARNING: rheMac8 does not have extFile # copy it to hgwbeta scp -p rheMac8.pushQ.sql qateam@hgwbeta:/tmp/ ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/rheMac8.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly ######################################################################### +# LIFTOVER TO rheMac10 (DONE - 2019-07-02 - Hiram) + ssh hgwdev + mkdir /hive/data/genomes/rheMac8/bed/blat.rheMac10.2019-07-02 + cd /hive/data/genomes/rheMac8/bed/blat.rheMac10.2019-07-02 + doSameSpeciesLiftOver.pl -verbose=2 \ + -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ + rheMac8 rheMac10 + time (doSameSpeciesLiftOver.pl -verbose=2 \ + -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + -ooc=/hive/data/genomes/rheMac8/jkStuff/rheMac8.11.ooc \ + rheMac8 rheMac10) > doLiftOverToRheMac10.log 2>&1 +XXX - running - Tue Jul 2 08:12:49 PDT 2019 + # real 1015m0.435s + + # see if the liftOver menus function in the browser from rheMac8 to rheMac10 + +#########################################################################