7b0c8bb2cb0e36f4b8a3335dfe755586cbdf584f hiram Wed Dec 7 21:32:28 2022 -0800 liftOver per user request 4 to 9 to 4 refs #30301 diff --git src/hg/makeDb/doc/bosTau9/initialBuild.txt src/hg/makeDb/doc/bosTau9/initialBuild.txt index 7b61206..70c5978 100644 --- src/hg/makeDb/doc/bosTau9/initialBuild.txt +++ src/hg/makeDb/doc/bosTau9/initialBuild.txt @@ -1,1175 +1,1200 @@ # for emacs: -*- mode: sh; -*- # This file describes browser build for the bosTau9 ######################################################################### # reuse photograph from bosTau previous versions (DONE - hiram - 2018-11-06) mkdir /hive/data/genomes/bosTau9 cd /hive/data/genomes/bosTau9 cp -p ../bosTau8/photoReference.txt . cat photoReference.txt # photoCreditURL http://www.genome.gov/dmd/img.cfm?node=Photos/Animals/Cow&id=79109 # photoCreditName NHGRI press photos ######################################################################### # Initial steps (DONE - 2018-11-06 - Hiram) # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/bosTau9 cd ~/kent/src/hg/makeDb/doc/bosTau9 # best to use a most recent document since it has the latest features and # procedures: sed -e 's/oviAri4/bosTau9/g; s/OviAri4/BosTau9/g; s/DONE/TBD/g;' \ ../oviAri4/initialBuild.txt > initialBuild.txt mkdir /hive/data/genomes/bosTau9/refseq cd /hive/data/genomes/bosTau9/refseq time (rsync --stats -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_mammalian/Bos_taurus/all_assembly_versions/GCF_002263795.1_ARS-UCD1.2/ ./) > fetch.log 2>&1 # sent 3,528 bytes received 3,992,632,460 bytes 52,882,595.87 bytes/sec # total size is 3,991,645,023 speedup is 1.00 # real 1m14.770s # check assembly size for later reference: faSize G*D1.2_genomic.fna.gz # 2715853792 bases (28162 N's 2715825630 real 1595305255 upper # 1120520375 lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (NW_020192071.1) # max 158534110 (NC_037328.1) median 21935 # %41.26 masked total, %41.26 masked real # this information is from the top of # bosTau9/refseq/GCF_002263795.1_ARS-UCD1.2_assembly_report.txt # Assembly name: ARS-UCD1.2 # Organism name: Bos taurus (cattle) # Infraspecific name: breed=Hereford # Isolate: L1 Dominette 01449 registration number 42190680 # Sex: female # Taxid: 9913 # BioSample: SAMN03145444 # BioProject: PRJNA391427 # Submitter: USDA ARS # Date: 2018-4-11 # Assembly type: haploid # Release type: major # Assembly level: Chromosome # Genome representation: full # WGS project: NKLS02 # Assembly method: Falcon v. FEB-2016 # Expected final version: yes # Reference guided assembly: de-novo # Genome coverage: 80.0x # Sequencing technology: PacBio; Illumina NextSeq 500; Illumina HiSeq; Illumina GAII # RefSeq category: Representative Genome # GenBank assembly accession: GCA_002263795.2 # RefSeq assembly accession: GCF_002263795.1 # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_002263805.2 GCF_002263805.1 Primary Assembly ## GCA_002263815.2 GCF_000001285.1 non-nuclear ############################################################################# # establish config.ra file (DONE - Hiram - 2018-11-06) # arguments here are: <db> <clade> <trackDbDir> <assembly_report.txt> cd /hive/data/genomes/bosTau9 $HOME/kent/src/hg/utils/automation/prepConfig.pl bosTau9 mammal \ cow ./refseq/*_assembly_report.txt > bosTau9.config.ra # compare to ../oviAri3 to see what might need to be fixed up: diff bosTau9.config.ra ../bosTau8/bosTau8.config.ra | less # fixup the 'commonName' from Cattle to Cow and orderKey from 3262 to 3626 cat bosTau9.config.ra # config parameters for makeGenomeDb.pl: db bosTau9 clade mammal genomeCladePriority 35 scientificName Bos taurus commonName Cow assemblyDate Apr. 2018 assemblyLabel USDA ARS assemblyShortLabel ARS-UCD1.2 orderKey 3626 # mitochondrial sequence included in refseq release # mitoAcc NC_006853.1 mitoAcc none fastaFiles /hive/data/genomes/bosTau9/ucsc/*.fa.gz agpFiles /hive/data/genomes/bosTau9/ucsc/*.agp # qualFiles none dbDbSpeciesDir cow photoCreditURL http://www.genome.gov/dmd/img.cfm?node=Photos/Animals/Cow&id=79109 photoCreditName NHGRI press photos ncbiGenomeId 82 ncbiAssemblyId 1677391 ncbiAssemblyName ARS-UCD1.2 ncbiBioProject 391427 ncbiBioSample SAMN03145444 genBankAccessionID GCF_002263795.1 taxId 9913 ############################################################################# # setup UCSC named files (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/ucsc cd /hive/data/genomes/bosTau9/ucsc # check for duplicate sequences: time faToTwoBit -noMask ../refseq/G*D1.2_genomic.fna.gz refseq.2bit # real 0m44.551s twoBitDup refseq.2bit # no output is a good result, otherwise, would have to eliminate duplicates # the scripts creating the fasta here will be using this refseq.2bit file time ~/kent/src/hg/utils/automation/ucscCompositeAgp.pl \ ../refseq/G*D1.2_genomic.fna.gz \ ../refseq/G*D1.2_assembly_structure/Primary_Assembly # NC_037328.1 chr1 # NC_037329.1 chr2 # NC_037330.1 chr3 # NC_037331.1 chr4 # NC_037332.1 chr5 # NC_037333.1 chr6 # NC_037334.1 chr7 # NC_037335.1 chr8 # NC_037336.1 chr9 # NC_037337.1 chr10 # NC_037338.1 chr11 # NC_037339.1 chr12 # NC_037340.1 chr13 # NC_037341.1 chr14 # NC_037342.1 chr15 # NC_037343.1 chr16 # NC_037344.1 chr17 # NC_037345.1 chr18 # NC_037346.1 chr19 # NC_037347.1 chr20 # NC_037348.1 chr21 # NC_037349.1 chr22 # NC_037350.1 chr23 # NC_037351.1 chr24 # NC_037352.1 chr25 # NC_037353.1 chr26 # NC_037354.1 chr27 # NC_037355.1 chr28 # NC_037356.1 chr29 # NC_037357.1 chrX # real 10m47.295s # unplaced sequences time ~/kent/src/hg/utils/automation/unplacedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # processed 2180 sequences into chrUn.fa.gz # real 0m27.379s # unlocalized sequences time ~/kent/src/hg/utils/automation/unlocalizedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # No unlocalized sequences # bash syntax here mitoAcc=`grep "^# mitoAcc" ../bosTau9.config.ra | awk '{print $NF}'` printf "# mitoAcc %s\n" "$mitoAcc" # mitoAcc NC_006853.1 zcat \ ../refseq/*_assembly_structure/non-nuclear/assem*/AGP/chrMT.comp.agp.gz \ | grep -v "^#" | sed -e "s/^$mitoAcc/chrM/;" > chrM.agp printf ">chrM\n" > chrM.fa twoBitToFa -noMask refseq.2bit:$mitoAcc stdout | grep -v "^>" >> chrM.fa gzip chrM.fa # verify chrM sequence is there: faCount chrM.fa.gz #seq len A C G T N cpg chrM 16338 5457 4238 2202 4441 0 358 # verify fasta and AGPs agree time faToTwoBit *.fa.gz test.2bit # real 0m58.603s time cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail -4 # All AGP and FASTA entries agree - both files are valid # real 0m3.117s # and no sequence lost from orginal: twoBitToFa test.2bit stdout | faSize stdin # 2715853792 bases (28162 N's 2715825630 real 2715825630 upper 0 # lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (chrUn_NW_020192071v1) # max 158534110 (chr1) median 21935 # same numbers as above # 2715853792 bases (28162 N's 2715825630 real 1595305255 upper # 1120520375 lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (NW_020192071.1) # max 158534110 (NC_037328.1) median 21935 # no longer need these temporary 2bit files rm refseq.2bit test.2bit ############################################################################# # Initial database build (DONE - 2018-11-06 - Hiram) cd /hive/data/genomes/bosTau9 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp bosTau9.config.ra) > agp.log 2>&1 # real 2m36.514s # verify there was no error in that step: tail agp.log # *** All done! (through the 'agp' step) # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db bosTau9.config.ra) > db.log 2>&1 # real 15m27.039s # verify gaps are all there twoBitInfo -nBed bosTau9.unmasked.2bit stdout | awk '{print $3-$2}' \ | ave stdin | sed -e 's/^/# /;' # Q1 25.000000 # median 25.000000 # Q3 100.000000 # average 72.958549 # min 23.000000 # max 252.000000 # count 386 # total 28162.000000 # standard deviation 71.040090 twoBitInfo -nBed bosTau9.unmasked.2bit stdout \ | awk '{printf "%s\t%d\t%d\t%d\n", $1,$2,$3,$3-$2}' \ | sort -k4,4nr | cut -f4 | uniq -c 42 252 116 100 1 99 1 85 1 66 1 65 1 60 1 44 1 36 220 25 1 23 # the gap table has nothing hgsql -e 'select count(*) from gap;' bosTau9 +----------+ | count(*) | +----------+ | 0 | +----------+ # otherwise, compare to the gap table: hgsql -e 'select chromEnd-chromStart from gap;' bosTau9 | ave stdin | sed -e 's/^/# /;' # check in the trackDb files created in TemporaryTrackDbCheckout/ # and add bosTau9 to trackDb/makefile # temporary symlink until masked sequence is available cd /hive/data/genomes/bosTau9 ln -s `pwd`/bosTau9.unmasked.2bit /gbdb/bosTau9/bosTau9.2bit ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/cpgIslandsUnmasked cd /hive/data/genomes/bosTau9/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/bosTau9/bosTau9.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku bosTau9) > do.log 2>&1 # real 3m41.462s cat fb.bosTau9.cpgIslandExtUnmasked.txt # 33761995 bases of 2715853792 (1.243%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/cytoBand cd /hive/data/genomes/bosTau9/bed/cytoBand makeCytoBandIdeo.csh bosTau9 ############################################################################# # run up idKeys files for chromAlias/ncbiRefSeq (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/idKeys cd /hive/data/genomes/bosTau9/bed/idKeys time (doIdKeys.pl \ -twoBit=/hive/data/genomes/bosTau9/bosTau9.unmasked.2bit \ -buildDir=`pwd` bosTau9) > do.log 2>&1 & # real 0m47.105s cat bosTau9.keySignature.txt # 7850e2d5dabb6134fdc9d7083f1a3a54 # one of them did not work, joinerCheck complained, remove it: hgsql -e 'delete from ncbiRefSeq where name="NM_001143743.1";' bosTau9 hgsql -e 'delete from ncbiRefSeqLink where protAcc="NP_001137215.1";' bosTau9 hgsql -e 'delete from ncbiRefSeqPsl where qName="NM_001143743.1";' bosTau9 hgsql -e 'delete from ncbiRefSeqCurated where name="NM_001143743.1";' bosTau9 hgsql -e 'delete from seqNcbiRefSeq where acc="NM_001143743.1";' bosTau9 ############################################################################# # gapOverlap (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/gapOverlap cd /hive/data/genomes/bosTau9/bed/gapOverlap time (doGapOverlap.pl \ -twoBit=/hive/data/genomes/bosTau9/bosTau9.unmasked.2bit bosTau9 ) \ > do.log 2>&1 # real 1m51.390s cat fb.bosTau9.gapOverlap.txt # 150 bases of 2715853792 (0.000%) in intersection # 1 items on chr13 zcat *.bed.gz | cut -f1 | cut -d'_' -f1 | sort | uniq -c |sort -r | head -5 1 chr13 ############################################################################# # tandemDups (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/tandemDups cd /hive/data/genomes/bosTau9/bed/tandemDups time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -twoBit=/hive/data/genomes/bosTau9/bosTau9.unmasked.2bit bosTau9) \ > do.log 2>&1 & # real 140m36.622s cat fb.bosTau9.tandemDups.txt # 110536957 bases of 2715853792 (4.070%) in intersection bigBedInfo bosTau9.tandemDups.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 13 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 # itemCount: 1,556,737 # primaryDataSize: 41,133,265 # primaryIndexSize: 152,196 # zoomLevels: 9 # chromCount: 1955 # basesCovered: 2,031,718,211 # meanDepth (of bases covered): 7.749018 # minDepth: 1.000000 # maxDepth: 1559.000000 # std of depth: 13.615893 ############################################################################# # ucscToINSDC and ucscToRefSeq table/track (DONE - 2018-11-08 - Hiram) # construct idKeys for the refseq sequence mkdir /hive/data/genomes/bosTau9/refseq/idKeys cd /hive/data/genomes/bosTau9/refseq/idKeys faToTwoBit ../GCF_002263795.1_ARS-UCD1.2_genomic.fna.gz bosTau9.refSeq.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/bosTau9.refSeq.2bit refseqBosTau9) > do.log 2>&1 & # real 2m57.680s cat refseqBosTau9.keySignature.txt # 8eb392728eaf8d55db9d9cf05639cc0e # and the genbank sequence needs keys too: mkdir /hive/data/genomes/bosTau9/refseq/idKeysGenbank cd /hive/data/genomes/bosTau9/refseq/idKeysGenbank faToTwoBit /hive/data/outside/ncbi/genomes/genbank/vertebrate_mammalian/Bos_taurus/all_assembly_versions/GCA_002263795.2_ARS-UCD1.2/GCA_002263795.2_ARS-UCD1.2_genomic.fna.gz bosTau9.genbank.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/bosTau9.genbank.2bit genbankBosTau9) > do.log 2>&1 & # real 3m3.732s cat genbankBosTau9.keySignature.txt # c5f6bb39f5c7053fa10deecfa9ce4fc6 mkdir /hive/data/genomes/bosTau9/bed/chromAlias cd /hive/data/genomes/bosTau9/bed/chromAlias join -t$'\t' ../idKeys/bosTau9.idKeys.txt \ ../../refseq/idKeysGenbank/genbankBosTau9.idKeys.txt | cut -f2- \ | sort -k1,1 | join -t$'\t' <(sort -k1,1 ../../chrom.sizes) - \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ | sort -k1,1 -k2,2n > ucscToINSDC.bed join -t$'\t' ../idKeys/bosTau9.idKeys.txt \ ../../refseq/idKeys/refseqBosTau9.idKeys.txt | cut -f2- \ | sort -k1,1 | join -t$'\t' <(sort -k1,1 ../../chrom.sizes) - \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ | sort -k1,1 -k2,2n > ucscToRefSeq.bed # should be same line counts throughout: wc -l * ../../chrom.sizes # 2210 ucscToINSDC.bed # 2211 ucscToRefSeq.bed # 2211 ../../chrom.sizes # need to find the accession for the INSDC equivalent to chrM: egrep chrM * # ucscToRefSeq.bed:chrM 0 16338 NC_006853.1 # lookup that accession at NCBI Entrez: AY526085.1 # and add to ucscToINSDC.bed: printf "chrM\t0\t16338\tAY526085.1\n" >> ucscToINSDC.bed # verify: grep chrM * # ucscToINSDC.bed:chrM 0 16338 AY526085.1 # ucscToRefSeq.bed:chrM 0 16338 NC_006853.1 export chrSize=`cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 20 # use the $chrSize in this sed sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab bosTau9 ucscToINSDC stdin ucscToINSDC.bed # should be the same for ucscToRefSeq: export chrSize=`cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 20 sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | sed -e 's/INSDC/RefSeq/g;' \ | hgLoadSqlTab bosTau9 ucscToRefSeq stdin ucscToRefSeq.bed # should be quiet for all OK checkTableCoords bosTau9 # should cover %100 entirely: featureBits -countGaps bosTau9 ucscToINSDC # 2715853792 bases of 2715853792 (100.000%) in intersection featureBits -countGaps bosTau9 ucscToRefSeq # 2715853792 bases of 2715853792 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2018-11-08 - Hiram) # after ucscToRefSeq and ucscToINSDC tables have been created mkdir /hive/data/genomes/bosTau9/bed/chromAlias cd /hive/data/genomes/bosTau9/bed/chromAlias hgsql -N -e 'select chrom,name from ucscToRefSeq;' bosTau9 \ | sort -k1,1 > ucsc.refseq.tab hgsql -N -e 'select chrom,name from ucscToINSDC;' bosTau9 \ | sort -k1,1 > ucsc.genbank.tab ### Adding Ensembl alias with v95 release, after idKeys made: 2019-01-16 join -t$'\t' ../idKeys/bosTau9.idKeys.txt \ ../../ens95/ensBosTau9.idKeys.txt | cut -f2- \ | sort -k1,1 | join -t$'\t' <(sort -k1,1 ../../chrom.sizes) - \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ | sort -k1,1 -k2,2n > ucscToEns.bed # Ensembl is missing a chrM sequence: wc -l *.bed 2210 ucscToEns.bed 2211 ucscToINSDC.bed 2211 ucscToRefSeq.bed cut -f1,4 ucscToEns.bed | sort > ucsc.ensembl.tab ~/kent/src/hg/utils/automation/chromAlias.pl ucsc.*.tab \ > bosTau9.chromAlias.tab for t in refseq genbank ensembl do c0=`cat ucsc.$t.tab | wc -l` c1=`grep $t bosTau9.chromAlias.tab | wc -l` ok="OK" if [ "$c0" -ne "$c1" ]; then ok="ERROR" fi printf "# checking $t: $c0 =? $c1 $ok\n" done # checking refseq: 2211 =? 2211 OK # checking genbank: 2211 =? 2211 OK # checking ensembl: 2210 =? 2210 OK hgLoadSqlTab bosTau9 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ bosTau9.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2018-11-06 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/cow/bosTau9 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" bosTau9 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c | sed -e 's/^/#\t/;' # 1 NC_.1 # 2210 NKLS.1 # implies a rule: 'N[CK][LS0-9_]+(\.[0-9]+)?' # verify this rule will find them all and eliminate them all: hgsql -N -e "select frag from gold;" bosTau9 | wc -l # 2211 hgsql -Ne "select frag from gold" bosTau9 \ | egrep -e 'N[CK][LS0-9_]+(\.[0-9]+)?' | wc -l # 2211 hgsql -Ne "select frag from gold" bosTau9 \ | egrep -v -e 'N[CK][LS0-9_]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/cow/bosTau9/trackDb.ra searchTable gold shortCircuit 1 termRegex N[CK][LS0-9_]+(\.[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 - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/repeatMasker cd /hive/data/genomes/bosTau9/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku bosTau9) > do.log 2>&1 & # real 531m36.333s # had quite a few with this error: # RepeatMasker bug?: Undefined id, line 5255479 of input: # 1073 25.3 0.4 0.4 chrUn_NW_020191554v1 44876 45087 (19682) C BTSAT2c Satellite/centr (11) 341 1 # get that list of items out of the do.log and remove them from # the bosTau9.sorted.fa.out to clean it up: mv bosTau9.sorted.fa.out bosTau9.sorted.fa.out.broken grep chrUn_NW do.log | cut -c24-59 | sort > grep.remove.list # there are 171 of these: wc -l grep.remove.list # 171 grep -v -f grep.remove.list bosTau9.sorted.fa.out.broken \ > bosTau9.sorted.fa.out # verify 171 lines removed: wc -l bosTau9.sorted.fa.out bosTau9.sorted.fa.out.broken # 5620007 bosTau9.sorted.fa.out # 5620178 bosTau9.sorted.fa.out.broken # 171 difference mv bosTau9.fa.out bosTau9.fa.out.broken grep -v -f grep.remove.list bosTau9.fa.out.broken \ > bosTau9.fa.out wc -l bosTau9.fa.out.broken bosTau9.fa.out # 5620178 bosTau9.fa.out.broken # 5620007 bosTau9.fa.out # 171 difference # the last command of doCat.csh: time /cluster/bin/scripts/extractNestedRepeats.pl bosTau9.fa.out \ | sort -k1,1 -k2,2n > bosTau9.nestedRepeats.bed # continuing: time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -continue=mask -smallClusterHub=ku bosTau9) > mask.log 2>&1 & # real 17m45.760s egrep "bases|Total|masked" faSize.rmsk.txt \ | fold -w 75 -s | sed -e 's/^/# /;' # 2715853792 bases (28162 N's 2715825630 real 1376420245 upper 1339405385 # lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (chrUn_NW_020192071v1) # max 158534110 (chr1) median 21935 # %49.32 masked total, %49.32 masked real egrep -i "versi|relea" do.log # RepeatMasker version open-4.0.7 # February 01 2017 (open-4-0-7) 1.331 version of RepeatMasker # CC Dfam_Consensus RELEASE 20170127; * # CC RepBase RELEASE 20170127; * time featureBits -countGaps bosTau9 rmsk # 1339405686 bases of 2715853792 (49.318%) in intersection # real 0m31.962s # why is it different than the faSize above ? # because rmsk masks out some N's as well as bases, the faSize 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 on high contig count assemblies: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' bosTau9 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 1339405686.000000 # real 0m24.033s ########################################################################## # running simple repeat (DONE - 2018-11-06 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/simpleRepeat cd /hive/data/genomes/bosTau9/bed/simpleRepeat # using trf409 6 here as similar size to genome (human == 6) time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409 6 bosTau9) > do.log 2>&1 & # real 173m39.504s cat fb.simpleRepeat # 78768566 bases of 2715853792 (2.900%) in intersection bigBedInfo *.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 16 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 # itemCount: 545,256 # primaryDataSize: 17,063,916 # primaryIndexSize: 103,156 # zoomLevels: 10 # chromCount: 2051 # basesCovered: 78,768,566 # meanDepth (of bases covered): 6.563866 # minDepth: 1.000000 # maxDepth: 206.000000 # std of depth: 9.700871 # adding this trfMask to the other masking cd /hive/data/genomes/bosTau9 # when using the Window Masker result: # twoBitMask bed/windowMasker/bosTau9.cleanWMSdust.2bit \ # -add bed/simpleRepeat/trfMask.bed bosTau9.2bit # you can safely ignore the warning about fields >= 13 # when using Rmsk results, add to rmsk after it is done: twoBitMask bosTau9.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed bosTau9.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa bosTau9.2bit stdout | faSize stdin > faSize.bosTau9.2bit.txt egrep "bases|Total|masked" faSize.bosTau9.2bit.txt \ | fold -w 75 -s | sed -e 's/^/# /;' # 2715853792 bases (28162 N's 2715825630 real 1375606800 upper 1340218830 # lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (chrUn_NW_020192071v1) # max 158534110 (chr1) median 21935 # %49.35 masked total, %49.35 masked real # reset the symlink rm /gbdb/bosTau9/bosTau9.2bit ln -s `pwd`/bosTau9.2bit /gbdb/bosTau9/bosTau9.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2018-11-08 - Hiram) ssh hgwdev mkdir /cluster/data/bosTau9/bed/microsat cd /cluster/data/bosTau9/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 bosTau9 microsat microsat.bed # Read 25219 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2018-11-07 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/windowMasker cd /hive/data/genomes/bosTau9/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev bosTau9) > do.log 2>&1 # real 95m24.111s # Masking statistics egrep "bases|Total|masked" faSize.bosTau9.cleanWMSdust.txt \ | fold -w 75 -s | sed -e 's/^/# /;' # 2715853792 bases (28162 N's 2715825630 real 1580978410 upper 1134847220 # lower) in 2211 sequences in 1 files # Total size: mean 1228337.3 sd 10762990.9 min 1034 (chrUn_NW_020192071v1) # max 158534110 (chr1) median 21935 # %41.79 masked total, %41.79 masked real cat fb.bosTau9.rmsk.windowmaskerSdust.txt # 907805797 bases of 2715853792 (33.426%) in intersection ############################################################################# # ncbiRefSeq (DONE - 2018-11-08 - Hiram) # can be run up after ucscToRefSeq table is constructed mkdir /hive/data/genomes/bosTau9/bed/ncbiRefSeq cd /hive/data/genomes/bosTau9/bed/ncbiRefSeq # adjust the name arguments time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev \ -fileServer=hgwdev -smallClusterHub=hgwdev-101 -workhorse=hgwdev \ refseq vertebrate_mammalian Bos_taurus \ GCF_002263795.1_ARS-UCD1.2 bosTau9) > do.log 2>&1 & # real 5m10.572s cat fb.ncbiRefSeq.bosTau9.txt # 80750008 bases of 2715853792 (2.973%) in intersection ############################################################################# # cpgIslands - (DONE - 2018-11-08 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/cpgIslands cd /hive/data/genomes/bosTau9/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku bosTau9) > do.log 2>&1 & # real 3m43.856s cat fb.bosTau9.cpgIslandExt.txt # 26618121 bases of 2715853792 (0.980%) in intersection ############################################################################## # genscan - (DONE - 2018-11-08 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/genscan cd /hive/data/genomes/bosTau9/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku bosTau9) > do.log 2>&1 & # real 48m49.605s # one broken one finished with 2,000,000 window size: time (././runGsBig2M.csh chr13 000 gtf/000/chr13.gtf pep/000/chr13.pep subopt/000/chr13.bed) > lastOne.log 2>&1 # real 28m54.073s time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -continue=makeBed -bigClusterHub=ku bosTau9) > makeBed.log 2>&1 & cat fb.bosTau9.genscan.txt # 56389215 bases of 2715853792 (2.076%) in intersection cat fb.bosTau9.genscanSubopt.txt # 51538764 bases of 2715853792 (1.898%) in intersection bigBedInfo bosTau9.genscan.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 12 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 # itemCount: 43,798 # primaryDataSize: 2,587,464 # primaryIndexSize: 37,772 # zoomLevels: 7 # chromCount: 804 # basesCovered: 1,855,898,050 # meanDepth (of bases covered): 1.000000 # minDepth: 1.000000 # maxDepth: 1.000000 # std of depth: -nan ############################################################################# # augustus gene track (DONE - 2018-11-08 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/augustus cd /hive/data/genomes/bosTau9/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev -workhorse=hgwdev bosTau9) > do.log 2>&1 & # real 109m41.672s cat fb.bosTau9.augustusGene.txt # 52391476 bases of 2715853792 (1.929%) in intersection bigBedInfo bosTau9.augustus.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 20 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 # itemCount: 30,862 # primaryDataSize: 2,187,353 # primaryIndexSize: 22,468 # zoomLevels: 7 # chromCount: 454 # basesCovered: 1,220,657,991 # meanDepth (of bases covered): 1.261447 # minDepth: 1.000000 # maxDepth: 5.000000 # std of depth: 0.630592 ############################################################################# # lastz/chain/net swap human/hg38 (TBD - 2018-04-25 - Hiram) # original alignment cd /hive/data/genomes/hg38/bed/lastzBosTau9.2018-04-25 cat fb.hg38.chainBosTau9Link.txt # 1388649593 bases of 3049335806 (45.539%) in intersection cat fb.hg38.chainSynBosTau9Link.txt # 1330693519 bases of 3049335806 (43.639%) in intersection cat fb.hg38.chainRBestBosTau9Link.txt # 1278396766 bases of 3049335806 (41.924%) in intersection # running the swap mkdir /hive/data/genomes/bosTau9/bed/blastz.hg38.swap cd /hive/data/genomes/bosTau9/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzBosTau9.2018-04-25/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 104m31.748s cat fb.bosTau9.chainHg38Link.txt # 1319553403 bases of 2587515673 (50.997%) in intersection cat fb.bosTau9.chainSynHg38Link.txt # 1280196824 bases of 2587515673 (49.476%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ bosTau9 hg38) > rbest.log 2>&1 & # real 638m15.603s cat fb.bosTau9.chainRBestHg38Link.txt # 1279077824 bases of 2587515673 (49.433%) in intersection ############################################################################# # lastz/chain/net swap mouse/mm10 (TBD - 2018-04-25 - Hiram) # alignment to mouse/mm10: cd /hive/data/genomes/mm10/bed/lastzBosTau9.2018-04-25 cat fb.mm10.chainBosTau9Link.txt # 693504453 bases of 2652783500 (26.143%) in intersection cat fb.mm10.chainRBestBosTau9Link.txt # 657097998 bases of 2652783500 (24.770%) in intersection # and for the swap: mkdir /hive/data/genomes/bosTau9/bed/blastz.mm0.swap cd /hive/data/genomes/bosTau9/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzBosTau9.2018-04-25/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 63m12.935s cat fb.bosTau9.chainMm10Link.txt # 680117358 bases of 2587515673 (26.285%) in intersection cat fb.bosTau9.chainSynMm10Link.txt # 643562837 bases of 2587515673 (24.872%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ bosTau9 mm10) > rbest.log 2>&1 & # real 437m1.637s cat fb.bosTau9.chainRBestMm10Link.txt # 656602300 bases of 2587515673 (25.376%) in intersection ############################################################################## # Create kluster run files (DONE - 2018-11-08 - Hiram) cd /hive/data/genomes/bosTau9 # numerator is bosTau9 gapless bases "real" as reported by: featureBits -noRandom -noHap bosTau9 gap # 0 bases of 2628411261 (0.000%) 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 \(2628411261 / 2861349177 \) \* 1024 # (2628411261 / 2861349177 ) * 1024 = 940.637778 # ==> use -repMatch=900 same as was bosTau8 cd /hive/data/genomes/bosTau9 blat bosTau9.2bit /dev/null /dev/null -tileSize=11 \ -makeOoc=jkStuff/bosTau9.11.ooc -repMatch=900 # Wrote 35432 overused 11-mers to jkStuff/bosTau9.11.ooc # bosTau8 at repMatch=900 was: # Wrote 33613 overused 11-mers to jkStuff/bosTau8.11.ooc # no unbridged gaps so no need to worry about gaplift file: hgsql -Ne "select bridge from gap" bosTau9 | sort | uniq -c # no gaps of any sort hgsql -Ne "select count(*) from gap" bosTau9 # +---+ # | 0 | # +---+ ############################################################################## # LIFTOVER TO bosTau8 (DONE - 2018-11-08 - Hiram) ssh hgwdev mkdir /hive/data/genomes/bosTau9/bed/blat.bosTau8.2018-11-08 cd /hive/data/genomes/bosTau9/bed/blat.bosTau8.2018-11-08 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -ooc=/hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ bosTau9 bosTau8) > do.log 2>&1 & # real 1255m56.756s # verify the convert link on the test browser is now active # from bosTau9 to bosTau8 ############################################################################## # LIFTOVER TO bosTau7 (DONE - 2018-11-08 - Hiram) ssh hgwdev mkdir /hive/data/genomes/bosTau9/bed/blat.bosTau7.2018-11-08 cd /hive/data/genomes/bosTau9/bed/blat.bosTau7.2018-11-08 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -ooc=/hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ bosTau9 bosTau7) > do.log 2>&1 & # real 831m15.041s # verify the convert link on the test browser is now active # from bosTau9 to bosTau7 ############################################################################## # LIFTOVER TO bosTau6 (DONE - 2018-11-08 - Hiram) ssh hgwdev mkdir /hive/data/genomes/bosTau9/bed/blat.bosTau6.2018-11-08 cd /hive/data/genomes/bosTau9/bed/blat.bosTau6.2018-11-08 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -ooc=/hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ bosTau9 bosTau6) > do.log 2>&1 & # real 1236m43.784s # verify the convert link on the test browser is now active # from bosTau9 to bosTau6 ############################################################################## # crispr 10K shoulders (DONE - 2018-11-16 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/crispr10K cd /hive/data/genomes/bosTau9/bed/crispr10K time (~/kent/src/hg/utils/automation/doCrispr.pl \ -stop=load -buildDir=`pwd` -smallClusterHub=hgwdev-101 bosTau9 ncbiRefSeq) \ > do.log 2>&1 # real 1192m19.444s # broke down, fixed, manually completed specScores time find tmp/outGuides -type f | xargs cut -f3-6 > ../specScores.tab # real 329m49.271s # effScores: real 1410m36.918s # offTargets: real 99m35.115s # load: real 132m24.530s # hive cleaning - 2021-04-26 - Hiram time (~/kent/src/hg/utils/automation/doCrispr.pl \ -continue=cleanup -buildDir=`pwd` -smallClusterHub=hgwdev bosTau9 \ -fileServer=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku -workhorse=hgwdev) > cleanup.log 2>&1 & ############################################################################## # crispr whole genome (DONE - 2022-03-01 - Hiram) mkdir /hive/data/genomes/bosTau9/bed/crisprAll cd /hive/data/genomes/bosTau9/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 \ bosTau9 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > indexFa.log 2>&1 # real 1m10.666s time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=ranges bosTau9 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > ranges.log 2>&1 # real 8554m11.613s time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=effScores bosTau9 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > effScores.log 2>&1 time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=offTargets bosTau9 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > offTargets.log 2>&1 time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=load bosTau9 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > load.log 2>&1 cat guides/run.time | sed -e 's/^/# /;' # Completed: 100 of 100 jobs # CPU time in finished jobs: 12054s 200.90m 3.35h 0.14d 0.000 y # IO & Wait Time: 282s 4.70m 0.08h 0.00d 0.000 y # Average job time: 123s 2.06m 0.03h 0.00d # Longest finished job: 432s 7.20m 0.12h 0.01d # Submission to last job: 434s 7.23m 0.12h 0.01d cat specScores/run.time | sed -e 's/^/# /;' # Completed: 841413 of 841413 jobs # CPU time in finished jobs: 71934084s 1198901.39m 19981.69h 832.57d 2.281 y # IO & Wait Time: 0s 0.00m 0.00h 0.00d 0.000 y # Average job time: 85s 1.41m 0.02h 0.00d # Longest finished job: 170s 2.83m 0.05h 0.00d # Submission to last job: 203959s 3399.32m 56.66h 2.36d grep -c . effScores.tab # 288692962 grep -c . specScores.tab # 218717447 cat effScores/run.time | sed -e 's/^/# /;' # Completed: 28864 of 28864 jobs # CPU time in finished jobs: 12570265s 209504.41m 3491.74h 145.49d 0.399 y # IO & Wait Time: 45737s 762.29m 12.70h 0.53d 0.001 y # Average job time: 437s 7.28m 0.12h 0.01d # Longest finished job: 7448s 124.13m 2.07h 0.09d # Submission to last job: 31650s 527.50m 8.79h 0.37d cat offTargets/run.time | sed -e 's/^/# /;' # Completed: 145438 of 145438 jobs # CPU time in finished jobs: 2306725s 38445.42m 640.76h 26.70d 0.073 y # IO & Wait Time: 901605s 15026.74m 250.45h 10.44d 0.029 y # Average job time: 22s 0.37m 0.01h 0.00d # Longest finished job: 133s 2.22m 0.04h 0.00d # Submission to last job: 14396s 239.93m 4.00h 0.17d ############################################################################## # GENBANK AUTO UPDATE (DONE - 2018-11-08 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt # Bos taurus 20115 1583423 13363 # edit etc/genbank.conf to add bosTau9 just after bosTau8 # bosTau9 (cow - Bos taurus - refseq GCF_002263795.1 ARS-UCD1.2 - taxId 9913) bosTau9.serverGenome = /hive/data/genomes/bosTau9/bosTau9.2bit bosTau9.clusterGenome = /hive/data/genomes/bosTau9/bosTau9.2bit bosTau9.ooc = /hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc bosTau9.lift = no bosTau9.perChromTables = no bosTau9.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} bosTau9.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} bosTau9.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} bosTau9.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} bosTau9.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} bosTau9.genbank.est.xeno.pslCDnaFilter = ${finished.genbank.est.xeno.pslCDnaFilter} bosTau9.downloadDir = bosTau9 # bosTau9.upstreamGeneTbl = refGene # defaults yes: genbank.mrna.native.load genbank.mrna.native.loadDesc # yes: genbank.est.native.load refseq.mrna.native.load # yes: refseq.mrna.native.loadDesc refseq.mrna.xeno.load # yes: refseq.mrna.xeno.loadDesc # defaults no: genbank.mrna.xeno.load genbank.mrna.xeno.loadDesc # no: genbank.est.native.loadDesc genbank.est.xeno.load # no: genbank.est.xeno.loadDesc # verify stated file paths do exist: grep bosTau9 etc/genbank.conf | egrep "Genome|ooc|lift" \ | awk '{print $NF}' | sort -u | xargs ls -og ls: cannot access no: No such file or directory -rw-rw-r-- 1 712534740 Nov 7 13:35 /hive/data/genomes/bosTau9/bosTau9.2bit -rw-rw-r-- 1 141736 Nov 8 13:13 /hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc # ls error on the file named 'no' is from the bosTau9.lift = no git commit -m 'adding bosTau9 refs #22425' etc/genbank.conf git push # add bosTau9 to: # etc/hgwdev.dbs git commit -m 'adding bosTau9 refs #22425' etc/hgwdev.dbs git push # update /cluster/data/genbank/: make etc-update ############################################################################# # BLATSERVERS ENTRY (DONE - 2018-11-08 - 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 ("bosTau9", "blat1c", "17908", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("bosTau9", "blat1c", "17909", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################## ## reset default position to the casein gene complex (milk production proteins) ## (DONE - 2018-11-08 - Hiram) ## https://www.ncbi.nlm.nih.gov/pmc/articles/PMC332753/ ## quote: The four genes reside on less than 200 kb of DNA in ## the order CASAS1-CASB-CASAS2-CASK. ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr6:85405597-85664387" where name="bosTau9";' hgcentraltest ############################################################################## # all.joiner update, downloads and in pushQ - (TBD - 2018-05-01 - Hiram) cd $HOME/kent/src/hg/makeDb/schema ~/kent/src/hg/utils/automation/verifyBrowser.pl bosTau9 # 64 tables in database bosTau9 - Cow, Bos taurus # verified 62 tables in database bosTau9, 2 extra tables, 24 optional tables # NCBI RefSeq genes 10 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 crispr10KRanges - extra table # 2 crispr10KTargets - extra table # 9 genbank tables found # verified 29 required tables, 0 missing tables # hg38 chainNet to bosTau9 found 3 required tables # mm10 chainNet to bosTau9 found 3 required tables # hg38 chainNet RBest and syntenic to bosTau9 found 6 optional tables # mm10 chainNet RBest and syntenic to bosTau9 found 3 optional tables # liftOver to previous versions: 3, from previous versions: 3 # fixup all.joiner until this is a clean output joinerCheck -database=bosTau9 -tableCoverage all.joiner joinerCheck -database=bosTau9 -times all.joiner joinerCheck -database=bosTau9 -keys all.joiner cd /hive/data/genomes/bosTau9 # clean up obsolete trackDb work, assuming you have already checked in # these trackDb files into the source tree rm -fr TemporaryTrackDbCheckout time (makeDownloads.pl -workhorse=hgwdev bosTau9) > downloads.log 2>&1 # now ready for pushQ entry mkdir /hive/data/genomes/bosTau9/pushQ cd /hive/data/genomes/bosTau9/pushQ time (makePushQSql.pl -redmineList bosTau9) > bosTau9.pushQ.sql 2> stderr.out # real 9m34.930s # remove the tandemDups and gapOverlap from the file list: sed -i -e "/tandemDups/d" redmine.bosTau9.table.list sed -i -e "/Tandem Dups/d" redmine.bosTau9.releaseLog.txt sed -i -e "/gapOverlap/d" redmine.bosTau9.table.list sed -i -e "/Gap Overlaps/d" redmine.bosTau9.releaseLog.txt # check for errors in stderr.out, some are OK, e.g.: # WARNING: bosTau9 does not have seq # WARNING: bosTau9 does not have extFile # add the path names to the listing files in the redmine issue # in the three appropriate entry boxes: /hive/data/genomes/bosTau9/pushQ/redmine.bosTau9.file.list /hive/data/genomes/bosTau9/pushQ/redmine.bosTau9.releaseLog.txt /hive/data/genomes/bosTau9/pushQ/redmine.bosTau9.table.list -######################################################################### +############################################################################## +# LIFTOVER TO bosTau4 (DONE - 2022-12-06 - Hiram) + ssh hgwdev + mkdir /hive/data/genomes/bosTau9/bed/blat.bosTau4.2022-12-06 + cd /hive/data/genomes/bosTau9/bed/blat.bosTau4.2022-12-06 + doSameSpeciesLiftOver.pl -verbose=2 \ + -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + -target2Bit=/hive/data/genomes/bosTau9/bosTau9.2bit \ + -targetSizes=/hive/data/genomes/bosTau9/chrom.sizes \ + -query2Bit=/hive/data/genomes/bosTau4/bosTau4.2bit \ + -querySizes=/hive/data/genomes/bosTau4/chrom.sizes \ + -ooc=/hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc \ + bosTau9 bosTau4 + time (doSameSpeciesLiftOver.pl -verbose=2 \ + -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + -target2Bit=/hive/data/genomes/bosTau9/bosTau9.2bit \ + -targetSizes=/hive/data/genomes/bosTau9/chrom.sizes \ + -query2Bit=/hive/data/genomes/bosTau4/bosTau4.2bit \ + -querySizes=/hive/data/genomes/bosTau4/chrom.sizes \ + -ooc=/hive/data/genomes/bosTau9/jkStuff/bosTau9.11.ooc \ + bosTau9 bosTau4) > doLiftOverToBosTau9.log 2>&1 + # real 384m15.787s + + # see if the liftOver menus function in the browser from bosTau9 to bosTau4 + +##############################################################################