# for emacs: -*- mode: sh; -*- # This file describes browser build for the eulMac1 # Assembly name: Emacaco_refEf_BWA_oneround # Organism name: Eulemur macaco (black lemur) # Isolate: Harmonia # Sex: female # Taxid: 30602 # BioSample: SAMN03699689 # BioProject: PRJNA284191 # Submitter: University of Chicago # Date: 2015-8-6 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: LGHX01 # Assembly method: BWA/samtools v. Jan-2013 # Genome coverage: 21.0x # Sequencing technology: Illumina HiSeq # RefSeq category: Representative Genome # GenBank assembly accession: GCA_001262655.1 # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_001262675.1 Primary Assembly ## GCA_001262695.1 non-nuclear ############################################################################# ## The non-nuclear sequence are 26 unassembled scaffolds # LGHX01026747.1 LGHX01026748.1 LGHX01026749.1 LGHX01026750.1 LGHX01026751.1 # LGHX01026752.1 LGHX01026753.1 LGHX01026754.1 LGHX01026755.1 LGHX01026756.1 # LGHX01026757.1 LGHX01026758.1 LGHX01026759.1 LGHX01026760.1 LGHX01026761.1 # LGHX01026762.1 LGHX01026763.1 LGHX01026764.1 LGHX01026765.1 LGHX01026766.1 # LGHX01026767.1 LGHX01026768.1 LGHX01026769.1 LGHX01026770.1 LGHX01026771.1 # LGHX01026772.1 ############################################################################# ############################################################################# # obtain photograph (DONE - 2017-10-02 - Hiram) mkdir -p /hive/data/genomes/eulMac1/photo cd /hive/data/genomes/eulMac1/photo # received photo in emal from David haring convert -geometry 400x400 -quality 80 '_DSC1281emm5942 harmonia 19.jpg' \ Eulemur_macaco,jpg printf "photoCreditURL\thttp://dukelemurcenter.zenfolio.com/ photoCreditName\tDavid Haring/Duke Primate Center\n" > photoReference.txt ############################################################################# # fetch sequence from new style download directory (DONE - 2017-10-02 - Hiram) mkdir -p /hive/data/genomes/eulMac1/genbank cd /hive/data/genomes/eulMac1/genbank rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/genbank/vertebrate_mammalian/Eulemur_macaco/all_assembly_versions/GCA_001262655.1_Emacaco_refEf_BWA_oneround/ ./ # sent 260 bytes received 1685753598 bytes 24609545.37 bytes/sec # total size is 1685546289 speedup is 1.00 # measure what we have here: faSize *round_genomic.fna.gz # 2119875225 bases (18835905 N's 2101039320 real 1503484919 upper # 597554401 lower) in 26772 sequences in 1 files # Total size: mean 79182.5 sd 187031.2 min 200 (LGHX01021690.1) # max 3277563 (LGHX01002207.1) median 1872 # %28.19 masked total, %28.44 masked real faCount *round_genomic.fna.gz | tail # seq len A C G T N cpg # total 2119875225 622450511 427776114 428150535 622662160 18835905 23174725 ############################################################################# # fixup to UCSC naming scheme (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulMac1/ucsc cd /hive/data/genomes/eulMac1/ucsc # verify no duplicate sequences: time faToTwoBit ../genbank/*round_genomic.fna.gz genbank.2bit # real 0m59.399s twoBitDup genbank.2bit # should be silent output, otherwise the duplicates need to be removed # since this is an unplaced contig assembly, verify all names are .1: twoBitInfo genbank.2bit stdout | awk '{print $1}' \ | sed -e 's/X[0-9]\+/X/;' | sort | uniq -c # 26772 LGHX.1 # in this case, all the .1's can be changed to: v1 time zcat ../genbank/*round_genomic.fna.gz \ | sed -e 's/.1 Eulemur .*/v1/;' \ | gzip -c > chrUn.eulMac1.fa.gz # real 11m22.965s # there is no supplied AGP file: hgFakeAgp -minContigGap=1 chrUn.eulMac1.fa.gz chrUn.eulMac1.agp # verify fasta and AGP match: time faToTwoBit chr*.fa.gz test.2bit # real 0m58.605s cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail # All AGP and FASTA entries agree - both files are valid # confirm no duplicates, should be silent output twoBitDup test.2bit # verify nothing lost compared to genbank: time twoBitToFa test.2bit stdout | faSize stdin # 2119875225 bases (18835905 N's 2101039320 real 1503484919 upper # 597554401 lower) in 26772 sequences in 1 files # Total size: mean 79182.5 sd 187031.2 min 200 (LGHX01021690v1) # max 3277563 (LGHX01002207v1) median 1872 # %28.19 masked total, %28.44 masked real # real 0m35.104s # same totals as above: # 2119875225 bases (18835905 N's 2101039320 real 1503484919 upper # 597554401 lower) in 26772 sequences in 1 files ############################################################################# # Initial database build (DONE - 2017-10-03 - Hiram) cd /hive/data/genomes/eulMac1 # establish the config.ra file: ~/kent/src/hg/utils/automation/prepConfig.pl eulMac1 mammal primate \ genbank/*_assembly_report.txt > eulMac1.config.ra # going to need a mitoAcc ? # fixup the genBankAccessionID and the ncbiGenomeId # set mitoAcc to none # verify this looks OK: cat eulMac1.config.ra # config parameters for makeGenomeDb.pl: db eulMac1 clade mammal genomeCladePriority 35 scientificName Eulemur macaco commonName Black lemur assemblyDate Aug. 2015 assemblyLabel University of Chicago assemblyShortLabel Emacaco_refEf_BWA_oneround orderKey 2437 mitoAcc none fastaFiles /hive/data/genomes/eulMac1/ucsc/*.fa.gz agpFiles /hive/data/genomes/eulMac1/ucsc/*.agp # qualFiles none dbDbSpeciesDir primate photoCreditURL http://dukelemurcenter.zenfolio.com/ photoCreditName David Haring/Duke Primate Center ncbiGenomeId 39850 ncbiAssemblyId 469011 ncbiAssemblyName Emacaco_refEf_BWA_oneround ncbiBioProject 284191 ncbiBioSample SAMN03699689 genBankAccessionID GCA_001262655.1 taxId 30602 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp eulMac1.config.ra) > agp.log 2>&1 # real 2m12.324s # verify it ran OK: # *** All done! (through the 'agp' step) # this is going to fail on the name "Sclater's lemur" name due to the 'quote # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=db \ eulMac1.config.ra ) > db.log 2>&1 # real 17m35.170s # check in the trackDb files created and add to trackDb/makefile # temporary symlink until after masking ln -s `pwd`/eulMac1.unmasked.2bit /gbdb/eulMac1/eulMac1.2bit ############################################################################# # cytoBandIdeo - (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/cytoBand cd /hive/data/genomes/eulMac1/bed/cytoBand makeCytoBandIdeo.csh eulMac1 ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/cpgIslandsUnmasked cd /hive/data/genomes/eulMac1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/eulMac1/eulMac1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku eulMac1) > do.log 2>&1 # real 8m28.848s cat fb.eulMac1.cpgIslandExtUnmasked.txt # 33641182 bases of 2101039320 (1.601%) in intersection ############################################################################# # running repeat masker (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/repeatMasker cd /hive/data/genomes/eulMac1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku eulMac1) > do.log 2>&1 & # real 462m49.738s cat faSize.rmsk.txt # 2119875225 bases (18835905 N's 2101039320 real 1273216740 upper # 827822580 lower) in 26772 sequences in 1 files # Total size: mean 79182.5 sd 187031.2 min 200 (LGHX01021690v1) # max 3277563 (LGHX01002207v1) median 1872 # %39.05 masked total, %39.40 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 eulMac1 rmsk # 829692002 bases of 2119875225 (39.139%) in intersection # real 0m37.883s # 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 for high contig count assemblies: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' eulMac1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 829692002.000000 # real 0m26.024s ########################################################################## # running simple repeat (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/simpleRepeat cd /hive/data/genomes/eulMac1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=5 eulMac1) > do.log 2>&1 & # real 12m4.537s cat fb.simpleRepeat # 16563239 bases of 2101039320 (0.788%) in intersection # add to this simple repeat to rmsk: cd /hive/data/genomes/eulMac1 twoBitMask eulMac1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed eulMac1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa eulMac1.2bit stdout | faSize stdin > faSize.eulMac1.2bit.txt cat faSize.eulMac1.2bit.txt # 2119875225 bases (18835905 N's 2101039320 real 1272661555 upper # 828377765 lower) in 26772 sequences in 1 files # Total size: mean 79182.5 sd 187031.2 min 200 (LGHX01021690v1) # max 3277563 (LGHX01002207v1) median 1872 # %39.08 masked total, %39.43 masked real # reset the 2bit gbdb symlink: rm /gbdb/eulMac1/eulMac1.2bit ln -s `pwd`/eulMac1.2bit /gbdb/eulMac1/eulMac1.2bit ############################################################################# # CREATE MICROSAT TRACK (DONE - 2017-10-03 - Hiram) ssh hgwdev mkdir /cluster/data/eulMac1/bed/microsat cd /cluster/data/eulMac1/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 eulMac1 microsat microsat.bed # Read 9717 elements of size 4 from microsat.bed ############################################################################# # ucscToINSDC table/track (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/ucscToINSDC cd /hive/data/genomes/eulMac1/bed/ucscToINSDC # there is no chrM sequence in this assembly # find accession for chrM grep chrM ../../eulMac1.agp # empty result # standard procedure does not wrk here, there is no Primary_Assembly/ # hierarchy. Simply make the list manually: cut -f1 ../../chrom.sizes | sort | while read U do C=`echo $U | sed -e 's/v1/.1/;'` printf "%s\t%s\n" "${U}" "${C}" done > ucscToINSDC.txt awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > name.coordinate.tab join ucscToINSDC.txt name.coordinate.tab \ | awk '{printf "%s\t%d\t%d\t%s\n", $1,$3,$4,$2}' > ucscToINSDC.bed # should be same line counts throughout: wc -l * # 26772 name.coordinate.tab # 26772 ucscToINSDC.bed # 26772 ucscToINSDC.txt cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1 # 14 # use the 14 in this sed sed -e "s/21/14/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab eulMac1 ucscToINSDC stdin ucscToINSDC.bed # checkTableCoords should be silent to indicate no errors checkTableCoords eulMac1 # should cover %100 entirely: featureBits -countGaps eulMac1 ucscToINSDC # 2119875225 bases of 2119875225 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/chromAlias cd /hive/data/genomes/eulMac1/bed/chromAlias hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' eulMac1 \ > ucsc.genbank.tab awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab \ | sort > eulMac1.chromAlias.tab hgLoadSqlTab eulMac1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ eulMac1.chromAlias.tab # verify in the browser that the names can be used in the search box # just as if they were chromosome names, e.g.: # LGHX01000033.1:400-500 ############################################################################# # fixup search rule for assembly track/gold table (DONE - 2017-10-03 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/primate/eulMac1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" eulMac1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c 26772 LGHXv1_1 8443 LGHXv1_10 1828 LGHXv1_100 ... ... etc ... # implies a search rule of: 'LGHX[0-9]+([v0-9_]+)?' # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" eulMac1 | wc -l # 635422 hgsql -N -e "select frag from gold;" eulMac1 \ | egrep -e 'LGHX[0-9]+([v0-9_]+)?' | wc -l # 635422 hgsql -N -e "select frag from gold;" eulMac1 \ | egrep -v -e 'LGHX[0-9]+([v0-9_]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/eulMac1/trackDb.ra searchTable gold shortCircuit 1 termRegex LGHX[0-9]+([v0-9_]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box, check full accession name, # accession name without .1 # truncated accession name produces multiple results # and the two chrM accessions, with and without the .1 and partial name # use: accessionName:n-m to display locations n to m on that accession git commit -m 'add gold table search rule refs #20266' trackDb.ra ########################################################################## ## WINDOWMASKER (DONE - 2017-10-04 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/windowMasker cd /hive/data/genomes/eulMac1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev eulMac1) > do.log 2>&1 # real 198m58.528s # Masking statistics cat faSize.eulMac1.cleanWMSdust.txt # 2119875225 bases (18835905 N's 2101039320 real 1491367473 upper # 609671847 lower) in 26772 sequences in 1 files # Total size: mean 79182.5 sd 187031.2 min 200 (LGHX01021690v1) # max 3277563 (LGHX01002207v1) median 1872 # %28.76 masked total, %29.02 masked real cat fb.eulMac1.rmsk.windowmaskerSdust.txt # 361342967 bases of 2119875225 (17.045%) in intersection ########################################################################## # cpgIslands - (DONE - 2017-10-04 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/cpgIslands cd /hive/data/genomes/eulMac1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku eulMac1) > do.log 2>&1 # real 5m36.111s cat fb.eulMac1.cpgIslandExt.txt # 29694380 bases of 2101039320 (1.413%) in intersection ############################################################################## # ncbiRefSeq gene track (TBD - 2016-05-05 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/ncbiRefSeq cd /hive/data/genomes/eulMac1/bed/ncbiRefSeq # working on this script, running step by step: time (/cluster/home/hiram/kent/src/hg/utils/automation/doNcbiRefSeq.pl \ -stop=download -buildDir=`pwd` -bigClusterHub=ku \ -fileServer=hgwdev -workhorse=hgwdev -smallClusterHub=ku -dbHost=hgwdev \ genbank vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 eulMac1) > download.log 2>&1 # real 12m36.320s time (/cluster/home/hiram/kent/src/hg/utils/automation/doNcbiRefSeq.pl \ -continue=process -stop=process -buildDir=`pwd` -bigClusterHub=ku \ -fileServer=hgwdev -workhorse=hgwdev -smallClusterHub=ku -dbHost=hgwdev \ genbank vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 eulMac1) > process.log 2>&1 # real 4m22.621s time (/cluster/home/hiram/kent/src/hg/utils/automation/doNcbiRefSeq.pl \ -continue=load -stop=load -buildDir=`pwd` -bigClusterHub=ku \ -fileServer=hgwdev -workhorse=hgwdev -smallClusterHub=ku -dbHost=hgwdev \ genbank vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 eulMac1) > load.log 2>&1 # real 0m21.690s cat fb.ncbiRefSeq.eulMac1.txt # 74646536 bases of 2725937399 (2.738%) in intersection ############################################################################## # genscan - (DONE - 2017-10-04 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/genscan cd /hive/data/genomes/eulMac1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku eulMac1) > do.log 2>&1 # real 24m23.813s cat fb.eulMac1.genscan.txt # 52771608 bases of 2101039320 (2.512%) in intersection cat fb.eulMac1.genscanSubopt.txt # 56898232 bases of 2101039320 (2.708%) in intersection ############################################################################# # augustus gene track (DONE - 2017-10-04 - Hiram) mkdir /hive/data/genomes/eulMac1/bed/augustus cd /hive/data/genomes/eulMac1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev eulMac1) > do.log 2>&1 # real 61m0.288s cat fb.eulMac1.augustusGene.txt # 49557505 bases of 2101039320 (2.359%) in intersection ############################################################################# # Create kluster run files (DONE - 2017-10-04 - Hiram) # find 'real' base count for this assembly: (numerator below) cd /hive/data/genomes/eulMac1 head -1 faSize.eulMac1.2bit.txt # 2119875225 bases (18835905 N's 2101039320 real 1272661555 upper # 828377765 lower) in 26772 sequences in 1 files # 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 \( 2101039320 / 2861349177 \) \* 1024 # ( 2101039320 / 2861349177 ) * 1024 = 751.905528 # ==> use -repMatch=700 according to size scaled down from 1024 for human. # and rounded down to nearest 100 cd /hive/data/genomes/eulMac1 time blat eulMac1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/eulMac1.11.ooc \ -repMatch=700 # Wrote 26018 overused 11-mers to jkStuff/eulMac1.11.ooc # real 0m37.223s # there are no non-bridged gaps # check non-bridged gaps to see what the typical size is: # hgsql -N \ # -e 'select * from gap where bridge="no" order by size;' eulMac1 \ # | sort -k7,7nr # minimum size is 50000 # gapToLift -verbose=2 -minGap=50000 eulMac1 \ # jkStuff/eulMac1.nonBridged.lft -bedFile=jkStuff/eulMac1.nonBridged.bed ######################################################################### # lastz/chain/net swap from hg38 (DONE - 2017-10-04 - Hiram) # alignment to hg38 cd /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04 cat fb.hg38.chainEulMac1Link.txt # 1027856175 bases of 3049335806 (33.708%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eulMac1) \ > rbest.log 2>&1 & # real 220m20.185s # and for the swap: mkdir /hive/data/genomes/eulMac1/bed/blastz.hg38.swap cd /hive/data/genomes/eulMac1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 47m2.650s cat fb.eulMac1.chainHg38Link.txt # 979925982 bases of 2101039320 (46.640%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulMac1 hg38) \ > rbest.log 2>&1 # real 200m34.710s ######################################################################### # lastz/chain/net swap from mm10 (DONE - 2017-10-05 - Hiram) # alignment on mm10 cd /hive/data/genomes/mm10/bed/lastzEulMac1.2017-10-05 cat fb.mm10.chainEulMac1Link.txt # 925968814 bases of 2652783500 (34.906%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` mm10 eulMac1) \ > rbest.log 2>&1 & # real 334m49.287s mkdir /hive/data/genomes/eulMac1/bed/blastz.mm10.swap cd /hive/data/genomes/eulMac1/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzEulMac1.2017-10-05/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 64m52.738s cat fb.eulMac1.chainMm10Link.txt # 895308387 bases of 2101039320 (42.613%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulMac1 mm10) \ > rbest.log 2>&1 # real 267m17.552s ############################################################################## # GENBANK AUTO UPDATE (DONE - 2017-10-04 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Eulemur albifrons 1 0 0 # Eulemur fulvus 8 0 0 # Eulemur fulvus collaris 2 0 0 # Eulemur mongoz 2 0 0 # edit etc/genbank.conf to add eulMac1 just before susScr3 # eulMac1 (Black lemur / Eulemur macaco / taxId 30602) eulMac1.serverGenome = /hive/data/genomes/eulMac1/eulMac1.2bit eulMac1.clusterGenome = /hive/data/genomes/eulMac1/eulMac1.2bit eulMac1.ooc = /hive/data/genomes/eulMac1/jkStuff/eulMac1.11.ooc eulMac1.lift = no eulMac1.refseq.mrna.native.pslCDnaFilter = ${lowCover.refseq.mrna.native.pslCDnaFilter} eulMac1.refseq.mrna.xeno.pslCDnaFilter = ${lowCover.refseq.mrna.xeno.pslCDnaFilter} eulMac1.genbank.mrna.native.pslCDnaFilter = ${lowCover.genbank.mrna.native.pslCDnaFilter} eulMac1.genbank.mrna.xeno.pslCDnaFilter = ${lowCover.genbank.mrna.xeno.pslCDnaFilter} eulMac1.genbank.est.native.pslCDnaFilter = ${lowCover.genbank.est.native.pslCDnaFilter} eulMac1.genbank.est.xeno.pslCDnaFilter = ${lowCover.genbank.est.xeno.pslCDnaFilter} eulMac1.downloadDir = eulMac1 # there are no refseq mrna native eulMac1.refseq.mrna.native.load = no eulMac1.refseq.mrna.xeno.load = yes # DO NOT NEED genbank.mrna.xeno except for human, mouse eulMac1.genbank.mrna.xeno.load = no eulMac1.genbank.mrna.native.load = no eulMac1.genbank.est.native.load = no eulMac1.perChromTables = no # And edit src/lib/gbGenome.c to add new species two lines: # static char *eulMacNames[] = {"Eulemur macaco", NULL}; # {"eulMac", eulMacNames}, git commit -m \ "adding eulFla1 and eulMac1 refs #20265 #20266" \ etc/genbank.conf src/lib/gbGenome.c git push # update /cluster/data/genbank/: make etc-update make install-server screen # control this business with a screen since it takes a while cd /cluster/data/genbank time ./bin/gbAlignStep -initial eulMac1 # logFile: var/build/logs/2017.10.04-19:56:27.eulMac1.initalign.log # real 41m14.159s tail -2 var/build/logs/2017.10.04-19:56:27.eulMac1.initalign.log # hgwdev 2017.10.04-20:35:40 eulMac1.initalign: Succeeded: eulMac1 # hgwdev 2017.10.04-20:37:41 eulMac1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.eulMac1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad eulMac1 # logFile: var/dbload/hgwdev/logs/2017.10.04-20:53:39.eulMac1.dbload.log # real 4m52.237s tail -1 var/dbload/hgwdev/logs/2017.10.04-20:53:39.eulMac1.dbload.log # hgwdev 2017.10.04-20:58:32 eulMac1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add eulMac1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m \ "Added eulMac1 - Black lemur - Eulemur macaco refs #20266" \ etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################## # BLATSERVERS ENTRY (DONE - 2017-10-04 - 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 ("eulMac1", "blat1d", "17888", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("eulMac1", "blat1d", "17889", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################## # set default position similar location as hg38 (DONE - 2017-10-04 - Hiram) hgsql -e \ 'update dbDb set defaultPos="LGHX01001029v1:67346-92292" where name="eulMac1";' \ hgcentraltest ############################################################################## # all.joiner update, downloads and in pushQ - (DONE - 2017-10-06 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until these are all clean outputs: joinerCheck -database=eulMac1 -tableCoverage all.joiner joinerCheck -database=eulMac1 -times all.joiner joinerCheck -database=eulMac1 -keys all.joiner cd /hive/data/genomes/eulMac1 time (makeDownloads.pl eulMac1) > downloads.log 2>&1 # real 15m27.413s # now ready for pushQ entry mkdir /hive/data/genomes/eulMac1/pushQ cd /hive/data/genomes/eulMac1/pushQ time (makePushQSql.pl -redmineList eulMac1) \ > eulMac1.pushQ.sql 2> stderr.out # real 3m49.428s # check for errors in stderr.out, some are OK, e.g.: # writing redmine listings to # redmine.eulMac1.file.list # redmine.eulMac1.table.list # redmine.eulMac1.releaseLog.txt # WARNING: eulMac1 does not have ucscToRefSeq # WARNING: eulMac1 does not have seq # WARNING: eulMac1 does not have extFile # WARNING: eulMac1 does not have estOrientInfo # WARNING: eulMac1 does not have mrnaOrientInfo # examine these files to make sure they appear sane, # then enter the full path names of these listing files: # /hive/data/genomes/eulMac1/pushQ/redmine.eulMac1.file.list # /hive/data/genomes/eulMac1/pushQ/redmine.eulMac1.releaseLog.txt # /hive/data/genomes/eulMac1/pushQ/redmine.eulMac1.table.list # into the Redmine #20266 and set to QA Ready. #########################################################################