# for emacs: -*- mode: sh; -*- # This file describes browser build for the rouAeg1 # New starting procedure, 2016-04-12 # # Must find the photograph first, can not continue until finding # the photograph. ######################################################################### # Initial steps, find photograph (DONE - 2016-04-12 - Hiram) # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/rouAeg1 cd ~/kent/src/hg/makeDb/doc/rouAeg1 sed -e 's/rheMac8/rouAeg1/g; s/RheMac8/RouAeg1/g; s/DONE/TBD/g;' \ ../rheMac8/initialBuild.txt > initialBuild.txt # the files required are probably already here, take a look into: # /hive/data/outside/ncbi/genomes/refseq///all_assembly_versions # and merely symlink them in: mkdir -p /hive/data/genomes/rouAeg1/refseq cd -p /hive/data/genomes/rouAeg1/refseq ln -s /hive/data/outside/ncbi/genomes/refseq/vertebrate_mammalian/Rousettus_aegyptiacus/all_assembly_versions/* ./ # need to find the photo, check NCBI 'genome' page to see what photo they # display, if they do not have one, can usually find a public domain photo # in wikimedia commons: https://commons.wikimedia.org/wiki/Main_Page mkdir /hive/data/genomes/rouAeg1/photo cd /hive/data/genomes/rouAeg1/photo # this photo from: Oren Peles https://www.linkedin.com/in/oren-peles-398aa617 # to commons via: https://commons.wikimedia.org/wiki/User:MathKnight wget --timestamping \ "https://upload.wikimedia.org/wikipedia/commons/1/15/PikiWiki_Israel_11327_Wildlife_and_Plants_of_Israel-Bat-003.jpg" convert -geometry 400x300 \ PikiWiki_Israel_11327_Wildlife_and_Plants_of_Israel-Bat-003.jpg \ Rousettus_aegyptiacus.jpg # check this Rousettus_aegyptiacus.jpg into ~/kent/src/hg/htdocs/images/ # and copy that to /usr/local/apache/htdocs/images/ # construct the required photoReference.txt cd /hive/data/genomes/rouAeg1 printf "photoCreditURL https://commons.wikimedia.org/wiki/User:MathKnight photoCreditName photographer Oren Peles via WikimediaCommons user MathKnight\n" \ > photoReference.txt # this information is from the top of # rouAeg1/refseq/*_assembly_report.txt # (aka: rouAeg1/refseq/GCF_001466805.2_Raegyp2.0_assembly_report.txt) # Assembly name: Raegyp2.0 # Organism name: Rousettus aegyptiacus (Egyptian rousette) # Isolate: 1219 # Sex: male # Taxid: 9407 # BioSample: SAMN04287759 # BioProject: PRJNA309421 # Submitter: Boston University School of Medicine # Date: 2016-3-17 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: LOCP02 # Assembly method: SparseAssembler v. OCTOBER-2015; DBG2OLC v. OCTOBER-2015; # LINKS v. 1.5.1; L_RNA_Scaffolder v. OCTOBER-2015; SSPACE v. 3.0 # Expected final version: No # Genome coverage: 169.2x # Sequencing technology: Illumina HiSeq; PacBio # GenBank assembly accession: GCA_001466805.2 (latest) # RefSeq assembly accession: GCF_001466805.2 (species-representative latest) # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_001466885.2 GCF_001466885.2 Primary Assembly ## GCF_000053295.1 non-nuclear ############################################################################# # establish config.ra file (DONE - Hiram - 2016-04-12) cd /hive/data/genomes/rouAeg1 ~/kent/src/hg/utils/automation/prepConfig.pl rouAeg1 mammal bats \ refseq/*_assembly_report.txt > rouAeg1.config.ra # verify it looks sane cat rouAeg1.config.ra # config parameters for makeGenomeDb.pl: db rouAeg1 clade mammal genomeCladePriority 35 scientificName Rousettus aegyptiacus commonName Egyptian rousette assemblyDate Mar 2016 assemblyLabel Boston University School of Medicine assemblyShortLabel Raegyp2.0 orderKey 5316 # mitochondrial sequence included in refseq release # mitoAcc NC_007393.1 mitoAcc none fastaFiles /hive/data/genomes/rouAeg1/ucsc/*.fa.gz agpFiles /hive/data/genomes/rouAeg1/ucsc/*.agp # qualFiles none dbDbSpeciesDir bats photoCreditURL https://commons.wikimedia.org/wiki/User:MathKnight photoCreditName photographer Oren Peles via WikimediaCommons user MathKnight ncbiGenomeId 7672 ncbiAssemblyId 707221 ncbiAssemblyName Raegyp2.0 ncbiBioProject 309421 genBankAccessionID GCF_001466805.2 taxId 9407 ############################################################################# # setup UCSC named files (DONE - 2016-04-12 - Hiram) mkdir /hive/data/genomes/rouAeg1/ucsc cd /hive/data/genomes/rouAeg1/ucsc # measure what is in the refseq release: faSize ../refseq/*genomic.fna.gz # 1910250568 bases (482376 N's 1909768192 real 1408250300 upper 501517892 lower) in 2490 sequences in 1 files # Total size: mean 767168.9 sd 1115019.8 min 1869 (NW_015494464.1) max 8996366 (NW_015492809.1) median 262214 # %26.25 masked total, %26.26 masked real # check for duplicate sequences: time faToTwoBit -noMask ../refseq/*_genomic.fna.gz refseq.2bit # real 0m52.302s twoBitDup refseq.2bit # no output is a good result, otherwise, would have to eliminate duplicates # bash syntax here mitoAcc=`grep "^# mitoAcc" ../rouAeg1.config.ra | awk '{print $NF}'` printf "# mitoAcc %s\n" "$mitoAcc" # mitoAcc NC_007393.1 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 # no longer need this 2bit rm refseq.2bit # the mito sequence is already named chrM printf "NC_007393.1\n" > excludeMito.txt # simple conversion of names .1 to v1 time faSomeRecords -exclude ../refseq/*_genomic.fna.gz excludeMito.txt \ stdout | sed -e 's/.1 Rou.*/v1/;' > ucsc.fa # real 1m49.479s time gzip ucsc.fa # real 10m21.337s zcat ../refseq/*_assembly_structure/Primary_Assembly/unplaced_scaffolds/AGP/unplaced.scaf.agp.gz \ | sed -e 's/.1\t/v1\t/;' > ucsc.agp # verify correspondence faToTwoBit *.fa.gz test.2bit cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail # All AGP and FASTA entries agree - both files are valid # no longer need these 2bit files rm test.2bit refseq.2bit ############################################################################# # Initial database build (DONE - 2016-04-13 - Hiram) # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp rouAeg1.config.ra) > agp.log 2>&1 # real 1m44.502s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db rouAeg1.config.ra) > db.log 2>&1 # real 16m6.304s # forgot to drop db rouAeg1 for a rerunning time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=dbDb rouAeg1.config.ra) > dbDb.log 2>&1 # real 0m9.467s # check in the trackDb files created and add to trackDb/makefile ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2016-04-14 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/cpgIslandsUnmasked cd /hive/data/genomes/rouAeg1/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/rouAeg1/rouAeg1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku rouAeg1) > do.log 2>&1 # real 5m44.521s cat fb.rouAeg1.cpgIslandExtUnmasked.txt # 86926460 bases of 1910250568 (4.551%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2016-04-14 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/cytoBand cd /hive/data/genomes/rouAeg1/bed/cytoBand makeCytoBandIdeo.csh rouAeg1 ############################################################################# # ucscToINSDC table/track (DONE - 2016-04-14 - Hiram) # the sequence here is working for a 'refseq' assembly with a chrM # situation may be specific depending upon what is available in the assembly mkdir /hive/data/genomes/rouAeg1/bed/ucscToINSDC cd /hive/data/genomes/rouAeg1/bed/ucscToINSDC # find accession for chrM grep chrM ../../rouAeg1.agp # chrM 1 16706 1 O NC_007393.1 1 16706 + # use that accession here: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../refseq/GCF_*structure/Primary_Assembly NC_007393.1 awk '{printf "%s\t%s\n", $2, $1}' ucscToINSDC.txt | sort > insdcToUcsc.txt # there is no name for chrM/NC_007393.1 sequence, there is no such # sequence with an INSDC name grep -v "^#" ../../refseq/GCF*_assembly_report.txt | cut -f5,7 \ | sed -e 's/na\b/notAvailable/;' | awk '{printf "%s\t%s\n", $2, $1}' \ | sort > insdc.refseq.txt # the sed \b means to match word awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > name.coordinate.tab # the tr commands avoid the problem of trying to use the -t argument # to the join command which doesn't accept -t'\t' but instead has # to use the unseen/can not copy command ctrl-v i join insdc.refseq.txt insdcToUcsc.txt | tr '[ ]' '[\t]' | sort -k3 \ | join -2 3 name.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-3,5 \ > ucscToINSDC.bed # should be same line counts throughout: wc -l * # 2490 insdc.refseq.txt # 2490 insdcToUcsc.txt # 2490 name.coordinate.tab # 2490 ucscToINSDC.bed # 2490 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 rouAeg1 ucscToINSDC stdin ucscToINSDC.bed checkTableCoords rouAeg1 # should cover %100 entirely: featureBits -countGaps rouAeg1 ucscToINSDC # 1910250568 bases of 1910250568 (100.000%) in intersection ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2016-04-14 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/bats/rouAeg1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" rouAeg1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c # 2489 LOCP.1 # 1 NC_.1 # implies a search rule of: '[CLNOP_]+[0-9]+(\.[0-9]+)?' # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" rouAeg1 | wc -l # 2490 hgsql -N -e "select frag from gold;" rouAeg1 \ | egrep -e '[CLNOP_]+[0-9]+(\.[0-9]+)?' | wc -l # 2490 hgsql -N -e "select frag from gold;" rouAeg1 \ | egrep -v -e '[CLNOP_]+[0-9]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/rouAeg1/trackDb.ra searchTable gold shortCircuit 1 termRegex [CLNOP_]+[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 - 2016-04-14 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/repeatMasker cd /hive/data/genomes/rouAeg1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku rouAeg1) > do.log 2>&1 # real 572m12.798s cat faSize.rmsk.txt # 1910250568 bases (482376 N's 1909768192 real 1292012610 upper 617755582 lower) # in 2490 sequences in 1 files # Total size: mean 767168.9 sd 1115019.8 min 1869 (NW_015494464v1) # max 8996366 (NW_015492809v1) median 262214 # %32.34 masked total, %32.35 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 rouAeg1 rmsk # 617755753 bases of 1910250568 (32.339%) in intersection # real 0m29.128s # 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: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' rouAeg1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 617755753.000000 # real 0m24.382s ########################################################################## # running simple repeat (DONE - 2016-04-14 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/simpleRepeat cd /hive/data/genomes/rouAeg1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ rouAeg1) > do.log 2>&1 # real 9m33.566s cat fb.simpleRepeat # 19230683 bases of 1910250568 (1.007%) in intersection # add to rmsk after it is done: cd /hive/data/genomes/rouAeg1 twoBitMask rouAeg1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed rouAeg1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa rouAeg1.2bit stdout | faSize stdin > faSize.rouAeg1.2bit.txt cat faSize.rouAeg1.2bit.txt # 1910250568 bases (482376 N's 1909768192 real 1291369125 upper # 618399067 lower) in 2490 sequences in 1 files # max 8996366 (NW_015492809v1) median 262214 # %32.37 masked total, %32.38 masked real rm /gbdb/rouAeg1/rouAeg1.2bit ln -s `pwd`/rouAeg1.2bit /gbdb/rouAeg1/rouAeg1.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2016-04-15 - Hiram) ssh hgwdev mkdir /cluster/data/rouAeg1/bed/microsat cd /cluster/data/rouAeg1/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 rouAeg1 microsat microsat.bed # Read 43339 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2016-04-15 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/windowMasker cd /hive/data/genomes/rouAeg1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev rouAeg1) > do.log 2>&1 # real 179m23.881s # Masking statistics cat faSize.rouAeg1.cleanWMSdust.txt # 1910250568 bases (482376 N's 1909768192 real 1396731798 upper 513036394 lower) # in 2490 sequences in 1 files # Total size: mean 767168.9 sd 1115019.8 min 1869 (NW_015494464v1) # max 8996366 (NW_015492809v1) median 262214 # %26.86 masked total, %26.86 masked real cat fb.rouAeg1.rmsk.windowmaskerSdust.txt # 242421551 bases of 1910250568 (12.691%) in intersection ########################################################################## # ncbiRefSeq - (DONE - 2016-04-15 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/ncbiRefSeq cd /hive/data/genomes/rouAeg1/bed/ncbiRefSeq 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 Rousettus_aegyptiacus \ GCF_001466805.2_Raegyp2.0 rouAeg1) > download.log 2>&1 # real 17m29.693s time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl \ -buildDir=`pwd` -bigClusterHub=ku -dbHost=hgwdev \ -continue=process -stop=process \ -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_mammalian Rousettus_aegyptiacus \ GCF_001466805.2_Raegyp2.0 rouAeg1) > process.log 2>&1 # real 5m46.726s time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl \ -buildDir=`pwd` -bigClusterHub=ku -dbHost=hgwdev \ -continue=load -stop=load \ -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_mammalian Rousettus_aegyptiacus \ GCF_001466805.2_Raegyp2.0 rouAeg1) > load.log 2>&1 # real 0m27.378s featureBits -countGaps rouAeg1 ncbiRefSeq # 99026731 bases of 1910250568 (5.184%) in intersection ########################################################################## # cpgIslands - (DONE - 2016-04-15 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/cpgIslands cd /hive/data/genomes/rouAeg1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku rouAeg1) > do.log 2>&1 # real 5m19.286s cat fb.rouAeg1.cpgIslandExt.txt # 80027987 bases of 1910250568 (4.189%) in intersection ############################################################################## # genscan - (DONE - 2016-04-15 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/genscan cd /hive/data/genomes/rouAeg1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku rouAeg1) > do.log 2>&1 # real 17m23.384s cat fb.rouAeg1.genscan.txt # 60809045 bases of 1910250568 (3.183%) in intersection cat fb.rouAeg1.genscanSubopt.txt # 50801373 bases of 1910250568 (2.659%) in intersection ######################################################################## # Create kluster run files (TBD - 2016-02-03 - Hiram) # numerator is rouAeg1 gapless bases "real" as reported by: featureBits -noRandom -noHap rouAeg1 gap # 0 bases of 1910250568 (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 \( 1910250568 / 2861349177 \) \* 1024 # ( 1910250568 / 2861349177 ) * 1024 = 683.627359 # ==> use -repMatch=600 according to size scaled down from 1024 for human. # and rounded down to nearest 50 cd /hive/data/genomes/rouAeg1 blat rouAeg1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/rouAeg1.11.ooc \ -repMatch=600 # Wrote 30666 overused 11-mers to jkStuff/rouAeg1.11.ooc # there are no gaps ? hgsql -e 'select count(*) from gap;' rouAeg1 # +----------+ # | count(*) | # +----------+ # | 0 | # +----------+ # check non-bridged gaps to see what the typical size is: # hgsql -N \ # -e 'select * from gap where bridge="no" order by size;' rouAeg1 \ # | 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 rouAeg1 jkStuff/nonBridged.lft \ # -bedFile=jkStuff/nonBridged.bed ######################################################################## # GENBANK AUTO UPDATE (TBD - 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 # Rousettus aegyptiacus 9 0 0 # Edit src/lib/gbGenome.c to add new species # edit etc/genbank.conf to add rouAeg1 just before saiBol1 # rouAeg1 Rousettus aegyptiacus (Egyptian rousette (fruit bat)) rouAeg1.serverGenome = /hive/data/genomes/rouAeg1/rouAeg1.2bit rouAeg1.clusterGenome = /hive/data/genomes/rouAeg1/rouAeg1.2bit rouAeg1.ooc = /hive/data/genomes/rouAeg1/jkStuff/rouAeg1.11.ooc rouAeg1.lift = no rouAeg1.perChromTables = no rouAeg1.refseq.mrna.native.pslCDnaFilter = ${lowCover.refseq.mrna.native.pslCDnaFilter} rouAeg1.refseq.mrna.xeno.pslCDnaFilter = ${lowCover.refseq.mrna.xeno.pslCDnaFilter} rouAeg1.genbank.mrna.native.pslCDnaFilter = ${lowCover.genbank.mrna.native.pslCDnaFilter} rouAeg1.genbank.mrna.xeno.pslCDnaFilter = ${lowCover.genbank.mrna.xeno.pslCDnaFilter} rouAeg1.genbank.est.native.pslCDnaFilter = ${lowCover.genbank.est.native.pslCDnaFilter} rouAeg1.genbank.est.xeno.pslCDnaFilter = ${lowCover.genbank.est.xeno.pslCDnaFilter} # refseq.mrna native and xeno are default yes # genbank.mrna and genbank.est native are default yes, the xeno is default no rouAeg1.refseq.mrna.native.load = no rouAeg1.genbank.est.native.load = no rouAeg1.downloadDir = rouAeg1 git commit -m "Added rouAeg Egyptian rousette (fruit bat) - Rousettus aegyptiacus; refs #17167" 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 rouAeg1 # logFile: var/build/logs/2016.04.19-13:27:55.rouAeg1.initalign.log # real 472m50.234s tail -2 var/build/logs/2016.04.19-13:27:55.rouAeg1.initalign.log # hgwdev 2016.04.19-21:19:14 rouAeg1.initalign: Succeeded: rouAeg1 # hgwdev 2016.04.19-21:20:45 rouAeg1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.rouAeg1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad rouAeg1 # logFile: var/dbload/hgwdev/logs/2016.04.20-10:24:34.rouAeg1.dbload.log # real 10m50.471s tail -1 var/dbload/hgwdev/logs/2016.04.20-10:24:34.rouAeg1.dbload.log # hgwdev 2016.04.20-10:35:24 rouAeg1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add rouAeg1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m "Added rouAeg1 Egyptian rousette fruit bat - Rousettus aegyptiacus - refs #17167" etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################# # augustus gene track (DONE - 2016-04-20 - Hiram) mkdir /hive/data/genomes/rouAeg1/bed/augustus cd /hive/data/genomes/rouAeg1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev rouAeg1) > do.log 2>&1 # real 70m56.666s cat fb.rouAeg1.augustusGene.txt # 54429943 bases of 1910250568 (2.849%) in intersection ######################################################################### # BLATSERVERS ENTRY (DONE - 2016-04-19 - 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 ("rouAeg1", "blat1d", "17862", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("rouAeg1", "blat1d", "17863", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to rheMac3 position (TBD - 2016-02-09 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr14:63580522-63594072" where name="rouAeg1";' 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=rouAeg1 -tableCoverage all.joiner joinerCheck -database=rouAeg1 -times all.joiner joinerCheck -database=rouAeg1 -keys all.joiner cd /hive/data/genomes/rouAeg1 time (makeDownloads.pl rouAeg1) > downloads.log 2>&1 # real 27m1.207s # now ready for pushQ entry mkdir /hive/data/genomes/rouAeg1/pushQ cd /hive/data/genomes/rouAeg1/pushQ time makePushQSql.pl rouAeg1 > rouAeg1.pushQ.sql 2> stderr.out # check for errors in stderr.out, some are OK, e.g.: # WARNING: hgwdev does not have /gbdb/rouAeg1/wib/gc5Base.wib # WARNING: hgwdev does not have /gbdb/rouAeg1/wib/quality.wib # WARNING: hgwdev does not have /gbdb/rouAeg1/bbi/quality.bw # WARNING: rouAeg1 does not have seq # WARNING: rouAeg1 does not have extFile # copy it to hgwbeta scp -p rouAeg1.pushQ.sql qateam@hgwbeta:/tmp/ ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/rouAeg1.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly #########################################################################