# for emacs: -*- mode: sh; -*- # This file describes browser build for the aotNan1 # Aotus nancymaae - Ma's night monkey # chrMT listed in assembly == NC_018116.1 == JN161100.1 # Assembly name: Anan_2.0 # Organism name: Aotus nancymaae (Ma's night monkey) # Isolate: 86115 # Sex: female # Taxid: 37293 # BioSample: SAMN03121886 # BioProject: PRJNA251539 # Submitter: Baylor College of Medicine # Date: 2017-6-9 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: JYKP02 # Assembly method: PBJelly2 v. 14.9.9; AllPathsLG v. 48744; Atlas Link v. 1.1; Atlas GapFill v. 2.2 # Expected final version: no # Genome coverage: 132.4x # Sequencing technology: PacBio RSII; PacBio Sequel; Illumina # RefSeq category: Representative Genome # GenBank assembly accession: GCA_000952055.2 # RefSeq assembly accession: GCF_000952055.2 # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000952065.2 GCF_000952065.2 Primary Assembly ## GCF_000982815.1 non-nuclear # ############################################################################# # obtain photograph (DONE - 2017-02-14 - Hiram) mkdir -p /hive/data/genomes/aotNan1/photo cd /hive/data/genomes/aotNan1/photo wget -O photoFile "https://upload.wikimedia.org/wikipedia/commons/9/97/Aotus.jpeg" convert -sharpen 0 -normalize -geometry 400x400 -quality 80 photoFile \ Aotus_nancymaae.jpg printf "photoCreditURL https://commons.wikimedia.org/wiki/File:Aotus.jpeg photoCreditName WikiMedia Commons: MarcSaCi " > ../photoReference.txt ############################################################################# # fetch sequence from new style download directory (DONE - 2017-09-21 - Hiram) mkdir -p /hive/data/genomes/aotNan1/refseq cd /hive/data/genomes/aotNan1/refseq rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_mammalian/Aotus_nancymaae/all_assembly_versions/GCF_000952055.2_Anan_2.0/ ./ # real 2m17.562s # sent 562 bytes received 3175894662 bytes 23097419.81 bytes/sec # total size is 3175504260 speedup is 1.00 # measure what we have here: faSize *0_genomic.fna.gz # 2861684817 bases (147245328 N's 2714439489 real 1768539569 upper # 945899920 lower) in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248.1) # max 42888418 (NW_018505940.1) median 3826 # %33.05 masked total, %34.85 masked real faCount *0_genomic.fna.gz | tail # #seq len A C G T N cpg # total 2861684817 804201968 552779694 553026611 804431216 147245328 26386584 ############################################################################# # fixup to UCSC naming scheme (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/aotNan1/ucsc cd /hive/data/genomes/aotNan1/ucsc # verify no duplicate sequences: time faToTwoBit ../refseq/*0_genomic.fna.gz refseq.2bit # real 1m22.482s twoBitDup refseq.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 refseq.2bit stdout | awk '{print $1}' \ | sed -e 's/_[0-9]\+//;' | sort | uniq -c # 1 NC.1 # 28921 NW.1 # in this case, all the .1's can be changed to: v1 zcat ../refseq/*0_assembly_structure/Primary_Assembly/unplaced_scaffolds/AGP/unplaced.scaf.agp.gz \ | grep -v "^#" | sed -e 's/\.1/v1/;' > chrUn.aotNan1.agp zcat ../refseq/*0_assembly_structure/non-nuclear/assembled_chromosomes/AGP/chrMT.comp.agp.gz \ | grep -v "^#" | sed -e 's/^NC_[0-9.]\+/chrM/;' > chrM.aotNan1.agp zcat ../refseq/*0_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \ | sed -e 's/.1 Aotus .*/v1/;' > chrUn.aotNan1.fa zcat ../refseq/*0_assembly_structure/non-nuclear/assembled_chromosomes/FASTA/chrMT.fna.gz \ | sed -e 's/NC_.*/chrM/;' > chrM.aotNan1.fa gzip chr*.fa # verify fasta and AGP match: time faToTwoBit chr*.fa.gz test.2bit # real 1m15.422s cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail # All AGP and FASTA entries agree - both files are valid # verify nothing lost compared to genbank: time twoBitToFa test.2bit stdout | faSize stdin # 2861684817 bases (147245328 N's 2714439489 real 2714439489 upper 0 lower) # in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248v1) # max 42888418 (NW_018505940v1) median 3826 # %0.00 masked total, %0.00 masked real # same totals as above: # 2861684817 bases (147245328 N's 2714439489 real 1768539569 upper # 945899920 lower) in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248.1) # max 42888418 (NW_018505940.1) median 3826 # %33.05 masked total, %34.85 masked real ############################################################################# # Initial database build (DONE - 2017-09-21 - Hiram) cd /hive/data/genomes/aotNan1 # establish the config.ra file: ~/kent/src/hg/utils/automation/prepConfig.pl aotNan1 mammal primate \ refseq/*_assembly_report.txt > aotNan1.config.ra # verify this looks OK: cat aotNan1.config.ra # config parameters for makeGenomeDb.pl: db aotNan1 clade mammal genomeCladePriority 35 scientificName Aotus nancymaae commonName Ma's night monkey assemblyDate Jun. 2017 assemblyLabel Baylor College of Medicine assemblyShortLabel Anan_2.0 orderKey 13320 # mitochondrial sequence included in refseq release # mitoAcc NC_018116.1 mitoAcc none fastaFiles /hive/data/genomes/aotNan1/ucsc/*.fa.gz agpFiles /hive/data/genomes/aotNan1/ucsc/*.agp # qualFiles none dbDbSpeciesDir primate photoCreditURL https://commons.wikimedia.org/wiki/File:Aotus.jpeg photoCreditName WikiMedia Commons: MarcSaCi ncbiGenomeId 14430 ncbiAssemblyId 1130511 ncbiAssemblyName Anan_2.0 ncbiBioProject 251539 ncbiBioSample SAMN03121886 genBankAccessionID GCF_000952055.2 taxId 37293 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp aotNan1.config.ra) > agp.log 2>&1 # real 2m44.493s # verify it ran OK: # *** All done! (through the 'agp' step) # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=db \ aotNan1.config.ra ) > db.log 2>&1 # real 21m54.488s # trouble with the name "Ma's night monkey" due to the ' quote # complete the SQL add: hgsql hgcentraltest -e "INSERT INTO defaultDb (genome, name) VALUES (\"Ma's night monkey\", \"aotNan1\")" hgsql hgcentraltest -e "INSERT INTO genomeClade (genome, clade, priority) VALUES (\"Ma's night monkey\", \"mammal\", 35)" # continuing time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=trackDb \ aotNan1.config.ra ) > trackDb.log 2>&1 # check in the trackDb files created and add to trackDb/makefile # temporary symlink until after masking ln -s `pwd`/aotNan1.unmasked.2bit /gbdb/aotNan1/aotNan1.2bit ############################################################################# # cytoBandIdeo - (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/cytoBand cd /hive/data/genomes/aotNan1/bed/cytoBand makeCytoBandIdeo.csh aotNan1 ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/cpgIslandsUnmasked cd /hive/data/genomes/aotNan1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/aotNan1/aotNan1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku aotNan1) > do.log 2>&1 # real 19m14.585s cat fb.aotNan1.cpgIslandExtUnmasked.txt # 25664010 bases of 2714439490 (0.945%) in intersection ############################################################################# # running repeat masker (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/repeatMasker cd /hive/data/genomes/aotNan1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku aotNan1) > do.log 2>&1 & # real 650m26.222s cat faSize.rmsk.txt # 2861684817 bases (147245328 N's 2714439489 real 1429443047 upper # 1284996442 lower) in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248v1) # max 42888418 (NW_018505940v1) median 3826 # %44.90 masked total, %47.34 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 aotNan1 rmsk # 1285173500 bases of 2861684817 (44.910%) in intersection # real 0m44.054s # 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 for high contig count assemblies: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' aotNan1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 1285173500.000000 # real 0m38.223s ########################################################################## # running simple repeat (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/simpleRepeat cd /hive/data/genomes/aotNan1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=5 aotNan1) > do.log 2>&1 & # real 10m16.197s cat fb.simpleRepeat # 57707811 bases of 2714439490 (2.126%) in intersection # add to this simple repeat to rmsk: cd /hive/data/genomes/aotNan1 twoBitMask aotNan1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed aotNan1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa aotNan1.2bit stdout | faSize stdin > faSize.aotNan1.2bit.txt cat faSize.aotNan1.2bit.txt # 2861684817 bases (147245328 N's 2714439489 real 1428220108 upper # 1286219381 lower) in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248v1) # max 42888418 (NW_018505940v1) median 3826 # %44.95 masked total, %47.38 masked real # reset the 2bit gbdb symlink: rm /gbdb/aotNan1/aotNan1.2bit ln -s `pwd`/aotNan1.2bit /gbdb/aotNan1/aotNan1.2bit ############################################################################# # CREATE MICROSAT TRACK (DONE - 2017-08-22 - Hiram) ssh hgwdev mkdir /cluster/data/aotNan1/bed/microsat cd /cluster/data/aotNan1/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 aotNan1 microsat microsat.bed # Read 33659 elements of size 4 from microsat.bed ############################################################################# # ucscToINSDC table/track (DONE - 2017-09-25 - 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/aotNan1/bed/ucscToINSDC cd /hive/data/genomes/aotNan1/bed/ucscToINSDC # find accession for chrM grep chrM ../../aotNan1.agp # chrM 1 16469 1 O NC_018116.1 1 16469 + # use that accession here: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../refseq/GCF_*structure/Primary_Assembly NC_018116.1 # this is actually ucscToRefSeq since this is a RefSeq assembly sort -k2 ucscToINSDC.txt > ucscToRefSeq.txt rm -f ucscToINSDC.txt awk '{printf "%s\t%s\n", $2, $1}' ucscToRefSeq.txt | sort > refseqToUcsc.txt # there is no INSDC name in the assembly_report for chrM/NC_018116.1 # use the INSDC name from before: JN161100.1 grep -v "^#" ../../refseq/GCF*_assembly_report.txt | cut -f5,7 \ | sed -e 's/na\b/JN161100.1/;' | awk '{printf "%s\t%s\n", $2, $1}' \ | sort > refseq.insdc.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 -2 2 refseq.insdc.txt ucscToRefSeq.txt | tr '[ ]' '[\t]' | sort -k3 \ | join -2 3 name.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-3,5 \ > ucscToINSDC.bed join -2 2 refseq.insdc.txt ucscToRefSeq.txt | tr '[ ]' '[\t]' | sort -k3 \ | join -2 3 name.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-4 \ > ucscToRefSeq.bed # verify chrM is correct: grep chrM *.bed # ucscToINSDC.bed:chrM 0 16469 JN161100.1 # ucscToRefSeq.bed:chrM 0 16469 NC_018116.1 # should be same line counts throughout: wc -l * # 28922 name.coordinate.tab # 28922 refseq.insdc.txt # 28922 refseqToUcsc.txt # 28922 ucscToINSDC.bed # 28922 ucscToRefSeq.bed # 28922 ucscToRefSeq.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 aotNan1 ucscToINSDC stdin ucscToINSDC.bed cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1 # 14 sed -e "s/21/14/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab aotNan1 ucscToRefSeq stdin ucscToRefSeq.bed # checkTableCoords should be silent to indicate no errors checkTableCoords aotNan1 # should cover %100 entirely: featureBits -countGaps aotNan1 ucscToINSDC # 2861684817 bases of 2861684817 (100.000%) in intersection featureBits -countGaps aotNan1 ucscToRefSeq # 2861684817 bases of 2861684817 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/chromAlias cd /hive/data/genomes/aotNan1/bed/chromAlias hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' aotNan1 \ > ucsc.refseq.tab hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' aotNan1 \ > ucsc.genbank.tab # verify chrM is correct: grep chrM * # ucsc.genbank.tab:chrM JN161100.1 genbank # ucsc.refseq.tab:chrM NC_018116.1 refseq awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \ | sort > aotNan1.chromAlias.tab hgLoadSqlTab aotNan1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ aotNan1.chromAlias.tab # verify in the browser that the names can be used in the search box # just as if they were chromosome names, e.g.: # NC_018116.1:400-500 # JN161100.1:600-700 # adding ensembl names 2017-12-13 cd /hive/data/genomes/aotNan1/bed/chromAlias mkdir previous mv *.tab previous cut -f1,2 previous/ucsc.genbank.tab| sort > ucsc.genbank.tab cut -f1,2 previous/ucsc.refseq.tab| sort > ucsc.refseq.tab join -t$'\t' ../idKeys/aotNan1.idKeys.txt \ ../../ensembl/ensemblAotNan1.idKeys.txt | cut -f2,3 \ | sort > ucsc.ensembl.tab ~/kent/src/hg/utils/automation/chromAlias.pl sort -o aotNan1.chromAlias.tab aotNan1.chromAlias.tab for t in refseq genbank ensembl do c0=`cat ucsc.$t.tab | wc -l` c1=`grep $t aotNan1.chromAlias.tab | wc -l` ok="OK" if [ "$c0" -ne "$c1" ]; then ok="ERROR" fi printf "# checking $t: $c0 =? $c1 $ok\n" done # checking refseq: 28922 =? 28922 OK # checking genbank: 28922 =? 28922 OK # checking ensembl: 28921 =? 28921 OK # note: ensembl does not have chrM hgLoadSqlTab aotNan1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ aotNan1.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-09-25 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/primate/aotNan1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" aotNan1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c 112850 JYKP.1 1 NC_.1 # implies a search rule of: '[JN][CY][KP0-9_]+(\.[0-9]+)?' # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" aotNan1 | wc -l # 112851 hgsql -N -e "select frag from gold;" aotNan1 \ | egrep -e '[JN][CY][KP0-9_]+(\.[0-9]+)?' | wc -l # 112851 hgsql -N -e "select frag from gold;" aotNan1 \ | egrep -v -e '[JN][CY][KP0-9_]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/aotNan1/trackDb.ra searchTable gold shortCircuit 1 termRegex [JN][CY][KP0-9_]+(\.[0-9]+)? 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 #20196' trackDb.ra ########################################################################## ## WINDOWMASKER (DONE - 2017-09-22 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/windowMasker cd /hive/data/genomes/aotNan1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev aotNan1) > do.log 2>&1 # real 222m45.822s # Masking statistics cat faSize.aotNan1.cleanWMSdust.txt # 2861684817 bases (147245328 N's 2714439489 real 1752382601 upper # 962056888 lower) in 28922 sequences in 1 files # Total size: mean 98944.9 sd 1012622.4 min 620 (NW_018502248v1) # max 42888418 (NW_018505940v1) median 3826 # %33.62 masked total, %35.44 masked real cat fb.aotNan1.rmsk.windowmaskerSdust.txt # 701551294 bases of 2861684817 (24.515%) in intersection ########################################################################## # run up idKeys files for ncbiRefSeq/chromAlias (DONE - 2017-12-12 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/idKeys cd /hive/data/genomes/aotNan1/bed/idKeys time (doIdKeys.pl -buildDir=`pwd` aotNan1) > do.log 2>&1 & # real 15m7.683s cat aotNan1.keySignature.txt # 58b0c1a568e25fcb17cb640f487eb747 ########################################################################## # cpgIslands - (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/cpgIslands cd /hive/data/genomes/aotNan1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku aotNan1) > do.log 2>&1 # real 6m41.678s cat fb.aotNan1.cpgIslandExt.txt # 22795786 bases of 2714439490 (0.840%) in intersection ############################################################################## # ncbiRefSeq gene track (TBD - 2016-05-05 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/ncbiRefSeq cd /hive/data/genomes/aotNan1/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 \ refseq vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 aotNan1) > 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 \ refseq vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 aotNan1) > 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 \ refseq vertebrate_mammalian Pan_paniscus \ GCF_000258655.2_panpan1.1 aotNan1) > load.log 2>&1 # real 0m21.690s cat fb.ncbiRefSeq.aotNan1.txt # 74646536 bases of 2725937399 (2.738%) in intersection ############################################################################## # genscan - (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/genscan cd /hive/data/genomes/aotNan1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku aotNan1) > do.log 2>&1 # real 51m49.116s cat fb.aotNan1.genscan.txt # 55052161 bases of 2714439490 (2.028%) in intersection cat fb.aotNan1.genscanSubopt.txt # 55424862 bases of 2714439490 (2.042%) in intersection ############################################################################# # augustus gene track (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/aotNan1/bed/augustus cd /hive/data/genomes/aotNan1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev aotNan1) > do.log 2>&1 # real 242m45.000s cat fb.aotNan1.augustusGene.txt # 49595111 bases of 2714439490 (1.827%) in intersection ############################################################################# # Create kluster run files (DONE - 2017-09-25 - Hiram) # find 'real' base count for this assembly: (numerator below) cd /hive/data/genomes/aotNan1 head -1 faSize.aotNan1.2bit.txt # 2861684817 bases (147245328 N's 2714439489 real 1428220108 upper # 1286219381 lower) in 28922 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 \( 2714439489 / 2861349177 \) \* 1024 # ( 2714439489 / 2861349177 ) * 1024 = 971.424969 # ==> use -repMatch=900 according to size scaled down from 1024 for human. # and rounded down to nearest 100 cd /hive/data/genomes/aotNan1 time blat aotNan1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/aotNan1.11.ooc \ -repMatch=900 # Wrote 32349 overused 11-mers to jkStuff/aotNan1.11.ooc # real 0m49.778s # 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;' aotNan1 \ # | sort -k7,7nr # minimum size is 50000 # gapToLift -verbose=2 -minGap=50000 aotNan1 \ # jkStuff/aotNan1.nonBridged.lft -bedFile=jkStuff/aotNan1.nonBridged.bed ######################################################################### # lastz/chain/net swap from hg38 (DONE - 2017-09-27 - Hiram) # alignment to hg38 cd /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25 cat fb.hg38.chainAotNan1Link.txt # 2153726630 bases of 3049335806 (70.629%) in intersection # and for the swap: mkdir /hive/data/genomes/aotNan1/bed/blastz.hg38.swap cd /hive/data/genomes/aotNan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m8.440s cat fb.aotNan1.chainHg38Link.txt # 2111600029 bases of 2714439490 (77.791%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` aotNan1 hg38) \ > rbest.log 2>&1 # real 427m26.453s ######################################################################### # lastz/chain/net swap from mm10 (DONE - 2017-08-27 - Hiram) # alignment on mm10 cd /hive/data/genomes/mm10/bed/lastzAotNan1.2017-09-25 cat fb.mm10.chainAotNan1Link.txt # 889500682 bases of 2652783500 (33.531%) in intersection mkdir /hive/data/genomes/aotNan1/bed/blastz.mm10.swap cd /hive/data/genomes/aotNan1/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzAotNan1.2017-09-25/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 68m48.755s cat fb.aotNan1.chainMm10Link.txt # 893851318 bases of 2714439490 (32.929%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` aotNan1 mm10) \ > rbest.log 2>&1 # real 383m10.761s ############################################################################## # GENBANK AUTO UPDATE (DONE - 2017-09-25 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Aotus nancymaae 352 0 16 # edit etc/genbank.conf to add aotNan1 just before susScr3 # aotNan1 (Ma's night monkey / Aotus nancymaae / taxId 37293) aotNan1.serverGenome = /hive/data/genomes/aotNan1/aotNan1.2bit aotNan1.clusterGenome = /hive/data/genomes/aotNan1/aotNan1.2bit aotNan1.ooc = /hive/data/genomes/aotNan1/jkStuff/aotNan1.11.ooc aotNan1.lift = /hive/data/genomes/aotNan1/jkStuff/aotNan1.nonBridged.lft aotNan1.perChromTables = no aotNan1.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} aotNan1.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} aotNan1.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} aotNan1.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} aotNan1.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} aotNan1.genbank.est.xeno.pslCDnaFilter = ${finished.genbank.est.xeno.pslCDnaFilter} aotNan1.downloadDir = aotNan1 aotNan1.refseq.mrna.native.load = yes aotNan1.refseq.mrna.xeno.load = yes # DO NOT NEED genbank.mrna.xeno except for human, mouse aotNan1.genbank.mrna.xeno.load = yes aotNan1.genbank.mrna.xeno.loadDesc = no aotNan1.genbank.est.native.load = yes # aotNan1.upstreamGeneTbl = ensGene # aotNan1.upstreamMaf = multiz12way # /hive/data/genomes/aotNan1/bed/multiz12way/species.list # And edit src/lib/gbGenome.c to add new species. Skipped # static char *aotNanNames[] = {"Aotus nancymaae", NULL}; # {"aotNan", aotNanNames}, git commit -m \ "Added aotNan1 - Ma's night monkey - Aotus nancymaae refs #20196" \ 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 aotNan1 # logFile: var/build/logs/2017.09.25-11:17:45.aotNan1.initalign.log # real 117m39.387s tail -2 var/build/logs/2017.09.25-11:17:45.aotNan1.initalign.log # hgwdev 2017.09.25-13:12:38 aotNan1.initalign: Succeeded: aotNan1 # hgwdev 2017.09.25-13:15:25 aotNan1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.aotNan1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad aotNan1 # logFile: var/dbload/hgwdev/logs/2017.09.25-13:20:30.aotNan1.dbload.log # about 5m 20s tail -1 var/dbload/hgwdev/logs/2017.09.25-13:20:30.aotNan1.dbload.log # hgwdev 2017.09.25-13:25:50 aotNan1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add aotNan1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m \ "Added aotNan1 - Ma's night monkey - Aotus nancymaae refs #20196" \ etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################## # BLATSERVERS ENTRY (DONE - 2017-08-03 - 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 ("aotNan1", "blat1b", "17886", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("aotNan1", "blat1b", "17887", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################## # set default position similar location as hg38 (DONE - 2017-09-28 - Hiram) hgsql -e \ 'update dbDb set defaultPos="NW_018491462v1:1624307-1640434" where name="aotNan1";' \ hgcentraltest ############################################################################## # all.joiner update, downloads and in pushQ - (DONE - 2017-09-28 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until these are all clean outputs: joinerCheck -database=aotNan1 -tableCoverage all.joiner joinerCheck -database=aotNan1 -times all.joiner joinerCheck -database=aotNan1 -keys all.joiner cd /hive/data/genomes/aotNan1 time (makeDownloads.pl aotNan1) > downloads.log 2>&1 # real 19m4.103s # now ready for pushQ entry mkdir /hive/data/genomes/aotNan1/pushQ cd /hive/data/genomes/aotNan1/pushQ time (makePushQSql.pl -redmineList aotNan1) \ > aotNan1.pushQ.sql 2> stderr.out # real 3m43.115s # check for errors in stderr.out, some are OK, e.g.: # writing redmine listings to # redmine.aotNan1.file.list # redmine.aotNan1.table.list # redmine.aotNan1.releaseLog.txt # WARNING: aotNan1 does not have seq # WARNING: aotNan1 does not have extFile # WARNING: aotNan1 does not have estOrientInfo # examine these files to make sure they appear sane, # then enter the full path names of these listing files: # /hive/data/genomes/aotNan1/pushQ/redmine.aotNan1.file.list # /hive/data/genomes/aotNan1/pushQ/redmine.aotNan1.releaseLog.txt # /hive/data/genomes/aotNan1/pushQ/redmine.aotNan1.table.list # into the Redmine #20196 and set to QA Ready. #########################################################################