# for emacs: -*- mode: sh; -*- # This file describes browser build for the cerAty1 # Cercocebus atys (sooty mangabey) # chrMT not in this assmbly, but there is a RefSeq MT sequence: # NC_028592.1 KT159932.1 # Assembly name: Caty_1.0 # Organism name: Cercocebus atys (sooty mangabey) # Isolate: FAK # Sex: female # Taxid: 9531 # BioSample: SAMN03379531 # BioProject: PRJNA279144 # Submitter: Human Genome Sequencing Center - BCM # Date: 2015-3-19 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: JZLG01 # Assembly method: AllPathsLG v. 41070; Atlas Link v. 1.0; Atlas GapFill v. 2.0; PBJelly2 v. 14.9.9 # Genome coverage: 192.0x # Sequencing technology: Illumina; PacBio RS # RefSeq category: Representative Genome # GenBank assembly accession: GCA_000955945.1 # RefSeq assembly accession: GCF_000955945.1 # RefSeq assembly and GenBank assemblies identical: yes # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000956035.1 GCF_000956035.1 Primary Assembly ############################################################################# # obtain photograph (DONE - 2017-02-14 - Hiram) mkdir -p /hive/data/genomes/cerAty1/photo cd /hive/data/genomes/cerAty1/photo wget -O photoFile "https://upload.wikimedia.org/wikipedia/commons/c/cc/Barcelona.Zoologico.Mangabey.Gris.jpg" convert -sharpen 0 -normalize -geometry 400x400 -quality 80 photoFile \ Cercocebus_atys.jpg printf "photoCreditURL https://commons.wikimedia.org/wiki/User:Yearofthedragon photoCreditName WikiMedia Commons: Year of the Dragon " > ../photoReference.txt ############################################################################# # fetch sequence from new style download directory (DONE - 2017-09-21 - Hiram) mkdir -p /hive/data/genomes/cerAty1/refseq cd /hive/data/genomes/cerAty1/refseq rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_mammalian/Cercocebus_atys/all_assembly_versions/GCF_000955945.1_Caty_1.0/ ./ # real 2m7.344s # sent 489 bytes received 3323271315 bytes 26064876.89 bytes/sec # total size is 3322863175 speedup is 1.00 # measure what we have here: faSize *0_genomic.fna.gz # 2848246356 bases (60973514 N's 2787272842 real 1799626545 upper # 987646297 lower) in 11433 sequences in 1 files # Total size: mean 249125.0 sd 1962567.1 min 322 (NW_012003277.1) # max 47169369 (NW_012006153.1) median 2053 # %34.68 masked total, %35.43 masked real faCount *0_genomic.fna.gz | tail # #seq len A C G T N cpg # total 2848246356 823546436 570424967 570203779 823097660 60973514 29571474 ############################################################################# # fixup to UCSC naming scheme (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/cerAty1/ucsc cd /hive/data/genomes/cerAty1/ucsc # add the mitochondrion sequence export mitoAcc=NC_028592.1 wget -O ${mitoAcc}.fa \ "http://www.ncbi.nlm.nih.gov/sviewer/viewer.fcgi?db=nuccore&dopt=fasta&sendto=on&id=$mitoAcc" echo ">chrM" > chrM.fa grep -v "^>" ${mitoAcc}.fa >> chrM.fa export mSize=`faCount chrM.fa | grep total | awk '{print $2}'` printf "chrM\t1\t$mSize\t1\tF\t$mitoAcc\t1\t$mSize\t+\n" > chrM.agp # verify no duplicate sequences: time faToTwoBit ../refseq/*0_genomic.fna.gz refseq.2bit # real 1m26.809s 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 # 11433 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.cerAty1.agp zcat ../refseq/*0_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \ | sed -e 's/.1 Cercocebus .*/v1/;' > chrUn.cerAty1.fa time gzip chr*.fa # real 15m9.994s # verify fasta and AGP match: time faToTwoBit chr*.fa.gz test.2bit # real 1m15.704s 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 # 2848262899 bases (60973514 N's 2787289385 real 2787289385 upper 0 lower) # in 11434 sequences in 1 files # Total size: mean 249104.7 sd 1962482.5 min 322 (NW_012003277v1) # max 47169369 (NW_012006153v1) median 2053 # %0.00 masked total, %0.00 masked real # real 0m47.619s # measure the original with the extra chrM sequence: faSize ../refseq/GCF_000955945.1_Caty_1.0_genomic.fna.gz chrM.fa.gz # 2848262899 bases (60973514 N's 2787289385 real 1799643088 upper # 987646297 lower) in 11434 sequences in 2 files # Total size: mean 249104.7 sd 1962482.5 min 322 (NW_012003277.1) # max 47169369 (NW_012006153.1) median 2053 # %34.68 masked total, %35.43 masked real # note same totals except for masking difference ############################################################################# # Initial database build (DONE - 2017-09-21 - Hiram) cd /hive/data/genomes/cerAty1 # establish the config.ra file: ~/kent/src/hg/utils/automation/prepConfig.pl cerAty1 mammal primate \ refseq/*_assembly_report.txt > cerAty1.config.ra # verify this looks OK: cat cerAty1.config.ra # config parameters for makeGenomeDb.pl: db cerAty1 clade mammal genomeCladePriority 35 scientificName Cercocebus atys commonName Sooty mangabey assemblyDate Mar. 2015 assemblyLabel Human Genome Sequencing Center - BCM assemblyShortLabel Caty_1.0 orderKey 19597 # chrM already added to source: NC_028592.1 KT159932.1 mitoAcc none fastaFiles /hive/data/genomes/cerAty1/ucsc/*.fa.gz agpFiles /hive/data/genomes/cerAty1/ucsc/*.agp # qualFiles none dbDbSpeciesDir primate photoCreditURL https://commons.wikimedia.org/wiki/User:Yearofthedragon photoCreditName WikiMedia Commons: Year of the Dragon ncbiGenomeId 13303 ncbiAssemblyId 313491 ncbiAssemblyName Caty_1.0 ncbiBioProject 279144 ncbiBioSample SAMN03379531 genBankAccessionID GCF_000955945.1 taxId 9531 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp cerAty1.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 \ cerAty1.config.ra ) > db.log 2>&1 # real 22m3.240s # check in the trackDb files created and add to trackDb/makefile # temporary symlink until after masking ln -s `pwd`/cerAty1.unmasked.2bit /gbdb/cerAty1/cerAty1.2bit ############################################################################# # cytoBandIdeo - (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/cytoBand cd /hive/data/genomes/cerAty1/bed/cytoBand makeCytoBandIdeo.csh cerAty1 ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/cpgIslandsUnmasked cd /hive/data/genomes/cerAty1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/cerAty1/cerAty1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku cerAty1) > do.log 2>&1 # real 18m37.676s cat fb.cerAty1.cpgIslandExtUnmasked.txt # 34770255 bases of 2787289397 (1.247%) in intersection ############################################################################# # running repeat masker (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/repeatMasker cd /hive/data/genomes/cerAty1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku cerAty1) > do.log 2>&1 & # real 584m8.842s cat faSize.rmsk.txt # 2848262899 bases (60973514 N's 2787289385 real 1397604894 upper # 1389684491 lower) in 11434 sequences in 1 files # Total size: mean 249104.7 sd 1962482.5 min 322 (NW_012003277v1) # max 47169369 (NW_012006153v1) median 2053 # %48.79 masked total, %49.86 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 cerAty1 rmsk # 1390342282 bases of 2848262899 (48.814%) in intersection # real 0m39.370s # 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 on high contig count assemblies: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' cerAty1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 1390342282.000000 # real 0m40.694s ########################################################################## # running simple repeat (DONE - 2017-09-21 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/simpleRepeat cd /hive/data/genomes/cerAty1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=5 cerAty1) > do.log 2>&1 & # real 243m44.834s cat fb.simpleRepeat # 73558951 bases of 2787289397 (2.639%) in intersection # add to this simple repeat to rmsk: cd /hive/data/genomes/cerAty1 twoBitMask cerAty1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed cerAty1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa cerAty1.2bit stdout | faSize stdin > faSize.cerAty1.2bit.txt cat faSize.cerAty1.2bit.txt # 2848262899 bases (60973514 N's 2787289385 real 1395908097 upper # 1391381288 lower) in 11434 sequences in 1 files # Total size: mean 249104.7 sd 1962482.5 min 322 (NW_012003277v1) # max 47169369 (NW_012006153v1) median 2053 # %48.85 masked total, %49.92 masked real # reset gbdb symlink rm /gbdb/cerAty1/cerAty1.2bit ln -s `pwd`/cerAty1.2bit /gbdb/cerAty1/cerAty1.2bit ############################################################################# # CREATE MICROSAT TRACK (DONE - 2017-09-22 - Hiram) ssh hgwdev mkdir /cluster/data/cerAty1/bed/microsat cd /cluster/data/cerAty1/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 cerAty1 microsat microsat.bed # Read 26504 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/cerAty1/bed/ucscToINSDC cd /hive/data/genomes/cerAty1/bed/ucscToINSDC # find accession for chrM grep chrM ../../cerAty1.agp # chrM 1 16543 1 F NC_028592.1 1 16543 + # use that accession here: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../refseq/GCF_*structure/Primary_Assembly NC_028592.1 # 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 entry for chrMT in the assembly report, hence the printf (printf "%s\t%s\n" "NC_028592.1" "KT159932.1"; grep -v "^#" ../../refseq/GCF*_assembly_report.txt | cut -f5,7 \ | awk '{printf "%s\t%s\n", $2, $1}') | sort > refseq.insdc.txt 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 16543 KT159932.1 # ucscToRefSeq.bed:chrM 0 16543 NC_028592.1 # should be same line counts throughout: wc -l * # 11434 name.coordinate.tab # 11434 refseq.insdc.txt # 11434 refseqToUcsc.txt # 11434 ucscToINSDC.bed # 11434 ucscToRefSeq.bed # 11434 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 cerAty1 ucscToINSDC stdin ucscToINSDC.bed cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1 sed -e "s/21/14/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab cerAty1 ucscToRefSeq stdin ucscToRefSeq.bed # checkTableCoords should be silent for no errors checkTableCoords cerAty1 # should cover %100 entirely: featureBits -countGaps cerAty1 ucscToINSDC # 2848262899 bases of 2848262899 (100.000%) in intersection featureBits -countGaps cerAty1 ucscToRefSeq # 2848262899 bases of 2848262899 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/chromAlias cd /hive/data/genomes/cerAty1/bed/chromAlias hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' cerAty1 \ > ucsc.refseq.tab hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' cerAty1 \ > ucsc.genbank.tab # verify chrM is correct: grep chrM * # ucsc.genbank.tab:chrM KT159932.1 genbank # ucsc.refseq.tab:chrM NC_028592.1 refseq awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \ | sort > cerAty1.chromAlias.tab hgLoadSqlTab cerAty1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ cerAty1.chromAlias.tab # adding ensembl names 2017-12-13 cd /hive/data/genomes/cerAty1/bed/chromAlias mkdir previous mv *.tab previous cut -f1,2 previous/ucsc.genbank.tab| sort > ucsc.genbank.tab cut -f1,2 previous/ucsc.refseq.tab| sort > ucsc.refseq.tab join -t$'\t' ../idKeys/cerAty1.idKeys.txt \ ../../ensembl/ensemblCerAty1.idKeys.txt | cut -f2,3 \ | sort > ucsc.ensembl.tab ~/kent/src/hg/utils/automation/chromAlias.pl sort -o cerAty1.chromAlias.tab cerAty1.chromAlias.tab for t in refseq genbank ensembl do c0=`cat ucsc.$t.tab | wc -l` c1=`grep $t cerAty1.chromAlias.tab | wc -l` ok="OK" if [ "$c0" -ne "$c1" ]; then ok="ERROR" fi printf "# checking $t: $c0 =? $c1 $ok\n" done # checking refseq: 11434 =? 11434 OK # checking genbank: 11434 =? 11434 OK # checking ensembl: 11433 =? 11433 OK # ensembl does not have chrM grep chrM *.tab ucsc.genbank.tab:chrM KT159932.1 ucsc.refseq.tab:chrM NC_028592.1 hgLoadSqlTab cerAty1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ cerAty1.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-09-25 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/primate/cerAty1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" cerAty1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c 76752 JZLG.1 1 NC_.1 # implies a search rule of: '[JN][CZ][GL0-9_]+(\.[0-9]+)?' # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" cerAty1 | wc -l # 76753 hgsql -N -e "select frag from gold;" cerAty1 \ | egrep -e '[JN][CZ][GL0-9_]+(\.[0-9]+)?' | wc -l # 76753 hgsql -N -e "select frag from gold;" cerAty1 \ | egrep -v -e '[JN][CZ][GL0-9_]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/cerAty1/trackDb.ra searchTable gold shortCircuit 1 termRegex [JN][CZ][GL0-9_]+(\.[0-9]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box git commit -m 'add gold table search rule refs #20199' trackDb.ra ########################################################################## ## WINDOWMASKER (DONE - 2017-09-22 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/windowMasker cd /hive/data/genomes/cerAty1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev cerAty1) > do.log 2>&1 # real 197m1.909s # Masking statistics cat faSize.cerAty1.cleanWMSdust.txt # 2848262899 bases (60973514 N's 2787289385 real 1783052426 upper # 1004236959 lower) in 11434 sequences in 1 files # Total size: mean 249104.7 sd 1962482.5 min 322 (NW_012003277v1) # max 47169369 (NW_012006153v1) median 2053 # %35.26 masked total, %36.03 masked real cat fb.cerAty1.rmsk.windowmaskerSdust.txt # 760728332 bases of 2848262899 (26.709%) in intersection ########################################################################## # run up idKeys files for ncbiRefSeq/chromAlias (DONE - 2017-12-12 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/idKeys cd /hive/data/genomes/cerAty1/bed/idKeys time (doIdKeys.pl -buildDir=`pwd` cerAty1) > do.log 2>&1 & # real 12m20.939s cat cerAty1.keySignature.txt # 8ae219619932349bebc17364408bf9d0 ########################################################################## # cpgIslands - (DONE - 2017-09-22 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/cpgIslands cd /hive/data/genomes/cerAty1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku cerAty1) > do.log 2>&1 # real 5m6.484s cat fb.cerAty1.cpgIslandExt.txt # 21140475 bases of 2787289397 (0.758%) in intersection ############################################################################## # ncbiRefSeq gene track (TBD - 2016-05-05 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/ncbiRefSeq cd /hive/data/genomes/cerAty1/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 cerAty1) > 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 cerAty1) > 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 cerAty1) > load.log 2>&1 # real 0m21.690s cat fb.ncbiRefSeq.cerAty1.txt # 74646536 bases of 2725937399 (2.738%) in intersection ############################################################################## # genscan - (DONE - 2017-09-22 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/genscan cd /hive/data/genomes/cerAty1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku cerAty1) > do.log 2>&1 # real 36m26.564s cat fb.cerAty1.genscan.txt # 52826695 bases of 2787289397 (1.895%) in intersection cat fb.cerAty1.genscanSubopt.txt # 51741322 bases of 2787289397 (1.856%) in intersection ############################################################################# # augustus gene track (DONE - 2017-09-22 - Hiram) mkdir /hive/data/genomes/cerAty1/bed/augustus cd /hive/data/genomes/cerAty1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev cerAty1) > do.log 2>&1 # real 82m50.229s cat fb.cerAty1.augustusGene.txt # 48318341 bases of 2787289397 (1.734%) in intersection ############################################################################# # Create kluster run files (DONE - 2017-09-28 - Hiram) # numerator is cerAty1 gapless bases "real" as reported by: cd /hive/data/genomes/cerAty1 head -1 faSize.cerAty1.2bit.txt # 2848262899 bases (60973514 N's 2787289385 real 1395908097 upper # 1391381288 lower) in 11434 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 \( 2787289385 / 2861349177 \) \* 1024 # ( 2787289385 / 2861349177 ) * 1024 = 997.495990 # ==> use -repMatch=900 according to size scaled down from 1024 for human. # and rounded down to nearest 100 cd /hive/data/genomes/cerAty1 time blat cerAty1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/cerAty1.11.ooc \ -repMatch=900 # Wrote 31843 overused 11-mers to jkStuff/cerAty1.11.ooc # real 0m50.689s # 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;' cerAty1 \ # | sort -k7,7nr # minimum size is 50000 # gapToLift -verbose=2 -minGap=50000 cerAty1 \ # jkStuff/cerAty1.nonBridged.lft -bedFile=jkStuff/cerAty1.nonBridged.bed ######################################################################### # lastz/chain/net swap from hg38 (DONE - 2017-08-28 - Hiram) # alignment to hg38 cd /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27 cat fb.hg38.chainCerAty1Link.txt # 2556764791 bases of 3049335806 (83.847%) in intersection # and for the swap: mkdir /hive/data/genomes/cerAty1/bed/blastz.hg38.swap cd /hive/data/genomes/cerAty1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m53.559s cat fb.cerAty1.chainHg38Link.txt # 2424226994 bases of 2787289397 (86.974%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` cerAty1 hg38) \ > rbest.log 2>&1 # real 226m2.420s ######################################################################### # lastz/chain/net swap from mm10 (DONE - 2017-00-28 - Hiram) # alignment on mm10 cd /hive/data/genomes/mm10/bed/lastzCerAty1.2017-09-27 cat fb.mm10.chainCerAty1Link.txt # 917680202 bases of 2652783500 (34.593%) in intersection mkdir /hive/data/genomes/cerAty1/bed/blastz.mm10.swap cd /hive/data/genomes/cerAty1/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzCerAty1.2017-09-27/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 68m6.225s cat fb.cerAty1.chainMm10Link.txt # 903892923 bases of 2787289397 (32.429%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` cerAty1 mm10) \ > rbest.log 2>&1 # real 305m14.804s ############################################################################## # 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 # Cercocebus atys 222 0 38 # Cercocebus chrysogaster 2 0 0 # Cercocebus torquatus 30 0 0 # Cercocebus torquatus torquatus 2 0 0 # edit etc/genbank.conf to add cerAty1 just before susScr3 # cerAty1 (Sooty mangabey - Cercocebus atys) taxId 9531 cerAty1.serverGenome = /hive/data/genomes/cerAty1/cerAty1.2bit cerAty1.clusterGenome = /hive/data/genomes/cerAty1/cerAty1.2bit cerAty1.ooc = /hive/data/genomes/cerAty1/jkStuff/cerAty1.11.ooc cerAty1.lift = no cerAty1.refseq.mrna.native.pslCDnaFilter = ${lowCover.refseq.mrna.native.pslCDnaFilter} cerAty1.refseq.mrna.xeno.pslCDnaFilter = ${lowCover.refseq.mrna.xeno.pslCDnaFilter} cerAty1.genbank.mrna.native.pslCDnaFilter = ${lowCover.genbank.mrna.native.pslCDnaFilter} cerAty1.genbank.mrna.xeno.pslCDnaFilter = ${lowCover.genbank.mrna.xeno.pslCDnaFilter} cerAty1.genbank.est.native.pslCDnaFilter = ${lowCover.genbank.est.native.pslCDnaFilter} cerAty1.genbank.est.xeno.pslCDnaFilter = ${lowCover.genbank.est.xeno.pslCDnaFilter} cerAty1.downloadDir = cerAty1 cerAty1.refseq.mrna.native.load = yes cerAty1.refseq.mrna.xeno.load = yes # DO NOT NEED genbank.mrna.xeno except for human, mouse cerAty1.genbank.mrna.xeno.load = no cerAty1.genbank.mrna.native.load = no cerAty1.genbank.est.native.load = no cerAty1.perChromTables = no # And edit src/lib/gbGenome.c to add new species. git commit -m "Added cerAty1/Sooty mangabey; refs #20199" \ 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 cerAty1 # logFile: var/build/logs/2017.09.25-08:50:49.cerAty1.initalign.log # real 540m3.271s tail -2 var/build/logs/2017.09.25-08:50:49.cerAty1.initalign.log # hgwdev 2017.09.25-17:50:23 cerAty1.initalign: Succeeded: cerAty1 # hgwdev 2017.09.25-17:50:53 cerAty1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.cerAty1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad cerAty1 # logFile: var/dbload/hgwdev/logs/2017.09.26-08:18:35.cerAty1.dbload.log # real 4m47.307s tail -1 var/dbload/hgwdev/logs/2017.09.26-08:18:35.cerAty1.dbload.log # hgwdev 2017.09.26-08:23:22 cerAty1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add cerAty1 to: # etc/align.dbs etc/hgwdev.dbs git commit -m "Added cerAty1/Sooty mangabey; refs #20199" \ etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################## # BLATSERVERS ENTRY (DONE - 2017-09-27 - 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 ("cerAty1", "blat1b", "17884", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("cerAty1", "blat1b", "17885", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################## # set default position similar to hg38 default (DONE - 2017-09-27 - Hiram) # same as susScr3: hgsql -e \ 'update dbDb set defaultPos="NW_012006482v1:1601032-1625412" where name="cerAty1";' \ hgcentraltest ############################################################################## # all.joiner update, downloads and in pushQ - (DONE - 2017-09-29 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until these commands are clean output: joinerCheck -database=cerAty1 -tableCoverage all.joiner joinerCheck -database=cerAty1 -times all.joiner joinerCheck -database=cerAty1 -keys all.joiner git commit -m 'adding rules for cerAty1 refs #20199' all.joiner cd /hive/data/genomes/cerAty1 time (makeDownloads.pl cerAty1) > downloads.log 2>&1 # real 18m58.858s # now ready for pushQ entry mkdir /hive/data/genomes/cerAty1/pushQ cd /hive/data/genomes/cerAty1/pushQ time (makePushQSql.pl -redmineList cerAty1) \ > cerAty1.pushQ.sql 2> stderr.out # real 3m46.855s # check for errors in stderr.out, some are OK, e.g.: # writing redmine listings to # redmine.cerAty1.file.list # redmine.cerAty1.table.list # redmine.cerAty1.releaseLog.txt # WARNING: cerAty1 does not have seq # WARNING: cerAty1 does not have extFile # WARNING: cerAty1 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/cerAty1/pushQ/redmine.cerAty1.file.list # /hive/data/genomes/cerAty1/pushQ/redmine.cerAty1.releaseLog.txt # /hive/data/genomes/cerAty1/pushQ/redmine.cerAty1.table.list # into the Redmine #20199 and set to QA Ready. #########################################################################