# for emacs: -*- mode: sh; -*- # This file describes browser build for the rhiRox1 # Golden snub-nosed monkey - Rhinopithecus roxellana # Assembly Statistics Report # Assembly Name: Rrox_v1 # Organism name: Rhinopithecus roxellana # Taxid: 61622 # Submitter: Novogene # Date: 2014-10-28 # BioSample: SAMN02427086 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # GenBank Assembly Accession: GCA_000769185.1 (latest) # RefSeq Assembly Accession: GCF_000769185.1 (species-representative latest) # RefSeq Assembly and GenBank Assemblies Identical: no # Reporting on GenBank assembly. # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000769195.1 GCF_000769195.1 Primary Assembly ## GCA_000769205.1 GCF_000058055.1 non-nuclear # Note: chrMT is included in this release (as scaffolds, not complete) # separate chrMt sequence NC_008218.1 will be used instead ############################################################################# # fetch sequence from new style download directory (DONE - 2014-11-26 - Hiram) # NCBI has redesigned their FTP download site, new type of address # and naming scheme mkdir -p /hive/data/genomes/rhiRox1/genbank cd /hive/data/genomes/rhiRox1/genbank rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/genbank/vertebrate_mammalian/Rhinopithecus_roxellana/all_assembly_versions/GCA_000769185.1_Rrox_v1/ ./ # measure what we have here: faSize GCA_000769185.1_Rrox_v1_genomic.fna.gz # 2899551855 bases (43508254 N's 2856043601 real 1805484870 upper # 1050558731 lower) in 135513 sequences in 1 files # Total size: mean 21396.9 sd 206576.0 min 145 (JABR01061848.1) # max 9848887 (KN296311.1) median 384 # %36.23 masked total, %36.78 masked real faSize GCA_000769185.1_Rrox_v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \ GCA_000769185.1_Rrox_v1_assembly_structure/non-nuclear/unlocalized_scaffolds/FASTA/chrMT.unlocalized.scaf.fna.gz # 2899551855 bases (43508254 N's 2856043601 real 2856043601 upper # 0 lower) in 135513 sequences in 2 files # Total size: mean 21396.9 sd 206576.0 min 145 (JABR01061848.1) # max 9848887 (KN296311.1) median 384 # %0.00 masked total, %0.00 masked real # note chrMT is already included in this assembly # But according the the assembly record at: # http://www.ncbi.nlm.nih.gov/assembly/GCA_000769185.1 # there is another chrM assembly which is complete export mitoAcc=NC_008218.1 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 $2}'` /bin/echo -e "chrM\t1\t$mSize\t1\tF\t$mitoAcc\t1\t$mSize\t+" > chrM.agp ############################################################################# # fixup to UCSC naming scheme (DONE - 2014-11-25 - Hiram) mkdir /hive/data/genomes/rhiRox1/ucsc cd /hive/data/genomes/rhiRox1/ucsc # this usual procedure does not work very well because the AGP definition # has no gaps. Instead, a simple process is used below to construct the # assembly with just its scaffold names. time ./unplaced.pl ../genbank/GCA_000769185.1_Rrox_v1_assembly_structure/Primary_Assembly # chrMT is not complete, only in contigs, add chrM_ prefix: zcat ../genbank/GCA_000769185.1_Rrox_v1_assembly_structure/non-nuclear/unlocalized_scaffolds/FASTA/chrMT.unlocalized.scaf.fna.gz \ | sed -e 's/ Rhin.*//; s/\.1/v1/; s/^>/>chrM_/' > chrMT.fa zcat ../genbank/GCA_000769185.1_Rrox_v1_assembly_structure/non-nuclear/unlocalized_scaffolds/AGP/chrMT.unlocalized.scaf.agp.gz \ | sed -e 's/\.1/v1/; s/^KN/chrM_KN/; s/^JABR/chrM_JABR/' > chrMT.agp # verify nothing lost compared to genbank: faSize *.fa # 2899551855 bases (43508254 N's 2856043601 real 2856043601 upper # 0 lower) in 135513 sequences in 2 files # Total size: mean 21396.9 sd 206576.0 min 145 (chrUn_JABR01061848v1) # max 9848887 (chrUn_KN296311v1) median 384 # %0.00 masked total, %0.00 masked real # same numbers as above. # the resulting AGP definition is useless, it contains no gaps # construct a fake AGP for the unplaced scaffolds: zcat ../genbank/GCA_000769185.1_Rrox_v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \ | sed -e 's/ Rhinopithecus.*//;' \ | hgFakeAgp -minContigGap=1 stdin stdout | sed -e 's/\.1/v1/; s/D/W/;' \ | sed -e 's/JABR\([0-9][0-9]*\)\.1_1/JABR\1.1/;' \ | sort -k1,1 -k2,2n > chrUn.rhiRox1.fake.agp # and corresponding fasta: zcat ../genbank/GCA_000769185.1_Rrox_v1_assembly_structure/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fna.gz \ | sed -e 's/.1 Rhinopithecus .*/v1/;' > chrUn.rhiRox1.fa ############################################################################# # Initial database build (DONE - 2015-02-15 - Hiram) cd /hive/data/genomes/rhiRox1 cat << '_EOF_' > rhiRox1.config.ra # Config parameters for makeGenomeDb.pl: db rhiRox1 clade primate genomeCladePriority 15 scientificName Rhinopithecus roxellana commonName Golden snub-nosed monkey assemblyDate Oct. 2014 assemblyLabel Novogene assemblyShortLabel Rrox_v1 orderKey 394 # chrM bioproject: 17209 # mitoAcc NC_008218.1 already included # NC_008218.1 mitoAcc none fastaFiles /hive/data/genomes/rhiRox1/ucsc/*.fa agpFiles /hive/data/genomes/rhiRox1/ucsc/*.agp # qualFiles none dbDbSpeciesDir rhinopithecus photoCreditURL http://jackhynes.com photoCreditName Jack Hynes - Wikimedia Commons ncbiGenomeId 7996 ncbiAssemblyId 218671 ncbiAssemblyName Rrox_v1 ncbiBioProject 266995 genBankAccessionID GCA_000769185.1 taxId 61622 '_EOF_' # << happy emacs # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp rhiRox1.config.ra) > agp.log 2>&1 # real 3m5.574s # verify end of agp.log indicates: # *** All done! (through the 'agp' step) # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db rhiRox1.config.ra) > db.log 2>&1 # real 23m52.788s # check in the trackDb files created and add to trackDb/makefile ########################################################################## # running repeat masker (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/repeatMasker cd /hive/data/genomes/rhiRox1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku rhiRox1) > do.log 2>&1 # real 2968m6.257s # one items caused extractNestedRepeats.pl to exit with an error, # continuing: time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -continue=mask -smallClusterHub=ku rhiRox1) > mask.log 2>&1 # real 27m42.685s cat faSize.rmsk.txt # 2899552139 bases (43508003 N's 2856044136 real 1399291226 upper # 1456752910 lower) in 135512 sequences in 1 files # Total size: mean 21397.0 sd 206576.8 min 145 (JABR01061848v1) # max 9848887 (KN296311v1) median 384 # %50.24 masked total, %51.01 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 rhiRox1 rmsk # 1457170203 bases of 2899552139 (50.255%) in intersection # real 1m27.493s # 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 ########################################################################## # running simple repeat (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/simpleRepeat cd /hive/data/genomes/rhiRox1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ rhiRox1) > do.log 2>&1 # real 124m30.486s cat fb.simpleRepeat # 88662812 bases of 2856044136 (3.104%) in intersection # add to rmsk after it is done: cd /hive/data/genomes/rhiRox1 twoBitMask rhiRox1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed rhiRox1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa rhiRox1.2bit stdout | faSize stdin > faSize.rhiRox1.2bit.txt cat faSize.rhiRox1.2bit.txt # 2899552139 bases (43508003 N's 2856044136 real 1397489568 upper # 1458554568 lower) in 135512 sequences in 1 files # Total size: mean 21397.0 sd 206576.8 min 145 (JABR01061848v1) # max 9848887 (KN296311v1) median 384 # %50.30 masked total, %51.07 masked real rm /gbdb/rhiRox1/rhiRox1.2bit ln -s `pwd`/rhiRox1.2bit /gbdb/rhiRox1/rhiRox1.2bit ########################################################################## # CREATE MICROSAT TRACK (DONE - 2015-06-22 - Hiram) ssh hgwdev mkdir /cluster/data/rhiRox1/bed/microsat cd /cluster/data/rhiRox1/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 rhiRox1 microsat microsat.bed # Read 34800 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/windowMasker cd /hive/data/genomes/rhiRox1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev rhiRox1) > do.log 2>&1 # real 272m57.847s # Masking statistics cat faSize.rhiRox1.cleanWMSdust.txt # 3011966170 bases (614872980 N's 2397093190 real 1630676135 upper # 766417055 lower) in 319549 sequences in 1 files # Total size: mean 9425.7 sd 1088158.8 min 201 (chrUn_JMHX01238739v1) # max 215897965 (chr1) median 823 # %25.45 masked total, %31.97 masked real time featureBits -countGaps rhiRox1 rmsk windowmaskerSdust \ > fb.rhiRox1.rmsk.windowmaskerSdust.txt 2>&1 # real 3m50.464s cat fb.rhiRox1.rmsk.windowmaskerSdust.txt # 830163015 bases of 2899552139 (28.631%) in intersection doWindowMasker.pl -continue=cleanup -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev rhiRox1 ########################################################################## # cpgIslands - (DONE - 2015-02-20 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/cpgIslands cd /hive/data/genomes/rhiRox1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku rhiRox1) > do.log 2>&1 & # real 117m34.561s cat fb.rhiRox1.cpgIslandExt.txt # 18261889 bases of 2856044136 (0.639%) in intersection ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/cpgIslandsUnmasked cd /hive/data/genomes/rhiRox1/bed/cpgIslandsUnmasked time doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/rhiRox1/rhiRox1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku rhiRox1 > do.log 2>&1 # real 477m51.846s cat fb.rhiRox1.cpgIslandExtUnmasked.txt # 33083948 bases of 2856044136 (1.158%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/cytoBand cd /hive/data/genomes/rhiRox1/bed/cytoBand makeCytoBandIdeo.csh rhiRox1 ######################################################################### # genscan - (DONE - 2014-12-01,11 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/genscan cd /hive/data/genomes/rhiRox1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku rhiRox1) > do.log 2>&1 # real 138m29.019s cat fb.rhiRox1.genscan.txt # 52089531 bases of 2856044136 (1.824%) in intersection cat fb.rhiRox1.genscanSubopt.txt # 53279783 bases of 2856044136 (1.866%) in intersection ######################################################################## # Create kluster run files (DONE - 2015-02-20 - Hiram) cd /hive/data/genomes/rhiRox1 # numerator is rhiRox1 gapless bases "real" as reported by: head -1 faSize.rhiRox1.2bit.txt # 2899552139 bases (43508003 N's 2856044136 real 1397489568 upper 1458554568 # lower) in 135512 sequences in 1 files # numerator is 'real' base count # 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 \( 2856044136 / 2861349177 \) \* 1024 # ( 2856044136 / 2861349177 ) * 1024 = 1022.101468 # ==> use -repMatch=1000 according to size scaled down from 1024 for human. # and rounded down to nearest 50 cd /hive/data/genomes/rhiRox1 time blat rhiRox1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/rhiRox1.11.ooc \ -repMatch=1000 # Wrote 30186 overused 11-mers to jkStuff/rhiRox1.11.ooc # real 0m49.404s # there are no non-bridged gaps, do not need to do this # check non-bridged gaps to see what the typical size is: # hgsql -N -e 'select * from gap where bridge="no" order by size;' rhiRox1 # | ave -tableOut -col=7 stdin # # min Q1 median Q3 max mean N sum stddev # 50076 58368.8 70128 100495 1.07816e+07 178173 670 1.19376e+08 672006 # note the minimum non-bridged gap size is 50,076 # gapToLift -verbose=2 -minGap=50000 rhiRox1 jkStuff/rhiRox1.nonBridged.lft \ # -bedFile=jkStuff/rhiRox1.nonBridged.bed # hgsql -N \ # -e 'select * from gap where bridge="no" order by size;' rhiRox1 \ # | ave -col=7 stdin # not needed: # gapToLift -verbose=2 -minGap=100 bosTau7 jkStuff/nonBridged.lft \ # -bedFile=jkStuff/nonBridged.bed # survey sizes: n50.pl chrom.sizes # reading: chrom.sizes # contig count: 135512, total size: 2899552139, one half size: # 1449776069 # cumulative N50 count contig contig size # 1448988959 532 KN299624v1 1553048 # 1449776069 one half size # 1450538183 533 KN299419v1 1549224 ############################################################################# # GENBANK AUTO UPDATE (DONE - 2015-02-20 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt # Rhinopithecus roxellana 9 0 1 # edit etc/genbank.conf to add rhiRox1 just after rheMac3 # rhiRox1 (Golden snub-nosed monkey) rhiRox1.serverGenome = /hive/data/genomes/rhiRox1/rhiRox1.2bit rhiRox1.clusterGenome = /hive/data/genomes/rhiRox1/rhiRox1.2bit rhiRox1.ooc = /hive/data/genomes/rhiRox1/rhiRox1.11.ooc rhiRox1.lift = no rhiRox1.perChromTables = no rhiRox1.refseq.mrna.native.pslCDnaFilter = ${ordered.refseq.mrna.native.pslCDnaFilter} rhiRox1.refseq.mrna.xeno.pslCDnaFilter = ${ordered.refseq.mrna.xeno.pslCDnaFilter} rhiRox1.genbank.mrna.native.pslCDnaFilter = ${ordered.genbank.mrna.native.pslCDnaFilter} rhiRox1.genbank.mrna.xeno.pslCDnaFilter = ${ordered.genbank.mrna.xeno.pslCDnaFilter} rhiRox1.genbank.est.native.pslCDnaFilter = ${ordered.genbank.est.native.pslCDnaFilter} rhiRox1.genbank.est.xeno.pslCDnaFilter = ${ordered.genbank.est.xeno.pslCDnaFilter} rhiRox1.downloadDir = rhiRox1 rhiRox1.refseq.mrna.native.load = yes rhiRox1.refseq.mrna.xeno.load = yes rhiRox1.refseq.mrna.xeno.loadDesc = yes rhiRox1.upstreamGeneTbl = refGene git commit -m "Added rhiRox1; refs #14438" etc/genbank.conf git push # update /cluster/data/genbank/: make etc-update # Edit src/lib/gbGenome.c to add new species. git commit -m "Added rhiRox Rhinopithecus roxellana refs #14438" \ src/lib/gbGenome.c git push make install-server screen # control this business with a screen since it takes a while cd /cluster/data/genbank time ./bin/gbAlignStep -initial rhiRox1 # logFile: var/build/logs/2014.10.13-13:00:37.rhiRox1.initalign.log # real 163m21.647s # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.rhiRox1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad rhiRox1 & # logFile: var/dbload/hgwdev/logs/2015.02.21-19:06:41.rhiRox1.dbload.log # real 10m59.824s # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add rhiRox1 to: # vi etc/align.dbs etc/hgwdev.dbs git commit -m "Added rhiRox1 - Golden snub-nosed monkey refs #14438" \ etc/align.dbs etc/hgwdev.dbs git push make etc-update ######################################################################### # SWAP hg38 LASTZ (DONE - 2015-03-23 - Hiram) # original alignment done at hg38.txt cd /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23 cat fb.hg38.chainRhiRox1Link.txt # 2595256243 bases of 3049335806 (85.109%) in intersection # running the swap mkdir /hive/data/genomes/rhiRox1/bed/blastz.hg38.swap cd /hive/data/genomes/rhiRox1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 174m27.934s cat fb.rhiRox1.chainHg38Link.txt # 2474156996 bases of 2856044136 (86.629%) in intersection ############################################################################## # create ucscToRefSeq name mapping (DONE - 2017-12-14 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/ucscToRefSeq cd /hive/data/genomes/rhiRox1/bed/ucscToRefSeq # run up idKeys for refseq release mkdir refseq cd refseq ln -s /hive/data/outside/ncbi/genomes/refseq/vertebrate_mammalian/Rhinopithecus_roxellana/all_assembly_versions/GCF_000769185.1_Rrox_v1/GCF_000769185.1_Rrox_v1_genomic.fna.gz ./ faToTwoBit *.fna.gz refseq.rhiRox1.2bit doIdKeys.pl -buildDir=`pwd` -twoBit=`pwd`/refseq.rhiRox1.2bit refseqRhiRox1 # real 68m59.898s cd /hive/data/genomes/rhiRox1/bed/ucscToRefSeq join -t$'\t' ../idKeys/rhiRox1.idKeys.txt refseq/refseqRhiRox1.idKeys.txt \ | cut -f2- | sort > ucsc.refseq.tab join -t$'\t' <(sort ../../chrom.sizes) ucsc.refseq.tab \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ | sort -k1,1 -k2,2n > ucscToRefSeq.bed # maximum size of UCSC chrom name for SQL index export SZ=`cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1` # SZ: 14 sed -e "s/21/$SZ/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab rhiRox1 ucscToRefSeq stdin ucscToRefSeq.bed checkTableCoords rhiRox1 ucscToRefSeq featureBits -countGaps rhiRox1 ucscToRefSeq # 2899552139 bases of 2899552139 (100.000%) in intersection ######################################################################### # ucscToINSDC table/track (DONE - 2015-03-23 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/ucscToINSDC cd /hive/data/genomes/rhiRox1/bed/ucscToINSDC grep chrM ../../rhiRox1.agp # chrM 1 16549 1 F NC_008218.1 1 16549 + # this is not the genbank name, lookup at NCBI entrez nucleotide: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../genbank/GCA_*assembly_structure/Primary_Assembly DQ355300.1 awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > name.coordinate.tab join name.coordinate.tab ucscToINSDC.txt | tr '[ ]' '[\t]' \ > ucscToINSDC.bed # verify all names are coming through, should be same line count: wc -l * # 135512 name.coordinate.tab # 135512 ucscToINSDC.bed # 135512 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/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab rhiRox1 ucscToINSDC stdin ucscToINSDC.bed checkTableCoords rhiRox1 # should cover %100 entirely: featureBits -countGaps rhiRox1 ucscToINSDC # 2899552139 bases of 2899552139 (100.000%) in intersection ############################################################################## # add chromAlias table (DONE - 2017-12-14 - Hiram) mkdir /hive/data/genomes/rhiRox1/bed/chromAlias cd /hive/data/genomes/rhiRox1/bed/chromAlias hgsql -N -e 'select chrom,name from ucscToRefSeq;' rhiRox1 \ | sort > ucsc.refseq.tab hgsql -N -e 'select chrom,name from ucscToINSDC;' rhiRox1 \ |sort > ucsc.genbank.tab join -t$'\t' ../idKeys/rhiRox1.idKeys.txt \ ../../ensembl/ensemblRhiRox1.idKeys.txt \ | cut -f2,3 | sort > ucsc.ensembl.tab ~/kent/src/hg/utils/automation/chromAlias.pl sort -o rhiRox1.chromAlias.tab rhiRox1.chromAlias.tab for t in refseq genbank ensembl do c0=`cat ucsc.$t.tab | wc -l` c1=`grep $t rhiRox1.chromAlias.tab | wc -l` ok="OK" if [ "$c0" -ne "$c1" ]; then ok="ERROR" fi printf "# checking $t: $c0 =? $c1 $ok\n" done # checking refseq: 135512 =? 135512 OK # checking genbank: 135512 =? 135512 OK # checking ensembl: 135512 =? 135512 OK hgLoadSqlTab rhiRox1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ rhiRox1.chromAlias.tab ############################################################################## # fixup search rule for assembly track/gold table (DONE - 2015-03-23 - Hiram) hgsql -N -e "select frag from gold;" rhiRox1 | sort -u \ > /tmp/rhiRox1.frag.gold.txt export maxLen=`awk '{print length($0)}' /tmp/rhiRox1.frag.gold.txt | sort -rn | head -1` echo "scan to column: $maxLen" export C=1 while [ $C -le $maxLen ]; do echo -n " $C: " awk '{ print substr($0,'$C',1) }' /tmp/rhiRox1.frag.gold.txt | sort -u | xargs echo | sed -e 's/ //g' C=`echo $C | awk '{print $1+1}'` done 1: JKN 2: ACN 3: 23B_ 4: 09R 5: 0456789 6: 0123456789 7: 0123456789 8: 0123456789 9: .0123456789 10: .0123456789 11: 0123456789_ 12: 0123456789 13: .0123456789 14: 0123456789 # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" rhiRox1 | wc -l # 196797 hgsql -N -e "select frag from gold;" rhiRox1 \ | egrep -e '[JKN][ACN][B23_][R09][0-9]+(\.[0-9_])?' | wc -l # 196797 hgsql -N -e "select frag from gold;" rhiRox1 \ | egrep -v -e '[JKN][ACN][B23_][R09][0-9]+(\.[0-9_])?' | wc -l # 0 # hence, add to trackDb/rhinopithecus/rhiRox1/trackDb.ra searchTable gold shortCircuit 1 termRegex [JKN][ACN][B23_][R09][0-9]+(\.[0-9_])? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 ######################################################################### # all.joiner update, downloads and in pushQ - (DONE 2015-03-23 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until this is a clean output joinerCheck -database=rhiRox1 -keys all.joiner joinerCheck -database=rhiRox1 -tableCoverage all.joiner joinerCheck -database=rhiRox1 -times all.joiner cd /hive/data/genomes/rhiRox1 time makeDownloads.pl rhiRox1 > downloads.log 2>&1 # real 18m36.348s # now ready for pushQ entry mkdir /hive/data/genomes/rhiRox1/pushQ cd /hive/data/genomes/rhiRox1/pushQ makePushQSql.pl rhiRox1 > rhiRox1.pushQ.sql 2> stderr.out # check for errors in stderr.out, some are OK, e.g.: # WARNING: hgwdev does not have /gbdb/rhiRox1/wib/gc5Base.wib # WARNING: hgwdev does not have /gbdb/rhiRox1/wib/quality.wib # WARNING: hgwdev does not have /gbdb/rhiRox1/bbi/qualityBw/quality.bw # WARNING: rhiRox1 does not have seq # WARNING: rhiRox1 does not have extFile # WARNING: rhiRox1 does not have estOrientInfo # WARNING: rhiRox1 does not have mrnaOrientInfo # copy it to hgwbeta scp -p rhiRox1.pushQ.sql qateam@hgwbeta:/tmp ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/rhiRox1.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly ######################################################################### # BLATSERVERS ENTRY (DONE - 2017-02-21 - 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 ("rhiRox1", "blat1b", "17872", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("rhiRox1", "blat1b", "17873", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ # augustus gene track (DONE - 2015-05-28 - Hiram) mkdir /hive/data/genomes/melGal5/bed/augustus cd /hive/data/genomes/melGal5/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev rhiRox1) > do.log 2>&1 # real 159m20.318s cat fb.rhiRox1.augustusGene.txt # 47747665 bases of 2856044136 (1.672%) in intersection #########################################################################