# for emacs: -*- mode: sh; -*- # This file describes browser build for the eulFla1 # Assembly name: Eflavifronsk33QCA # Organism name: Eulemur flavifrons (Sclater's lemur) # Isolate: Harlow # Sex: female # Taxid: 87288 # BioSample: SAMN03699688 # BioProject: PRJNA284191 # Submitter: University of Chicago # Date: 2015-8-6 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: LGHW01 # Assembly method: SOAPdenovo v. 1.05 # Genome coverage: 52.0x # Sequencing technology: Illumina HiSeq # RefSeq category: Representative Genome # GenBank assembly accession: GCA_001262665.1 # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_001262685.1 Primary Assembly ## GCA_001262705.1 non-nuclear ############################################################################# ## The non-nuclear sequence are unassembled scaffolds: ## LGHW01038363.1 LGHW01038364.1 LGHW01038365.1 LGHW01038366.1 LGHW01038367.1 ## which also have sequence names: ## C40721736 C40918911 C40931277 C41178897 C41368095 ############################################################################# ############################################################################# # obtain photograph (DONE - 2017-09-29 - Hiram) mkdir -p /hive/data/genomes/eulFla1/photo cd /hive/data/genomes/eulFla1/photo wget --timestamping "https://c2.staticflickr.com/4/3526/4007720968_a6f54da3c7_b.jpg" convert -geometry 400x400 -quality 80 4007720968_a6f54da3c7_b.jpg \ Eulemur_flavifrons,jpg printf "photoCreditURL\thttps://www.flickr.com/photos/joachim_s_mueller/4007720968 photoCreditName\tJoachim S. Müller - flickr\n" > ../photoReference.txt ############################################################################# # fetch sequence from new style download directory (DONE - 2017-09-29 - Hiram) mkdir -p /hive/data/genomes/eulFla1/refseq cd /hive/data/genomes/eulFla1/refseq time rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/genbank/vertebrate_mammalian/Eulemur_flavifrons/all_assembly_versions/GCA_001262665.1_Eflavifronsk33QCA/ ./ # sent 260 bytes received 1668710754 bytes 18438795.73 bytes/sec # total size is 1668505543 speedup is 1.00 # real 1m29.589s # measure what we have here: faSize *A_genomic.fna.gz # 2115568035 bases (21464517 N's 2094103518 real 1491887963 upper # 602215555 lower) in 38367 sequences in 1 files # Total size: mean 55140.3 sd 161501.2 min 200 (LGHW01019419.1) # max 3296881 (LGHW01002226.1) median 829 # %28.47 masked total, %28.76 masked real faCount *A_genomic.fna.gz | tail # seq len A C G T N cpg # total 2115568035 620069520 426698123 427084696 620251179 21464517 23371225 ############################################################################# # fixup to UCSC naming scheme (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulFla1/ucsc cd /hive/data/genomes/eulFla1/ucsc # verify no duplicate sequences: time faToTwoBit ../genbank/*A_genomic.fna.gz genbank.2bit # real 1m0.926s twoBitDup genbank.2bit # should be silent output, otherwise the duplicates need to be removed # LGHW01001554.1 and LGHW01001553.1 are identical echo "LGHW01001554v1" > duplicate.list # since this is an unplaced contig assembly, verify all names are .1: twoBitInfo genbank.2bit stdout | awk '{print $1}' \ | sed -e 's/W[0-9]\+/W/;' | sort | uniq -c # 38367 LGHW.1 # in this case, all the .1's can be changed to: v1 time zcat ../genbank/*A_genomic.fna.gz \ | sed -e 's/.1 Eulemur .*/v1/;' \ | faSomeRecords -exclude stdin duplicate.list stdout \ | gzip -c > chrUn.eulFla1.fa.gz # real 11m24.997s # there is no supplied AGP file: hgFakeAgp -minContigGap=1 chrUn.eulFla1.fa.gz chrUn.eulFla1.agp # verify fasta and AGP match: time faToTwoBit chr*.fa.gz test.2bit # real 1m0.560s cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail # All AGP and FASTA entries agree - both files are valid # confirm no duplicates, should be silent output twoBitDup test.2bit # verify nothing lost compared to genbank: time twoBitToFa test.2bit stdout | faSize stdin # 2115567618 bases (21464219 N's 2094103399 real 1491887844 upper # 602215555 lower) in 38366 sequences in 1 files # Total size: mean 55141.7 sd 161503.1 min 200 (LGHW01019419v1) # max 3296881 (LGHW01002226v1) median 829 # %28.47 masked total, %28.76 masked real # real 0m35.359s # same totals as above minus the one duplicate: # 2115568035 bases (21464517 N's 2094103518 real 1491887963 upper # 602215555 lower) in 38367 sequences in 1 files calc 2115568035 - 2115567618 # 2115568035 - 2115567618 = 417.000000 twoBitInfo test.2bit stdout | grep LGHW01001553 # LGHW01001553v1 417 ############################################################################# # Initial database build (DONE - 2017-10-02 - Hiram) cd /hive/data/genomes/eulFla1 # establish the config.ra file: ~/kent/src/hg/utils/automation/prepConfig.pl eulFla1 mammal primate \ genbank/*_assembly_report.txt > eulFla1.config.ra # going to need a mitoAcc ? # fixup the genBankAccessionID and the ncbiGenomeId # set mitoAcc to none # verify this looks OK: cat eulFla1.config.ra # config parameters for makeGenomeDb.pl: db eulFla1 clade mammal genomeCladePriority 35 scientificName Eulemur flavifrons commonName Sclater's lemur assemblyDate Aug. 2015 assemblyLabel University of Chicago assemblyShortLabel Eflavifronsk33QCA orderKey 19179 mitoAcc none fastaFiles /hive/data/genomes/eulFla1/ucsc/*.fa.gz agpFiles /hive/data/genomes/eulFla1/ucsc/*.agp # qualFiles none dbDbSpeciesDir primate photoCreditURL https://www.flickr.com/photos/joachim_s_mueller/4007720968 photoCreditName Joachim S. Müller - flickr ncbiGenomeId 39851 ncbiAssemblyId 469021 ncbiAssemblyName Eflavifronsk33QCA ncbiBioProject 284191 ncbiBioSample SAMN03699688 genBankAccessionID GCA_001262665.1 taxId 87288 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp eulFla1.config.ra) > agp.log 2>&1 # real 2m17.806s # verify it ran OK: # *** All done! (through the 'agp' step) # this is going to fail on the name "Sclater's lemur" name due to the 'quote # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=db \ eulFla1.config.ra ) > db.log 2>&1 # real 21m54.488s # fixing the broken name business with the 'quote time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=dbDb \ -stop=dbDb eulFla1.config.ra ) > dbDb.log 2>&1 # and now finishing: time (makeGenomeDb.pl -workhorse=hgwdev \ -dbHost=hgwdev -fileServer=hgwdev -continue=trackDb \ -stop=trackDb eulFla1.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`/eulFla1.unmasked.2bit /gbdb/eulFla1/eulFla1.2bit ############################################################################# # cytoBandIdeo - (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/cytoBand cd /hive/data/genomes/eulFla1/bed/cytoBand makeCytoBandIdeo.csh eulFla1 ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/cpgIslandsUnmasked cd /hive/data/genomes/eulFla1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/eulFla1/eulFla1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku eulFla1) > do.log 2>&1 # real 19m14.585s cat fb.eulFla1.cpgIslandExtUnmasked.txt # 25664010 bases of 2714439490 (0.945%) in intersection ############################################################################# # running repeat masker (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/repeatMasker cd /hive/data/genomes/eulFla1/bed/repeatMasker # RM doesn't recognize the scientific name. It does recognize # the top-level name: time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -species=eulemur -smallClusterHub=ku eulFla1) > do.log 2>&1 & # real 471m32.191s cat faSize.rmsk.txt # 2115567618 bases (21464219 N's 2094103399 real 1265558057 upper # 828545342 lower) in 38366 sequences in 1 files # Total size: mean 55141.7 sd 161503.1 min 200 (LGHW01019419v1) # max 3296881 (LGHW01002226v1) median 829 # %39.16 masked total, %39.57 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 eulFla1 rmsk # 829162700 bases of 2115567618 (39.193%) in intersection # real 0m39.973s # 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;' eulFla1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 829162700.000000 # real 0m26.279s ########################################################################## # running simple repeat (DONE - 2017-10-02 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/simpleRepeat cd /hive/data/genomes/eulFla1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=5 eulFla1) > do.log 2>&1 & # real 20m28.539s cat fb.simpleRepeat # 36541207 bases of 2094103399 (1.745%) in intersection # add to this simple repeat to rmsk: cd /hive/data/genomes/eulFla1 twoBitMask eulFla1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed eulFla1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa eulFla1.2bit stdout | faSize stdin > faSize.eulFla1.2bit.txt cat faSize.eulFla1.2bit.txt # 2115567618 bases (21464219 N's 2094103399 real 1264862321 upper # 829241078 lower) in 38366 sequences in 1 files # Total size: mean 55141.7 sd 161503.1 min 200 (LGHW01019419v1) # max 3296881 (LGHW01002226v1) median 829 # %39.20 masked total, %39.60 masked real # reset the 2bit gbdb symlink: rm /gbdb/eulFla1/eulFla1.2bit ln -s `pwd`/eulFla1.2bit /gbdb/eulFla1/eulFla1.2bit ############################################################################# # CREATE MICROSAT TRACK (DONE - 2017-10-03 - Hiram) ssh hgwdev mkdir /cluster/data/eulFla1/bed/microsat cd /cluster/data/eulFla1/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 eulFla1 microsat microsat.bed # Read 10681 elements of size 4 from microsat.bed ############################################################################# # ucscToINSDC table/track (DONE - 2017-10-03 - 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/eulFla1/bed/ucscToINSDC cd /hive/data/genomes/eulFla1/bed/ucscToINSDC # there is no chrM sequence in this assembly # find accession for chrM grep chrM ../../eulFla1.agp # empty result # standard procedure does not wrk here, there is no Primary_Assembly/ # hierarchy. Simply make the list manually: grep -v "^#" \ ../../genbank/GCA_001262665.1_Eflavifronsk33QCA_assembly_report.txt \ | cut -f5 | sort | while read C do U=`echo $C | sed -e 's/\.1/v1/;'` printf "%s\t%s\n" "${U}" "${C}" done | grep -v `cat ../../ucsc/duplicate.list` > ucscToINSDC.txt awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > name.coordinate.tab join ucscToINSDC.txt name.coordinate.tab \ | awk '{printf "%s\t%d\t%d\t%s\n", $1,$3,$4,$2}' > ucscToINSDC.bed # should be same line counts throughout: wc -l * # 38366 name.coordinate.tab # 38366 ucscToINSDC.bed # 38366 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 eulFla1 ucscToINSDC stdin ucscToINSDC.bed # checkTableCoords should be silent to indicate no errors checkTableCoords eulFla1 # should cover %100 entirely: featureBits -countGaps eulFla1 ucscToINSDC # 2115567618 bases of 2115567618 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/chromAlias cd /hive/data/genomes/eulFla1/bed/chromAlias hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' eulFla1 \ > ucsc.genbank.tab awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab \ | sort > eulFla1.chromAlias.tab hgLoadSqlTab eulFla1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ eulFla1.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.: # LGHW01000002.1:400-500 ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-10-03 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/primate/eulFla1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" eulFla1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c 38366 LGHWv1_1 6536 LGHWv1_10 288 LGHWv1_100 279 LGHWv1_101 ... ... etc ... # implies a search rule of: 'LGHW[0-9]+([v0-9_]+)?' # verify this rule will find them all or eliminate them all: hgsql -N -e "select frag from gold;" eulFla1 | wc -l # 292741 hgsql -N -e "select frag from gold;" eulFla1 \ | egrep -e 'LGHW[0-9]+([v0-9_]+)?' | wc -l # 292741 hgsql -N -e "select frag from gold;" eulFla1 \ | egrep -v -e 'LGHW[0-9]+([v0-9_]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/eulFla1/trackDb.ra searchTable gold shortCircuit 1 termRegex LGHW[0-9]+([v0-9_]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box, check full accession name, # accession name without .1 # truncated accession name produces multiple results # and the two chrM accessions, with and without the .1 and partial name # use: accessionName:n-m to display locations n to m on that accession git commit -m 'adding gold assembly table search rule refs #20265' trackDb.ra ########################################################################## ## WINDOWMASKER (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/windowMasker cd /hive/data/genomes/eulFla1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev eulFla1) > do.log 2>&1 # real 177m42.461s # Masking statistics cat faSize.eulFla1.cleanWMSdust.txt # 2115567618 bases (21464219 N's 2094103399 real 1479955562 upper # 614147837 lower) in 38366 sequences in 1 files # Total size: mean 55141.7 sd 161503.1 min 200 (LGHW01019419v1) # max 3296881 (LGHW01002226v1) median 829 # %29.03 masked total, %29.33 masked real cat fb.eulFla1.rmsk.windowmaskerSdust.txt # 365950058 bases of 2115567618 (17.298%) in intersection ########################################################################## # cpgIslands - (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/cpgIslands cd /hive/data/genomes/eulFla1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku eulFla1) > do.log 2>&1 # real 14m18.603s cat fb.eulFla1.cpgIslandExt.txt # 30746846 bases of 2094103399 (1.468%) in intersection ############################################################################## # ncbiRefSeq gene track (TBD - 2016-05-05 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/ncbiRefSeq cd /hive/data/genomes/eulFla1/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 eulFla1) > 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 eulFla1) > 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 eulFla1) > load.log 2>&1 # real 0m21.690s cat fb.ncbiRefSeq.eulFla1.txt # 74646536 bases of 2725937399 (2.738%) in intersection ############################################################################## # genscan - (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/genscan cd /hive/data/genomes/eulFla1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku eulFla1) > do.log 2>&1 # real 81m43.851s cat fb.eulFla1.genscan.txt # 53866217 bases of 2094103399 (2.572%) in intersection cat fb.eulFla1.genscanSubopt.txt # 57319829 bases of 2094103399 (2.737%) in intersection ############################################################################# # augustus gene track (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/eulFla1/bed/augustus cd /hive/data/genomes/eulFla1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev eulFla1) > do.log 2>&1 # real 75m39.619s cat fb.eulFla1.augustusGene.txt # 49451995 bases of 2094103399 (2.361%) in intersection ############################################################################# # Create kluster run files (DONE - 2017-10-03 - Hiram) # find 'real' base count for this assembly: (numerator below) cd /hive/data/genomes/eulFla1 head -1 faSize.eulFla1.2bit.txt # 2115567618 bases (21464219 N's 2094103399 real 1264862321 upper # 829241078 lower) in 38366 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 \( 2094103399 / 2861349177 \) \* 1024 # ( 2094103399 / 2861349177 ) * 1024 = 749.423348 # ==> use -repMatch=700 according to size scaled down from 1024 for human. # and rounded down to nearest 100 cd /hive/data/genomes/eulFla1 time blat eulFla1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/eulFla1.11.ooc \ -repMatch=700 # Wrote 25954 overused 11-mers to jkStuff/eulFla1.11.ooc # real 0m34.771s # 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;' eulFla1 \ # | sort -k7,7nr # minimum size is 50000 # gapToLift -verbose=2 -minGap=50000 eulFla1 \ # jkStuff/eulFla1.nonBridged.lft -bedFile=jkStuff/eulFla1.nonBridged.bed ######################################################################### # lastz/chain/net swap from hg38 (DONE - 2017-10-03 - Hiram) # alignment to hg38 cd /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03 cat fb.hg38.chainEulFla1Link.txt # 1016209837 bases of 3049335806 (33.326%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eulFla1) \ > rbest.log 2>&1 & # real 210m50.610s # and for the swap: mkdir /hive/data/genomes/eulFla1/bed/blastz.hg38.swap cd /hive/data/genomes/eulFla1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 76m58.704s cat fb.eulFla1.chainHg38Link.txt # 2053319068 bases of 2610518382 (78.656%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulFla1 hg38) \ > rbest.log 2>&1 # real 227m7.064s ######################################################################### cd /hive/data/genomes/hg38/bed/lastzEulFla1.2017-09-25 cat fb.hg38.chainEulFla1Link.txt # 2153726630 bases of 3049335806 (70.629%) in intersection # and for the swap: mkdir /hive/data/genomes/eulFla1/bed/blastz.hg38.swap cd /hive/data/genomes/eulFla1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEulFla1.2017-09-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m8.440s cat fb.eulFla1.chainHg38Link.txt # 2111600029 bases of 2714439490 (77.791%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulFla1 hg38) \ > rbest.log 2>&1 # real 427m26.453s # working up a load procedure for rbest time ($HOME/kent/src/hg/utils/automation/doRecipBest.pl -load -continue=load -workhorse=hgwdev -buildDir=`pwd` eulFla1 hg38) \ > loadRBest.log 2>&1 ######################################################################### # lastz/chain/net swap from mm10 (DONE - 2017-10-04 - Hiram) # alignment on mm10 cd /hive/data/genomes/mm10/bed/lastzEulFla1.2017-10-04 cat fb.mm10.chainEulFla1Link.txt # 916687191 bases of 2652783500 (34.556%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` mm10 eulFla1) \ > rbest.log 2>&1 & # real 330m53.327s mkdir /hive/data/genomes/eulFla1/bed/blastz.mm10.swap cd /hive/data/genomes/eulFla1/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzEulFla1.2017-10-04/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 65m26.113s cat fb.eulFla1.chainMm10Link.txt # 887070088 bases of 2094103399 (42.360%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulFla1 mm10) \ > rbest.log 2>&1 # real 270m35.579s ############################################################################## # GENBANK AUTO UPDATE (DONE - 2017-10-03 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Eulemur albifrons 1 0 0 # Eulemur fulvus 8 0 0 # Eulemur fulvus collaris 2 0 0 # Eulemur mongoz 2 0 0 # edit etc/genbank.conf to add eulFla1 just before susScr3 # eulFla1 (Sclater's lemur / Eulemur flavifrons / taxId 87288) eulFla1.serverGenome = /hive/data/genomes/eulFla1/eulFla1.2bit eulFla1.clusterGenome = /hive/data/genomes/eulFla1/eulFla1.2bit eulFla1.ooc = /hive/data/genomes/eulFla1/jkStuff/eulFla1.11.ooc eulFla1.lift = no eulFla1.refseq.mrna.native.pslCDnaFilter = ${lowCover.refseq.mrna.native.pslCDnaFilter} eulFla1.refseq.mrna.xeno.pslCDnaFilter = ${lowCover.refseq.mrna.xeno.pslCDnaFilter} eulFla1.genbank.mrna.native.pslCDnaFilter = ${lowCover.genbank.mrna.native.pslCDnaFilter} eulFla1.genbank.mrna.xeno.pslCDnaFilter = ${lowCover.genbank.mrna.xeno.pslCDnaFilter} eulFla1.genbank.est.native.pslCDnaFilter = ${lowCover.genbank.est.native.pslCDnaFilter} eulFla1.genbank.est.xeno.pslCDnaFilter = ${lowCover.genbank.est.xeno.pslCDnaFilter} eulFla1.downloadDir = eulFla1 # there are no refseq mrna native eulFla1.refseq.mrna.native.load = no eulFla1.refseq.mrna.xeno.load = yes # DO NOT NEED genbank.mrna.xeno except for human, mouse eulFla1.genbank.mrna.xeno.load = no eulFla1.genbank.mrna.native.load = no eulFla1.genbank.est.native.load = no eulFla1.perChromTables = no # And edit src/lib/gbGenome.c to add new species. Skipped # static char *eulFlaNames[] = {"Eulemur flavifrons", NULL}; # {"eulFla", eulFlaNames}, git commit -m 'adding eulFla1 and eulMac1 refs #20265 #20266' \ etc/genbank.conf src/lib/gbGenome.c git push # update /cluster/data/genbank/: make etc-update make install-server screen # control this business with a screen since it takes a while cd /cluster/data/genbank time ./bin/gbAlignStep -initial eulFla1 # logFile: var/build/logs/2017.10.03-14:57:13.eulFla1.initalign.log # real 71m38.539s tail -2 var/build/logs/2017.10.03-14:57:13.eulFla1.initalign.log # hgwdev 2017.10.03-16:07:52 eulFla1.initalign: Succeeded: eulFla1 # hgwdev 2017.10.03-16:08:51 eulFla1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.eulFla1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad eulFla1 # logFile: var/dbload/hgwdev/logs/2017.10.04-15:38:39.eulFla1.dbload.log # real 4m41.216s tail -1 var/dbload/hgwdev/logs/2017.10.04-15:38:39.eulFla1.dbload.log # hgwdev 2017.10.04-15:43:20 eulFla1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add eulFla1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m \ "Added eulFla1 - Sclater's lemur - Eulemur flavifrons refs #20265" \ etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################## # BLATSERVERS ENTRY (DONE - 2017-10-04 - Hiram) # After getting a blat server assigned by the Blat Server Gods, ssh hgwdev hgsql -e 'INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("eulFla1", "blat1d", "17886", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("eulFla1", "blat1d", "17887", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################## # set default position similar location as hg38 (DONE - 2017-10-04 - Hiram) hgsql -e \ 'update dbDb set defaultPos="LGHW01001035v1:72874-89024" where name="eulFla1";' \ hgcentraltest ############################################################################## # all.joiner update, downloads and in pushQ - (DONE - 2017-10-06 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until these are all clean outputs: joinerCheck -database=eulFla1 -tableCoverage all.joiner joinerCheck -database=eulFla1 -times all.joiner joinerCheck -database=eulFla1 -keys all.joiner cd /hive/data/genomes/eulFla1 time (makeDownloads.pl eulFla1) > downloads.log 2>&1 # real 15m6.200s # now ready for pushQ entry mkdir /hive/data/genomes/eulFla1/pushQ cd /hive/data/genomes/eulFla1/pushQ time (makePushQSql.pl -redmineList eulFla1) \ > eulFla1.pushQ.sql 2> stderr.out # real 3m44.165s # check for errors in stderr.out, some are OK, e.g.: # writing redmine listings to # redmine.eulFla1.file.list # redmine.eulFla1.table.list # redmine.eulFla1.releaseLog.txt # WARNING: eulFla1 does not have ucscToRefSeq # WARNING: eulFla1 does not have seq # WARNING: eulFla1 does not have extFile # WARNING: eulFla1 does not have estOrientInfo # WARNING: eulFla1 does not have mrnaOrientInfo # examine these files to make sure they appear sane, # then enter the full path names of these listing files: # /hive/data/genomes/eulFla1/pushQ/redmine.eulFla1.file.list # /hive/data/genomes/eulFla1/pushQ/redmine.eulFla1.releaseLog.txt # /hive/data/genomes/eulFla1/pushQ/redmine.eulFla1.table.list # into the Redmine #20265 and set to QA Ready. #########################################################################