# for emacs: -*- mode: sh; -*- # This file describes browser build for the xenLae2 ######################################################################### # photo obtained from WikiMedia Commons # (DONE - 2017-02-15 - Hiram) mkdir /hive/data/genomes/xenLae2/photo cd /hive/data/genomes/xenLae2/photo wget -O photoFile.jpg 'https://upload.wikimedia.org/wikipedia/commons/5/58/Krallenfrosch_Xenopus_laevis.jpg' convert -sharpen 0 -normalize -geometry 400x400 photoFile.jpg Xenopus_laevis.jpg cat photoReference.txt printf "photoCreditURL https://commons.wikimedia.org/wiki/User:Holleday photoCreditName WikiMedia Commons: Holger Krisp, Ulm, Germany\n" \ > photoReference.txt ######################################################################### # Initial steps (DONE - 2017-03-28 - Hiram) # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/xenLae2 cd ~/kent/src/hg/makeDb/doc/xenLae2 # best to use a most recent document since it has the latest features and # procedures: sed -e 's/xenTro9/xenLae2/g; s/XenTro9/XenLae2/g; s/DONE/TBD/g;' \ ../xenTro9/initialBuild.txt > initialBuild.txt mkdir /hive/data/genomes/xenLae2/refseq cd /hive/data/genomes/xenLae2/refseq rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_other/Xenopus_laevis/all_assembly_versions/GCF_001663975.1_Xenopus_laevis_v2/ ./ # sent 2315 bytes received 3583884310 bytes 23972485.79 bytes/sec # total size is 3583438147 speedup is 1.00 # real 2m29.676s # check assembly size for later reference: faSize G*v2_genomic.fna.gz # 2718433805 bases (309709018 N's 2408724787 real 1444442369 upper # 964282418 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (NW_016802823.1) # max 219802468 (NC_030724.1) median 353 # %35.47 masked total, %40.03 masked real # this information is from the top of # xenLae2/refseq/GCF_001663975.1_Xenopus_laevis_v2_assembly_report.txt # Assembly name: Xenopus_laevis_v2 # Organism name: Xenopus laevis (African clawed frog) # Infraspecific name: strain=J # Sex: female # Taxid: 8355 # BioSample: SAMN04518361 # BioProject: PRJNA338693 # Submitter: International Xenopus Sequencing Consortium # Date: 2016-8-9 # Assembly type: haploid # Release type: major # Assembly level: Chromosome # Genome representation: full # WGS project: LYTH01 # Assembly method: Meraculous v. May-2013 # Genome coverage: 30x # Sequencing technology: Illumina HiSeq 2000 # RefSeq category: Representative Genome # GenBank assembly accession: GCA_001663975.1 # RefSeq assembly accession: GCF_001663975.1 # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_001663985.1 GCF_001663985.1 Primary Assembly ## GCF_000028935.1 non-nuclear ############################################################################# # establish config.ra file (DONE - Hiram - 2017-03-28) # arguments here are: cd /hive/data/genomes/xenLae2 $HOME/kent/src/hg/utils/automation/prepConfig.pl xenLae2 vertebrate \ xenTro ./refseq/*_assembly_report.txt > xenLae2.config.ra # verify it looks sane, fix anything that is odd, especially common name # and orderKey for example: cat xenLae2.config.ra # config parameters for makeGenomeDb.pl: db xenLae2 clade vertebrate genomeCladePriority 70 scientificName Xenopus laevis commonName African clawed frog assemblyDate Aug. 2016 assemblyLabel International Xenopus Sequencing Consortium assemblyShortLabel Xenopus_laevis_v2 orderKey 1225 # mitochondrial sequence included in refseq release # mitoAcc NC_001573.1 mitoAcc none fastaFiles /hive/data/genomes/xenLae2/ucsc/*.fa.gz agpFiles /hive/data/genomes/xenLae2/ucsc/*.agp # qualFiles none dbDbSpeciesDir xenTro photoCreditURL https://commons.wikimedia.org/wiki/User:Holleday photoCreditName WikiMedia Commons: Holger Krisp, Ulm, Germany ncbiGenomeId 81 ncbiAssemblyId 779791 ncbiAssemblyName Xenopus_laevis_v2 ncbiBioProject 338693 ncbiBioSample SAMN04518361 genBankAccessionID GCF_001663975.1 taxId 8355 ############################################################################# # setup UCSC named files (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenLae2/ucsc cd /hive/data/genomes/xenLae2/ucsc # check for duplicate sequences: time faToTwoBit -noMask ../refseq/G*v2_genomic.fna.gz refseq.2bit # real 1m8.052s twoBitDup refseq.2bit # no output is a good result, otherwise, would have to eliminate duplicates ~/kent/src/hg/utils/automation/ucscCompositeAgp.pl \ ../refseq/G*v2_genomic.fna.gz \ ../refseq/G*v2_assembly_structure/Primary_Assembly # NC_030724.1 chr1L # NC_030725.1 chr1S # NC_030726.1 chr2L # NC_030727.1 chr2S # NC_030728.1 chr3L # NC_030729.1 chr3S # NC_030730.1 chr4L # NC_030731.1 chr4S # NC_030732.1 chr5L # NC_030733.1 chr5S # NC_030734.1 chr6L # NC_030735.1 chr6S # NC_030736.1 chr7L # NC_030737.1 chr7S # NC_030738.1 chr8L # NC_030739.1 chr8S # NC_030740.1 chr9_10L # NC_030741.1 chr9_10S time ~/kent/src/hg/utils/automation/unplacedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # processed 108014 sequences into chrUn.fa.gz # real 83m59.891s # there are no unlocalized sequences # time ~/kent/src/hg/utils/automation/unlocalizedWithChroms.pl \ # ../refseq/*_assembly_structure/Primary_Assembly # bash syntax here mitoAcc=`grep "^# mitoAcc" ../xenLae2.config.ra | awk '{print $NF}'` printf "# mitoAcc %s\n" "$mitoAcc" # mitoAcc NC_001573.1 zcat \ ../refseq/*_assembly_structure/non-nuclear/assem*/AGP/chrMT.comp.agp.gz \ | grep -v "^#" | sed -e "s/^$mitoAcc/chrM/;" > chrM.agp printf ">chrM\n" > chrM.fa twoBitToFa -noMask refseq.2bit:$mitoAcc stdout | grep -v "^>" >> chrM.fa faSize chrM.fa # 17553 bases (0 N's 17553 real 17553 upper 0 lower) in 1 sequences in 1 files gzip chrM.fa # verify fasta and AGPs agree time faToTwoBit *.fa.gz test.2bit # real 1m21.548s time cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail -4 # All AGP and FASTA entries agree - both files are valid # real 1m7.969s # and no sequence lost from orginal: twoBitToFa test.2bit stdout | faSize stdin # 2718433805 bases (309709018 N's 2408724787 real 2408724787 upper # 0 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (chrUn_NW_016802823v1) # max 219802468 (chr1L) median 353 # same numbers as above # 2718433805 bases (309709018 N's 2408724787 real 1444442369 upper # 964282418 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (NW_016802823.1) # max 219802468 (NC_030724.1) median 353 # no longer need these temporary 2bit files rm refseq.2bit test.2bit ############################################################################# # Initial database build (DONE - 2017-03-28 - Hiram) cd /hive/data/genomes/xenLae2 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp xenLae2.config.ra) > agp.log 2>&1 # real 4m7.680s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db xenLae2.config.ra) > db.log 2>&1 # real 21m58.644s # check in the trackDb files created in TemporaryTrackDbCheckout/ # and add xenLae2 to trackDb/makefile # temporary symlink until masked sequence is available cd /hive/data/genomes/xenLae2 ln -s `pwd`/xenLae2.unmasked.2bit /gbdb/xenLae2/xenLae2.2bit ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/cpgIslandsUnmasked cd /hive/data/genomes/xenLae2/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/xenLae2/xenLae2.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku xenLae2) > do.log 2>&1 # real 25m59.275s cat fb.xenLae2.cpgIslandExtUnmasked.txt # 25514118 bases of 2408724787 (1.059%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/cytoBand cd /hive/data/genomes/xenLae2/bed/cytoBand makeCytoBandIdeo.csh xenLae2 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (DONE - 2017-03-30 - Hiram) # the sequence here is working for a 'refseq' assembly # beware of a chrM situation may be specific depending upon what is # available in the assembly mkdir /hive/data/genomes/xenLae2/bed/ucscToINSDC cd /hive/data/genomes/xenLae2/bed/ucscToINSDC # find accession for chrM grep chrM ../../xenLae2.agp # chrM 1 17553 1 O NC_001573.1 1 17553 + # find the genbank accession for NC_001573.1 at Entrez nucleotide # The NC_001573.1 name is the RefSeq name, the genbank name is: M10217.1 # the assembly_report does not have this M name since the chrM sequence # is not in the genbank assembly: grep NC_001573.1 ../../refseq/GCF*v2_assembly_report.txt # MT assembled-molecule MT Mitochondrion na <> NC_001573.1 non-nuclear 17553 na # if there is a chrM, use its INSDC name as a second argument: # this is a RefSeq assembly, use the chrM refSeq name: ~/kent/src/hg/utils/automation/ucscToINSDC.sh \ ../../refseq/GCF_*structure/Primary_Assembly NC_001573.1 # 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 # chrM processing needs special help, fixup with the sed # extract the refseq vs. genbank names from the assembly_report # columns 5 and 7 are the INSDC and RefSeq names grep -v "^#" ../../refseq/GCF*_assembly_report.txt | cut -f5,7 \ | awk '{printf "%s\t%s\n", $2, $1}' | sed -e 's/na/M10217.1/' \ | sort > refseq.insdc.txt awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > ucsc.coordinate.tab join -2 2 refseq.insdc.txt ucscToRefSeq.txt | tr '[ ]' '[\t]' | sort -k3 \ | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-4 \ > ucscToRefSeq.bed join -2 2 refseq.insdc.txt ucscToRefSeq.txt | tr '[ ]' '[\t]' | sort -k3 \ | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-3,5 \ > ucscToINSDC.bed # verify chrM is correct: grep chrM *.bed # ucscToINSDC.bed:chrM 0 17553 M10217.1 # ucscToRefSeq.bed:chrM 0 17553 NC_001573.1 # should be same line counts throughout: wc -l * # 108033 refSeqToUcsc.txt # 108033 refseq.insdc.txt # 108033 ucsc.coordinate.tab # 108033 ucscToINSDC.bed # 108033 ucscToRefSeq.bed # 108033 ucscToRefSeq.txt export chrSize=`cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 20 # use the 20 in this sed sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab xenLae2 ucscToINSDC stdin ucscToINSDC.bed # should be the same for ucscToRefSeq: export chrSize=`cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 20 sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | sed -e 's/INSDC/RefSeq/g;' > ucscToRefSeq.sql hgLoadSqlTab xenLae2 ucscToRefSeq ./ucscToRefSeq.sql ucscToRefSeq.bed # checkTableCoords should be silent checkTableCoords xenLae2 # each should cover %100 entirely: featureBits -countGaps xenLae2 ucscToINSDC # 2718433805 bases of 2718433805 (100.000%) in intersection featureBits -countGaps xenLae2 ucscToRefSeq # 2718433805 bases of 2718433805 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-03-30 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/chromAlias cd /hive/data/genomes/xenLae2/bed/chromAlias hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' xenLae2 \ > ucsc.refseq.tab hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' xenLae2 \ > ucsc.genbank.tab awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \ | sort > xenLae2.chromAlias.tab hgLoadSqlTab xenLae2 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ xenLae2.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-03-30 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/xenTro/xenLae2 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" xenLae2 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c # 324060 LYTH.1 # 1 NC_.1 # implies a rule: '[LN][CY][T_][H0-9]+(\.[0-9]+)?' # verify this rule will find them all and eliminate them all: hgsql -N -e "select frag from gold;" xenLae2 | wc -l # 324061 hgsql -N -e "select frag from gold;" xenLae2 \ | egrep -e '[LN][CY][T_][H0-9]+(\.[0-9]+)?' | wc -l # 324061 hgsql -N -e "select frag from gold;" xenLae2 \ | egrep -v -e '[LN][CY][T_][H0-9]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/chicken/xenLae2/trackDb.ra searchTable gold shortCircuit 1 termRegex [LN][CY][T_][H0-9]+(\.[0-9]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box ########################################################################## # running repeat masker (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/repeatMasker cd /hive/data/genomes/xenLae2/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku xenLae2) > do.log 2>&1 & # real 343m21.012s cat faSize.rmsk.txt # 2718433805 bases (309709018 N's 2408724787 real 2100533696 upper # 308191091 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (chrUn_NW_016802823v1) # max 219802468 (chr1L) median 353 # %11.34 masked total, %12.79 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 xenLae2 rmsk # 308308896 bases of 2718433805 (11.341%) in intersection # real 0m44.605s # why is it different than the faSize above ? # because rmsk masks out some N's as well as bases, the faSize count above # separates out the N's from the bases, it doesn't show lower case N's # faster way to get the same result on high contig count assemblies: time hgsql -N -e 'select genoName,genoStart,genoEnd from rmsk;' xenLae2 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 308308896.000000 # real 0m12.737s ########################################################################## # running simple repeat (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/simpleRepeat cd /hive/data/genomes/xenLae2/bed/simpleRepeat # using trf409 3 here guessing smaller genome (human == 6) time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409 3 xenLae2) > do.log 2>&1 & # real 53m53.100s cat fb.simpleRepeat # 118499828 bases of 1369865365 (8.650%) in intersection # adding this trfMask to the other masking cd /hive/data/genomes/xenLae2 # when using the Window Masker result: twoBitMask bed/windowMasker/xenLae2.cleanWMSdust.2bit \ -add bed/simpleRepeat/trfMask.bed xenLae2.2bit # you can safely ignore the warning about fields >= 13 # when using Rmsk results, add to rmsk after it is done: # twoBitMask xenLae2.rmsk.2bit \ # -add bed/simpleRepeat/trfMask.bed xenLae2.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa xenLae2.2bit stdout | faSize stdin > faSize.xenLae2.2bit.txt cat faSize.xenLae2.2bit.txt # 2718433805 bases (309709018 N's 2408724787 real 1431126103 upper # 977598684 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (chrUn_NW_016802823v1) # max 219802468 (chr1L) median 353 # %35.96 masked total, %40.59 masked real # reset the symlink rm /gbdb/xenLae2/xenLae2.2bit ln -s `pwd`/xenLae2.2bit /gbdb/xenLae2/xenLae2.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2017-03-29 - Hiram) ssh hgwdev mkdir /cluster/data/xenLae2/bed/microsat cd /cluster/data/xenLae2/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 xenLae2 microsat microsat.bed # Read 8726 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/windowMasker cd /hive/data/genomes/xenLae2/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev xenLae2) > do.log 2>&1 # real 375m16.032s # Masking statistics cat faSize.xenLae2.cleanWMSdust.txt # 2718433805 bases (309709018 N's 2408724787 real 1431849546 upper # 976875241 lower) in 108033 sequences in 1 files # Total size: mean 25163.0 sd 1845423.8 min 200 (chrUn_NW_016802823v1) # max 219802468 (chr1L) median 353 # %35.94 masked total, %40.56 masked real cat fb.xenLae2.rmsk.windowmaskerSdust.txt # 280390601 bases of 2718433805 (10.314%) in intersection ########################################################################## # run up idKeys files for ncbiRefSeq (DONE - 2017-03-30 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/idKeys cd /hive/data/genomes/xenLae2/bed/idKeys time (doIdKeys.pl -buildDir=`pwd` xenLae2) > do.log 2>&1 & # real 81m30.344s cat xenLae2.keySignature.txt # c4fea4971ed2f6afd8f2180d9cbebf03 ########################################################################## # cpgIslands - (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/cpgIslands cd /hive/data/genomes/xenLae2/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku xenLae2) > do.log 2>&1 & # real 20m39.583s cat fb.xenLae2.cpgIslandExt.txt # 4222160 bases of 2408724787 (0.175%) in intersection ############################################################################## # genscan - (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/genscan cd /hive/data/genomes/xenLae2/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku xenLae2) > do.log 2>&1 & # real 244m58.113s cat fb.xenLae2.genscan.txt # 58126492 bases of 2408724787 (2.413%) in intersection cat fb.xenLae2.genscanSubopt.txt # 56170972 bases of 2408724787 (2.332%) in intersection ############################################################################# # augustus gene track (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/augustus cd /hive/data/genomes/xenLae2/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=chicken -dbHost=hgwdev -workhorse=hgwdev xenLae2) > do.log 2>&1 & # real 200m38.406s cat fb.xenLae2.augustusGene.txt # 59344395 bases of 2408724787 (2.464%) in intersection ############################################################################# # lastz/chain/net swap human/hg38 (DONE - 2017-03-30 - Hiram) # original alignment cd /hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29 cat fb.hg38.chainXenLae2Link.txt # 97526523 bases of 3049335806 (3.198%) in intersection # and for the swap: mkdir /hive/data/genomes/xenLae2/bed/blastz.hg38.swap cd /hive/data/genomes/xenLae2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 28m54.570s cat fb.xenLae2.chainHg38Link.txt # 114726989 bases of 2408724787 (4.763%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenLae2 hg38) \ > rbest.log 2>&1 # real 712m34.326s ######################################################################### # lastz/chain/net swap mouse/mm10 (DONE - 2017-03-30 - Hiram) # original alignment cd /hive/data/genomes/mm10/bed/lastzXenLae2.2017-03-29 cat fb.mm10.chainXenLae2Link.txt # 82272699 bases of 2652783500 (3.101%) in intersection # and for the swap: mkdir /hive/data/genomes/xenLae2/bed/blastz.mm10.swap cd /hive/data/genomes/xenLae2/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzXenLae2.2017-03-29/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 # real 26m14.884s # forgot the syntenicNet time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzXenLae2.2017-03-29/DEF \ -continue=syntenicNet -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -syntenicNet -swap -chainMinScore=5000 \ -chainLinearGap=loose) > syntenicNet.log 2>&1 & # real 1m52.642s cat fb.xenLae2.chainMm10Link.txt # 116001603 bases of 2408724787 (4.816%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenLae2 mm10) \ > rbest.log 2>&1 # real 746m4.542s ############################################################################# # Create kluster run files (DONE - 2017-03-29 - Hiram) # numerator is xenLae2 gapless bases "real" as reported by: featureBits -noRandom -noHap xenLae2 gap # 276189979 bases of 2231632100 (12.376%) in intersection # ^^^ # denominator is hg19 gapless bases as reported by: # featureBits -noRandom -noHap hg19 gap # 234344806 bases of 2861349177 (8.190%) in intersection # 1024 is threshold used for human -repMatch: calc \( 2231632100 / 2861349177 \) \* 1024 # ( 2231632100 / 2861349177 ) * 1024 = 798.641176 # ==> use -repMatch=800 according to size scaled down from 1024 for human. # and rounded up to nearest 100 cd /hive/data/genomes/xenLae2 blat xenLae2.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/xenLae2.11.ooc \ -repMatch=800 # Wrote 39757 overused 11-mers to jkStuff/xenLae2.11.ooc # xenTro9 was: # Wrote 31375 overused 11-mers to jkStuff/xenLae2.11.ooc # xenTro7 was: # Wrote 31229 overused 11-mers to jkStuff/xenTro7.11.ooc # check non-bridged gaps to see what the typical size is: hgsql -N \ -e 'select * from gap where bridge="no" order by size;' xenLae2 \ | sort -k7,7nr | ave -col=7 stdin # there are no non-bridged gaps in this assembly # # all these gap sizes are 100 # # minimum gap size is 100 and produces a reasonable number of lifts # gapToLift -verbose=2 -minGap=10 xenLae2 jkStuff/nonBridged.lft \ # -bedFile=jkStuff/nonBridged.bed ######################################################################### # GENBANK AUTO UPDATE (DONE - 2017-04-05 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt # Xenopus laevis 20030 694634 11007 # edit etc/genbank.conf to add xenLae2 just before macFas5 # xenLae2 'Xenopus laevis' 19 chroms + 108014 contigs xenLae2.serverGenome = /hive/data/genomes/xenLae2/xenLae2.2bit xenLae2.clusterGenome = /hive/data/genomes/xenLae2/xenLae2.2bit xenLae2.ooc = /hive/data/genomes/xenLae2/jkStuff/xenLae2.11.ooc xenLae2.lift = no xenLae2.perChromTables = no xenLae2.downloadDir = xenLae2 # xenLae2.mgc = yes xenLae2.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} xenLae2.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} xenLae2.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} xenLae2.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} xenLae2.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} # DO NOT NEED genbank.mrna.xeno except for human, mouse # defaults yes: genbank.mrna.native.load, genbank.mrna.native.loadDesc, # genbank.est.native.load, refseq.mrna.native.load, refseq.mrna.native.loadDesc, # refseq.mrna.xeno.load , refseq.mrna.xeno.loadDesc # xenLae2.upstreamGeneTbl = ensGene # xenLae2.upstreamMaf = multiz9way /hive/data/genomes/xenTro7/bed/multiz9way/species.list # Edit src/lib/gbGenome.c to add new species. git commit -m "Added xenLae Xenopus laevis refs #17435" \ etc/genbank.conf src/lib/gbGenome.c git push # update /cluster/data/genbank/etc/: make etc-update # update /cluster/data/genbank/bin/: make install-server cd /cluster/data/genbank time ./bin/gbAlignStep -initial xenLae2 # logFile: var/build/logs/2017.04.03-15:27:22.xenLae2.initalign.log # real 1307m39.971s tail -2 var/build/logs/2017.04.03-15:27:22.xenLae2.initalign.log # hgwdev 2017.04.04-13:14:01 xenLae2.initalign: Succeeded: xenLae2 # hgwdev 2017.04.04-13:15:02 xenLae2.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.xenLae2 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad xenLae2 # logFile: var/dbload/hgwdev/logs/2017.04.04-13:15:52.xenLae2.dbload.log # real 174m9.891s tail -1 var/dbload/hgwdev/logs/2017.04.04-13:15:52.xenLae2.dbload.log # hgwdev 2017.04.04-16:10:02 xenLae2.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add xenLae2 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m 'adding xenLae2 to the update alignments refs #17435' etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################# # ncbiRefSeq (TBD - 2016-05-13 - Hiram) mkdir /hive/data/genomes/xenLae2/bed/ncbiRefSeq cd /hive/data/genomes/xenLae2/bed/ncbiRefSeq # running step wise as this script is still under development time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev \ -stop=download -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_other Gallus_gallus \ GCF_000002315.4_Gallus_gallus-5.0 xenLae2) > download.log 2>&1 # real 16m29.536s time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ -continue=process -bigClusterHub=ku -dbHost=hgwdev \ -stop=process -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_other Gallus_gallus \ GCF_000002315.4_Gallus_gallus-5.0 xenLae2) > process.log 2>&1 # real 3m58.858s time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ -continue=load -bigClusterHub=ku -dbHost=hgwdev \ -stop=load -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_other Gallus_gallus \ GCF_000002315.4_Gallus_gallus-5.0 xenLae2) > load.log 2>&1 # real 0m33.205s cat fb.ncbiRefSeq.xenLae2.txt # 82563006 bases of 1218501075 (6.776%) in intersection featureBits -enrichment xenLae2 refGene ncbiRefSeq # refGene 1.181%, ncbiRefSeq 6.776%, both 1.175%, cover 99.49%, # enrich 14.68x ######################################################################### # BLATSERVERS ENTRY (DONE - 2017-03-30 - 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 ("xenLae2", "blat1c", "17888", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("xenLae2", "blat1c", "17889", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to same region as xenTro9 ## (DONE - 2017-04-05 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr9_10L:104687822-104704936" where name="xenLae2";' hgcentraltest ######################################################################### # all.joiner update, downloads and in pushQ - (TBD - 2017-03-06 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # fixup all.joiner until this is a clean output joinerCheck -database=xenLae2 -tableCoverage all.joiner joinerCheck -database=xenLae2 -times all.joiner joinerCheck -database=xenLae2 -keys all.joiner cd /hive/data/genomes/xenLae2 time (makeDownloads.pl -workhorse=hgwdev xenLae2) > downloads.log 2>&1 # real 28m8.550s # now ready for pushQ entry mkdir /hive/data/genomes/xenLae2/pushQ cd /hive/data/genomes/xenLae2/pushQ time (makePushQSql.pl -redmineList xenLae2) > xenLae2.pushQ.sql 2> stderr.out # real 7m13.295s # check for errors in stderr.out, some are OK, e.g.: # WARNING: hgwdev does not have /gbdb/xenLae2/wib/gc5Base.wib # WARNING: hgwdev does not have /gbdb/xenLae2/wib/quality.wib # WARNING: hgwdev does not have /gbdb/xenLae2/bbi/quality.bw # WARNING: xenLae2 does not have seq # WARNING: xenLae2 does not have extFile # copy it to hgwbeta scp -p xenLae2.pushQ.sql qateam@hgwbeta:/tmp/ ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/xenLae2.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly ######################################################################### # fix common name hgsql -e 'update dbDb set organism="Mouse lemur" where name="xenLae2";' \ hgcentraltest hgsql -e 'update dbDb set genome="Mouse lemur" where name="xenLae2";' \ hgcentraltest hgsql -e 'delete from genomeClade where genome="Gray mouse lemur";' \ hgcentraltest hgsql -e 'delete from defaultDb where genome="Gray mouse lemur";' \ hgcentraltest #########################################################################