82e20c618a9b836885c82fd2d9fdbe941d3955e9 hiram Tue Mar 2 11:02:47 2021 -0800 completed liftOvers to xenTro10 refs #24693 diff --git src/hg/makeDb/doc/xenTro9/initialBuild.txt src/hg/makeDb/doc/xenTro9/initialBuild.txt index 5e04b5f..59eae45 100644 --- src/hg/makeDb/doc/xenTro9/initialBuild.txt +++ src/hg/makeDb/doc/xenTro9/initialBuild.txt @@ -1,805 +1,823 @@ # for emacs: -*- mode: sh; -*- # This file describes browser build for the xenTro9 ######################################################################### # reuse photograph obtained for xenTro previous versions # (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9 cd /hive/data/genomes/xenTro9 cp -p ../xenTro7/photoReference.txt . cat photoReference.txt photoCreditURL http://www.unc.edu/ photoCreditName UNC Chapel Hill, Chris Showell, all rights reserved ######################################################################### # Initial steps (DONE - 2017-03-27 - Hiram) # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/xenTro9 cd ~/kent/src/hg/makeDb/doc/xenTro9 # best to use a most recent document since it has the latest features and # procedures: sed -e 's/micMur3/xenTro9/g; s/MicMur3/XenTro9/g; s/DONE/TBD/g;' \ ../micMur3/initialBuild.txt > initialBuild.txt mkdir /hive/data/genomes/xenTro9/refseq cd /hive/data/genomes/xenTro9/refseq rsync -L -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genomes/refseq/vertebrate_other/Xenopus_tropicalis/all_assembly_versions/GCF_000004195.3_Xenopus_tropicalis_v9.1/ ./ # sent 1555 bytes received 2014571885 bytes 16858355.15 bytes/sec # total size is 2014319744 speedup is 1.00 # real 1m58.966s # check assembly size for later reference: faSize G*v9.1_genomic.fna.gz # 1440398454 bases (70533089 N's 1369865365 real 840265201 upper 529600164 # lower) in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (NW_016690147.1) # max 194866763 (NC_030677.1) median 4812 # %36.77 masked total, %38.66 masked real # this information is from the top of # xenTro9/refseq/GCF_000004195.3_Xenopus_tropicalis_v9.1_assembly_report.txt # Assembly name: Xenopus_tropicalis_v9.1 # Organism name: Xenopus tropicalis (tropical clawed frog) # Infraspecific name: strain=Nigerian # Sex: female # Taxid: 8364 # BioSample: SAMN00000117 # BioProject: PRJNA205740 # Submitter: DOE Joint Genome Institute # Date: 2016-7-13 # Assembly type: haploid # Release type: major # Assembly level: Chromosome # Genome representation: full # WGS project: AAMC03 # Assembly method: Meraculous v. May-2013 # Genome coverage: 7.6x # Sequencing technology: Illumina HiSeq 2000 # RefSeq category: Representative Genome # GenBank assembly accession: GCA_000004195.3 # RefSeq assembly accession: GCF_000004195.3 # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000004205.3 GCF_000004205.3 Primary Assembly ## GCF_000005075.1 non-nuclear ############################################################################# # establish config.ra file (DONE - Hiram - 2017-03-27) # arguments here are: <db> <clade> <trackDbDir> <assembly_report.txt> cd /hive/data/genomes/xenTro9 $HOME/kent/src/hg/utils/automation/prepConfig.pl xenTro9 vertebrate \ xenTro ./refseq/*_assembly_report.txt > xenTro9.config.ra # fixup common name to remain compatible with previous xenTro versions: # and orderKey wasn't correct # verify it looks sane cat xenTro9.config.ra # config parameters for makeGenomeDb.pl: db xenTro9 clade vertebrate # genomeCladePriority 70 scientificName Xenopus tropicalis commonName X. tropicalis assemblyDate Jul. 2016 assemblyLabel DOE Joint Genome Institute assemblyShortLabel Xenopus_tropicalis_v9.1 orderKey 24036 # mitochondrial sequence included in refseq release # mitoAcc NC_006839.1 mitoAcc none fastaFiles /hive/data/genomes/xenTro9/ucsc/*.fa.gz agpFiles /hive/data/genomes/xenTro9/ucsc/*.agp # qualFiles none dbDbSpeciesDir xenTro photoCreditURL http://www.unc.edu/ photoCreditName UNC Chapel Hill, Chris Showell, all rights reserved ncbiGenomeId 80 ncbiAssemblyId 768701 ncbiAssemblyName Xenopus_tropicalis_v9.1 ncbiBioProject 205740 ncbiBioSample SAMN00000117 genBankAccessionID GCF_000004195.3 taxId 8364 ############################################################################# # setup UCSC named files (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/ucsc cd /hive/data/genomes/xenTro9/ucsc # check for duplicate sequences: time faToTwoBit -noMask ../refseq/G*v9.1_genomic.fna.gz refseq.2bit # real 0m44.569s twoBitDup refseq.2bit # no output is a good result, otherwise, would have to eliminate duplicates # the scripts creating the fasta here will be using this refseq.2bit file ~/kent/src/hg/utils/automation/ucscCompositeAgp.pl \ ../refseq/G*v9.1_genomic.fna.gz \ ../refseq/G*v9.1_assembly_structure/Primary_Assembly # NC_030677.1 chr1 # NC_030678.1 chr2 # NC_030679.1 chr3 # NC_030680.1 chr4 # NC_030681.1 chr5 # NC_030682.1 chr6 # NC_030683.1 chr7 # NC_030684.1 chr8 # NC_030685.1 chr9 # NC_030686.1 chr10 time ~/kent/src/hg/utils/automation/unplacedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # processed 6811 sequences into chrUn.fa.gz # real 2m25.232s # there are no unlocalized sequences # time ~/kent/src/hg/utils/automation/unlocalizedWithChroms.pl \ # ../refseq/*_assembly_structure/Primary_Assembly # bash syntax here mitoAcc=`grep "^# mitoAcc" ../xenTro9.config.ra | awk '{print $NF}'` printf "# mitoAcc %s\n" "$mitoAcc" # mitoAcc NC_006839.1 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 gzip chrM.fa # verify fasta and AGPs agree time faToTwoBit *.fa.gz test.2bit # real 1m13.235s time cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail -4 # All AGP and FASTA entries agree - both files are valid # real 0m9.944s # and no sequence lost from orginal: twoBitToFa test.2bit stdout | faSize stdin # 1440398454 bases (70533089 N's 1369865365 real 1369865365 upper 0 lower) # in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (chrUn_NW_016690147v1) # max 194866763 (chr1) median 4812 # same numbers as above # 1440398454 bases (70533089 N's 1369865365 real 840265201 upper 529600164 # lower) in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (NW_016690147.1) # max 194866763 (NC_030677.1) median 4812 # no longer need these temporary 2bit files rm refseq.2bit test.2bit ############################################################################# # Initial database build (DONE - 2017-03-27 - Hiram) cd /hive/data/genomes/xenTro9 # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp xenTro9.config.ra) > agp.log 2>&1 # real 2m43.431s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db xenTro9.config.ra) > db.log 2>&1 # real 20m35.233s # was missing some business in the script for trackDb: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=trackDb xenTro9.config.ra) > trackDb.log 2>&1 # check in the trackDb files created in TemporaryTrackDbCheckout/ # and add xenTro9 to trackDb/makefile # temporary symlink until masked sequence is available cd /hive/data/genomes/xenTro9 ln -s `pwd`/xenTro9.unmasked.2bit /gbdb/xenTro9/xenTro9.2bit ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/cpgIslandsUnmasked cd /hive/data/genomes/xenTro9/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/xenTro9/xenTro9.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku xenTro9) > do.log 2>&1 # real 41m47.778s cat fb.xenTro9.cpgIslandExtUnmasked.txt # 14956579 bases of 1369865365 (1.092%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/cytoBand cd /hive/data/genomes/xenTro9/bed/cytoBand makeCytoBandIdeo.csh xenTro9 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (DONE - 2017-03-27 - 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/xenTro9/bed/ucscToINSDC cd /hive/data/genomes/xenTro9/bed/ucscToINSDC # find accession for chrM grep chrM ../../xenTro9.agp # chrM 1 17610 1 O NC_006839.1 1 17610 + # find the genbank accession for NC_006839.1 at Entrez nucleotide # The NC_006839.1 name is the RefSeq name, the genbank name is: AY789013.1 # the assembly_report does not have this AY name since the chrM sequence # is not in the genbank assembly: grep NC_006839.1 ../../refseq/GCF*v9.1_assembly_report.txt # MT assembled-molecule MT Mitochondrion na <> NC_006839.1 non-nuclear 17610 chrM # 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_028718.1 # 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/AY789013.1/' \ | 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 printf "chrM\t0\t17610\tNC_006839.1\n" >> 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 printf "chrM\t0\t17610\tAY789013.1\n" >> ucscToINSDC.bed # verify chrM is correct: grep chrM *.bed # ucscToINSDC.bed:chrM AY789013.1 # ucscToRefSeq.bed:chrM NC_006839.1 # should be same line counts throughout: # in this case one is missing in the final result due to the duplicate # contig being removed wc -l * # 6822 refSeqToUcsc.txt # 6822 refseq.insdc.txt # 6822 ucsc.coordinate.tab # 6822 ucscToINSDC.bed # 6822 ucscToRefSeq.bed # 6822 ucscToRefSeq.txt export chrSize=`cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 20 # use the 25 in this sed sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab xenTro9 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 xenTro9 ucscToRefSeq ./ucscToRefSeq.sql ucscToRefSeq.bed # checkTableCoords should be silent checkTableCoords xenTro9 # each should cover %100 entirely: featureBits -countGaps xenTro9 ucscToINSDC # 1440398454 bases of 1440398454 (100.000%) in intersection featureBits -countGaps xenTro9 ucscToRefSeq # 1440398454 bases of 1440398454 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/chromAlias cd /hive/data/genomes/xenTro9/bed/chromAlias hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' xenTro9 \ > ucsc.refseq.tab hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' xenTro9 \ > ucsc.genbank.tab awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \ | sort > xenTro9.chromAlias.tab hgLoadSqlTab xenTro9 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ xenTro9.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-03-28 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/xenTro/xenTro9 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" xenTro9 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c # 61329 AAMC.1 # 1 NC_.1 # implies a rule: '[AN][AC][M_][C0-9]+(\.[0-9]+)?' # verify this rule will find them all and eliminate them all: hgsql -N -e "select frag from gold;" xenTro9 | wc -l # 61330 hgsql -N -e "select frag from gold;" xenTro9 \ | egrep -e '[AN][AC][M_][C0-9]+(\.[0-9]+)?' | wc -l # 61330 hgsql -N -e "select frag from gold;" xenTro9 \ | egrep -v -e '[AN][AC][M_][C0-9]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/chicken/xenTro9/trackDb.ra searchTable gold shortCircuit 1 termRegex [AN][AC][M_][C0-9]+(\.[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 - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/repeatMasker cd /hive/data/genomes/xenTro9/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku xenTro9) > do.log 2>&1 & # real 462m52.098s cat faSize.rmsk.txt # 1440398454 bases (70533089 N's 1369865365 real 899399454 upper # 470465911 lower) in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (chrUn_NW_016690147v1) # max 194866763 (chr1) median 4812 # %32.66 masked total, %34.34 masked real egrep -i "versi|relea" do.log # RepeatMasker version open-4.0.5 # January 31 2015 (open-4-0-5) version of RepeatMasker # CC RELEASE 20140131; * time featureBits -countGaps xenTro9 rmsk # 471365620 bases of 1440398454 (32.725%) in intersection # real 0m20.783s # 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;' xenTro9 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 471365620.000000 # real 0m16.203s ########################################################################## # running simple repeat (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/simpleRepeat cd /hive/data/genomes/xenTro9/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 xenTro9) > 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/xenTro9 # when using the Window Masker result: # twoBitMask bed/windowMasker/xenTro9.cleanWMSdust.2bit \ # -add bed/simpleRepeat/trfMask.bed xenTro9.2bit # you can safely ignore the warning about fields >= 13 # when using Rmsk results, add to rmsk after it is done: twoBitMask xenTro9.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed xenTro9.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa xenTro9.2bit stdout | faSize stdin > faSize.xenTro9.2bit.txt cat faSize.xenTro9.2bit.txt # 1440398454 bases (70533089 N's 1369865365 real 898405355 upper # 471460010 lower) in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (chrUn_NW_016690147v1) # max 194866763 (chr1) median 4812 # %32.73 masked total, %34.42 masked real # reset the symlink rm /gbdb/xenTro9/xenTro9.2bit ln -s `pwd`/xenTro9.2bit /gbdb/xenTro9/xenTro9.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2017-03-27 - Hiram) ssh hgwdev mkdir /cluster/data/xenTro9/bed/microsat cd /cluster/data/xenTro9/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 xenTro9 microsat microsat.bed # Read 13167 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2017-03-27 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/windowMasker cd /hive/data/genomes/xenTro9/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev xenTro9) > do.log 2>&1 # real 129m31.454s # Masking statistics cat faSize.xenTro9.cleanWMSdust.txt # 1440398454 bases (70533089 N's 1369865365 real 830396076 upper # 539469289 lower) in 6822 sequences in 1 files # Total size: mean 211140.2 sd 5118536.3 min 226 (chrUn_NW_016690147v1) # max 194866763 (chr1) median 4812 # %37.45 masked total, %39.38 masked real cat fb.xenTro9.rmsk.windowmaskerSdust.txt # 361644174 bases of 1440398454 (25.107%) in intersection ########################################################################## # run up idKeys files for ncbiRefSeq (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/idKeys cd /hive/data/genomes/xenTro9/bed/idKeys time (doIdKeys.pl -buildDir=`pwd` xenTro9) > do.log 2>&1 & # real 12m20.939s cat xenTro9.keySignature.txt # 8ae219619932349bebc17364408bf9d0 ########################################################################## # cpgIslands - (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/cpgIslands cd /hive/data/genomes/xenTro9/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku xenTro9) > do.log 2>&1 & # real 3m28.088s cat fb.xenTro9.cpgIslandExt.txt # 4735284 bases of 1369865365 (0.346%) in intersection ############################################################################## # genscan - (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/genscan cd /hive/data/genomes/xenTro9/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku xenTro9) > do.log 2>&1 & # real 105m32.304s cat fb.xenTro9.genscan.txt # 49227165 bases of 1369865365 (3.594%) in intersection cat fb.xenTro9.genscanSubopt.txt # 37665356 bases of 1369865365 (2.750%) in intersection ############################################################################# # augustus gene track (DONE - 2017-03-28 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/augustus cd /hive/data/genomes/xenTro9/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=chicken -dbHost=hgwdev -workhorse=hgwdev xenTro9) > do.log 2>&1 & # real 79m25.311s cat fb.xenTro9.augustusGene.txt # 38938672 bases of 1369865365 (2.843%) in intersection ############################################################################# # lastz/chain/net swap human/hg38 (DONE - 2017-03-30 - Hiram) # original alignment cd /hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29 cat fb.hg38.chainXenTro9Link.txt # 117720401 bases of 3049335806 (3.861%) in intersection # and for the swap: mkdir /hive/data/genomes/xenTro9/bed/blastz.hg38.swap cd /hive/data/genomes/xenTro9/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 61m0.707s cat fb.xenTro9.chainHg38Link.txt # 108900066 bases of 1369865365 (7.950%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 hg38) \ > rbest.log 2>&1 # real 749m24.229s ############################################################################# # lastz/chain/net swap mouse/mm10 (DONE - 2017-03-30 - Hiram) cd /hive/data/genomes/mm10/bed/lastzXenTro9.2017-03-29 cat fb.mm10.chainXenTro9Link.txt # 87053836 bases of 2652783500 (3.282%) in intersection # and for the swap mkdir /hive/data/genomes/xenTro9/bed/blastz.mm10.swap cd /hive/data/genomes/xenTro9/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzXenTro9.2017-03-29/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet -swap -chainMinScore=5000 -chainLinearGap=loose) \ > swap.log 2>&1 & # real 53m19.485s cat fb.xenTro9.chainMm10Link.txt # 90150612 bases of 1369865365 (6.581%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 mm10) \ > rbest.log 2>&1 & # real 597m52.740s ############################################################################# # Create kluster run files (DONE - 2017-03-28 - Hiram) # numerator is xenTro9 gapless bases "real" as reported by: featureBits -noRandom -noHap xenTro9 gap # 45444714 bases of 1227082306 (3.703%) 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 \( 1227082306 / 2861349177 \) \* 1024 # ( 1227082306 / 2861349177 ) * 1024 = 439.139792 # ==> use -repMatch=500 according to size scaled down from 1024 for human. # and rounded up to nearest 100 cd /hive/data/genomes/xenTro9 blat xenTro9.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/xenTro9.11.ooc \ -repMatch=500 # Wrote 31375 overused 11-mers to jkStuff/xenTro9.11.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;' xenTro9 \ | 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 xenTro9 jkStuff/nonBridged.lft \ # -bedFile=jkStuff/nonBridged.bed ######################################################################### # LIFTOVER TO xenTro7 (DONE - 2017-03-28 - Hiram) ssh hgwdev mkdir /hive/data/genomes/xenTro9/bed/blat.xenTro7.2017-03-27 cd /hive/data/genomes/xenTro9/bed/blat.xenTro7.2017-03-27 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -ooc=/hive/data/genomes/xenTro9/jkStuff/xenTro9.11.ooc \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ xenTro9 xenTro7) > do.log 2>&1 # real 407m17.792s # verify the convert link on the test browser is now active from xenTro9 to # xenTro7 ######################################################################### # LIFTOVER TO xenTro3 (DONE - 2017-03-28 - Hiram) ssh hgwdev mkdir /hive/data/genomes/xenTro9/bed/blat.xenTro3.2017-03-28 cd /hive/data/genomes/xenTro9/bed/blat.xenTro3.2017-03-28 time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ -ooc=/hive/data/genomes/xenTro9/jkStuff/xenTro9.11.ooc \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ xenTro9 xenTro3) > do.log 2>&1 # real 422m44.841s # verify the convert link on the test browser is now active from xenTro9 to # xenTro3 ######################################################################## # GENBANK AUTO UPDATE (DONE - 2017-03-28 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt # Xenopus tropicalis 18478 1271480 8612 # edit etc/genbank.conf to add xenTro9 just before macFas5 # xenTro9 'Xenopus tropicalis' 11 chroms + 6811 contigs xenTro9.serverGenome = /hive/data/genomes/xenTro9/xenTro9.2bit xenTro9.clusterGenome = /hive/data/genomes/xenTro9/xenTro9.2bit xenTro9.ooc = /hive/data/genomes/xenTro9/jkStuff/xenTro9.11.ooc xenTro9.lift = no xenTro9.perChromTables = no xenTro9.downloadDir = xenTro9 # xenTro9.mgc = yes xenTro9.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} xenTro9.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} xenTro9.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} xenTro9.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} xenTro9.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 # xenTro7.upstreamGeneTbl = ensGene # xenTro7.upstreamMaf = multiz9way /hive/data/genomes/xenTro7/bed/multiz9way/species.list git commit -m 'adding xenTro9 X, tropicalis refs #19151' etc/genbank.conf git push # update /cluster/data/genbank/: make etc-update cd /cluster/data/genbank time ./bin/gbAlignStep -initial xenTro9 # logFile: var/build/logs/2017.03.28-10:19:21.xenTro9.initalign.log # real 424m59.280s tail -2 var/build/logs/2017.03.28-10:19:21.xenTro9.initalign.log # hgwdev 2017.03.28-17:22:09 xenTro9.initalign: Succeeded: xenTro9 # hgwdev 2017.03.28-17:24:20 xenTro9.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.xenTro9 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad xenTro9 # logFile: var/dbload/hgwdev/logs/2017.03.28-18:08:41.xenTro9.dbload.log # real 30m42.283s tail -1 var/dbload/hgwdev/logs/2017.03.28-18:08:41.xenTro9.dbload.log # hgwdev 2017.03.28-18:39:24 xenTro9.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add xenTro9 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m 'adding xenTro9 to the update alignments refs #19151' etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################# # ncbiRefSeq (TBD - 2016-05-13 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/ncbiRefSeq cd /hive/data/genomes/xenTro9/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 xenTro9) > 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 xenTro9) > 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 xenTro9) > load.log 2>&1 # real 0m33.205s cat fb.ncbiRefSeq.xenTro9.txt # 82563006 bases of 1218501075 (6.776%) in intersection featureBits -enrichment xenTro9 refGene ncbiRefSeq # refGene 1.181%, ncbiRefSeq 6.776%, both 1.175%, cover 99.49%, # enrich 14.68x ######################################################################### # BLATSERVERS ENTRY (DONE - 2017-03-29 - 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 ("xenTro9", "blat1d", "17884", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("xenTro9", "blat1d", "17885", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to same as xenTro7 ## (DONE - 2017-03-29 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr9:15945953-15959305" where name="xenTro9";' 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=xenTro9 -tableCoverage all.joiner joinerCheck -database=xenTro9 -times all.joiner joinerCheck -database=xenTro9 -keys all.joiner cd /hive/data/genomes/xenTro9 time (makeDownloads.pl -workhorse=hgwdev xenTro9) > downloads.log 2>&1 # real 14m41.395s # now ready for pushQ entry mkdir /hive/data/genomes/xenTro9/pushQ cd /hive/data/genomes/xenTro9/pushQ time (makePushQSql.pl -redmineList xenTro9) > xenTro9.pushQ.sql 2> stderr.out # real 7m21.629s # check for errors in stderr.out, some are OK, e.g.: # WARNING: hgwdev does not have /gbdb/xenTro9/wib/gc5Base.wib # WARNING: hgwdev does not have /gbdb/xenTro9/wib/quality.wib # WARNING: hgwdev does not have /gbdb/xenTro9/bbi/quality.bw # WARNING: xenTro9 does not have seq # WARNING: xenTro9 does not have extFile # copy it to hgwbeta scp -p xenTro9.pushQ.sql qateam@hgwbeta:/tmp/ ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/xenTro9.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly ######################################################################### +# LIFTOVER TO xenTro10 (DONE - 2021-02-22 - Hiram) + ssh hgwdev + mkdir /hive/data/genomes/xenTro9/bed/blat.xenTro10.2021-02-22 + cd /hive/data/genomes/xenTro9/bed/blat.xenTro10.2021-02-22 + doSameSpeciesLiftOver.pl -debug -verbose=2 -buildDir=`pwd` \ + -ooc=/hive/data/genomes/xenTro9/jkStuff/xenTro9.11.ooc \ + -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + xenTro9 xenTro10 + time (doSameSpeciesLiftOver.pl -verbose=2 -buildDir=`pwd` \ + -ooc=/hive/data/genomes/xenTro9/jkStuff/xenTro9.11.ooc \ + -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ + xenTro9 xenTro10) > do.log 2>&1 & + # real 575m48.416s + + # verify the convert link on the test browser is now active from xenTro9 to + # xenTro10 + +#########################################################################