be590b26ca854e89606338fcfecb9c9ac85273b8 hiram Thu Sep 3 12:53:49 2020 -0700 ready for genbank run refs #24074 diff --git src/hg/makeDb/doc/calJac4/initialBuild.txt src/hg/makeDb/doc/calJac4/initialBuild.txt index b60e3e8..a5f59e7 100644 --- src/hg/makeDb/doc/calJac4/initialBuild.txt +++ src/hg/makeDb/doc/calJac4/initialBuild.txt @@ -1,1382 +1,1332 @@ # for emacs: -*- mode: sh; -*- # This file describes browser build for the calJac4 # GCF_009663435.1 # Can use existing photograph (otherwise find one before starting here) ######################################################################### # Initial steps, reuse existing photograph (DONE - 2020-09-01 - Hiram) # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/calJac4 cd ~/kent/src/hg/makeDb/doc/calJac4 sed -e 's/mm39/calJac4/g; s/Mm39/CalJac4/g; s/DONE/TBD/g;' \ ../mm39/initialBuild.txt > initialBuild.txt mkdir -p /hive/data/genomes/calJac4/refseq cd /hive/data/genomes/calJac4 # reuse existing photo from calJac3: cp -p ../calJac3/photoReference.txt . cat photoReference.txt photoCreditURL http://www.genome.gov/dmd/img.cfm?node=Photos/Animals/Marmoset%20(Callithrix%20jacchus)&id=79119 photoCreditName Photo courtesy of NHGRI press photos ## download from NCBI cd /hive/data/genomes/calJac4/refseq time rsync -L -a -P --stats \ rsync://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/663/435/GCF_009663435.1_Callithrix_jacchus_cj1700_1.1/ ./ # sent 3,522 bytes received 5,637,592,146 bytes 59,032,415.37 bytes/sec # total size is 5,636,202,618 speedup is 1.00 # real 1m34.674s # this information is from the top of # calJac4/refseq/*_assembly_report.txt # (aka: calJac4/refseq/GCF_009663435.1_Callithrix_jacchus_cj1700_1.1_assembly_report.txt # Assembly name: Callithrix_jacchus_cj1700_1.1 # Organism name: Callithrix jacchus (white-tufted-ear marmoset) # Infraspecific name: strain=cj1700 # Sex: female # Taxid: 9483 # BioProject: PRJNA566173 # Submitter: McDonnell Genome Institute at Washington University # Date: 2020-05-22 # Assembly type: haploid # Release type: major # Assembly level: Chromosome # Genome representation: full # WGS project: WJHW01 # Reference guided assembly: GCA_000004665.1 # Genome coverage: 40.0x # GenBank assembly accession: GCA_009663435.2 # RefSeq assembly accession: GCF_009663435.1 # RefSeq assembly and GenBank assemblies identical: no # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_009663445.2 GCF_009663445.1 Primary Assembly ## GCF_013177605.1 non-nuclear # check assembly size for later reference: faSize G*_1.1_genomic.fna.gz # 2897824427 bases (38007443 N's 2859816984 real 1774139275 upper # 1085677709 lower) in 964 sequences in 1 files # Total size: mean 3006041.9 sd 20298858.9 min 285 (NW_023264940.1) # max 217961735 (NC_048383.1) median 42174 # %37.47 masked total, %37.96 masked real # Survey types of gaps: zgrep -v "^#" *gaps.txt.gz | cut -f5 | sort | uniq -c | sed -e 's/^/# /;' # 15 between_scaffolds # 22 centromere # 1 unknown # 341 within_scaffold # And total size in gaps: zgrep -v "^#" *gaps.txt.gz | awk '{print $3-$2+1}' | ave stdin \ | sed -e 's/^/# /;' # Q1 100.000000 # median 24093.000000 # Q3 55774.500000 # average 100283.488127 # min 13.000000 # max 1000000.000000 # count 379 # total 38007442.000000 # standard deviation 236845.788902 # survey the sequence to see if it has IUPAC characters: time zgrep -v "^>" G*_1.1_genomic.fna.gz \ | perl -ne '{print join("\n",split(//))}' \ | sed -e '/^$/d' | sort | uniq -c | sort -rn | sed -e 's/^/# /;' # 511573847 T # 510890385 A # 376024857 G # 375650186 C # 334954379 t # 334153924 a # 208296872 g # 208272534 c # 38007443 N # real 31m20.194s ############################################################################# # establish config.ra file (DONE - 2020-09-01 - Hiram) cd /hive/data/genomes/calJac4 ~/kent/src/hg/utils/automation/prepConfig.pl calJac4 mammal marmoset \ refseq/*_assembly_report.txt > calJac4.config.ra # fix commonName: commonName White-tufted-ear marmoset to: commonName Marmoset # fix orderKey: orderKey 23305 to orderKey 13093 # fix bioSample: ncbiBioSample notFound to ncbiBioSample SAMN12783337 # see also: https://www.ncbi.nlm.nih.gov/biosample/?term=SAMN12783337 # compare with previous version to see if it is sane: diff calJac4.config.ra ../calJac3/calJac3.config.ra # verify it really does look sane cat calJac4.config.ra # config parameters for makeGenomeDb.pl: db calJac4 clade mammal genomeCladePriority 35 scientificName Callithrix jacchus commonName White-tufted-ear marmoset assemblyDate May 2020 assemblyLabel McDonnell Genome Institute at Washington University assemblyShortLabel Callithrix_jacchus_cj1700_1.1 orderKey 13083 # mitochondrial sequence included in refseq release # mitoAcc NC_025586.1 mitoAcc none fastaFiles /hive/data/genomes/calJac4/ucsc/*.fa.gz agpFiles /hive/data/genomes/calJac4/ucsc/*.agp # qualFiles none dbDbSpeciesDir marmoset photoCreditURL http://www.genome.gov/dmd/img.cfm?node=Photos/Animals/Marmoset%20(Callithrix%20jacchus)&id=79119 photoCreditName Photo courtesy of NHGRI press photos ncbiGenomeId 442 ncbiAssemblyId 7157801 ncbiAssemblyName Callithrix_jacchus_cj1700_1.1 ncbiBioProject 566173 ncbiBioSample SAMN12783337 genBankAccessionID GCF_009663435.1 taxId 9483 ############################################################################# # setup UCSC named files (DONE - 2020-09-01 - Hiram) mkdir /hive/data/genomes/calJac4/ucsc cd /hive/data/genomes/calJac4/ucsc # check for duplicate sequences: time faToTwoBit -noMask ../refseq/G*_1.1_genomic.fna.gz refseq.2bit # real 0m39.757s twoBitDup refseq.2bit # no output is a good result, otherwise, would have to eliminate duplicates # the scripts creating the fasta here will be creating a refseq.2bit file # to be removed later # compare gaps with what the gaps.gz file reported: twoBitInfo -nBed refseq.2bit refseq.gap.bed awk '{print $3-$2}' *.gap.bed | ave stdin | sed -e 's/^/# /;' # Q1 70.000000 # median 24007.000000 # Q3 55774.500000 # average 100019.586842 # min 1.000000 # max 1000000.000000 # count 380 # total 38007443.000000 # standard deviation 236589.057301 # comparing with above, there is 1 gap here more, appears to be size 1 # Check what the AGP says later on here. The gaps file defined: # count 379 # total 38007442.000000 time ~/kent/src/hg/utils/automation/ucscCompositeAgp.pl \ ../refseq/G*_1.1_genomic.fna.gz \ ../refseq/*_assembly_structure/Primary_Assembly NC_048383.1 chr1 NC_048384.1 chr2 NC_048385.1 chr3 NC_048386.1 chr4 NC_048387.1 chr5 NC_048388.1 chr6 NC_048389.1 chr7 NC_048390.1 chr8 NC_048391.1 chr9 NC_048392.1 chr10 NC_048393.1 chr11 NC_048394.1 chr12 NC_048395.1 chr13 NC_048396.1 chr14 NC_048397.1 chr15 NC_048398.1 chr16 NC_048399.1 chr17 NC_048400.1 chr18 NC_048401.1 chr19 NC_048402.1 chr20 NC_048403.1 chr21 NC_048404.1 chr22 NC_048405.1 chrX NC_048406.1 chrY real 10m48.905s time ~/kent/src/hg/utils/automation/unplacedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # processed 930 sequences into chrUn.fa.gz # real 0m13.261s time ~/kent/src/hg/utils/automation/unlocalizedWithChroms.pl \ ../refseq/*_assembly_structure/Primary_Assembly # 11 # 1 # 13 # 10 # 9 # 12 # 14 # processed 9 sequences into chr*_random.gz 7 files # real 0m0.552s # bash syntax here mitoAcc=`grep "^# mitoAcc" ../calJac4.config.ra | awk '{print $NF}'` printf "# mitoAcc %s\n" "$mitoAcc" # mitoAcc NC_025586.1 zcat \ ../refseq/*_assembly_structure/non-nuclear/assem*/AGP/chrMT.comp.agp.gz \ | grep -v "^#" | sed -e "s/^$mitoAcc/chrM/;" > chrM.agp cat chrM.agp # chrM 1 16499 1 O KM588314.1 1 16499 + printf ">chrM\n" > chrM.fa twoBitToFa -noMask refseq.2bit:$mitoAcc stdout | grep -v "^>" >> chrM.fa gzip chrM.fa faSize chrM.fa.gz # 16499 bases (0 N's 16499 real 16499 upper 0 lower) in 1 sequences in 1 files # verify fasta and AGPs agree time faToTwoBit *.fa.gz test.2bit # real 0m47.608s cat *.agp | checkAgpAndFa stdin test.2bit 2>&1 | tail -4 # All AGP and FASTA entries agree - both files are valid # and no sequence lost from orginal: twoBitToFa test.2bit stdout | faSize stdin # 2897824427 bases (38007443 N's 2859816984 real 2859816984 upper 0 lower) # in 964 sequences in 1 files # Total size: mean 3006041.9 sd 20298858.9 min 285 (chrUn_NW_023264940v1) # max 217961735 (chr1) median 42174 # same numbers as above (except for upper/lower masking) # 2897824427 bases (38007443 N's 2859816984 real 1774139275 upper # 1085677709 lower) in 964 sequences in 1 files # See if the AGP files define all the gaps: # categories of gaps: awk '$5 == "N"' *.agp | cut -f7 | sort | uniq -c | sed -e 's/^/# /;' # 22 centromere # 15 contig # 341 scaffold # the gaps file defined: # 15 between_scaffolds # 22 centromere # 1 unknown # 341 within_scaffold awk '$5 == "N"' *.agp | awk '{print $3-$2+1}' | ave stdin \ | sed -e 's/^/# /;' # Q1 100.000000 # median 24230.500000 # Q3 55834.000000 # average 100548.682540 # min 13.000000 # max 1000000.000000 # count 378 # total 38007402.000000 # standard deviation 237103.349286 # the 2bit sequence has 2 more gaps and 41 more bases in gap: # count 380 # total 38007443.000000 # the gaps file defined 1 more gap at 40 bases: # count 379 # total 38007442.000000 XXX - TBD - Wed Sep 2 07:44:09 PDT 2020 # survey gap types from gap file # the gaps file defines 23 more gaps than the AGP files, # the gaps file defines 13 more gaps but 54 less bases than the sequence # note the 'unknown' types (== 23 gaps) zgrep -v "^#" ../refseq/*gaps* | cut -f5,6 | sort | uniq -c \ | sed -e 's/^/# /;' # 15 between_scaffolds na # 22 centromere na # 1 unknown inferred_from_sequence # 341 within_scaffold map # the single 'unknown' gap is the 40 base gap that is not in the AGP files zgrep "unknown" ../refseq/*gaps* # NC_048406.1 8006927 8006966 40 unknown inferred_from_sequence # survey of AGP types of gaps: # beware, can also be type U in col 5, doesn't happen here: awk '$5 == "U"' *.agp (no output) awk '$5 == "N"' *.agp | awk '{print $7,$NF}' | sort | uniq -c \ | sed -e 's/^/# /;' # 22 centromere na # 15 contig na # 341 scaffold map # name equivalences in the assembly_report file: grep -v "^#" \ ../refseq/G*_1.1_assembly_report.txt \ | awk '{printf "%s\t%s\n", $1,$5}' | sort > ncbi.assembly.genbank.equivalence grep -v "^#" \ ../refseq/G*_1.1_assembly_report.txt \ | awk '{printf "%s\t%s\n", $1,$7}' | sort > ncbi.assembly.refseq.equivalence join -t$'\t' ncbi.assembly.genbank.equivalence \ ncbi.assembly.refseq.equivalence > ncbi.genbank.refseq.names (the MT sequence has 'na' for genbank name) # no longer need these temporary 2bit files rm test.2bit refseq.2bit refseq.gap.bed ############################################################################# # Initial database build (DONE - 2020-09-02 - Hiram) # verify sequence and AGP are OK: cd /hive/data/genomes/calJac4 time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp calJac4.config.ra) > agp.log 2>&1 # real 2m16.607s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db calJac4.config.ra) > db.log 2>&1 # real 15m10.248s # check in the trackDb files created in TemporaryTrackDbCheckout/ - # and add calJac4 to trackDb/makefile refs #22271 + # and add calJac4 to trackDb/makefile refs #24074 # fixing up the images reference to calJac4.jpg # temporary symlink until masked sequence is available cd /hive/data/genomes/calJac4 ln -s `pwd`/calJac4.unmasked.2bit /gbdb/calJac4/calJac4.2bit ############################################################################# # verify gap table vs NCBI gap file (TBD - 2020-07-27 - Hiram) mkdir /hive/data/genomes/calJac4/bed/gap cd /hive/data/genomes/calJac4/bed/gap zgrep -v "^#" ../../refseq/G*_gaps.txt.gz \ | awk '{printf "%s\t%d\t%d\t%s_%s\n", $1,$2-1,$3,$5,$6}' \ | sort -k1,1 -k2,2n > refseq.gap.bed # type survey: cut -f4 *.bed | sort | uniq -c | sed -e 's/^/# /;' # 60 between_scaffolds_na # 20 centromere_na # 21 short_arm_na # 42 telomere_na # 4 unknown_inferred_from_sequence # 19 unknown_unspecified # 5 within_scaffold_align_genus # 36 within_scaffold_map # 96 within_scaffold_paired-ends # 44 within_scaffold_unspecified # how much defined by NCBI: awk '{print $3-$2}' *.bed | ave stdin | grep -w total # total 73600614.000000 # how much in the gap table: hgsql -e 'select * from gap;' calJac4 | awk '{print $4-$3}' \ | ave stdin | grep -w total # total 73598294.000000 # an extra 2320 bases marked in the gap file # Compare to mm10: hgsql -e 'select * from gap;' mm10 | awk '{print $4-$3}' \ | ave stdin | sed -e 's/^/# /;' # Q1 100.000000 # median 838.000000 # Q3 50000.000000 # average 113665.609898 # min 0.000000 # max 2890000.000000 # count 687 # total 78088274.000000 # standard deviation 485103.795880 hgsql -e 'select * from gap;' calJac4 | awk '{print $4-$3}' \ | ave stdin | sed -e 's/^/# /;' # Q1 1357.000000 # median 50000.000000 # Q3 100000.000000 # average 226456.289231 # min 0.000000 # max 2890000.000000 # count 325 # total 73598294.000000 # standard deviation 687212.981441 ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/cpgIslandsUnmasked cd /hive/data/genomes/calJac4/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/calJac4/calJac4.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku calJac4) > do.log 2>&1 XXX - running - Wed Sep 2 10:08:50 PDT 2020 # real 3m30.591s cat fb.calJac4.cpgIslandExtUnmasked.txt # 56535294 bases of 2481941580 (2.278%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/cytoBand cd /hive/data/genomes/calJac4/bed/cytoBand makeCytoBandIdeo.csh calJac4 ############################################################################# -# run up idKeys files for chromAlias/ncbiRefSeq (TBD - 2020-07-27 - Hiram) +# run up idKeys files for chromAlias/ncbiRefSeq (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/idKeys cd /hive/data/genomes/calJac4/bed/idKeys time (doIdKeys.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit \ -buildDir=`pwd` calJac4) > do.log 2>&1 & -XXX - running - Wed Sep 2 10:09:29 PDT 2020 - # real 0m45.175s + # real 1m55.340s cat calJac4.keySignature.txt - # 804f78d880a5a7f049c472046b563601 + # 01e329dd4e2641908a563b4ff1c8b648 ############################################################################# # gapOverlap (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/gapOverlap cd /hive/data/genomes/calJac4/bed/gapOverlap time (doGapOverlap.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4 ) \ > do.log 2>&1 & -XXX - running - Wed Sep 2 10:10:14 PDT 2020 - # real 1m49.446s + # XXX empty result ?? did it run in 54 seconds ? + # real 0m54.302s # there is one only: wc -l bed.tab # 1 bed.tab cut -f2- bed.tab chr6 47663669 47714277 chr6:47663670-47714277 304 + 47663669 47714277 0 2 304,304 0,50304 cat fb.calJac4.gapOverlap.txt # 608 bases of 2728222451 (0.000%) in intersection ############################################################################# # tandemDups (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/tandemDups cd /hive/data/genomes/calJac4/bed/tandemDups time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4) \ > do.log 2>&1 & -XXX - running - Wed Sep 2 10:10:14 PDT 2020 - # real 440m10.886s - - # one job in pairedEnds needs more memory: - time ./runOne 29 20000 chrY tmp/chrY.bed.gz - # real 28m57.353s - - # continuing - time (~/kent/src/hg/utils/automation/doTandemDup.pl \ - -continue=collapsePairedEnds \ - -twoBit=/hive/data/genomes/calJac4/calJac4.unmasked.2bit calJac4) \ - > collapsePairedEnds.log 2>&1 & - # real 3m23.138s + # real 193m21.761s cat fb.calJac4.tandemDups.txt - # 66584052 bases of 2728222451 (2.441%) in intersection + # 80358205 bases of 2897824427 (2.773%) in intersection bigBedInfo calJac4.tandemDups.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 13 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 -# itemCount: 858,983 -# primaryDataSize: 22,513,298 -# primaryIndexSize: 62,976 +# itemCount: 1,402,773 +# primaryDataSize: 36,657,311 +# primaryIndexSize: 119,132 # zoomLevels: 9 -# chromCount: 57 -# basesCovered: 1,408,031,925 -# meanDepth (of bases covered): 5.083425 +# chromCount: 894 +# basesCovered: 1,457,658,879 +# meanDepth (of bases covered): 8.428920 # minDepth: 1.000000 -# maxDepth: 240.000000 -# std of depth: 8.811752 +# maxDepth: 344.000000 +# std of depth: 18.274027 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (DONE - 2020-09-01 - Hiram) # construct idKeys for the genbank sequence mkdir /hive/data/genomes/calJac4/refseq/idKeys cd /hive/data/genomes/calJac4/refseq/idKeys faToTwoBit ../G*_1.1_genomic.fna.gz calJac4.refseq.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/calJac4.refseq.2bit refseqCalJac4) > do.log 2>&1 & + # real 6m36.946s sed -e 's/^/ # /;' refseqCalJac4.keySignature.txt # 01e329dd4e2641908a563b4ff1c8b648 mkdir /hive/data/genomes/calJac4/genbank cd /hive/data/genomes/calJac4/genbank faToTwoBit \ /hive/data/outside/ncbi/genomes/GCA/009/663/435/GCA_009663435.2_Callithrix_jacchus_cj1700_1.1/GCA_009663435.2_Callithrix_jacchus_cj1700_1.1_genomic.fna.gz \ calJac4.genbank.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/calJac4.genbank.2bit genbankCalJac4) > do.log 2>&1 & -XXX - running - Wed Sep 2 09:23:10 PDT 2020 - # real 0m45.317s + # real 2m56.082s sed -e 's/^/ # /;' genbankCalJac4.keySignature.txt - # 804f78d880a5a7f049c472046b563601 + # b89236d2c39771ea1089bd6bfa04ba4f mkdir /hive/data/genomes/calJac4/bed/chromAlias cd /hive/data/genomes/calJac4/bed/chromAlias join -t$'\t' ../idKeys/calJac4.idKeys.txt \ - ../../genbank/idKeys/genbankCalJac4.idKeys.txt | cut -f2- \ + ../../genbank/genbankCalJac4.idKeys.txt | cut -f2- \ | sort -k1,1 | join -t$'\t' <(sort -k1,1 ../../chrom.sizes) - \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ | sort -k1,1 -k2,2n > ucscToINSDC.bed + join -t$'\t' ../idKeys/calJac4.idKeys.txt \ + ../../refseq/idKeys/refseqCalJac4.idKeys.txt | cut -f2- \ + | sort -k1,1 | join -t$'\t' <(sort -k1,1 ../../chrom.sizes) - \ + | awk '{printf "%s\t0\t%d\t%s\n", $1, $2, $3}' \ + | sort -k1,1 -k2,2n > ucscToRefSeq.bed + # the genbank list is missing chrM, look it up in Entrez nucleotide, then: + grep chrM ucscToRefSeq.bed | sed -e 's/NC_025586.1/KM588314.1/;' \ + >> ucscToINSDC.bed + # and re-sort + cat ucscToINSDC.bed | sort -k1,1 -k2,2n > t + mv t ucscToINSDC.bed # should be same line counts throughout: wc -l * ../../chrom.sizes - # 61 ucscToINSDC.bed - # 61 ../../chrom.sizes + # 964 ucscToINSDC.bed + # 964 ucscToRefSeq.bed + # 964 ../../chrom.sizes export chrSize=`cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize - # 22 + # 27 # use the $chrSize in this sed sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab calJac4 ucscToINSDC stdin ucscToINSDC.bed + export chrSize=`cut -f1 ucscToRefSeq.bed | awk '{print length($0)}' | sort -n | tail -1` + echo $chrSize + sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ + | sed -e 's/INSDC/RefSeq/g;' \ + | hgLoadSqlTab calJac4 ucscToRefSeq stdin ucscToRefSeq.bed + # should be quiet for all OK - checkTableCoords calJac4 + checkTableCoords calJac4 ucscToINSDC + checkTableCoords calJac4 ucscToRefSeq # should cover %100 entirely: featureBits -countGaps calJac4 ucscToINSDC - # 2728222451 bases of 2728222451 (100.000%) in intersection + # 2897824427 bases of 2897824427 (100.000%) in intersection + + featureBits -countGaps calJac4 ucscToRefSeq + # 2897824427 bases of 2897824427 (100.000%) in intersection ######################################################################### -# add chromAlias table (TBD - 2020-07-27 - Hiram) +# add chromAlias table (DONE - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/chromAlias cd /hive/data/genomes/calJac4/bed/chromAlias grep -v "^#" ../../refseq/G*_1.1_assembly_report.txt \ - | awk '{printf "%s\t%s\n", $5,$1}' | sort > ncbi.assembly.txt + | awk '{printf "%s\t%s\n", $5,$1}' | sort > ncbi.genbank.txt + grep -v "^#" ../../refseq/G*_1.1_assembly_report.txt \ + | awk '{printf "%s\t%s\n", $7,$1}' | sort > ncbi.refseq.txt hgsql -N -e 'select chrom,name from ucscToINSDC;' calJac4 \ | sort -k1,1 > ucsc.genbank.tab + hgsql -N -e 'select chrom,name from ucscToRefSeq;' calJac4 \ + | sort -k1,1 > ucsc.refseq.tab - join -t$'\t' -1 2 <(sort -k2,2 ucsc.genbank.tab) ncbi.assembly.txt + # the awk removes lines where the UCSC name is identical to the NCBI name + join -t$'\t' -1 2 <(sort -k2,2 ucsc.refseq.tab) ncbi.refseq.txt \ + | cut -f2-3 | awk '$1 != $2' | sort > ucsc.assembly.tab - # lookup the chrM sequence in the assembly to determine the RefSeq ID: printf "chrM\tNC_005089.1\n" > ucsc.refseq.tab - wc -l *.tab - # 61 ucsc.assembly.tab - # 61 ucsc.genbank.tab - # 1 ucsc.refseq.tab + # genbank and refseq should be the same, assembly can be less + wc -l *.tab ../../chrom.sizes + # 940 ucsc.assembly.tab + # 964 ucsc.genbank.tab + # 964 ucsc.refseq.tab + # 964 ../../chrom.sizes ~/kent/src/hg/utils/automation/chromAlias.pl ucsc.*.tab \ > calJac4.chromAlias.tab # working: assembly # working: genbank +# working: refseq -for t in assembly genbank +for t in assembly genbank refseq do c0=`cat ucsc.$t.tab | wc -l` c1=`grep $t calJac4.chromAlias.tab | wc -l` ok="OK" if [ "$c0" -ne "$c1" ]; then ok="ERROR" fi printf "# checking $t: $c0 =? $c1 $ok\n" done -# checking assembly: 61 =? 61 OK -# checking genbank: 61 =? 61 OK +# checking assembly: 940 =? 940 OK +# checking genbank: 964 =? 964 OK +# checking refseq: 964 =? 964 OK # verify chrM is here properly: grep chrM calJac4.chromAlias.tab -# AY172335.1 chrM genbank +# KM588314.1 chrM genbank # MT chrM assembly -# NC_005089.1 chrM refseq +# NC_025586.1 chrM refseq hgLoadSqlTab calJac4 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ calJac4.chromAlias.tab ######################################################################### -# fixup search rule for assembly track/gold table (TBD - 2020-07-27 - Hiram) - cd ~/kent/src/hg/makeDb/trackDb/mouse/calJac4 +# fixup search rule for assembly track/gold table (DONE - 2020-09-03 - Hiram) + cd ~/kent/src/hg/makeDb/trackDb/marmoset/calJac4 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" calJac4 \ | sed -e 's/[0-9.]\+//;' | sort | uniq -c | sed -e 's/^/# /;' -# 15228 AC -# 816 AEKQ -# 8 AEKR -# 1 AF -# 3876 AL -# 1 AY -# 844 BX -# 191 CAAA -# 135 CR -# 684 CT -# 63 CU -# 37 FO -# 3 FP -# 29 FQ -# 14 LO -# 249 LXEJ -# 30 MF -# 44 MG -# 18 MH -# 2 MN - - # implies a rule: '[ABCFLM][ACEFGHLNOPQRTUXY][AEKJQR0-9]+(\.[0-9_]+)?' +# 68 AC +# 1 KM +# 1360 WJHW + + # implies a rule: '[AKW][CMJ][HW0-9]+(\.[0-9_]+)?' # verify this rule will find them all and eliminate them all: hgsql -N -e "select frag from gold;" calJac4 | wc -l - # 22273 + # 1429 hgsql -N -e "select frag from gold;" calJac4 \ - | egrep -e '[ABCFLM][ACEFGHLNOPQRTUXY][AEKJQR0-9]+(\.[0-9_]+)?' | wc -l - # 1795 + | egrep -e '[AKW][CMJ][HW0-9]+(\.[0-9_]+)?' | wc -l + # 1429 hgsql -N -e "select frag from gold;" calJac4 \ - | egrep -v -e '[ABCFLM][ACEFGHLNOPQRTUXY][AEKJQR0-9]+(\.[0-9_]+)?' | wc -l + | egrep -v -e '[AKW][CMJ][HW0-9]+(\.[0-9_]+)?' | wc -l # 0 # hence, add to trackDb/rhesus/calJac4/trackDb.ra searchTable gold shortCircuit 1 -termRegex [ABCFLM][ACEFGHLNOPQRTUXY][AEKJQR0-9]+(\.[0-9_]+)? +termRegex [AKW][CMJ][HW0-9]+(\.[0-9_]+)? query select chrom,chromStart,chromEnd,frag from %s where frag like '%s%%' searchPriority 8 # verify searches work in the position box - git commit -m 'adding search rule for gold/assembly track refs #22271' \ + git commit -m 'adding search rule for gold/assembly track refs #24074' \ trackDb.ra ########################################################################## # running repeat masker (DONE - 2020-09-02 - Hiram) # using new repeat masker version 4.1.0 mkdir /hive/data/genomes/calJac4/bed/repeatMasker cd /hive/data/genomes/calJac4/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=hgwdev calJac4) > do.log 2>&1 -XXX - running - Wed Sep 2 10:11:32 PDT 2020 # real 402m37.300s cat faSize.rmsk.txt # 2897824427 bases (38007443 N's 2859816984 real 1455718019 upper # 1404098965 lower) in 964 sequences in 1 files # Total size: mean 3006041.9 sd 20298858.9 min 285 (chrUn_NW_023264940v1) # max 217961735 (chr1) median 42174 # %48.45 masked total, %49.10 masked real egrep -i "versi|relea" do.log # RepeatMasker,v 1.332 2017/04/17 19:01:11 rhubley Exp $ # CC Dfam_Consensus RELEASE 20181026; * # CC RepBase RELEASE 20181026; sed -e 's/^/# /;' versionInfo.txt # The repeat files provided for this assembly were generated using RepeatMasker. # Smit, AFA, Hubley, R & Green, P., # RepeatMasker Open-4.0. # 1996-2010 <http://www.repeatmasker.org>. # # VERSION: # RepeatMasker version development-$Id: RepeatMasker,v 1.332 2017/04/17 19:01:11 rhubley Exp $ # Search Engine: Crossmatch [ 1.090518 ] # Master RepeatMasker Database: /hive/data/staging/data/RepeatMasker181121/Libraries/RepeatMaskerLib.embl ( Complete Database: dc20181026-rb20181026 ) # # # RepeatMasker version development-$Id: RepeatMasker,v 1.332 2017/04/17 19:01:11 rhubley Exp $ # CC Dfam_Consensus RELEASE 20181026; * # CC RepBase RELEASE 20181026; * # # RepeatMasker engine: -engine crossmatch -s # # RepeatMasker library options: -species 'Callithrix jacchus' # # PARAMETERS: # /hive/data/staging/data/RepeatMasker/RepeatMasker -engine crossmatch -s -align -species 'Callithrix jacchus' time featureBits -countGaps calJac4 rmsk # 1404097506 bases of 2897824427 (48.454%) in intersection # real 0m23.891s # 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;' calJac4 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 1404097506.000000 # real 0m21.422s ########################################################################## # running simple repeat (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/simpleRepeat cd /hive/data/genomes/calJac4/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=6 calJac4) > do.log 2>&1 # real 128m26.410s cat fb.simpleRepeat # 106897704 bases of 2859817025 (3.738%) in intersection -XXX - when WM finished - Wed Sep 2 17:30:02 PDT 2020 - cd /hive/data/genomes/calJac4 # if using the Window Masker result: cd /hive/data/genomes/calJac4 # twoBitMask bed/windowMasker/calJac4.cleanWMSdust.2bit \ # -add bed/simpleRepeat/trfMask.bed calJac4.2bit # you can safely ignore the warning about fields >= 13 # add to rmsk after it is done: twoBitMask calJac4.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed calJac4.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa calJac4.2bit stdout | faSize stdin > faSize.calJac4.2bit.txt cat faSize.calJac4.2bit.txt -# 2728222451 bases (73600668 N's 2654621783 real 1460027726 upper -# 1194594057 lower) in 61 sequences in 1 files -# Total size: mean 44724958.2 sd 64970951.3 min 1976 (chr4_JH584295v1_random) -# max 195154279 (chr1) median 182347 -# %43.79 masked total, %45.00 masked real +# 2897824427 bases (38007443 N's 2859816984 real 1454005411 upper +# 1405811573 lower) in 964 sequences in 1 files +# Total size: mean 3006041.9 sd 20298858.9 min 285 (chrUn_NW_023264940v1) +# max 217961735 (chr1) median 42174 +# %48.51 masked total, %49.16 masked real rm /gbdb/calJac4/calJac4.2bit ln -s `pwd`/calJac4.2bit /gbdb/calJac4/calJac4.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2020-09-02 - Hiram) ssh hgwdev mkdir /hive/data/genomes/calJac4/bed/microsat cd /hive/data/genomes/calJac4/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 calJac4 microsat microsat.bed # Read 41788 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2020-09-02 - Hiram) mkdir /hive/data/genomes/calJac4/bed/windowMasker cd /hive/data/genomes/calJac4/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev calJac4) > do.log 2>&1 -XXX - running - Wed Sep 2 17:31:19 PDT 2020 - # real 90m16.169s + # real 119m59.049s # Masking statistics cat faSize.calJac4.cleanWMSdust.txt -# 2482000080 bases (58500 N's 2481941580 real 1630728232 upper 851213348 lower) -# in 2198 sequences in 1 files -# Total size: mean 1129208.4 sd 8542765.0 min 13084 (chrUn_JAAHUQ010000994v1) -# max 124992030 (chrX) median 43246 -# %34.30 masked total, %34.30 masked real - - # completed before rmsk was done, to finish: - featureBits -countGaps calJac4 rmsk windowmaskerSdust 2> fb.calJac4.rmsk.windowmaskerSdust.txt - cat fb.calJac4.rmsk.windowmaskerSdust.txt - # 753903955 bases of 2728222451 (27.634%) in intersection - - time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ - -continue=cleanup -dbHost=hgwdev calJac4) > cleanup.log 2>&1 - # real 1m7.841s +# 2897824427 bases (38007443 N's 2859816984 real 1756905691 upper 1102911293 lower) in 964 sequences in 1 files +# Total size: mean 3006041.9 sd 20298858.9 min 285 (chrUn_NW_023264940v1) max 217961735 (chr1) median 42174 +# %38.06 masked total, %38.57 masked real ########################################################################## -# cpgIslands - (TBD - 2020-07-30 - Hiram) +# cpgIslands - (DONE - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/cpgIslands cd /hive/data/genomes/calJac4/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku calJac4) > do.log 2>&1 # real 3m28.053s cat fb.calJac4.cpgIslandExt.txt # 10571422 bases of 2654624157 (0.398%) in intersection ############################################################################## -# genscan - (TBD - 2020-07-30 - Hiram) +# genscan - (DONE - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/genscan cd /hive/data/genomes/calJac4/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku calJac4) > do.log 2>&1 +XXX - running - Thu Sep 3 11:46:01 PDT 2020 # real 8m19.775s # one job broken: ./runGsBig2M.csh chr10 000 gtf/000/chr10.gtf pep/000/chr10.pep subopt/000/chr10.bed # real 34m35.712s # continuing time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -continue=makeBed -bigClusterHub=ku calJac4) > makeBed.log 2>&1 # real 0m45.365s cat fb.calJac4.genscan.txt # 55445747 bases of 2654624157 (2.089%) in intersection cat fb.calJac4.genscanSubopt.txt # 57607700 bases of 2654624157 (2.170%) in intersection ######################################################################### -# ncbiGene (WORKING - 2020-07-30 - Hiram) +# ncbiGene (TBD - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/xenoRefGene cd /hive/data/genomes/calJac4/bed/xenoRefGene time (~/kent/src/hg/utils/automation/doXenoRefGene.pl -buildDir=`pwd` \ -bigClusterHub=ku -workhorse=hgwdev -dbHost=hgwdev calJac4) > do.log 2>&1 & # real 67m18.015s ######################################################################### -# Create kluster run files (TBD - 2020-07-30 - Hiram) +# Create kluster run files (DONE - 2020-09-03 - Hiram) # numerator is calJac4 gapless bases "real" as reported by: featureBits -noRandom -noHap calJac4 gap - # 73490654 bases of 2649940489 (2.773%) in intersection + # 36757259 bases of 2793460667 (1.316%) 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 \( 2649940489 / 2861349177 \) \* 1024 - # ( 2649940489 / 2861349177 ) * 1024 = 948.342510 + calc \( 2793460667 / 2861349177 \) \* 1024 + # ( 2793460667 / 2861349177 ) * 1024 = 999.704526 - # ==> use -repMatch=900 according to size scaled down from 1024 for human. - # and rounded down to nearest 50 + # ==> use -repMatch=1000 according to size scaled down from 1024 for human. cd /hive/data/genomes/calJac4 time blat calJac4.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/calJac4.11.ooc \ - -repMatch=900 - # Wrote 31807 overused 11-mers to jkStuff/calJac4.11.ooc - # real 0m23.024s - - # mm10 at repMatch=1000: - # Wrote 27208 overused 11-mers to jkStuff/mm10.11.ooc - # real 2m9.568s + -repMatch=1000 + # Wrote 34987 overused 11-mers to jkStuff/calJac4.11.ooc + # real 0m29.438s + # calJac3 at repMatch=950 + # Wrote 32908 overused 11-mers to jkStuff/calJac3.11.ooc + + # survey sizes of all gaps: + hgsql -N -e 'select size from gap;' calJac4 | ave stdin | sed -e 's/^/# /;' +# Q1 100.000000 +# median 24230.500000 +# Q3 55834.000000 +# average 100548.682540 +# min 13.000000 +# max 1000000.000000 +# count 378 +# total 38007402.000000 +# standard deviation 237103.349286 + hgsql -N -e 'select size from gap;' calJac4 | sort -n | uniq -c | sed -e 's/^/# /;' # survey sizes of non-bridged gaps: hgsql -N -e 'select size from gap where bridge="no" order by size;' \ calJac4 | sort | uniq -c | sort -k2,2n | sed -e 's/^/# /;' -# 1 8000 -# 21 10000 -# 2 30000 -# 43 50000 -# 3 60000 -# 1 61000 -# 2 63000 -# 1 66000 -# 1 71000 -# 1 81000 -# 42 100000 -# 1 140000 -# 1 174000 -# 1 300000 -# 1 350000 -# 1 500000 -# 20 2890000 - - # and survey the bridged gaps over 5,000 bases: - hgsql -N -e 'select size from gap where bridge="yes" and size > 4999;' \ - calJac4 | sort | uniq -c | sort -k2,2n | sed -e 's/^/# /;' -# 2 5000 -# 1 7000 -# 1 15000 -# 1 15500 -# 1 16000 -# 1 18000 -# 1 18500 -# 1 19208 -# 1 20000 -# 1 25500 -# 1 30000 -# 1 49000 -# 44 50000 -# 1 79000 -# 2 100000 -# 1 135500 -# 1 145000 -# 1 166000 -# 1 200000 -# 1 222000 -# 1 225000 -# 1 285000 -# 1 295000 -# 3 300000 -# 1 360000 -# 1 425000 -# 1 430000 -# 1 522000 - - # use gap size of 5000 to construct a lift file: - gapToLift -allowBridged -verbose=2 -minGap=5000 calJac4 \ - jkStuff/calJac4.5Kgaps.lft -bedFile=jkStuff/calJac4.5Kgaps.bed - wc -l jkStuff/calJac4.5Kgaps* - # 176 jkStuff/calJac4.5Kgaps.bed - # 176 jkStuff/calJac4.5Kgaps.lft - - # to see the gaps used: - bedInvert.pl chrom.sizes jkStuff/calJac4.5Kgaps.bed \ +# 7 100 +# 8 50000 +# 22 1000000 + + # and survey the number bridged gaps over 50,000 bases: + hgsql -N -e 'select size from gap where bridge="yes" and size > 49999;' \ + calJac4 | wc -l + # 86 + + # forget the non-bridged of size 100, use 50,000 and allow bridged + + # use gap size of 50000 to construct a lift file: + gapToLift -allowBridged -verbose=2 -minGap=50000 calJac4 \ + jkStuff/calJac4.gaps.lft -bedFile=jkStuff/calJac4.gaps.bed + wc -l jkStuff/calJac4.gaps*. + # 1073 jkStuff/calJac4.gaps.bed + # 1073 jkStuff/calJac4.gaps.lft + + # to see the gaps sizes used: + bedInvert.pl chrom.sizes jkStuff/calJac4.gaps.bed \ | cut -f4 | sort -n | uniq -c | less ######################################################################## # lastz/chain/net swap human/hg38 (TBD - 2020-04-10 - Hiram) # original alignment cd /hive/data/genomes/hg38/bed/lastzCalJac4.2020-04-02 cat fb.hg38.chainCalJac4Link.txt # 1549397508 bases of 3110768607 (49.808%) in intersection cat fb.hg38.chainSynCalJac4Link.txt # 1488468205 bases of 3110768607 (47.849%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 calJac4) > rbest.log 2>&1 & # real 310m32.196s cat fb.hg38.chainRBest.CalJac4.txt # 1425406620 bases of 3110768607 (45.822%) in intersection # and for the swap: mkdir /hive/data/genomes/calJac4/bed/blastz.hg38.swap cd /hive/data/genomes/calJac4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCalJac4.2020-04-02/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 99m10.990s cat fb.calJac4.chainHg38Link.txt # 1493209286 bases of 2481941580 (60.163%) in intersection cat fb.calJac4.chainSynHg38Link.txt # 1448164376 bases of 2481941580 (58.348%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ calJac4 hg38) > rbest.log 2>&1 & # real 257m59.713s cat fb.calJac4.chainRBest.Hg38.txt # 1425296830 bases of 2481941580 (57.427%) in intersection ########################################################################### # lastz/chain/net swap mouse/mm10 (TBD - 2020-04-20 - Hiram) # original alignment cat fb.mm10.chainCalJac4Link.txt # 777883731 bases of 2652783500 (29.323%) in intersection cat fb.mm10.chainSynCalJac4Link.txt # 736602602 bases of 2652783500 (27.767%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev mm10 calJac4 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 219m16.168s cat fb.mm10.chainRBest.CalJac4.txt # 741307883 bases of 2652783500 (27.945%) in intersection mkdir /hive/data/genomes/calJac4/bed/blastz.mm10.swap cd /hive/data/genomes/calJac4/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzCalJac4.2020-04-02/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & # real 50m20.639s cat fb.calJac4.chainMm10Link.txt # 772902855 bases of 2481941580 (31.141%) in intersection cat fb.calJac4.chainSynMm10Link.txt # 737924732 bases of 2481941580 (29.732%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev calJac4 mm10 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 173m38.016s cat fb.calJac4.chainRBest.Mm10.txt # 740357755 bases of 2481941580 (29.830%) in intersection ############################################################################## -# GENBANK AUTO UPDATE (TBD - 2020-07-30 - Hiram) +# GENBANK AUTO UPDATE (DONE - 2020-09-03 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # organism mrnaCnt estCnt refSeqCnt - # Mus musculus 581990 4871398 37663 - # Mus musculus albula 4 0 0 - # Mus musculus bactrianus 4 0 0 - # Mus musculus brevirostris 2 0 0 - # Mus musculus castaneus 28 2 0 - # Mus musculus domesticus 1703 70 0 - # Mus musculus kobuvirus 2 0 0 - # Mus musculus molossinus 38 0 0 - # Mus musculus musculus 71 4 0 - # Mus musculus musculus x M. m. castaneus 1 0 0 - # Mus musculus papillomavirus type 1 10 0 0 - # Mus musculus picornavirus 3 0 0 - # Mus musculus wagneri 2 0 0 + # Callithrix geoffroyi 7 0 0 + # Callithrix jacchus 1607 292992 221 + # Callithrix kuhlii 1 0 0 + # Callithrix penicillata 1 0 0 + # Callithrix pygmaea 5 0 0 + # Callithrix sp. 4 0 0 # edit etc/genbank.conf to add calJac4 just after mm10 -# calJac4 - (house mouse - GCA_000001635.9 - GRCm39) +# Marmoset - GCF_009663435.1 - Callithrix_jacchus_cj1700_1.1 calJac4.serverGenome = /hive/data/genomes/calJac4/calJac4.2bit calJac4.ooc = /hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc -calJac4.lift = /hive/data/genomes/calJac4/jkStuff/calJac4.5Kgaps.lft +calJac4.lift = /hive/data/genomes/calJac4/jkStuff/calJac4.gaps.lft +calJac4.perChromTables = no calJac4.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} calJac4.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} calJac4.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} calJac4.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} calJac4.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} +calJac4.genbank.est.xeno.pslCDnaFilter = ${finished.genbank.est.xeno.pslCDnaFilter} calJac4.downloadDir = calJac4 +calJac4.refseq.mrna.native.load = yes calJac4.refseq.mrna.xeno.load = yes calJac4.refseq.mrna.xeno.loadDesc = yes calJac4.genbank.mrna.xeno.load = yes -calJac4.genbank.mrna.blatTargetDb = yes -calJac4.upstreamGeneTbl = refGene -# calJac4.mgc = yes -# calJac4.orfeome = yes -# calJac4.ccds.buildId = 21 -# calJac4.upstreamMaf = multiz60way /hive/data/genomes/calJac4/bed/multiz60way/species.list +# calJac4.upstreamGeneTbl = ensGene +# calJac4.upstreamMaf = multiz13way /hive/data/genomes/calJac4/bed/multiz13way/species.list # verify the files specified exist before checking in the file: grep ^calJac4 etc/genbank.conf | grep hive | awk '{print $NF}' | xargs ls -og -# -rw-rw-r-- 1 127236 Jul 30 09:23 /hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc -# -rw-rw-r-- 1 7714 Jul 30 09:50 /hive/data/genomes/calJac4/jkStuff/calJac4.5Kgaps.lft -# -rw-rw-r-- 1 714181470 Jul 30 09:03 /hive/data/genomes/calJac4/calJac4.2bit +# -rw-rw-r-- 1 755819249 Sep 3 10:51 /hive/data/genomes/calJac4/calJac4.2bit +# -rw-rw-r-- 1 139956 Sep 3 11:54 /hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc +# -rw-rw-r-- 1 61169 Sep 3 12:42 /hive/data/genomes/calJac4/jkStuff/calJac4.gaps.lft - git commit -m "Added calJac4 mouse; refs #22271" etc/genbank.conf + git commit -m "Added calJac4 marmoset; refs #24074" etc/genbank.conf git push # update /cluster/data/genbank/: make etc-update # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add calJac4 to: # etc/hgwdev.dbs etc/align.dbs - git commit -m "Added calJac4 - mouse refs #22271" etc/hgwdev.dbs etc/align.dbs + git commit -m "Added calJac4 - marmoset refs #24074" etc/hgwdev.dbs etc/align.dbs git push make etc-update # wait a few days for genbank magic to take place, the tracks will # appear ############################################################################# -# augustus gene track (TBD - 2020-07-30 - Hiram) +# augustus gene track (TBD - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/augustus cd /hive/data/genomes/calJac4/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev calJac4) > do.log 2>&1 # real 119m8.866s cat fb.calJac4.augustusGene.txt # 49120541 bases of 2654624157 (1.850%) in intersection ######################################################################### # ncbiRefSeq (TBD - 2019-11-20 - Hiram) ### XXX ### Not available on GCA/genbank assemblies mkdir /hive/data/genomes/calJac4/bed/ncbiRefSeq cd /hive/data/genomes/calJac4/bed/ncbiRefSeq # running step wise just to be careful time (~/kent/src/hg/utils/automation/doNcbiRefSeq.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev \ -stop=download -fileServer=hgwdev -smallClusterHub=ku -workhorse=hgwdev \ refseq vertebrate_mammalian Gorilla_gorilla \ GCA_008122165.1_Kamilah_GGO_v0 calJac4) > download.log 2>&1 # real 1m37.523s 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_mammalian Gorilla_gorilla \ GCF_008122165.1_Kamilah_GGO_v0 calJac4) > process.log 2>&1 # real 2m9.450s 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_mammalian Gorilla_gorilla \ GCF_008122165.1_Kamilah_GGO_v0 calJac4) > load.log 2>&1 # real 0m21.982s cat fb.ncbiRefSeq.calJac4.txt # 74279781 bases of 2999027915 (2.477%) in intersection # add: include ../../refSeqComposite.ra alpha # to the gorilla/calJac4/trackDb.ra to turn on the track in the browser # XXX 2019-11-20 - ready for this after genbank runs featureBits -enrichment calJac4 refGene ncbiRefSeq # refGene 0.402%, ncbiRefSeq 3.148%, both 0.402%, cover 99.90%, enrich 31.73x featureBits -enrichment calJac4 ncbiRefSeq refGene # ncbiRefSeq 3.148%, refGene 0.402%, both 0.402%, cover 12.76%, enrich 31.73x featureBits -enrichment calJac4 ncbiRefSeqCurated refGene # ncbiRefSeqCurated 0.401%, refGene 0.402%, both 0.400%, cover 99.66%, enrich 247.79x featureBits -enrichment calJac4 refGene ncbiRefSeqCurated # refGene 0.402%, ncbiRefSeqCurated 0.401%, both 0.400%, cover 99.33%, enrich 247.79x ############################################################################## -# LIFTOVER TO mm10 (TBD - 2020-07-30 - Hiram) +# LIFTOVER TO mm10 (TBD - 2020-09-03 - Hiram) ssh hgwdev - mkdir /hive/data/genomes/calJac4/bed/blat.mm10.2020-07-30 - cd /hive/data/genomes/calJac4/bed/blat.mm10.2020-07-30 + mkdir /hive/data/genomes/calJac4/bed/blat.mm10.2020-09-03 + cd /hive/data/genomes/calJac4/bed/blat.mm10.2020-09-03 doSameSpeciesLiftOver.pl -verbose=2 \ -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -query2Bit=/hive/data/genomes/mm10/mm10.2bit \ -querySizes=/hive/data/genomes/mm10/chrom.sizes \ -ooc=/hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc \ calJac4 mm10 time (doSameSpeciesLiftOver.pl -verbose=2 \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -query2Bit=/hive/data/genomes/mm10/mm10.2bit \ -querySizes=/hive/data/genomes/mm10/chrom.sizes \ -ooc=/hive/data/genomes/calJac4/jkStuff/calJac4.11.ooc \ calJac4 mm10) > doLiftOverToMm10.log 2>&1 # real 257m18.898s # see if the liftOver menus function in the browser from calJac4 to mm10 ############################################################################## # BLATSERVERS ENTRY (TBD - 2020-04-02 - Hiram) # request sent 2020-08-17 # After getting a blat server assigned by the Blat Server Gods, ssh hgwdev hgsql -e 'INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("calJac4", "blat1b", "17904", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("calJac4", "blat1b", "17905", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to gene: CDH2 upon recommendation from Kerstin ## (TBD - 2020-06-22 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr7:60683331-61003907" where name="calJac4";' hgcentraltest ############################################################################## -# crispr whole genome (TBD - 2020-07-30 - Hiram) +# crispr whole genome (TBD - 2020-09-03 - Hiram) mkdir /hive/data/genomes/calJac4/bed/crisprAll cd /hive/data/genomes/calJac4/bed/crisprAll # the large shoulder argument will cause the entire genome to be scanned # this takes a while for a new genome to get the bwa indexing done time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 -stop=ranges \ calJac4 augustusGene -shoulder=250000000 -tableName=crisprAll \ -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) >> ranges.log 2>&1 # real 62m2.060s - failed on 'genscan' genes # real 1m16.884s - rerun on 'augustusGene' time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=guides -stop=specScores calJac4 augustusGene \ -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > specScores.log 2>&1 # real 6558m26.295s cat guides/run.time | sed -e 's/^/# /;' # Completed: 100 of 100 jobs # CPU time in finished jobs: 13031s 217.19m 3.62h 0.15d 0.000 y # IO & Wait Time: 299s 4.98m 0.08h 0.00d 0.000 y # Average job time: 133s 2.22m 0.04h 0.00d # Longest finished job: 920s 15.33m 0.26h 0.01d # Submission to last job: 935s 15.58m 0.26h 0.01d cat specScores/run.time | sed -e 's/^/# /;' # Completed: 2947790 of 2947790 jobs # CPU time in finished jobs: 247411142s 4123519.03m 68725.32h 2863.55d 7.845 y # IO & Wait Time: 0s 0.00m 0.00h 0.00d 0.000 y # Average job time: 82s 1.37m 0.02h 0.00d # Longest finished job: 353s 5.88m 0.10h 0.00d # Submission to last job: 561467s 9357.78m 155.96h 6.50d # Number of specScores: 220274834 ### remember to get back to hgwdev to run this time (~/kent/src/hg/utils/automation/doCrispr.pl -verbose=2 \ -continue=effScores -stop=load calJac4 augustusGene \ -shoulder=250000000 -tableName=crisprAll -fileServer=hgwdev \ -buildDir=`pwd` -smallClusterHub=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev) > load.log 2>&1 # real 1615m13.200s cat effScores/run.time | sed -e 's/^/# /;' # Completed: 27714 of 27714 jobs # CPU time in finished jobs: 13108172s 218469.53m 3641.16h 151.71d 0.416 y # IO & Wait Time: 52457s 874.29m 14.57h 0.61d 0.002 y # Average job time: 475s 7.91m 0.13h 0.01d # Longest finished job: 2486s 41.43m 0.69h 0.03d # Submission to last job: 44334s 738.90m 12.31h 0.51d cat offTargets/run.time | sed -e 's/^/# /;' # Completed: 147390 of 147390 jobs # CPU time in finished jobs: 2280286s 38004.77m 633.41h 26.39d 0.072 y # IO & Wait Time: 505943s 8432.38m 140.54h 5.86d 0.016 y # Average job time: 19s 0.32m 0.01h 0.00d # Longest finished job: 36s 0.60m 0.01h 0.00d # Submission to last job: 13489s 224.82m 3.75h 0.16d bigBedInfo crispr.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 22 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 # itemCount: 276,331,386 # primaryDataSize: 12,229,621,910 # primaryIndexSize: 17,345,476 # zoomLevels: 10 # chromCount: 33 # basesCovered: 2,179,930,088 # meanDepth (of bases covered): 2.915516 # minDepth: 1.000000 # maxDepth: 32.000000 # std of depth: 1.944181 ######################################################################### # all.joiner update, downloads and in pushQ - (WORKING - 2019-11-20 - Hiram) cd $HOME/kent/src/hg/makeDb/schema # verify all the business is done for release ~/kent/src/hg/utils/automation/verifyBrowser.pl calJac4 # 66 tables in database calJac4 - Dog, Canis lupus familiaris # verified 55 tables in database calJac4, 11 extra tables, 14 optional tables # chainNetRBestHg38 3 optional tables # chainNetRBestMm10 3 optional tables # chainNetSynHg38 3 optional tables # chainNetSynMm10 3 optional tables # gapOverlap 1 optional tables # tandemDups 1 optional tables # 1 chainCanFam3 - extra table # 2 chainCanFam3Link - extra table # 3 chainRBestCanFam3 - extra table # 4 chainRBestCanFam3Link - extra table # . . . etc . . . # 8 crisprAllTargets - extra table # 9 netCanFam3 - extra table # 10 netRBestCanFam3 - extra table # 11 netSynCanFam3 - extra table # 13 genbank tables found # verified 28 required tables, 1 missing tables # 1 ucscToRefSeq - missing table # hg38 chainNet to calJac4 found 3 required tables # mm10 chainNet to calJac4 found 3 required tables # hg38 chainNet RBest and syntenic to calJac4 found 6 optional tables # mm10 chainNet RBest and syntenic to calJac4 found 3 optional tables # liftOver to previous versions: 1, from previous versions: 1 # fixup all.joiner until this is a clean output joinerCheck -database=calJac4 -tableCoverage all.joiner joinerCheck -database=calJac4 -times all.joiner joinerCheck -database=calJac4 -keys all.joiner # when clean, check in: - git commit -m 'adding rules for calJac4 refs #22271' all.joiner + git commit -m 'adding rules for calJac4 refs #24074' all.joiner git push # run up a 'make alpha' in hg/hgTables to get this all.joiner file # into the hgwdev/genome-test system cd /hive/data/genomes/calJac4 time (makeDownloads.pl calJac4) > downloads.log 2>&1 # real 16m11.233s # now ready for pushQ entry mkdir /hive/data/genomes/calJac4/pushQ cd /hive/data/genomes/calJac4/pushQ time ($HOME/kent/src/hg/utils/automation/makePushQSql.pl -redmineList calJac4) > calJac4.pushQ.sql 2> stderr.out # real 15m2.385s # remove the tandemDups and gapOverlap from the file list: sed -i -e "/tandemDups/d" redmine.calJac4.table.list sed -i -e "/Tandem Dups/d" redmine.calJac4.releaseLog.txt sed -i -e "/gapOverlap/d" redmine.calJac4.table.list sed -i -e "/Gap Overlaps/d" redmine.calJac4.releaseLog.txt # check for errors in stderr.out, some are OK, e.g.: # WARNING: calJac4 does not have ucscToRefSeq # WARNING: hgwdev does not have /gbdb/calJac4/ncbiRefSeq/ncbiRefSeqVersion.txt # WARNING: hgwdev does not have /gbdb/calJac4/ncbiRefSeq/ncbiRefSeqOther.bb # WARNING: hgwdev does not have /gbdb/calJac4/ncbiRefSeq/ncbiRefSeqOther.ix # WARNING: hgwdev does not have /gbdb/calJac4/ncbiRefSeq/ncbiRefSeqOther.ixx # WARNING: hgwdev does not have /gbdb/calJac4/ncbiRefSeq/seqNcbiRefSeq.rna.fa # WARNING: calJac4 does not have seq # WARNING: calJac4 does not have extFile # verify the file list does correctly match to files cat redmine.calJac4.file.list | while read L do eval ls $L > /dev/null done # should be silent, missing files will show as errors # verify database tables, how many to expect: wc -l redmine.calJac4.table.list # 52 redmine.calJac4.table.list # how many actual: awk -F'.' '{printf "hgsql -N %s -e '"'"'show table status like \"%s\";'"'"'\n", $1, $2}' redmine.calJac4.table.list | sh | wc -l # 52 # would be a smaller number actual if some were missing # add the path names to the listing files in the redmine issue # in the three appropriate entry boxes: # /hive/data/genomes/calJac4/pushQ/redmine.calJac4.file.list # /hive/data/genomes/calJac4/pushQ/redmine.calJac4.releaseLog.txt # /hive/data/genomes/calJac4/pushQ/redmine.calJac4.table.list #########################################################################