# for emacs: -*- mode: sh; -*- # This file describes browser build for the tupChi1 ######################################################################### # obtain photograph: (DONE - 2007-02-20 - Hiram) # going to re-use the tupBel1 photograph cd /hive/data/genomes/tupChi1 # establish photoReference.txt printf 'photoCreditURL\thttp://commons.wikimedia.org/wiki/File:Tupaia_belangeri.JPEG photoCreditName\tWikiMedia Commons: Jonathan Beilby\n' > photoReference.txt ######################################################################### # Initial steps (DONE - 2013-02-26 - Hiram) # this is a catch-up procedure. This minimal browser was constructed # quickly in 2013 # To start this initialBuild.txt document, from a previous assembly document: mkdir ~/kent/src/hg/makeDb/doc/tupChi1 cd ~/kent/src/hg/makeDb/doc/tupChi1 # best to use a most recent document since it has the latest features and # procedures: sed -e 's/rhiBie/tupChi/g; s/RhiBie/TupChi/g; s/DONE/TBD/g;' \ ../rhiBie1/initialBuild.txt > initialBuild.txt mkdir /hive/data/genomes/tupChi1/genbank cd /hive/data/genomes/tupChi1/genbank # this was done with the older hierarchy: rsync -a -P \ rsync://ftp.ncbi.nlm.nih.gov/genbank/genomes/Eukaryotes/vertebrates_mammals/Tupaia_chinensis/TupChi_1.0/ ./ sent 219 bytes received 1043861189 bytes 3177660.30 bytes/sec total size is 1043732280 speedup is 1.00 # appears to be a scaffold-only assembly: faSize Primary_Assembly//unplaced_scaffolds/FASTA/unplaced.scaf.fa.gz # 2846580235 bases (140191100 N's 2706389135 real 2706389135 upper 0 lower) # in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (gi|444524349|gb|KB360401.1|) # max 19269909 (gi|444728026|gb|KB320563.1|) median 444 # %0.00 masked total, %0.00 masked real # this information is from the top of tupChi1/genbank/ASSEMBLY_INFO # DATE: 31-Jan-2013 # ORGANISM: Tupaia chinensis # TAXID: 246437 # ASSEMBLY LONG NAME: TupChi_1.0 # ASSEMBLY SHORT NAME: TupChi_1.0 # ASSEMBLY SUBMITTER: BGI # ASSEMBLY TYPE: Haploid # NUMBER OF ASSEMBLY-UNITS: 1 # ASSEMBLY ACCESSION: GCA_000334495.1 # FTP-RELEASE DATE: 07-Feb-2013 # this information is from the top of # tupChi1/refseq/GCF_000334495.1_TupChi_1.0_assembly_report.txt # Assembly name: TupChi_1.0 # Organism name: Tupaia chinensis (Chinese tree shrew) # Sex: male # Taxid: 246437 # BioSample: SAMN01084043 # BioProject: PRJNA221634 # Submitter: BGI # Date: 2013-1-31 # Assembly type: haploid # Release type: major # Assembly level: Scaffold # Genome representation: full # WGS project: ALAR01 # Assembly method: SOAPdenovo v. 1.05 # Genome coverage: 80x # Sequencing technology: Illumina HiSeq 2000 # RefSeq category: Representative Genome # GenBank assembly accession: GCA_000334495.1 # RefSeq assembly accession: GCF_000334495.1 # RefSeq assembly and GenBank assemblies identical: yes # ## Assembly-Units: ## GenBank Unit Accession RefSeq Unit Accession Assembly-Unit name ## GCA_000334505.1 GCF_000334505.1 Primary Assembly ############################################################################# # establish config.ra file (DONE - Hiram - 2017-03-08) # arguments here are: cd /hive/data/genomes/tupChi1 ~/kent/src/hg/utils/automation/prepConfig.pl tupChi1 mammal \ treeShrew ./refseq/*_assembly_report.txt # verify it looks sane, fixed the genBankAccessionID to match the # genbank ID, not the RefSeq ID, and set orderKey to what it is cat tupChi1.config.ra # config parameters for makeGenomeDb.pl: db tupChi1 clade mammal scientificName Tupaia chinensis commonName Chinese tree shrew assemblyDate Jan. 2013 assemblyLabel BGI assemblyShortLabel TupChi_1.0 orderKey 3365 mitoAcc notFound fastaFiles /hive/data/genomes/tupChi1/ucsc/*.fa.gz agpFiles /hive/data/genomes/tupChi1/ucsc/*.agp # qualFiles none dbDbSpeciesDir treeShrew photoCreditURL http://commons.wikimedia.org/wiki/File:Tupaia_belangeri.JPEG photoCreditName WikiMedia Commons: Jonathan Beilby ncbiGenomeId 13028 ncbiAssemblyId 531728 ncbiAssemblyName TupChi_1.0 ncbiBioProject 221634 ncbiBioSample SAMN01084043 genBankAccessionID GCA_000334495.1 taxId 246437 ############################################################################# # setup UCSC named files (DONE - 2017-03-25 - Hiram) mkdir /hive/data/genomes/tupChi1/ucsc cd /hive/data/genomes/tupChi1/ucsc # this previous process merely removed the .1 from all the accessions zcat \ | ../genbank/Primary_Assembly/unplaced_scaffolds/AGP/unplaced.scaf.agp.gz \ | sed -e 's/\.1\t/\t/;' > tupChi1.ucsc.agp zcat \ ../genbank/Primary_Assembly/unplaced_scaffolds/FASTA/unplaced.scaf.fa.gz \ | sed -e 's/^>gi.*gb./>/; s/\.1. Tupaia.*//;' | gzip -c \ > tupChi1.ucsc.fa.gz # verify fasta and AGPs agree time faToTwoBit tupChi1.ucsc.fa.gz test.2bit checkAgpAndFa tupChi1.ucsc.agp 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 # 2846580235 bases (140191100 N's 2706389135 real 2706389135 upper 0 lower) # in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (KB360401) # max 19269909 (KB320563) median 444 # same numbers as above, minus the one contig (205 bases) # 2846580235 bases (140191100 N's 2706389135 real 2706389135 upper 0 lower) # in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (gi|444524349|gb|KB360401.1|) # max 19269909 (gi|444728026|gb|KB320563.1|) median 444 # no longer need these temporary 2bit files rm refseq.2bit unplaced.2bit test.2bit ############################################################################# # Initial database build (DONE - 2013-03-25 - Hiram) # these procedures were done manually, the script was not used # verify sequence and AGP are OK: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev -fileServer=hgwdev \ -stop=agp tupChi1.config.ra) > agp.log 2>&1 # real 3m32.248s # then finish it off: time (makeGenomeDb.pl -workhorse=hgwdev -dbHost=hgwdev \ -fileServer=hgwdev -continue=db tupChi1.config.ra) > db.log 2>&1 # real 23m23.025s # check in the trackDb files created in TemporaryTrackDbCheckout/ # and add tupChi1 to trackDb/makefile # temporary symlink until masked sequence is available cd /hive/data/genomes/tupChi1 ln -s `pwd`/tupChi1.unmasked.2bit /gbdb/tupChi1/tupChi1.2bit ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2014-07-16 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/cpgIslandsUnmasked cd /hive/data/genomes/tupChi1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/tupChi1/tupChi1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku tupChi1) > do.log 2>&1 # real 38m7.138s cat fb.tupChi1.cpgIslandExtUnmasked.txt # 41084726 bases of 2706389135 (1.518%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2017-03-08 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/cytoBand cd /hive/data/genomes/tupChi1/bed/cytoBand makeCytoBandIdeo.csh tupChi1 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (DONE - 2017-03-08 - Hiram) # the sequence here is working for a 'genbank' assembly # beware of a chrM situation may be specific depending upon what is # available in the assembly mkdir /hive/data/genomes/tupChi1/bed/ucscToINSDC cd /hive/data/genomes/tupChi1/bed/ucscToINSDC # normal script doesn't work here, manually fairly simple: cut -f1 ../../chrom.sizes | awk '{printf "%s\t%s.1\n", $1, $1}' \ | sort > ucscToINSDC.txt awk '{printf "%s\t%s\n", $2, $1}' ucscToINSDC.txt | sort > insdcToUcsc.txt # 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}' | sort > refseq.insdc.txt awk '{printf "%s\t0\t%d\n", $1,$2}' ../../chrom.sizes \ | sort > ucsc.coordinate.tab sort -k2 refseq.insdc.txt \ | join -1 2 -2 2 - ucscToINSDC.txt | sort -k3 \ | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-4 \ > ucscToINSDC.bed sort -k2 refseq.insdc.txt \ | join -1 2 -2 2 - ucscToINSDC.txt | sort -k3 \ | join -2 3 ucsc.coordinate.tab - | tr '[ ]' '[\t]' | cut -f1-3,5 \ > ucscToRefSeq.bed # 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 * # 50750 insdcToUcsc.txt # 50750 refseq.insdc.txt # 50750 ucsc.coordinate.tab # 50750 ucscToINSDC.bed # 50750 ucscToINSDC.txt # 50750 ucscToRefSeq.bed export chrSize=`cut -f1 ucscToINSDC.bed | awk '{print length($0)}' | sort -n | tail -1` echo $chrSize # 8 sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | hgLoadSqlTab tupChi1 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 $chrSize # 14 sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | sed -e 's/INSDC/RefSeq/g;' > ucscToRefSeq.sql hgLoadSqlTab tupChi1 ucscToRefSeq ./ucscToRefSeq.sql ucscToRefSeq.bed # checkTableCoords should be silent checkTableCoords tupChi1 # each should cover %100 entirely: featureBits -countGaps tupChi1 ucscToINSDC # 2846580235 bases of 2846580235 (100.000%) in intersection featureBits -countGaps tupChi1 ucscToRefSeq # 2846580235 bases of 2846580235 (100.000%) in intersection ######################################################################### # add chromAlias table (DONE - 2016-09-13 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/chromAlias cd /hive/data/genomes/tupChi1/bed/chromAlias hgsql -N -e 'select chrom,name,"refseq" from ucscToRefSeq;' tupChi1 \ > ucsc.refseq.tab hgsql -N -e 'select chrom,name,"genbank" from ucscToINSDC;' tupChi1 \ > ucsc.genbank.tab awk '{printf "%s\t%s\t%s\n", $2,$1,$3}' ucsc.genbank.tab ucsc.refseq.tab \ | sort > tupChi1.chromAlias.tab hgLoadSqlTab tupChi1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ tupChi1.chromAlias.tab ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2017-03-08 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/rhinopithecus/tupChi1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" tupChi1 \ | sed -e 's/[0-9][0-9]*//;' | sort | uniq -c 242445 ALAR.1 # implies a rule: 'ALAR[0-9]+(\.[0-9]+)?' # verify this rule will find them all and eliminate them all: hgsql -N -e "select frag from gold;" tupChi1 | wc -l # 242445 hgsql -N -e "select frag from gold;" tupChi1 \ | egrep -e 'ALAR[0-9]+(\.[0-9]+)?' | wc -l # 242445 hgsql -N -e "select frag from gold;" tupChi1 \ | egrep -v -e 'ALAR[0-9]+(\.[0-9]+)?' | wc -l # 0 # hence, add to trackDb/chicken/tupChi1/trackDb.ra searchTable gold shortCircuit 1 termRegex ALAR[0-9]+(\.[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 - 2013-04-16 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/repeatMasker cd /hive/data/genomes/tupChi1/bed/repeatMasker o doRepeatMasker.pl -buildDir=`pwd` -stop=mask \ -bigClusterHub=swarm -dbHost=hgwdev -workhorse=hgwdev \ -species "Tupaia chinensis" -useRMBlastn \ -smallClusterHub=encodek tupChi1 # Elapsed time: 320m12s cat faSize.rmsk.txt # 2846580235 bases (140191100 N's 2706389135 real 2112282279 upper # 594106856 lower) in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (KB360401) # max 19269909 (KB320563) median 444 # %20.87 masked total, %21.95 masked real egrep -i "versi|relea" mask.log # RepeatMasker version open-4.0.0 # January 10 2013 (open-4-0-0) version of RepeatMasker # CC RELEASE 20120418; * time featureBits -countGaps tupChi1 rmsk # 594515212 bases of 2846580235 (20.885%) in intersection # real 1m5.558s # 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;' tupChi1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" # total 594515212.000000 # real 0m34.661s # catching up some stuff that was not originally done time doRepeatMasker.pl -buildDir=`pwd` -stop=install -continue=install \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -species "Tupaia chinensis" -useRMBlastn \ -smallClusterHub=ku tupChi1 -debug # edit that doLoad.bash to eliminate the load of rmsk table, but # allow it to do all the other tasks time (./doLoad.bash) > doLoad.log 2>&1 # real 2m58.024s time (doRepeatMasker.pl -buildDir=`pwd` -continue=cleanup \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -species "Tupaia chinensis" -useRMBlastn \ -smallClusterHub=ku tupChi1) > cleanup.log 2>&1 # real 9m38.260s ########################################################################## # running simple repeat (DONE - 2013-04-14 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/simpleRepeat cd /hive/data/genomes/tupChi1/bed/simpleRepeat time doSimpleRepeat.pl -buildDir=`pwd` \ -smallClusterHub=swarm -workhorse=hgwdev -stop=filter \ tupChi1 > filter.log 2>&1 # real 23m19.327s # need to catch up with undone steps: doSimpleRepeat.pl -buildDir=`pwd` \ -smallClusterHub=ku -workhorse=hgwdev -stop=load \ -continue=load -debug tupChi1 # edit the doLoad.csh to remove the hgLoad command, allow the featureBits cat fb.simpleRepeat # 118057864 bases of 2706389135 (4.362%) in intersection time (doSimpleRepeat.pl -buildDir=`pwd` \ -smallClusterHub=ku -workhorse=hgwdev \ -continue=cleanup tupChi1) > cleanup.log 2>&1 # adding this trfMask to the other masking cd /hive/data/genomes/tupChi1 # when using the Window Masker result: twoBitMask bed/windowMasker/tupChi1.cleanWMSdust.2bit \ -add bed/simpleRepeat/trfMask.bed tupChi1.2bit # you can safely ignore the warning about fields >= 13 # when using Rmsk results, add to rmsk after it is done: # twoBitMask tupChi1.rmsk.2bit \ # -add bed/simpleRepeat/trfMask.bed tupChi1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa tupChi1.2bit stdout | faSize stdin > faSize.tupChi1.2bit.txt cat faSize.tupChi1.2bit.txt # 2846580235 bases (140191100 N's 2706389135 real 1623275627 upper # 1083113508 lower) in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (KB360401) # max 19269909 (KB320563) median 444 # %38.05 masked total, %40.02 masked real # reset the symlink rm /gbdb/tupChi1/tupChi1.2bit ln -s `pwd`/tupChi1.2bit /gbdb/tupChi1/tupChi1.2bit ######################################################################### # CREATE MICROSAT TRACK (DONE - 2017-03-08 - Hiram) ssh hgwdev mkdir /hive/data/genomes/tupChi1/bed/microsat cd /hive/data/genomes/tupChi1/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 tupChi1 microsat microsat.bed # Read 75464 elements of size 4 from microsat.bed ########################################################################## ## WINDOWMASKER (DONE - 2013-04-16 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/windowMasker cd /hive/data/genomes/tupChi1/bed/windowMasker time doWindowMasker.pl -stop=twobit -buildDir=`pwd` \ -workhorse=hgwdev tupChi1 > twobit.log 2>&1 # real 187m29.301s # Masking statistics cat faSize.tupChi1.cleanWMSdust.txt # 2846580235 bases (140191100 N's 2706389135 real 1623675807 upper # 1082713328 lower) in 50750 sequences in 1 files # Total size: mean 56090.3 sd 501058.6 min 200 (KB360401) # max 19269909 (KB320563) median 444 # %38.04 masked total, %40.01 masked real # there is noting in the load that hasn't already been done doWindowMasker.pl -stop=load -buildDir=`pwd` \ -debug -continue=load -workhorse=hgwdev tupChi1 featureBits -countGaps tupChi1 rmsk windowmaskerSdust \ > fb.tupChi1.rmsk.windowmaskerSdust.txt 2>&1 cat fb.tupChi1.rmsk.windowmaskerSdust.txt # 275112679 bases of 2846580235 (9.665%) in intersection ########################################################################## # run up idKeys files for ncbiRefSeq (DONE - 2016-05-06 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/idKeys cd /hive/data/genomes/tupChi1/bed/idKeys time (doIdKeys.pl -buildDir=`pwd` tupChi1) > do.log 2>&1 & # real 23m54.611s cat tupChi1.keySignature.txt # 27aeb5bf402d8bca898fa163fa113c73 ########################################################################## # cpgIslands - (DONE - 2013-11-25 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/cpgIslands cd /hive/data/genomes/tupChi1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku tupChi1) > do.log 2>&1 & # Elapsed time: 26m52s cat fb.tupChi1.cpgIslandExt.txt # 28673313 bases of 2706389135 (1.059%) in intersection ############################################################################## # genscan - (DONE - 2013-09-10 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/genscan cd /hive/data/genomes/tupChi1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku tupChi1) > do.log 2>&1 & # Elapsed time: 155m3s cat fb.tupChi1.genscan.txt # 43982227 bases of 2706389135 (1.625%) in intersection cat fb.tupChi1.genscanSubopt.txt # 53805481 bases of 2977074741 (1.807%) in intersection ############################################################################# # augustus gene track (DONE - 2017-03-01 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/augustus cd /hive/data/genomes/tupChi1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev -workhorse=hgwdev tupChi1) > do.log 2>&1 & # reel 104m18.398s cat fb.tupChi1.augustusGene.txt # 47275232 bases of 2977074741 (1.588%) in intersection ######################################################################### # Create kluster run files (DONE - 2017-03-08 - Hiram) # numerator is tupChi1 gapless bases "real" as reported by: featureBits -noRandom -noHap tupChi1 gap # 140191100 bases of 2706389135 (5.180%) 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 \( 2706389135 / 2861349177 \) \* 1024 # ( 2706389135 / 2861349177 ) * 1024 = 968.543964 # ==> use -repMatch=900 according to size scaled down from 1024 for human. # and rounded down to nearest 50 cd /hive/data/genomes/tupChi1 blat tupChi1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/tupChi1.11.ooc \ -repMatch=900 # Wrote 32705 overused 11-mers to jkStuff/tupChi1.11.ooc # check non-bridged gaps to see what the typical size is: hgsql -N \ -e 'select * from gap where bridge="no" order by size;' tupChi1 \ | 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 tupChi1 jkStuff/nonBridged.lft \ # -bedFile=jkStuff/nonBridged.bed ######################################################################## # GENBANK AUTO UPDATE (DONE - 2017-03-09 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt # Tupaia chinensis 50514 1 17 # edit etc/genbank.conf to add tupChi1 just before macFas5 # tupChi1 (Chinese shrew) tupChi1.serverGenome = /hive/data/genomes/tupChi1/tupChi1.2bit tupChi1.clusterGenome = /hive/data/genomes/tupChi1/tupChi1.2bit tupChi1.ooc = /hive/data/genomes/tupChi1/jkStuff/tupChi1.11.ooc tupChi1.lift = no tupChi1.perChromTables = no tupChi1.downloadDir = tupChi1 tupChi1.refseq.mrna.native.pslCDnaFilter = ${ordered.refseq.mrna.native.pslCDnaFilter} tupChi1.refseq.mrna.xeno.pslCDnaFilter = ${ordered.refseq.mrna.xeno.pslCDnaFilter} tupChi1.genbank.mrna.native.pslCDnaFilter = ${ordered.genbank.mrna.native.pslCDnaFilter} tupChi1.genbank.mrna.xeno.pslCDnaFilter = ${ordered.genbank.mrna.xeno.pslCDnaFilter} tupChi1.genbank.est.native.pslCDnaFilter = ${ordered.genbank.est.native.pslCDnaFilter} # DO NOT NEED genbank.mrna.xeno except for human, mouse # the defaults: genbank.mrna.native.load, yes genbank.est.native.load yes # refseq.mrna.native.load yes, refseq.mrna.xeno.load yes git commit -m "Added tupChi1; refs #10146" etc/genbank.conf git push # update /cluster/data/genbank/: make etc-update # also add to src/lib/gbGenome.c # static char *tupChiNames[] = {"Tupaia chinensis", NULL}; # {"tupChi", tupChiNames}, git commit -m "Added tupChi1 refs #10146" src/lib/gbGenome.c make install-server cd /cluster/data/genbank time ./bin/gbAlignStep -initial tupChi1 # logFile: var/build/logs/2017.03.09-13:19:25.tupChi1.initalign.log # about 4 hours tail -2 2017.03.05-06:48:55.tupChi1.initalign.log # hgwdev 2017.03.09-17:21:30 tupChi1.initalign: Succeeded: tupChi1 # hgwdev 2017.03.09-17:22:19 tupChi1.initalign: finish # To re-do, rm the dir first: # /cluster/data/genbank/work/initial.tupChi1 # load database when finished ssh hgwdev cd /cluster/data/genbank time ./bin/gbDbLoadStep -drop -initialLoad tupChi1 # logFile: var/dbload/hgwdev/logs/2017.03.09-17:42:50.tupChi1.dbload.log # real 18m8.811s tail -1 var/dbload/hgwdev/logs/2017.03.09-17:42:50.tupChi1.dbload.log # hgwdev 2017.03.09-18:00:59 tupChi1.dbload: finish # enable daily alignment and update of hgwdev cd ~/kent/src/hg/makeDb/genbank git pull # add tupChi1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs git commit -m 'adding tupChi1 to the update alignments refs #10146' etc/align.dbs etc/hgwdev.dbs git push make etc-update ############################################################################# # ncbiRefSeq (TBD - 2016-05-13 - Hiram) mkdir /hive/data/genomes/tupChi1/bed/ncbiRefSeq cd /hive/data/genomes/tupChi1/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 tupChi1) > 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 tupChi1) > 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 tupChi1) > load.log 2>&1 # real 0m33.205s cat fb.ncbiRefSeq.tupChi1.txt # 82563006 bases of 1218501075 (6.776%) in intersection featureBits -enrichment tupChi1 refGene ncbiRefSeq # refGene 1.181%, ncbiRefSeq 6.776%, both 1.175%, cover 99.49%, # enrich 14.68x ######################################################################### # BLATSERVERS ENTRY (DONE - 2017-03-10 - 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 ("tupChi1", "blat1c", "17886", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("tupChi1", "blat1c", "17887", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to MEPE gene (egg shell protein) ## located via blat of the chicken protein ## (TBD - 2017-01-17 - Hiram) ssh hgwdev hgsql -e 'update dbDb set defaultPos="chr4:21251858-21288049" where name="tupChi1";' 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=tupChi1 -tableCoverage all.joiner joinerCheck -database=tupChi1 -times all.joiner joinerCheck -database=tupChi1 -keys all.joiner cd /hive/data/genomes/tupChi1 time (makeDownloads.pl -workhorse=hgwdev tupChi1) > downloads.log 2>&1 # real 24m57.372s # now ready for pushQ entry mkdir /hive/data/genomes/tupChi1/pushQ cd /hive/data/genomes/tupChi1/pushQ time (makePushQSql.pl tupChi1) > tupChi1.pushQ.sql 2> stderr.out # real 11m29.572s # check for errors in stderr.out, some are OK, e.g.: # WARNING: tupChi1 does not have seq # WARNING: tupChi1 does not have extFile # WARNING: tupChi1 does not have estOrientInfo # copy it to hgwbeta scp -p tupChi1.pushQ.sql qateam@hgwbeta:/tmp/ ssh qateam@hgwbeta "./bin/x86_64/hgsql qapushq < /tmp/tupChi1.pushQ.sql" # in that pushQ entry walk through each entry and see if the # sizes will set properly #########################################################################