437c39fa3d4b82d90f8cddf3aae8ee1630881fa0 hiram Tue Nov 26 13:47:13 2019 -0800 running up liftOvers refs #24568 diff --git src/hg/makeDb/doc/regenCho1/initialBuild.txt src/hg/makeDb/doc/regenCho1/initialBuild.txt index 594b0dc..8c2cc5b 100644 --- src/hg/makeDb/doc/regenCho1/initialBuild.txt +++ src/hg/makeDb/doc/regenCho1/initialBuild.txt @@ -274,103 +274,99 @@ # and add regenCho1 to trackDb/makefile # temporary symlink until masked sequence is available cd /hive/data/genomes/regenCho1 ln -s `pwd`/regenCho1.unmasked.2bit /gbdb/regenCho1/regenCho1.2bit ############################################################################## # cpgIslands on UNMASKED sequence (DONE - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/cpgIslandsUnmasked cd /hive/data/genomes/regenCho1/bed/cpgIslandsUnmasked time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku -buildDir=`pwd` \ -tableName=cpgIslandExtUnmasked \ -maskedSeq=/hive/data/genomes/regenCho1/regenCho1.unmasked.2bit \ -workhorse=hgwdev -smallClusterHub=ku regenCho1) > do.log 2>&1 -XXX - running - Mon Nov 25 15:18:59 PST 2019 - # real 3m46.939s + # real 3m30.732s cat fb.regenCho1.cpgIslandExtUnmasked.txt - # 11929440 bases of 2534810853 (0.471%) in intersection + # 13292341 bases of 2266312740 (0.587%) in intersection ############################################################################# # cytoBandIdeo - (DONE - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/cytoBand cd /hive/data/genomes/regenCho1/bed/cytoBand makeCytoBandIdeo.csh regenCho1 ############################################################################# # run up idKeys files for chromAlias/ncbiRefSeq (DONE - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/idKeys cd /hive/data/genomes/regenCho1/bed/idKeys time (doIdKeys.pl \ -twoBit=/hive/data/genomes/regenCho1/regenCho1.unmasked.2bit \ -buildDir=`pwd` regenCho1) > do.log 2>&1 & -XXX - running - Mon Nov 25 15:20:21 PST 2019 - # real 0m47.105s + # real 3m20.182s cat regenCho1.keySignature.txt - # 7850e2d5dabb6134fdc9d7083f1a3a54 + # ab4b597342e6842b8b2d85ba44f45f1d ############################################################################# # gapOverlap (DONE - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/gapOverlap cd /hive/data/genomes/regenCho1/bed/gapOverlap time (doGapOverlap.pl \ -twoBit=/hive/data/genomes/regenCho1/regenCho1.unmasked.2bit regenCho1 ) \ > do.log 2>&1 & -XXX - running - Mon Nov 25 15:21:16 PST 2019 - # real 1m51.246s + # real 2m50.902s - # there are 7 items found: + # there are 4 items found: wc -l bed.tab - # 7 bed.tab + # 4 bed.tab cat fb.regenCho1.gapOverlap.txt - # 5912 bases of 2762428432 (0.000%) in intersection + # 1900 bases of 2531519022 (0.000%) in intersection ############################################################################# # tandemDups (DONE - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/tandemDups cd /hive/data/genomes/regenCho1/bed/tandemDups time (~/kent/src/hg/utils/automation/doTandemDup.pl \ -twoBit=/hive/data/genomes/regenCho1/regenCho1.unmasked.2bit regenCho1) \ > do.log 2>&1 & -XXX - running - Mon Nov 25 15:24:00 PST 2019 - # real 369m58.055s + # real 462m49.910s cat fb.regenCho1.tandemDups.txt - # 86298981 bases of 2762428432 (3.124%) in intersection + # 38468992 bases of 2531519022 (1.520%) in intersection bigBedInfo regenCho1.tandemDups.bb | sed -e 's/^/# /;' # version: 4 # fieldCount: 13 # hasHeaderExtension: yes # isCompressed: yes # isSwapped: 0 # extraIndexCount: 0 -# itemCount: 1,039,087 -# primaryDataSize: 27,356,255 -# primaryIndexSize: 178,160 +# itemCount: 530,201 +# primaryDataSize: 14,192,892 +# primaryIndexSize: 160,912 # zoomLevels: 9 -# chromCount: 3504 -# basesCovered: 1,365,621,612 -# meanDepth (of bases covered): 6.439341 +# chromCount: 3872 +# basesCovered: 1,023,131,655 +# meanDepth (of bases covered): 3.894087 # minDepth: 1.000000 -# maxDepth: 307.000000 -# std of depth: 12.663540 +# maxDepth: 326.000000 +# std of depth: 11.009630 ######################################################################### # ucscToINSDC and ucscToRefSeq table/track (TBD - 2019-11-25 - Hiram) # construct idKeys for the refseq sequence mkdir /hive/data/genomes/regenCho1/refseq/idKeys cd /hive/data/genomes/regenCho1/refseq/idKeys faToTwoBit ../GCF_000002315.5_GRCg6a_genomic.fna.gz regenCho1.refSeq.2bit time (doIdKeys.pl -buildDir=`pwd` \ -twoBit=`pwd`/regenCho1.refSeq.2bit refseqRegenCho1) > do.log 2>&1 & # real 0m48.786s cat refseqRegenCho1.keySignature.txt # 7850e2d5dabb6134fdc9d7083f1a3a54 @@ -430,68 +426,98 @@ # 27 sed -e "s/21/$chrSize/" $HOME/kent/src/hg/lib/ucscToINSDC.sql \ | sed -e 's/INSDC/RefSeq/g;' \ | hgLoadSqlTab regenCho1 ucscToRefSeq stdin ucscToRefSeq.bed # should be quiet for all OK checkTableCoords regenCho1 # should cover %100 entirely: featureBits -countGaps regenCho1 ucscToINSDC # 1065365425 bases of 1065365425 (100.000%) in intersection featureBits -countGaps regenCho1 ucscToRefSeq # 1065365425 bases of 1065365425 (100.000%) in intersection ######################################################################### -# add chromAlias table (TBD - 2019-11-25 - Hiram) +# add chromAlias table (DONE - 2019-11-26 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/chromAlias cd /hive/data/genomes/regenCho1/bed/chromAlias - ln -s ../../ucsc/ucsc.regeneron.name.translate regen.tab + sort ../../ucsc/ucsc.regeneron.name.translate > regen.tab ~/kent/src/hg/utils/automation/chromAlias.pl regen.tab \ > regenCho1.chromAlias.tab join regen.tab <(sort -k1,1 ../../chrom.sizes) \ | awk '{printf "%s\t0\t%d\t%s\n", $1, $3, $2}' > regen.alias.bed wc -l * -# 6846 regen.alias.bed -# 6846 regen.tab -# 6846 regenCho1.chromAlias.tab +# 7811 regen.alias.bed +# 7811 regen.tab +# 7811 regenCho1.chromAlias.tab + hgLoadSqlTab regenCho1 chromAlias ~/kent/src/hg/lib/chromAlias.sql \ regenCho1.chromAlias.tab # display the Regeneron AGP file as a track: - ln -s ../../ucsc/ucsc.agp ./translatedRegen.agp + ln -s ../../regeneron/REGN_CHO.agp . + + awk '{printf "%d\t%s\t%d\t%s\t%d\n", $2, $4, $3, $1, $3}' regen.alias.bed \ + > regenToUcsc.lift - grep -v "^#" translatedRegen.agp | grep -w scaffold \ + + grep -v "^#" REGN_CHO.agp | grep -w yes \ | awk '{printf "%s\t%d\t%d\tgap\t0\t.\n", $1, $2-1, $3}' > regen.gaps.bed - grep -v "^#" translatedRegen.agp | grep -v -w scaffold \ + grep -v "^#" REGN_CHO.agp | grep -v -w yes \ | awk '{printf "%s\t%d\t%d\t%s\t0\t%s\n", $1, $2-1, $3, $6, $9}' \ > regen.contigs.bed sort -k1,1 -k2,2n regen.gaps.bed regen.contigs.bed > regen.agp.bed - hgLoadBed regenCho1 regenAGP regen.agp.bed - # Read 17962 elements of size 6 from regen.agp.bed + liftUp regen.agp.lifted.bed regenToUcsc.lift error regen.agp.bed + + hgLoadBed regenCho1 regenAGP regen.agp.lifted.bed + # Read 15529 elements of size 6 from regen.agp.lifted.bed + + grep -w gap regen.agp.lifted.bed | hgLoadBed regenCho1 regenAGPGap stdin + # Read 3859 elements of size 6 from stdin + + featureBits -countGaps regenCho1 gap + # 265206282 bases of 2531519022 (10.476%) in intersection + + featureBits -countGaps regenCho1 regenAGPGap + # 265493399 bases of 2531519022 (10.488%) in intersection + + featureBits -countGaps regenCho1 gap regenAGPGap + # 265206282 bases of 2531519022 (10.476%) in intersection + + # the REGN_CHO.agp is missing the chrM sequence added in this browser + featureBits -countGaps regenCho1 regenAGP + 2531502738 bases of 2531519022 (99.999%) in intersection + + grep chrM ../../chrom.sizes + # chrM 16284 - cut -f1-4 regen.gaps.bed | hgLoadBed regenCho1 regenAGPGap stdin - # Read 5558 elements of size 4 from stdin + calc \( 2531502738 + 16284 \) - 2531519022 + + calc 2531502738 + 16284 + # 2531502738 + 16284 = 2531519022.000000 + calc \( 2531502738 + 16284 \) - 2531519022 + # ( 2531502738 + 16284 ) - 2531519022 = 0.000000 ######################################################################### # fixup search rule for assembly track/gold table (DONE - 2019-11-25 - Hiram) cd ~/kent/src/hg/makeDb/trackDb/criGri/regenCho1 # preview prefixes and suffixes: hgsql -N -e "select frag from gold;" regenCho1 \ | sed -e 's/[0-9_FR]\+//;' | sort | uniq -c 1 chrM 7659 pi 33 pisub 3 pisuba 3 pisubb 51824 ss @@ -513,195 +539,193 @@ searchTable gold shortCircuit 1 termRegex [cps][his]+(sub)?[rM0-9]+(_[ab0-9FR]+)? 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 - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/repeatMasker cd /hive/data/genomes/regenCho1/bed/repeatMasker time (doRepeatMasker.pl -buildDir=`pwd` \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -smallClusterHub=ku regenCho1) > do.log 2>&1 & -XXX - running - Mon Nov 25 15:35:50 PST 2019 - # real 48m25.181s + # real 518m50.143s cat faSize.rmsk.txt -#2762428432 bases (227617579 N's 2534810853 real 1422483022 upper -# 1112327831 lower) in 6846 sequences in 1 files -#Total size: mean 403509.8 sd 6476189.8 min 101 (pi012238F) -# max 248247500 (ss100001) median 10668 -# %40.27 masked total, %43.88 masked real +# 2531519022 bases (265206282 N's 2266312740 real 1530161366 upper +# 736151374 lower) in 7812 sequences in 1 files +# Total size: mean 324055.2 sd 6387461.2 min 105 (pi011564F) +# max 240360982 (ss100001) median 12236 +# %29.08 masked total, %32.48 masked real egrep -i "versi|relea" do.log # RepeatMasker version development-$Id: RepeatMasker,v 1.332 2017/04/17 19:01:11 rhubley Exp $ # February 01 2017 (open-4-0-8) 1.332 version of RepeatMasker # grep RELEASE /hive/data/staging/data/RepeatMasker/Libraries/RepeatMaskerLib.embl # CC Dfam_Consensus RELEASE 20181026; * time featureBits -countGaps regenCho1 rmsk - # 1112341443 bases of 2762428432 (40.267%) in intersection - # real 0m35.822s + # 736157955 bases of 2531519022 (29.080%) in intersection + # real 0m29.036s # 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;' regenCho1 \ | bedSingleCover.pl stdin | ave -col=4 stdin | grep "^total" - # total 1112341443.000000 - # real 0m20.990s + # total 736157955.000000 + # real 0m18.986s ########################################################################## # running simple repeat (DONE - 2019-11-25 - Hiram) # The '-trf409 4' is a bit smaller than human which is 6 mkdir /hive/data/genomes/regenCho1/bed/simpleRepeat cd /hive/data/genomes/regenCho1/bed/simpleRepeat time (doSimpleRepeat.pl -buildDir=`pwd` -bigClusterHub=ku \ -dbHost=hgwdev -workhorse=hgwdev -smallClusterHub=ku \ -trf409=4 regenCho1) > do.log 2>&1 & -XXX - running - Mon Nov 25 15:36:08 PST 2019 - # real 58m3.288s + # real 17m24.592s cat fb.simpleRepeat - # 91165405 bases of 2534810853 (3.597%) in intersection + # 68344927 bases of 2266312740 (3.016%) in intersection cd /hive/data/genomes/regenCho1 # when using the Window Masker result: cd /hive/data/genomes/regenCho1 # twoBitMask bed/windowMasker/regenCho1.cleanWMSdust.2bit \ # -add bed/simpleRepeat/trfMask.bed regenCho1.2bit # you can safely ignore the warning about fields >= 13 # or using the rmsk result after it is done: twoBitMask regenCho1.rmsk.2bit \ -add bed/simpleRepeat/trfMask.bed regenCho1.2bit # you can safely ignore the warning about fields >= 13 twoBitToFa regenCho1.2bit stdout | faSize stdin > faSize.regenCho1.2bit.txt - cat faSize.regenCho1.2bit.txt -# 2762428432 bases (227617579 N's 2534810853 real 1418746093 upper -# 1116064760 lower) in 6846 sequences in 1 files -# Total size: mean 403509.8 sd 6476189.8 min 101 (pi012238F) -# max 248247500 (ss100001) median 10668 -# %40.40 masked total, %44.03 masked real + cat faSize.regenCho1.2bit.txt | sed -e 's/^/# /;' +# 2531519022 bases (265206282 N's 2266312740 real 1528440046 upper +# 737872694 lower) in 7812 sequences in 1 files +# Total size: mean 324055.2 sd 6387461.2 min 105 (pi011564F) +# max 240360982 (ss100001) median 12236 +# %29.15 masked total, %32.56 masked real rm /gbdb/regenCho1/regenCho1.2bit ln -s `pwd`/regenCho1.2bit /gbdb/regenCho1/regenCho1.2bit ######################################################################### -# CREATE MICROSAT TRACK (TBD - 2019-06-29 - Hiram) +# CREATE MICROSAT TRACK (DONE - 2019-11-26 - Hiram) ssh hgwdev mkdir /cluster/data/regenCho1/bed/microsat cd /cluster/data/regenCho1/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 regenCho1 microsat microsat.bed - # Read 228853 elements of size 4 from microsat.bed + # Read 226558 elements of size 4 from microsat.bed ########################################################################## -## WINDOWMASKER (TBD - 2019-11-25 - Hiram) +## WINDOWMASKER (DONE - 2019-11-26 - Hiram) # wait for RepeatMasker to finish before this, since this is going # to compare itself with the rmsk result mkdir /hive/data/genomes/regenCho1/bed/windowMasker cd /hive/data/genomes/regenCho1/bed/windowMasker time (doWindowMasker.pl -buildDir=`pwd` -workhorse=hgwdev \ -dbHost=hgwdev regenCho1) > do.log 2>&1 - # real 26m58.753s + # real 132m19.374s # Masking statistics cat faSize.regenCho1.cleanWMSdust.txt -# 2762428432 bases (227617579 N's 2534810853 real 1629368138 upper -# 905442715 lower) in 6846 sequences in 1 files -# Total size: mean 403509.8 sd 6476189.8 min 101 (pi012238F) -# max 248247500 (ss100001) median 10668 -# %32.78 masked total, %35.72 masked real +# 2531519022 bases (265206282 N's 2266312740 real 1539053551 upper +# 727259189 lower) in 7812 sequences in 1 files +# Total size: mean 324055.2 sd 6387461.2 min 105 (pi011564F) +# max 240360982 (ss100001) median 12236 +# %28.73 masked total, %32.09 masked real cat fb.regenCho1.rmsk.windowmaskerSdust.txt - # 696560115 bases of 2762428432 (25.215%) in intersection + # 432987841 bases of 2531519022 (17.104%) in intersection ########################################################################## -# cpgIslands - (TBD - 2019-06-29 - Hiram) +# cpgIslands - (DONE - 2019-11-26 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/cpgIslands cd /hive/data/genomes/regenCho1/bed/cpgIslands time (doCpgIslands.pl -dbHost=hgwdev -bigClusterHub=ku \ -workhorse=hgwdev -smallClusterHub=ku regenCho1) > do.log 2>&1 - # real 3m59.256s + # real 3m34.486s cat fb.regenCho1.cpgIslandExt.txt - # 10317331 bases of 2534810853 (0.407%) in intersection + # 11992730 bases of 2266312740 (0.529%) in intersection ############################################################################## -# genscan - (TBD - 2019-06-29 - Hiram) +# genscan - (DONE - 2019-11-26 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/genscan cd /hive/data/genomes/regenCho1/bed/genscan time (doGenscan.pl -buildDir=`pwd` -workhorse=hgwdev -dbHost=hgwdev \ -bigClusterHub=ku regenCho1) > do.log 2>&1 +XXX - running - Tue Nov 26 10:15:46 PST 2019 # real 126m0.077s cat fb.regenCho1.genscan.txt # 54712419 bases of 2534810853 (2.158%) in intersection cat fb.regenCho1.genscanSubopt.txt # 56830306 bases of 2534810853 (2.242%) in intersection ######################################################################### # Create kluster run files (TBD - 2019-06-29 - Hiram) # numerator is regenCho1 gapless bases "real" as reported by: featureBits -noRandom -noHap regenCho1 gap - # 227617579 bases of 2534810853 (8.980%) in intersection + # 265206282 bases of 2266312740 (11.702%) 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 \( 2534810853 / 2861349177 \) \* 1024 - # ( 2534810853 / 2861349177 ) * 1024 = 907.140706 + calc \( 2266312740 / 2861349177 \) \* 1024 + # ( 2266312740 / 2861349177 ) * 1024 = 811.052445 - # ==> use -repMatch=350 according to size scaled down from 1024 for human. + # ==> use -repMatch=800 according to size scaled down from 1024 for human. # and rounded down to nearest 50 cd /hive/data/genomes/regenCho1 blat regenCho1.2bit \ /dev/null /dev/null -tileSize=11 -makeOoc=jkStuff/regenCho1.11.ooc \ - -repMatch=900 - # Wrote 29409 overused 11-mers to jkStuff/regenCho1.11.ooc - # rn6 was repMatch 1000 and: - # Wrote 27021 overused 11-mers to jkStuff/rn6.11.ooc - # rn5 at repMatch 950: Wrote 34513 overused 11-mers to jkStuff/rn5.11.ooc - + -repMatch=800 + # Wrote 24088 overused 11-mers to jkStuff/regenCho1.11.ooc + # criGriChoV2 was repMatch 850 and: + # Wrote 22423 overused 11-mers to jkStuff/criGriChoV2.11.ooc # check non-bridged gaps to see what the typical size is: hgsql -N \ -e 'select * from gap where bridge="no" order by size;' regenCho1 \ | sort -k7,7nr | ave -col=7 stdin - # min 51690.000000 - # max 136961.000000 + # min 52599.000000 + # max 165458.000000 gapToLift -verbose=2 -minGap=50000 regenCho1 jkStuff/nonBridged.lift \ -bedFile=jkStuff/nonBridged.bed wc -l jkStuff/nonBri* - # 6866 jkStuff/nonBridged.bed - # 6866 jkStuff/nonBridged.lift + # 7832 jkStuff/nonBridged.bed + # 7832 jkStuff/nonBridged.lift ######################################################################## # lastz/chain/net swap human/hg38 (TBD - 2019-11-25 - Hiram) # original alignment cd /hive/data/genomes/hg38/bed/lastzRegenCho1.2019-11-25 cat fb.hg38.chainRegenCho1Link.txt # 154079940 bases of 3095998939 (4.977%) in intersection cat fb.hg38.chainSynRegenCho1Link.txt # 95877644 bases of 3095998939 (3.097%) in intersection cat fb.hg38.chainRBest.RegenCho1.txt # 106665747 bases of 3095998939 (3.445%) in intersection # and for the swap: mkdir /hive/data/genomes/regenCho1/bed/blastz.hg38.swap @@ -746,90 +770,95 @@ /hive/data/genomes/mm10/bed/lastzRegenCho1.2019-11-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 6m41.043s cat fb.regenCho1.chainMm10Link.txt # 88539346 bases of 1055588482 (8.388%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` regenCho1 mm10) > rbest.log 2>&1 & # real 94m11.007s cat fb.regenCho1.chainRBest.Mm10.txt # 79474812 bases of 1055588482 (7.529%) in intersection -######################################################################### -# GENBANK AUTO UPDATE (TBD - 2019-06-29 - Hiram) +############################################################################## +# GENBANK AUTO UPDATE (DONE - 2019-11-26 - Hiram) ssh hgwdev cd $HOME/kent/src/hg/makeDb/genbank git pull # /cluster/data/genbank/data/organism.lst shows: # #organism mrnaCnt estCnt refSeqCnt - # Rattus norvegicus 130197 1103594 17642 - - # edit etc/genbank.conf to add regenCho1 just before galGal5 - -# regenCho1 (Regeneron rat assembly) + # Cricetulus barabensis 34 2 0 + # Cricetulus griseus 90146 12 344 + # Cricetulus longicaudatus 58 0 0 + # Cricetulus migratorius 18 0 0 + # Cricetulus sp. 36 0 0 + + # edit etc/genbank.conf to add regenCho1 just before criGriChoV2 +# regenCho1 (Cricetulus griseus - Chinese hamster ovary cell line CHO-K1) regenCho1.serverGenome = /hive/data/genomes/regenCho1/regenCho1.2bit regenCho1.ooc = /hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc regenCho1.lift = /hive/data/genomes/regenCho1/jkStuff/nonBridged.lift -regenCho1.refseq.mrna.native.pslCDnaFilter = ${finished.refseq.mrna.native.pslCDnaFilter} -regenCho1.refseq.mrna.xeno.pslCDnaFilter = ${finished.refseq.mrna.xeno.pslCDnaFilter} -regenCho1.genbank.mrna.native.pslCDnaFilter = ${finished.genbank.mrna.native.pslCDnaFilter} -regenCho1.genbank.mrna.xeno.pslCDnaFilter = ${finished.genbank.mrna.xeno.pslCDnaFilter} -regenCho1.genbank.est.native.pslCDnaFilter = ${finished.genbank.est.native.pslCDnaFilter} regenCho1.downloadDir = regenCho1 -regenCho1.refseq.mrna.xeno.load = yes -regenCho1.refseq.mrna.xeno.loadDesc = yes -regenCho1.genbank.mrna.xeno.load = yes regenCho1.perChromTables = no -regenCho1.mgc = yes +regenCho1.refseq.mrna.native.pslCDnaFilter = ${ordered.refseq.mrna.native.pslCDnaFilter} +regenCho1.refseq.mrna.xeno.pslCDnaFilter = ${ordered.refseq.mrna.xeno.pslCDnaFilter} +regenCho1.genbank.mrna.native.pslCDnaFilter = ${ordered.genbank.mrna.native.pslCDnaFilter} +regenCho1.genbank.mrna.xeno.pslCDnaFilter = ${ordered.genbank.mrna.xeno.pslCDnaFilter} +regenCho1.genbank.est.native.pslCDnaFilter = ${ordered.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 # regenCho1.upstreamGeneTbl = ensGene -# regenCho1.upstreamMaf = multiz13way /hive/data/genomes/regenCho1/bed/multiz13way/species.list.txt +# regenCho1.upstreamMaf = multiz9way /hive/data/genomes/regenCho1/bed/multiz9way/species.list # verify the files specified exist before checking in the file: grep ^regenCho1 etc/genbank.conf | grep hive | awk '{print $NF}' | xargs ls -og -# -rw-rw-r-- 1 247657 Jun 29 17:16 /hive/data/genomes/regenCho1/jkStuff/nonBridged.lift -# -rw-rw-r-- 1 117644 Jun 29 17:13 /hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc -# -rw-rw-r-- 1 720490674 Jun 29 16:59 /hive/data/genomes/regenCho1/regenCho1.2bit +# -rw-rw-r-- 1 283099 Nov 26 11:49 /hive/data/genomes/regenCho1/jkStuff/nonBridged.lift +# -rw-rw-r-- 1 96360 Nov 26 10:19 /hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc +# -rw-rw-r-- 1 661068165 Nov 26 10:12 /hive/data/genomes/regenCho1/regenCho1.2bit - git commit -m "Added regenCho1 - Regeneron rat refs #21579" etc/genbank.conf + git commit -m "Added regenCho1 - Regeneron CHO refs #24568" 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 regenCho1 to: # etc/align.dbs etc/hgwdev.dbs git add etc/align.dbs etc/hgwdev.dbs - git commit -m "Added regenCho1 - Regeneron rat refs #21579" etc/hgwdev.dbs + git commit -m "Added regenCho1 - Regeneron CHO refs #24568" 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 - 2019-06-29 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/augustus cd /hive/data/genomes/regenCho1/bed/augustus time (doAugustus.pl -buildDir=`pwd` -bigClusterHub=ku \ -species=human -dbHost=hgwdev \ -workhorse=hgwdev regenCho1) > do.log 2>&1 +XXX - running - Tue Nov 26 10:15:46 PST 2019 # real 194m56.414s cat fb.regenCho1.augustusGene.txt # 48867584 bases of 2534810853 (1.928%) in intersection ######################################################################### # ncbiRefSeq (TBD - 2019-11-25 - Hiram) mkdir /hive/data/genomes/regenCho1/bed/ncbiRefSeq cd /hive/data/genomes/regenCho1/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_other Gallus_gallus \ @@ -865,90 +894,51 @@ # this makes the 'protein' link disappear from the gene details page # curious that this gene is marked as a non-coding gene anyway ? # gene: FET1 at chr4:63,102,774-63,105,516- featureBits -enrichment regenCho1 refGene ncbiRefSeq # refGene 1.374%, ncbiRefSeq 8.397%, both 1.370%, cover 99.73%, enrich 11.88x featureBits -enrichment regenCho1 ncbiRefSeq refGene # ncbiRefSeq 8.397%, refGene 1.374%, both 1.370%, cover 16.32%, enrich 11.88x featureBits -enrichment regenCho1 ncbiRefSeqCurated refGene # ncbiRefSeqCurated 1.368%, refGene 1.374%, both 1.364%, cover 99.71%, enrich 72.59x featureBits -enrichment regenCho1 refGene ncbiRefSeqCurated # refGene 1.374%, ncbiRefSeqCurated 1.368%, both 1.364%, cover 99.32%, enrich 72.59x ######################################################################### -# LIFTOVER TO rn6 (TBD - 2019-06-29 - Hiram) +# LIFTOVER TO criGriChoV2 (DONE - 2019-11-26 - Hiram) ssh hgwdev - mkdir /hive/data/genomes/regenCho1/bed/blat.rn6.2019-06-29 - cd /hive/data/genomes/regenCho1/bed/blat.rn6.2019-06-29 + mkdir /hive/data/genomes/regenCho1/bed/blat.criGriChoV2.2019-11-26 + cd /hive/data/genomes/regenCho1/bed/blat.criGriChoV2.2019-11-26 doSameSpeciesLiftOver.pl -verbose=2 \ -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc \ - regenCho1 rn6 + regenCho1 criGriChoV2 time (doSameSpeciesLiftOver.pl -verbose=2 \ -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ -ooc=/hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc \ - regenCho1 rn6) > doLiftOverToRn6.log 2>&1 + regenCho1 criGriChoV2) > doLiftOverToRn6.log 2>&1 +XXX - running - Tue Nov 26 10:21:21 PST 2019 # about 3 hours 20 minutes # see if the liftOver menus function in the browser from regenCho1 to galGal5 # would like to see this as a track: time chainToPsl regenCho1ToRn6.over.chain.gz ../../chrom.sizes \ /hive/data/genomes/rn6/chrom.sizes ../../regenCho1.2bit \ /hive/data/genomes/rn6/regenCho1.2bit regenCho1ToRn6.psl -XXX - running - Mon Jul 1 13:33:33 PDT 2019 - -######################################################################### -# LIFTOVER TO regenRn1 (TBD - 2019-09-09 - Hiram) - ssh hgwdev - mkdir /hive/data/genomes/regenCho1/bed/blat.regenRn1.2019-09-09 - cd /hive/data/genomes/regenCho1/bed/blat.regenRn1.2019-09-09 - doSameSpeciesLiftOver.pl -verbose=2 \ - -debug -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ - -ooc=/hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc \ - regenCho1 regenRn1 - time (doSameSpeciesLiftOver.pl -verbose=2 \ - -bigClusterHub=ku -dbHost=hgwdev -workhorse=hgwdev \ - -ooc=/hive/data/genomes/regenCho1/jkStuff/regenCho1.11.ooc \ - regenCho1 regenRn1) > doLiftOverToRegenRn1.log 2>&1 - # real 248m28.261s - - # see if the liftOver menus function in the browser from regenCho1 to regenRn1 - - # would like to see this as a track: - hgLoadChain regenCho1 chainRegenRn1 regenCho1ToRegenRn1.over.chain.gz - # Loading 71615 chains into regenCho1.chainRegenRn1 - - chainSort regenCho1ToRegenRn1.over.chain.gz stdout \ - | chainPreNet stdin \ - /hive/data/genomes/regenCho1/chrom.sizes \ - /hive/data/genomes/regenRn1/chrom.sizes stdout \ - | chainNet stdin -minSpace=1 /hive/data/genomes/regenCho1/chrom.sizes \ - /hive/data/genomes/regenRn1/chrom.sizes stdout /dev/null \ - | netSyntenic stdin noClass.net - - netClass -verbose=0 -noAr noClass.net regenCho1 regenRn1 regenCho1.regenRn1.net - - netFilter -minGap=10 regenCho1.regenRn1.net \ - | hgLoadNet -verbose=0 regenCho1 netRegenRn1 stdin - - featureBits regenCho1 chainRegenRn1Link > fb.regenCho1.chainRegenRn1Link.txt 2>&1 - - cat fb.regenCho1.chainRegenRn1Link.txt - # 2436426341 bases of 2534810853 (96.119%) in intersection ######################################################################### # BLATSERVERS ENTRY (TBD - 2019-11-25 - 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 ("regenCho1", "blat1a", "17892", "1", "0"); \ INSERT INTO blatServers (db, host, port, isTrans, canPcr) \ VALUES ("regenCho1", "blat1a", "17893", "0", "1");' \ hgcentraltest # test it with some sequence ############################################################################ ## reset default position to MEPE gene (egg shell protein) @@ -1010,35 +1000,36 @@ # real 307m41.143s ######################################################################### # all.joiner update, downloads and in pushQ - (TBD - 2018-10-17 - Hiram) xyz cd $HOME/kent/src/hg/makeDb/schema # verify all the business is done for release ~/kent/src/hg/utils/automation/verifyBrowser.pl regenCho1 # fixup all.joiner until this is a clean output joinerCheck -database=regenCho1 -tableCoverage all.joiner joinerCheck -database=regenCho1 -times all.joiner joinerCheck -database=regenCho1 -keys all.joiner # when clean, check in: - git commit -m 'adding rules for regenCho1 refs #22113' all.joiner + git commit -m 'adding rules for regenCho1 refs #24568' all.joiner git push # run up a 'make alpha' in hg/hgTables to get this all.joiner file # into the hgwdev/genome-test system +XXX - ready when tracks are done - Tue Nov 26 13:35:39 PST 2019 cd /hive/data/genomes/regenCho1 time (makeDownloads.pl regenCho1) > downloads.log 2>&1 # real 10m7.605s # now ready for pushQ entry mkdir /hive/data/genomes/regenCho1/pushQ cd /hive/data/genomes/regenCho1/pushQ time (makePushQSql.pl -redmineList regenCho1) > regenCho1.pushQ.sql 2> stderr.out # real 9m58.779s # remove the extra chainNet files from the listings: sed -i -e "/etNig1/d" redmine.regenCho1.file.list sed -i -e "/asAcu1/d" redmine.regenCho1.file.list sed -i -e "/etNig1/d" redmine.regenCho1.table.list sed -i -e "/onAlb1/d" redmine.regenCho1.table.list