86543de97fd1c1f6d8c3c34e23109ffc3703cf82 hiram Mon Jun 15 10:39:41 2020 -0700 starting lastz chain net to panPan3 refs #25720 diff --git src/hg/makeDb/doc/mm10.txt src/hg/makeDb/doc/mm10.txt index 4dee6ba..56315a2 100644 --- src/hg/makeDb/doc/mm10.txt +++ src/hg/makeDb/doc/mm10.txt @@ -17660,31 +17660,30 @@ BASE=/hive/data/genomes/mm10/bed/lastzCanFam4.2020-04-02 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 & # real 483m10.607s cat fb.mm10.chainCanFam4Link.txt # 777883731 bases of 2652783500 (29.323%) in intersection cat fb.mm10.chainSynCanFam4Link.txt # 736602602 bases of 2652783500 (27.767%) in intersection - time (doRecipBest.pl -load -workhorse=hgwdev mm10 canFam4 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 219m16.168s cat fb.mm10.chainRBest.CanFam4.txt # 741307883 bases of 2652783500 (27.945%) in intersection mkdir /hive/data/genomes/canFam4/bed/blastz.mm10.swap cd /hive/data/genomes/canFam4/bed/blastz.mm10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm10/bed/lastzCanFam4.2020-04-02/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & # real 50m20.639s @@ -17820,16 +17819,81 @@ # score using zscore, min(zscore*100),1000), and reformat awk '{OFS="\t"; print $1, $2, $3, $4, ($13>10)? 1000 : int($13 * 100), $6, $7, $8, $9, $10, $13}' \ ccres.prescored.bed | bedSort stdin ccres.scored.bed set f = encodeCcreCombined # Reformat to add fields for filtering and mouseover, etc. set bin = ~/kent/src/hg/makeDb/outside/encode3/ccre perl $bin/makeCcreCombined.pl < ccres.scored.bed > $f.bed set lib = ~/kent/src/hg/lib bedToBigBed -tab -type=bed9+6 -as=$lib/$f.as $f.bed /hive/data/genomes/mm10/chrom.sizes $f.bb mkdir -p /gbdb/mm10/encode3/ccre ln -s `pwd`/$f.bb /gbdb/mm10/encode3/ccre ############################################################################## +# LASTZ mouse/mm10 bonobo/panPan3 - (DONE - 2020-06-15 - Hiram) + mkdir /hive/data/genomes/mm10/bed/lastzPanPan3.2020-06-15 + cd /hive/data/genomes/mm10/bed/lastzPanPan3.2020-06-15 + printf '# mouse vs bonobo +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz +BLASTZ_M=254 + +# TARGET: Mouse Mm10 +SEQ1_DIR=/hive/data/genomes/mm10/mm10.2bit +SEQ1_LEN=/hive/data/genomes/mm10/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +# the default matrix is: +# A C G T +# A 91 -114 -31 -123 +# C -114 100 -125 -31 +# G -31 -125 100 -114 +# T -123 -31 -114 91 + +# QUERY: bonobo panPan3 +SEQ2_DIR=/hive/data/genomes/panPan3/panPan3.2bit +SEQ2_LEN=/hive/data/genomes/panPan3/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LIMIT=30 +SEQ2_LAP=0 + +BASE=/hive/data/genomes/mm10/bed/lastzPanPan3.2020-06-15 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > do.log 2>&1 +XXX - running - Mon Jun 15 10:19:12 PDT 2020 + # real 360m9.534s + + cat fb.mm10.chainPanPan3Link.txt + # 928638440 bases of 2652783500 (35.006%) in intersection + cat fb.mm10.chainSynPanPan3Link.txt + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` mm10 panPan3) \ + > rbest.log 2>&1 & + # real 765m26.648s + cat fb.mm10.chainRBest.PanPan3.txt + + # and for the swap: + mkdir /hive/data/genomes/panPan3/bed/blastz.mm10.swap + cd /hive/data/genomes/panPan3/bed/blastz.mm10.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/mm10/bed/lastzPanPan3.2020-06-15/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 106m54.032s + + cat fb.panPan3.chainMm10Link.txt + # 911279510 bases of 2725937399 (33.430%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` panPan3 mm10) \ + > rbest.log 2>&1 + # real 620m0.039s + +##############################################################################