a7784bd524306cf2cb63fc2ae2a4bb0ea4258c34 hiram Mon Oct 26 10:02:43 2020 -0700 lastz chainNet mm39 rn6 rheMac10 per MarkD request no redmine diff --git src/hg/makeDb/doc/mm39/lastzRuns.txt src/hg/makeDb/doc/mm39/lastzRuns.txt index f76acdb..0666856 100644 --- src/hg/makeDb/doc/mm39/lastzRuns.txt +++ src/hg/makeDb/doc/mm39/lastzRuns.txt @@ -1,136 +1,267 @@ ############################################################################## # LASTZ Great Dane canFam5 (DONE - 2020-08-17 - Hiram) # establish a screen to control this job mkdir /hive/data/genomes/mm39/bed/lastzCanFam5.2020-08-17 cd /hive/data/genomes/mm39/bed/lastzCanFam5.2020-08-17 printf '# German shepard canFam5 vs mouse BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz BLASTZ_M=254 -# TARGET: Mouse Mm10 +# TARGET: Mouse Mm39 SEQ1_DIR=/hive/data/genomes/mm39/mm39.2bit SEQ1_LEN=/hive/data/genomes/mm39/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=40 # QUERY: German shepard canFam5 SEQ2_DIR=/hive/data/genomes/canFam5/canFam5.2bit SEQ2_LEN=/hive/data/genomes/canFam5/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/mm39/bed/lastzCanFam5.2020-08-17 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 & # real 200m16.271s cat fb.mm39.chainCanFam5Link.txt # 778327929 bases of 2654624157 (29.320%) in intersection cat fb.mm39.chainSynCanFam5Link.txt # 735515331 bases of 2654624157 (27.707%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev mm39 canFam5 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 213m30.572s cat fb.mm39.chainRBest.CanFam5.txt # 740738480 bases of 2654624157 (27.904%) in intersection mkdir /hive/data/genomes/canFam5/bed/blastz.mm39.swap cd /hive/data/genomes/canFam5/bed/blastz.mm39.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm39/bed/lastzCanFam5.2020-08-17/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & # real 44m12.732s cat fb.canFam5.chainMm39Link.txt # 762233776 bases of 2337131234 (32.614%) in intersection cat fb.canFam5.chainSynMm39Link.txt # 731337903 bases of 2337131234 (31.292%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev canFam5 mm39 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 174m14.398s cat fb.canFam5.chainRBest.Mm39.txt # 739648625 bases of 2337131234 (31.648%) in intersection ############################################################################## # LASTZ mouse mm39 vs marmoset calJac4 (DONE - 2020-09-04 - Hiram) # establish a screen to control this job mkdir /hive/data/genomes/mm39/bed/lastzCalJac4.2020-09-04 cd /hive/data/genomes/mm39/bed/lastzCalJac4.2020-09-04 printf '# mouse vs marmoset calJac4 BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz BLASTZ_M=254 # TARGET: Mouse Mm39 SEQ1_DIR=/hive/data/genomes/mm39/mm39.2bit SEQ1_LEN=/hive/data/genomes/mm39/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=40 # QUERY: marmoset calJac4 SEQ2_DIR=/hive/data/genomes/calJac4/calJac4.2bit SEQ2_LEN=/hive/data/genomes/calJac4/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/mm39/bed/lastzCalJac4.2020-09-04 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 & # real 269m7.515s cat fb.mm39.chainCalJac4Link.txt # 878425270 bases of 2654624157 (33.090%) in intersection cat fb.mm39.chainSynCalJac4Link.txt # 830808798 bases of 2654624157 (31.297%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev mm39 calJac4 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 342m45.296s cat fb.mm39.chainRBest.CalJac4.txt # 835984408 bases of 2654624157 (31.492%) in intersection mkdir /hive/data/genomes/calJac4/bed/blastz.mm39.swap cd /hive/data/genomes/calJac4/bed/blastz.mm39.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/mm39/bed/lastzCalJac4.2020-09-04/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 & # real 51m44.991s cat fb.calJac4.chainMm39Link.txt # 885334904 bases of 2859817025 (30.958%) in intersection cat fb.calJac4.chainSynMm39Link.txt # 831225065 bases of 2859817025 (29.066%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev calJac4 mm39 \ -buildDir=`pwd` -workhorse=hgwdev) > rbest.log 2>&1 & # real 298m22.974s cat fb.calJac4.chainRBest.Mm39.txt # 834211414 bases of 2859817025 (29.170%) in intersection ############################################################################## +# LASTZ Rat rn6 (DONE - 2020-10-20 - Hiram) + mkdir /hive/data/genomes/mm39/bed/lastzRn6.2020-10-20 + cd /hive/data/genomes/mm39/bed/lastzRn6.2020-10-20 + + printf '# rat vs mouse +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz +# TARGET: Mouse Mm39 +SEQ1_DIR=/hive/data/genomes/mm39/mm39.2bit +SEQ1_LEN=/hive/data/genomes/mm39/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 + +# QUERY: Rat Rn6 +SEQ2_DIR=/hive/data/genomes/rn6/rn6.2bit +SEQ2_LEN=/hive/data/genomes/rn6/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=500 + +BASE=/hive/data/genomes/mm39/bed/lastzRn6.2020-10-20 +TMPDIR=/dev/shm +' > DEF + + # establish a screen to control this job + screen -S mm39Rn6 + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 & + # real 364m51.738s + + cat fb.mm39.chainRn6Link.txt + # 1882154751 bases of 2654624157 (70.901%) in intersection + cat fb.mm39.chainSynRn6Link.txt + # 1758846483 bases of 2654624157 (66.256%) in intersection + + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + mm39 rn6) > rbest.log 2>&1 & + # real 580m33.404s + cat fb.mm39.chainRBest.Rn6.txt + # 1738608299 bases of 2654624157 (65.494%) in intersection + + mkdir /hive/data/genomes/rn6/bed/blastz.mm39.swap + cd /hive/data/genomes/rn6/bed/blastz.mm39.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/mm39/bed/lastzRn6.2020-10-20/DEF \ + -swap -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + # real 129m25.422s + + cat fb.rn6.chainMm39Link.txt + # 1940254184 bases of 2729860805 (71.075%) in intersection + cat fb.rn6.chainSynMm39Link.txt + # 1808524707 bases of 2729860805 (66.250%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + rn6 mm39) > rbest.log 2>&1 + # real 675m42.654s + + cat fb.rn6.chainRBest.Mm39.txt + # 1740516499 bases of 2729860805 (63.758%) in intersection + +############################################################################## +# LASTZ Rhesus rheMac10 (DONE - 2020-10-20 - Hiram) + mkdir /hive/data/genomes/mm39/bed/lastzRheMac10.2020-10-20 + cd /hive/data/genomes/mm39/bed/lastzRheMac10.2020-10-20 + + printf '# rhesus vs mouse +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz +# TARGET: Mouse Mm39 +SEQ1_DIR=/hive/data/genomes/mm39/mm39.2bit +SEQ1_LEN=/hive/data/genomes/mm39/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 + +# QUERY: Rhesus RheMac10 +SEQ2_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit +SEQ2_LEN=/hive/data/genomes/rheMac10/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=500 + +BASE=/hive/data/genomes/mm39/bed/lastzRheMac10.2020-10-20 +TMPDIR=/dev/shm +' > DEF + + # establish a screen to control this job + screen -S mm39RheMac10 + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 & + # real 243m13.015s + + cat fb.mm39.chainRheMac10Link.txt + # 924807390 bases of 2654624157 (34.838%) in intersection + cat fb.mm39.chainSynRheMac10Link.txt + # 878558648 bases of 2654624157 (33.095%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + mm39 rheMac10) > rbest.log 2>&1 & + # real 309m44.560s + + cat fb.mm39.chainRBest.RheMac10.txt + # 880466873 bases of 2654624157 (33.167%) in intersection + + + mkdir /hive/data/genomes/rheMac10/bed/blastz.mm39.swap + cd /hive/data/genomes/rheMac10/bed/blastz.mm39.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/mm39/bed/lastzRheMac10.2020-10-20/DEF \ + -swap -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 + # real 51m43.176s + + cat fb.rheMac10.chainMm39Link.txt + # 920110067 bases of 2936892733 (31.329%) in intersection + cat fb.rheMac10.chainSynMm39Link.txt + # 876443625 bases of 2936892733 (29.843%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + rheMac10 mm39) > rbest.log 2>&1 + # real 255m21.492s + + cat fb.rheMac10.chainRBest.Mm39.txt + # 879043885 bases of 2936892733 (29.931%) in intersection + +#########################################################################