6091558bab452de0ba020f3e08a9d20ef9aa3d81 hiram Wed Mar 18 19:09:58 2020 -0700 lastz runs for 12-way alignment on danRer10 per research request no redmine diff --git src/hg/makeDb/doc/xenTro9/lastzRuns.txt src/hg/makeDb/doc/xenTro9/lastzRuns.txt index 2985ac2..d83b3c9 100644 --- src/hg/makeDb/doc/xenTro9/lastzRuns.txt +++ src/hg/makeDb/doc/xenTro9/lastzRuns.txt @@ -1,425 +1,491 @@ ######################################################################### # Tibetan frog/nanPar1 Lastz run (DONE - 2017-03-30 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/lastzNanPar1.2017-03-30 cd /hive/data/genomes/xenTro9/bed/lastzNanPar1.2017-03-30 printf '# X. tropicalis vs. Nanorana parkeri - Tibetan frog BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 # QUERY: Nanorana parkeri - Tibetan frog - nanPar1 SEQ2_DIR=/hive/data/genomes/nanPar1/nanPar1.2bit SEQ2_LEN=/hive/data/genomes/nanPar1/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/xenTro9/bed/lastzNanPar1.2017-03-30 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -syntenicNet) > do.log 2>&1 # real 282m18.989s cat fb.xenTro9.chainNanPar1Link.txt # 112048590 bases of 1369865365 (8.180%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 nanPar1) \ > rbest.log 2>&1 & # real 300m19.432s # running the swap mkdir /hive/data/genomes/nanPar1/bed/blastz.xenTro9.swap cd /hive/data/genomes/nanPar1/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/xenTro9/bed/lastzNanPar1.2017-03-30/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 28m46.600s cat fb.nanPar1.chainXenTro9Link.txt # 132516087 bases of 1977771384 (6.700%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` nanPar1 xenTro9) \ > rbest.log 2>&1 # real 282m18.000s ######################################################################### # African clawed frog/xenLae2 Lastz run (DONE - 2017-04-03 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/lastzXenLae2.2017-04-03 cd /hive/data/genomes/xenTro9/bed/lastzXenLae2.2017-04-03 printf '# X. tropicalis vs. Xenopus laevis - African clawed frog BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=100 # QUERY: Xenopus laevis - African clawed frog - xenLae2 SEQ2_DIR=/hive/data/genomes/xenLae2/xenLae2.2bit SEQ2_LEN=/hive/data/genomes/xenLae2/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/xenTro9/bed/lastzXenLae2.2017-04-03 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -syntenicNet) > do.log 2>&1 & # real 4062m36.015s cat fb.xenTro9.chainXenLae2Link.txt # 751739555 bases of 1369865365 (54.877%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 xenLae2) \ > rbest.log 2>&1 & # real 3339m16.984s # running the swap mkdir /hive/data/genomes/xenLae2/bed/blastz.xenTro9.swap cd /hive/data/genomes/xenLae2/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/xenTro9/bed/lastzXenLae2.2017-04-03/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 1547m40.071s # broke down during load chains, lots and lots of them, continuing: time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/xenTro9/bed/lastzXenLae2.2017-04-03/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -continue=download -syntenicNet) > download.log 2>&1 & # real 24m32.130s cat fb.xenLae2.chainXenTro9Link.txt # 1107603590 bases of 2408724787 (45.983%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenLae2 xenTro9) \ > rbest.log 2>&1 # real 6008m44.551s ######################################################################### # chicken/galGal5 Lastz run (DONE - 2017-04-07 - Hiram) mkdir /hive/data/genomes/xenTro9/bed/lastzGalGal5.2017-04-07 cd /hive/data/genomes/xenTro9/bed/lastzGalGal5.2017-04-07 printf '# X. tropicalis vs. Gallus gallus - chicken BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=100 # QUERY: Gallus gallus - chicken - galGal5 SEQ2_DIR=/hive/data/genomes/galGal5/galGal5.2bit SEQ2_LEN=/hive/data/genomes/galGal5/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LIMIT=150 SEQ2_LAP=0 BASE=/hive/data/genomes/xenTro9/bed/lastzGalGal5.2017-04-07 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -syntenicNet) > do.log 2>&1 & # real 89m28.631s cat fb.xenTro9.chainGalGal5Link.txt # 46400669 bases of 1369865365 (3.387%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 galGal5) \ > rbest.log 2>&1 & # real 114m23.753s # running the swap mkdir /hive/data/genomes/galGal5/bed/blastz.xenTro9.swap cd /hive/data/genomes/galGal5/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/xenTro9/bed/lastzGalGal5.2017-04-07/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 5m30.479s cat fb.galGal5.chainXenTro9Link.txt # 43878637 bases of 1218501075 (3.601%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` galGal5 xenTro9) \ > rbest.log 2>&1 # real 105m25.032s ######################################################################### # fugu/fr3 Lastz run (DONE - 2017-04-07 - Hiram) # establish a screen to control this job with a name to indicate what it is screen -S xenTro9Fr3 mkdir /hive/data/genomes/xenTro9/bed/lastzFr3.2017-04-07 cd /hive/data/genomes/xenTro9/bed/lastzFr3.2017-04-07 printf '# X. tropicalis vs. fugu BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=100 # QUERY: fugu fr3 SEQ2_DIR=/scratch/data/fr3/fr3.2bit SEQ2_LEN=/scratch/data/fr3/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LAP=0 SEQ2_LIMIT=30 BASE=/hive/data/genomes/xenTro9/bed/lastzFr3.2017-04-07 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet -chainMinScore=5000 -chainLinearGap=loose) > do.log 2>&1 & # real 55m16.105s cat fb.xenTro9.chainFr3Link.txt # 51739752 bases of 1369865365 (3.777%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 fr3) \ > rbest.log 2>&1 & # real 162m7.854s # and for the swap mkdir /hive/data/genomes/fr3/bed/blastz.xenTro9.swap cd /hive/data/genomes/fr3/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 -syntenicNet \ /hive/data/genomes/xenTro9/bed/lastzFr3.2017-04-07/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 & # real 5m38.419s cat fb.fr3.chainXenTro9Link.txt # 44999126 bases of 350961831 (12.822%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` fr3 xenTro9) \ > rbest.log 2>&1 & # real 155m25.885s ######################################################################### # lizard/anoCar2 Lastz run (DONE - 2017-04-07 - Hiram) # establish a screen to control this job with a name to indicate what it is screen -S xenTro9AnoCar2 mkdir /hive/data/genomes/xenTro9/bed/lastzAnoCar2.2017-04-07 cd /hive/data/genomes/xenTro9/bed/lastzAnoCar2.2017-04-07 printf '# X. tropicalis vs. lizard BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=100 # QUERY: lizard anoCar2 SEQ2_DIR=/hive/data/genomes/anoCar2/anoCar2.2bit SEQ2_LEN=/hive/data/genomes/anoCar2/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LAP=0 SEQ2_LIMIT=30 BASE=/hive/data/genomes/xenTro9/bed/lastzAnoCar2.2017-04-07 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet -chainMinScore=5000 -chainLinearGap=loose) > do.log 2>&1 & # real 121m27.998s cat fb.xenTro9.chainAnoCar2Link.txt # 81882044 bases of 1369865365 (5.977%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 anoCar2) \ > rbest.log 2>&1 & # real 361m17.474s # and for the swap mkdir /hive/data/genomes/anoCar2/bed/blastz.xenTro9.swap cd /hive/data/genomes/anoCar2/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 -syntenicNet \ /hive/data/genomes/xenTro9/bed/lastzAnoCar2.2017-04-07/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 & # real 13m27.766s cat fb.anoCar2.chainXenTro9Link.txt # 81560791 bases of 1701353770 (4.794%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` anoCar2 xenTro9) \ > rbest.log 2>&1 & # real 361m17.474s ######################################################################### # lastz chainNet swap canFam3/dog (DONE - 2017-04-06 - Hiram) # original alignment cd /hive/data/genomes/canFam3/bed/lastzXenTro9.2017-04-05 cat fb.canFam3.chainXenTro9Link.txt # 73335538 bases of 2392715236 (3.065%) in intersection # and the swap mkdir /hive/data/genomes/xenTro9/bed/blastz.canFam3.swap cd /hive/data/genomes/xenTro9/bed/blastz.canFam3.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/canFam3/bed/lastzXenTro9.2017-04-05/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 # real 11m49.432s cat fb.xenTro9.chainCanFam3Link.txt # 45357837 bases of 1369865365 (3.311%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 canFam3) \ > rbest.log 2>&1 # real 131m41.477s ############################################################################## # painted turtle/chrPic2 Lastz run (DONE - 2017-04-07 - Hiram) # establish a screen to control this job with a name to indicate what it is screen -S xenTro9ChrPic2 mkdir /hive/data/genomes/xenTro9/bed/lastzChrPic2.2017-04-07 cd /hive/data/genomes/xenTro9/bed/lastzChrPic2.2017-04-07 printf '# X. tropicalis vs. painted turtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # TARGET: X. tropicalis xenTro9 SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=50 # QUERY: painted turtle chrPic2 SEQ2_DIR=/hive/data/genomes/chrPic2/chrPic2.2bit SEQ2_LEN=/hive/data/genomes/chrPic2/chrom.sizes SEQ2_CHUNK=10000000 SEQ2_LAP=0 SEQ2_LIMIT=400 BASE=/hive/data/genomes/xenTro9/bed/lastzChrPic2.2017-04-07 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet -chainMinScore=5000 -chainLinearGap=loose) > do.log 2>&1 & # real 87m24.954s cat fb.xenTro9.chainChrPic2Link.txt # 88481334 bases of 1369865365 (6.459%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 chrPic2) \ > rbest.log 2>&1 & # real 214m30.935s # and for the swap mkdir /hive/data/genomes/chrPic2/bed/blastz.xenTro9.swap cd /hive/data/genomes/chrPic2/bed/blastz.xenTro9.swap time (doBlastzChainNet.pl -verbose=2 -syntenicNet \ /hive/data/genomes/xenTro9/bed/lastzChrPic2.2017-04-07/DEF \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 & # real 20m40.608s cat fb.chrPic2.chainXenTro9Link.txt # 108165726 bases of 2173204089 (4.977%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` chrPic2 xenTro9) \ > rbest.log 2>&1 & # about 1.5 hours # had to finish the recipBest step manually due to network interruption, # then continuing: time (doRecipBest.pl -continue=download -workhorse=hgwdev \ -buildDir=`pwd` chrPic2 xenTro9) > rbest.download.log 2>&1 & ############################################################################## # swap lastz chainNet opossum/monDom5 (DONE - 2017-04-07 - Hiram) # original alignment cd /hive/data/genomes/monDom5/bed/lastzXenTro9.2017-04-05 cat fb.monDom5.chainXenTro9Link.txt # 77656334 bases of 3501660299 (2.218%) in intersection # and the swap mkdir /hive/data/genomes/xenTro9/bed/blastz.monDom5.swap cd /hive/data/genomes/xenTro9/bed/blastz.monDom5.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/monDom5/bed/lastzXenTro9.2017-04-05/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 # real 63m13.594s cat fb.xenTro9.chainMonDom5Link.txt # 74164292 bases of 1369865365 (5.414%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 monDom5) \ > rbest.log 2>&1 & # real 798m41.569s ############################################################################ # swap chainNet/lastz monDom5/Opossum (DONE - 2017-04-07 - Hiram) # alignment to monDom5 cd /hive/data/genomes/monDom5/bed/lastzXenTro9.2017-04-05 cat fb.monDom5.chainXenTro9Link.txt # 77656334 bases of 3501660299 (2.218%) in intersection # and the swap mkdir /hive/data/genomes/xenTro9/bed/blastz.monDom5.swap cd /hive/data/genomes/xenTro9/bed/blastz.monDom5.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/monDom5/bed/lastzXenTro9.2017-04-05/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 # real 63m13.594s cat fb.xenTro9.chainMonDom5Link.txt # 74164292 bases of 1369865365 (5.414%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 monDom5) \ > rbest.log 2>&1 & # real 798m41.569s -############################################################################ +############################################################################## +# zebrafish/danRer10 Lastz run (DONE - 2020-02-25 - Hiram) + mkdir /hive/data/genomes/xenTro9/bed/lastzDanRer10.2020-02-25 + cd /hive/data/genomes/xenTro9/bed/lastzDanRer10.2020-02-25 + + printf '# X. tropicalis vs. zebrafish +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz +BLASTZ_Y=3400 +BLASTZ_L=6000 +BLASTZ_K=2200 +BLASTZ_Q=/cluster/data/blastz/HoxD55.q + +# TARGET: X. tropicalis xenTro9 +SEQ1_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit +SEQ1_LEN=/hive/data/genomes/xenTro9/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=50 + +# QUERY: zebrafish danRer10 +SEQ2_DIR=/hive/data/genomes/danRer10/danRer10.2bit +SEQ2_LEN=/hive/data/genomes/danRer10/chrom.sizes +SEQ2_CHUNK=10000000 +SEQ2_LAP=0 +SEQ2_LIMIT=400 + +BASE=/hive/data/genomes/xenTro9/bed/lastzDanRer10.2020-02-25 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet -chainMinScore=5000 -chainLinearGap=loose) > do.log 2>&1 & + # real 352m56.937s + + cat fb.xenTro9.chainDanRer10Link.txt + # 96287465 bases of 1369865365 (7.029%) in intersection + + cat fb.xenTro9.chainSynDanRer10Link.txt + # 14698582 bases of 1369865365 (1.073%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + xenTro9 danRer10) > rbest.log 2>&1 & + # real 199m53.878s + + # and for the swap + mkdir /hive/data/genomes/danRer10/bed/blastz.xenTro9.swap + cd /hive/data/genomes/danRer10/bed/blastz.xenTro9.swap + time (doBlastzChainNet.pl -verbose=2 -syntenicNet \ + /hive/data/genomes/xenTro9/bed/lastzDanRer10.2020-02-25/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -swap -chainMinScore=5000 -chainLinearGap=loose) > swap.log 2>&1 & + # real 23m32.189s + + cat fb.danRer10.chainXenTro9Link.txt + # 92191324 bases of 1369683683 (6.731%) in intersection + cat fb.danRer10.chainSynXenTro9Link.txt + # 15810671 bases of 1369683683 (1.154%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + danRer10 xenTro9) > rbest.log 2>&1 & + # real 221m8.515s + + cat fb.danRer10.chainRBest.XenTro9.txt + # 54642559 bases of 1369683683 (3.989%) in intersection + +##############################################################################