d29dd0c1d169ab64eb4a07913120740e0ea179b9 hiram Thu Oct 17 10:23:41 2019 -0700 lastz/chain/net runs for 7-way alignment refs #21579 diff --git src/hg/makeDb/doc/regenRn1/lastzRuns.txt src/hg/makeDb/doc/regenRn1/lastzRuns.txt new file mode 100644 index 0000000..92bfb0d --- /dev/null +++ src/hg/makeDb/doc/regenRn1/lastzRuns.txt @@ -0,0 +1,269 @@ +######################################################################### +# LASTZ rat/regenRn1 vs rabbit/oryCun2 - (DONE - 2019-10-11 - Hiram) + mkdir /hive/data/genomes/regenRn1/bed/lastzOryCun2.2019-10-11 + cd /hive/data/genomes/regenRn1/bed/lastzOryCun2.2019-10-11 + + printf '# Rat vs. rabbit +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz + +# TARGET: Rat Rn6 +SEQ1_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit +SEQ1_LEN=/hive/data/genomes/regenRn1/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=15 + +# QUERY: rabbit oryCun2 +SEQ2_DIR=/hive/data/genomes/oryCun2/oryCun2.2bit +SEQ2_LEN=/hive/data/genomes/oryCun2/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=20 + +BASE=/hive/data/genomes/regenRn1/bed/lastzOryCun2.2019-10-11 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku -noDbNameCheck \ + -smallClusterHub=hgwdev -chainMinScore=3000 -chainLinearGap=medium \ + -syntenicNet) > do.log 2>&1 + # real 184m23.050s + + cat fb.regenRn1.chainOryCun2Link.txt + # 586652448 bases of 2282482188 (25.702%) in intersection + + cat fb.regenRn1.chainSynOryCun2Link.txt + # 539247828 bases of 2282482188 (23.625%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 oryCun2) > rbest.log 2>&1 & + # real 268m49.478s + + cat fb.regenRn1.chainRBest.OryCun2.txt + # 558355463 bases of 2282482188 (24.463%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/oryCun2/bed/blastz.regenRn1.swap + cd /hive/data/genomes/oryCun2/bed/blastz.regenRn1.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/regenRn1/bed/lastzOryCun2.2019-10-11/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 34m44.321s + + cat fb.oryCun2.chainRegenRn1Link.txt + # 594376030 bases of 2604023284 (22.825%) in intersection + cat fb.oryCun2.chainSynRegenRn1Link.txt + # 537850488 bases of 2604023284 (20.655%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` oryCun2 regenRn1) > rbest.log 2>&1 + # real 287m55.750s + + cat fb.oryCun2.chainRBest.RegenRn1.txt + # 557937174 bases of 2604023284 (21.426%) in intersection + +######################################################################### +# LASTZ rat/regenRn1 vs pig/susScr11 - (DONE - 2019-10-14 - Hiram) + mkdir /hive/data/genomes/regenRn1/bed/lastzSusScr11.2019-10-14 + cd /hive/data/genomes/regenRn1/bed/lastzSusScr11.2019-10-14 + + printf '# Rat vs. pig +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz + +# TARGET: Rat Rn6 +SEQ1_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit +SEQ1_LEN=/hive/data/genomes/regenRn1/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=5 + +# QUERY: pig susScr11 +SEQ2_DIR=/hive/data/genomes/susScr11/susScr11.2bit +SEQ2_LEN=/hive/data/genomes/susScr11/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=5 + +BASE=/hive/data/genomes/regenRn1/bed/lastzSusScr11.2019-10-14 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku -noDbNameCheck \ + -smallClusterHub=hgwdev -chainMinScore=3000 -chainLinearGap=medium \ + -syntenicNet) > do.log 2>&1 + # real 226m34.300s + + cat fb.regenRn1.chainSusScr11Link.txt + # 642554959 bases of 2282482188 (28.152%) in intersection + + cat fb.regenRn1.chainSynSusScr11Link.txt + # 606015870 bases of 2282482188 (26.551%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 susScr11) > rbest.log 2>&1 & + # real 224m31.973s + + cat fb.regenRn1.chainRBest.SusScr11.txt + # 614448249 bases of 2282482188 (26.920%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/susScr11/bed/blastz.regenRn1.swap + cd /hive/data/genomes/susScr11/bed/blastz.regenRn1.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/regenRn1/bed/lastzSusScr11.2019-10-14/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 43m19.318s + + cat fb.susScr11.chainRegenRn1Link.txt + # 635932961 bases of 2472073034 (25.725%) in intersection + cat fb.susScr11.chainSynRegenRn1Link.txt + # 605094540 bases of 2472073034 (24.477%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` susScr11 regenRn1) > rbest.log 2>&1 + # real 195m27.050s + + cat fb.susScr11.chainRBest.RegenRn1.txt + # 613864682 bases of 2472073034 (24.832%) in intersection + +######################################################################## + LASTZ rat/regenRn1 vs dog/canFam3 - (DONE - 2019-10-14 - Hiram) + mkdir /hive/data/genomes/regenRn1/bed/lastzCanFam3.2019-10-14 + cd /hive/data/genomes/regenRn1/bed/lastzCanFam3.2019-10-14 + + printf '# Rat vs. dog +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz + +# TARGET: Rat Rn6 +SEQ1_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit +SEQ1_LEN=/hive/data/genomes/regenRn1/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=5 + +# QUERY: dog canFam3 +SEQ2_DIR=/hive/data/genomes/canFam3/canFam3.2bit +SEQ2_LEN=/hive/data/genomes/canFam3/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=25 + +BASE=/hive/data/genomes/regenRn1/bed/lastzCanFam3.2019-10-14 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku -noDbNameCheck \ + -smallClusterHub=hgwdev -chainMinScore=3000 -chainLinearGap=medium \ + -syntenicNet) > do.log 2>&1 + # real 219m7.084s + + cat fb.regenRn1.chainCanFam3Link.txt + # 678205600 bases of 2282482188 (29.714%) in intersection + + cat fb.regenRn1.chainSynCanFam3Link.txt + # 644550064 bases of 2282482188 (28.239%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 canFam3) > rbest.log 2>&1 & + # real 186m51.804s + + cat fb.regenRn1.chainRBest.CanFam3.txt + # 651971618 bases of 2282482188 (28.564%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/canFam3/bed/blastz.regenRn1.swap + cd /hive/data/genomes/canFam3/bed/blastz.regenRn1.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/regenRn1/bed/lastzCanFam3.2019-10-14/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 39m44.272s + + cat fb.canFam3.chainRegenRn1Link.txt + # 672809905 bases of 2392715236 (28.119%) in intersection + cat fb.canFam3.chainSynRegenRn1Link.txt + # 642327040 bases of 2392715236 (26.845%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` canFam3 regenRn1) > rbest.log 2>&1 + # real 162m51.212s + + cat fb.canFam3.chainRBest.RegenRn1.txt + # 651196229 bases of 2392715236 (27.216%) in intersection + +######################################################################### + LASTZ rat/regenRn1 vs crab-eating macaque/macFas5 - (DONE - 2019-10-14 - Hiram) + mkdir /hive/data/genomes/regenRn1/bed/lastzMacFas5.2019-10-14 + cd /hive/data/genomes/regenRn1/bed/lastzMacFas5.2019-10-14 + + printf '# Rat vs. crab-eating macaque +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz + +# TARGET: Rat Rn6 +SEQ1_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit +SEQ1_LEN=/hive/data/genomes/regenRn1/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=5 + +# QUERY: crab-eating macaque macFas5 +SEQ2_DIR=/hive/data/genomes/macFas5/macFas5.2bit +SEQ2_LEN=/hive/data/genomes/macFas5/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=25 + +BASE=/hive/data/genomes/regenRn1/bed/lastzMacFas3.2019-10-14 +TMPDIR=/dev/shm +' > DEF + +# note mistake in BASE directory name, changed directory name after +# the run was complete, and the DEF file was altered to MacFas5 +# and the symlinks fixed in htdocs-hgdownload + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku -noDbNameCheck \ + -smallClusterHub=hgwdev -chainMinScore=3000 -chainLinearGap=medium \ + -syntenicNet) > do.log 2>&1 + # real 256m56.897s + + cat fb.regenRn1.chainMacFas5Link.txt + # 815551694 bases of 2282482188 (35.731%) in intersection + + cat fb.regenRn1.chainSynMacFas5Link.txt + # 774681241 bases of 2282482188 (33.940%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 macFas5) > rbest.log 2>&1 & + # real 282m53.369s + + cat fb.regenRn1.chainRBest.MacFas5.txt + # 782563616 bases of 2282482188 (34.286%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/macFas5/bed/blastz.regenRn1.swap + cd /hive/data/genomes/macFas5/bed/blastz.regenRn1.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/regenRn1/bed/lastzMacFas5.2019-10-14/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 55m38.846s + + cat fb.macFas5.chainRegenRn1Link.txt + # 811540597 bases of 2803866698 (28.944%) in intersection + cat fb.macFas5.chainSynRegenRn1Link.txt + # 771643309 bases of 2803866698 (27.521%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` macFas5 regenRn1) > rbest.log 2>&1 + # real 271m41.030s + + cat fb.macFas5.chainRBest.RegenRn1.txt + # 781449190 bases of 2803866698 (27.870%) in intersection + +#########################################################################