3bff517ce5a5210e0c7eb6f700b82eb0236f97f4 hiram Tue Nov 26 12:06:36 2019 -0800 chain/net hg38 to gorGor6 done refs #24524 diff --git src/hg/makeDb/doc/hg38/lastzRuns.txt src/hg/makeDb/doc/hg38/lastzRuns.txt index 72cae22..7af83b0 100644 --- src/hg/makeDb/doc/hg38/lastzRuns.txt +++ src/hg/makeDb/doc/hg38/lastzRuns.txt @@ -12231,15 +12231,167 @@ -syntenicNet) > swap.log 2>&1 # real 61m39.505s cat fb.rheMac10.chainHg38Link.txt # 2485840115 bases of 2936892733 (84.642%) in intersection cat fb.rheMac10.chainSynHg38Link.txt # 2465210442 bases of 2936892733 (83.939%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` rheMac10 hg38) > rbest.log 2>&1 # real 126m29.919s cat fb.rheMac10.chainRBest.Hg38.txt # 2424028492 bases of 2936892733 (82.537%) in intersection ######################################################################### +# LASTZ human/hg38 vs. rat/regenRn1 - (DONE - 2019-09-12 - Hiram) + mkdir /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 + cd /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 + + printf '# human vs rat +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz + +# TARGET: human hg38 +SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit +SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes +SEQ1_CTGDIR=/hive/data/genomes/hg38/hg38.contigs.2bit +SEQ1_CTGLEN=/hive/data/genomes/hg38/hg38.contigs.chrom.sizes +SEQ1_LIFT=/hive/data/genomes/hg38/jkStuff/hg38.contigs.lift +SEQ1_CHUNK=40000000 +SEQ1_LIMIT=30 +SEQ1_LAP=10000 + +# QUERY: rat regenRn1 +SEQ2_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit +SEQ2_LEN=/hive/data/genomes/regenRn1/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LIMIT=30 +SEQ2_LAP=0 + +BASE=/hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > do.log 2>&1 & + # real 162m40.237s + + cat fb.hg38.chainRegenRn1Link.txt + # 863041482 bases of 3095998939 (27.876%) in intersection + cat fb.hg38.chainSynRegenRn1Link.txt + # 809332351 bases of 3095998939 (26.141%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 regenRn1) > rbest.log 2>&1 & +XXX - running - Fri Sep 13 11:41:44 PDT 2019 + # real 328m4.069s + + cat fb.hg38.chainRBest.RegenRn1.txt + # 857127621 bases of 3095998939 (27.685%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/regenRn1/bed/blastz.hg38.swap + cd /hive/data/genomes/regenRn1/bed/blastz.hg38.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 63m47.773s + + cat fb.regenRn1.chainHg38Link.txt + # 827167139 bases of 2282482188 (36.240%) in intersection + cat fb.regenRn1.chainSynHg38Link.txt + # 788025130 bases of 2282482188 (34.525%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 hg38) > rbest.log 2>&1 +XXX - running - Fri Sep 13 12:07:31 PDT 2019 + # real 300m30.411s + + cat fb.regenRn1.chainRBest.Hg38.txt + # 858923025 bases of 2534810853 (33.885%) in intersection + +######################################################################### +# LASTZ human/hg38 Gorilla/gorGor6 - (DONE - 2019-11-20 - Hiram) + mkdir /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 + cd /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 + + printf '# human vs gorilla +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz +BLASTZ_T=2 +BLASTZ_O=600 +BLASTZ_E=150 +BLASTZ_M=254 +BLASTZ_K=4500 +BLASTZ_Y=15000 +BLASTZ_Q=/hive/data/staging/data/blastz/human_chimp.v2.q +# A C G T +# A 90 -330 -236 -356 +# C -330 100 -318 -236 +# G -236 -318 100 -330 +# T -356 -236 -330 90 + +# TARGET: human hg38 +SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit +SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_IN_CONTIGS=0 + +# QUERY: gorilla gorGor6 +SEQ2_DIR=/hive/data/genomes/gorGor6/gorGor6.2bit +SEQ2_LEN=/hive/data/genomes/gorGor6/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=50 + +BASE=/hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 +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 + # broken cluster run due to path name for BLASTZ_Q, continuing: + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -continue=cat -syntenicNet) > cat.log 2>&1 + # real 77m19.538s + + cat fb.hg38.chainGorGor6Link.txt + # 2908900659 bases of 3095998939 (93.957%) in intersection + cat fb.hg38.chainSynGorGor6Link.txt + # 2885980361 bases of 3095998939 (93.216%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 gorGor6) \ + > rbest.log 2>&1 & + # real 65m39.724s + + cat fb.hg38.chainRBest.GorGor6.txt + # 2693876207 bases of 3095998939 (87.012%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/gorGor6/bed/blastz.hg38.swap + cd /hive/data/genomes/gorGor6/bed/blastz.hg38.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20/DEF \ + -swap -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 63m46.473s + + cat fb.gorGor6.chainHg38Link.txt + # 2738870921 bases of 2999027915 (91.325%) in intersection + cat fb.gorGor6.chainSynHg38Link.txt + # 2728591501 bases of 2999027915 (90.983%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` gorGor6 hg38) \ + > rbest.log 2>&1 +XXX - running - Tue Nov 26 11:55:51 PST 2019 + # real 125m35.459s + +###########################################################################