b8a0cff9eb03810570fe87d6dfc36e8ab3b2ad45 jnavarr5 Mon Sep 16 11:46:47 2024 -0700 Making liftOver chains for a MLQ, refs #34395 diff --git src/hg/makeDb/doc/asmHubs/lastzRuns.txt src/hg/makeDb/doc/asmHubs/lastzRuns.txt index 74f30b5..f02a726 100644 --- src/hg/makeDb/doc/asmHubs/lastzRuns.txt +++ src/hg/makeDb/doc/asmHubs/lastzRuns.txt @@ -2871,15 +2871,173 @@ # 1437058753 bases of 1992663268 (72.117%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ -query2bit="/hive/data/genomes/asmHubs/GCF/002/263/795/GCF_002263795.3/GCF_002263795.3.2bit" \ -querySizes="/hive/data/genomes/asmHubs/GCF/002/263/795/GCF_002263795.3/GCF_002263795.3.chrom.sizes.txt" \ -target2bit="/hive/data/genomes/asmHubs/GCF/000/767/855/GCF_000767855.1/GCF_000767855.1.2bit" \ -targetSizes="/hive/data/genomes/asmHubs/GCF/000/767/855/GCF_000767855.1/GCF_000767855.1.chrom.sizes.txt" \ GCF_000767855.1 GCF_002263795.3) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 204m42.533s sed -e 's/^/ # /;' fb.GCF_000767855.1.chainRBest.GCF_002263795.3.txt # 1444586026 bases of 1992663268 (72.495%) in intersection ############################################################################## +############################################################################## +# LASTZ carabao GCF_029407905.1 vs. water buffalo GCF_019923935.1 +# (DONE - 2024-09-13 - jairo) + + mkdir /hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 + cd /hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 + + printf '# water buffalo GCF_019923935.1 vs. carabao GCF_029407905.1 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: carabao 2023-03-31 GCF_029407905.1_PCC_UOA_SB_1v2 +SEQ1_DIR=/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.2bit +SEQ1_LEN=/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.chrom.sizes.txt +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=40 + +# QUERY: water buffalo 2021-09-10 GCF_019923935.1_NDDB_SH_1 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -tAsmId GCF_029407905.1_PCC_UOA_SB_1v2 -qAsmId GCF_019923935.1_NDDB_SH_1 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 885m53.106s + + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainGCF_019923935.1Link.txt + # 2656984138 bases of 2898492518 (91.668%) in intersection + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainSynGCF_019923935.1Link.txt + # 2641684883 bases of 2898492518 (91.140%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + -target2Bit="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.chrom.sizes.txt" \ + -query2Bit="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.chrom.sizes.txt" \ + GCF_029407905.1 GCF_019923935.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m39.417s + + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainRBest.GCF_019923935.1.txt + # 2596886253 bases of 2898492518 (89.594%) in intersection + + ### and for the swap +# swap into: /hive/data/genomes/asmHubs/allBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1/trackData/blastz.GCF_029407905.1.swap +# running /hive/data/genomes/asmHubs/allBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1/trackData/blastz.GCF_029407905.1.swap/runSwap.sh ++ cd /hive/data/genomes/asmHubs/refseqBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1 ++ export defaultName=GCF_019923935.1_NDDB_SH_1 ++ defaultName=GCF_019923935.1_NDDB_SH_1 ++ export asmId=GCF_019923935.1_NDDB_SH_1 ++ asmId=GCF_019923935.1_NDDB_SH_1 ++ export buildDir=/hive/data/genomes/asmHubs/refseqBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1 ++ buildDir=/hive/data/genomes/asmHubs/refseqBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1 ++ rm -f GCF_019923935.1_NDDB_SH_1.chromAlias.txt ++ ln -s trackData/chromAlias/GCF_019923935.1_NDDB_SH_1.chromAlias.txt . ++ '[' -s trackData/chromAlias/GCF_019923935.1_NDDB_SH_1.chromAlias.bb ']' ++ rm -f GCF_019923935.1_NDDB_SH_1.chromAlias.bb ++ ln -s trackData/chromAlias/GCF_019923935.1_NDDB_SH_1.chromAlias.bb . ++ /cluster/home/jairo/kent/src/hg/utils/automation/asmHubTrackDb.sh GCF_019923935.1_NDDB_SH_1 GCF_019923935.1_NDDB_SH_1 /hive/data/genomes/asmHubs/refseqBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1 +# no ensGene found +composite chainNet +############################################################################## +# LASTZ carabao GCF_029407905.1 vs. water buffalo GCF_019923935.1 +# (DONE - 2024-09-13 - jairo) + + mkdir /hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 + cd /hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 + + printf '# water buffalo GCF_019923935.1 vs. carabao GCF_029407905.1 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: carabao 2023-03-31 GCF_029407905.1_PCC_UOA_SB_1v2 +SEQ1_DIR=/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.2bit +SEQ1_LEN=/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.chrom.sizes.txt +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=40 + +# QUERY: water buffalo 2021-09-10 GCF_019923935.1_NDDB_SH_1 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -tAsmId GCF_029407905.1_PCC_UOA_SB_1v2 -qAsmId GCF_019923935.1_NDDB_SH_1 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 885m53.106s + + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainGCF_019923935.1Link.txt + # 2656984138 bases of 2898492518 (91.668%) in intersection + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainSynGCF_019923935.1Link.txt + # 2641684883 bases of 2898492518 (91.140%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + -target2Bit="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.chrom.sizes.txt" \ + -query2Bit="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.chrom.sizes.txt" \ + GCF_029407905.1 GCF_019923935.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m39.417s + + sed -e 's/^/ # /;' fb.GCF_029407905.1.chainRBest.GCF_019923935.1.txt + # 2596886253 bases of 2898492518 (89.594%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCF/019/923/935/GCF_019923935.1_NDDB_SH_1/trackData/blastz.GCF_029407905.1.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -tAsmId GCF_029407905.1_PCC_UOA_SB_1v2 -qAsmId GCF_019923935.1_NDDB_SH_1 /hive/data/genomes/asmHubs/allBuild/GCF/029/407/905/GCF_029407905.1_PCC_UOA_SB_1v2/trackData/lastzGCF_019923935.1.2024-09-13/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 339m15.873s + + sed -e 's/^/ # /;' fb.GCF_019923935.1.chainGCF_029407905.1Link.txt + # 2608426896 bases of 2622460639 (99.465%) in intersection + sed -e 's/^/ # /;' fb.GCF_019923935.1.chainSynGCF_029407905.1Link.txt + # 2600500347 bases of 2622460639 (99.163%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + -query2bit="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCF/029/407/905/GCF_029407905.1/GCF_029407905.1.chrom.sizes.txt" \ + -target2bit="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCF/019/923/935/GCF_019923935.1/GCF_019923935.1.chrom.sizes.txt" \ + GCF_019923935.1 GCF_029407905.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 91m43.292s + + sed -e 's/^/ # /;' fb.GCF_019923935.1.chainRBest.GCF_029407905.1.txt + # 2597306727 bases of 2622460639 (99.041%) in intersection + +############################################################################## + +real 1396m44.789s +user 0m4.932s +sys 0m5.466s