2ec8bd4117dbc3240979b3f03020452bb96461c4 gperez2 Thu Feb 10 17:04:13 2022 -0800 kinetoplastids GCA_000340355.2 vs. kinetoplastids GCF_000002845.2 lastz/chain/net run for user, refs #28824 diff --git src/hg/makeDb/doc/asmHubs/lastzRuns.txt src/hg/makeDb/doc/asmHubs/lastzRuns.txt index fb4bf6b..2d08c55 100644 --- src/hg/makeDb/doc/asmHubs/lastzRuns.txt +++ src/hg/makeDb/doc/asmHubs/lastzRuns.txt @@ -1578,15 +1578,122 @@ -targetSizes="/hive/data/genomes/asmHubs/GCF/000/826/765/GCF_000826765.1/GCF_000826765.1.chrom.sizes.txt" \ GCF_000826765.1 GCF_011125445.2) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 73m55.254s sed -e 's/^/ # /;' fb.GCF_000826765.1.chainRBest.GCF_011125445.2.txt # 865608764 bases of 1021898560 (84.706%) in intersection ############################################################################## real 1621m36.194s user 0m2.046s sys 0m2.922s ############################################################################## +# LASTZ kinetoplastids GCA_000340355.2 vs. kinetoplastids GCF_000002845.2 (DONE - 2022-02-06 - Gerardo) + +# should be able to run this from anywhere, this time it was run from: + cd kent/src/hg/utils/automation + + time (~/kent/src/hg/utils/automation/pairLastz.sh \ + GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6 GCF_000002845.2_ASM284v2 other other) \ + > GCA_000340355_GCF_000002845_20220204.log 2>&1 & + # check the total time +grep -w real GCA_000340355_GCF_000002845_20220204.log | tail -1 | sed -e 's/^/ # /;' + # real 27m14.153s + + # this GCA_000340355_GCF_000002845_20220204.log log file happens to have a copy of the make doc, as well + # as the copy of the make doc left in the target assembly directory: +# /hive/data/genomes/asmHubs/allBuild/GCA/000/340/355/GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6/trackData/lastzGCF_000002845.2.2022-02-06/makeDoc.txt + + # this command outputs this makeDoc text: + + cat kent/src/hg/utils/automation/GCA_000340355_GCF_000002845_20220204.log + +############################################################################## +# LASTZ kinetoplastids GCA_000340355.2 vs. kinetoplastids GCF_000002845.2 +# (DONE - 2022-02-06 - Gerardo) + + mkdir /hive/data/genomes/asmHubs/allBuild/GCA/000/340/355/GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6/trackData/lastzGCF_000002845.2.2022-02-06 + cd /hive/data/genomes/asmHubs/allBuild/GCA/000/340/355/GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6/trackData/lastzGCF_000002845.2.2022-02-06 + + printf '# kinetoplastids GCF_000002845.2 vs. kinetoplastids GCA_000340355.2 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: kinetoplastids GCA_000340355.2 +SEQ1_DIR=/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.2bit +SEQ1_LEN=/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.chrom.sizes.txt +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=40 + +# QUERY: kinetoplastids GCF_000002845.2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/asmHubs/allBuild/GCA/000/340/355/GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6/trackData/lastzGCF_000002845.2.2022-02-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -tAsmId GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6 -qAsmId GCF_000002845.2_ASM284v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 21m44.561s + + sed -e 's/^/ # /;' fb.GCA_000340355.2.chainGCF_000002845.2Link.txt + # 31699291 bases of 35210150 (90.029%) in intersection + sed -e 's/^/ # /;' fb.GCA_000340355.2.chainSynGCF_000002845.2Link.txt + # 30406396 bases of 35210150 (86.357%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + -target2Bit="/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.chrom.sizes.txt" \ + -query2Bit="/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.chrom.sizes.txt" \ + GCA_000340355.2 GCF_000002845.2) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 1m2.843s + + sed -e 's/^/ # /;' fb.GCA_000340355.2.chainRBest.GCF_000002845.2.txt + # 30393628 bases of 35210150 (86.321%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCF/000/002/845/GCF_000002845.2_ASM284v2/trackData/blastz.GCA_000340355.2.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -tAsmId GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6 -qAsmId GCF_000002845.2_ASM284v2 /hive/data/genomes/asmHubs/allBuild/GCA/000/340/355/GCA_000340355.2_Leishmania_braziliensis_M2903-1.0.6/trackData/lastzGCF_000002845.2.2022-02-06/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 3m24.068s + + sed -e 's/^/ # /;' fb.GCF_000002845.2.chainGCA_000340355.2Link.txt + # 31582268 bases of 32068771 (98.483%) in intersection + sed -e 's/^/ # /;' fb.GCF_000002845.2.chainSynGCA_000340355.2Link.txt + # 30612946 bases of 32068771 (95.460%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + -query2bit="/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/000/340/355/GCA_000340355.2/GCA_000340355.2.chrom.sizes.txt" \ + -target2bit="/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCF/000/002/845/GCF_000002845.2/GCF_000002845.2.chrom.sizes.txt" \ + GCF_000002845.2 GCA_000340355.2) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 1m2.112s + + sed -e 's/^/ # /;' fb.GCF_000002845.2.chainRBest.GCA_000340355.2.txt + # 30310385 bases of 32068771 (94.517%) in intersection + +############################################################################## + +real 27m14.153s +user 0m1.233s +sys 0m1.147s