166f7ceea61ae6355730d52f2ab9edf5b3542103 hiram Sun Apr 2 14:50:37 2023 -0700 record of lastz runs HPRC genomes to hg38 refs #30508 diff --git src/hg/makeDb/doc/hg38/hprcLastz.txt src/hg/makeDb/doc/hg38/hprcLastz.txt index 1168ce3..019da49 100644 --- src/hg/makeDb/doc/hg38/hprcLastz.txt +++ src/hg/makeDb/doc/hg38/hprcLastz.txt @@ -403,15 +403,335 @@ sed -e 's/^/ # /;' fb.GCA_018472565.1.chainSynHg38Link.txt # 2876160791 bases of 3053585067 (94.190%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ \ -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/565/GCA_018472565.1/GCA_018472565.1.2bit" \ -targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/565/GCA_018472565.1/GCA_018472565.1.chrom.sizes.txt" \ GCA_018472565.1 hg38) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 81m37.111s sed -e 's/^/ # /;' fb.GCA_018472565.1.chainRBest.Hg38.txt # 2839163719 bases of 3053585067 (92.978%) in intersection ############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472575.1 +# (DONE - 2023-03-31 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472575.1.2023-03-31 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472575.1.2023-03-31 + + printf '# human GCA_018472575.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# 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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018472575.1_HG00621.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472575.1.2023-03-31 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472575.1_HG00621.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 1656m19.999s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472575.1Link.txt + # 2930227171 bases of 3299210039 (88.816%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472575.1Link.txt + # 2919500649 bases of 3299210039 (88.491%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.chrom.sizes.txt" \ + hg38 GCA_018472575.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m49.485s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472575.1.txt + # 2712261274 bases of 3299210039 (82.209%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/575/GCA_018472575.1_HG00621.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472575.1_HG00621.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472575.1.2023-03-31/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 176m35.017s + + sed -e 's/^/ # /;' fb.GCA_018472575.1.chainHg38Link.txt + # 2749841756 bases of 2905948993 (94.628%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472575.1.chainSynHg38Link.txt + # 2740982328 bases of 2905948993 (94.323%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/575/GCA_018472575.1/GCA_018472575.1.chrom.sizes.txt" \ + GCA_018472575.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m18.079s + + sed -e 's/^/ # /;' fb.GCA_018472575.1.chainRBest.Hg38.txt + # 2711354036 bases of 2905948993 (93.304%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472585.1 +# (DONE - 2023-03-31 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472585.1.2023-03-31 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472585.1.2023-03-31 + + printf '# human GCA_018472585.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# 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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018472585.1_HG00673.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472585.1.2023-03-31 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472585.1_HG00673.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 1885m29.234s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472585.1Link.txt + # 2929448512 bases of 3299210039 (88.792%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472585.1Link.txt + # 2918442760 bases of 3299210039 (88.459%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.chrom.sizes.txt" \ + hg38 GCA_018472585.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 73m33.209s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472585.1.txt + # 2710429846 bases of 3299210039 (82.154%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/585/GCA_018472585.1_HG00673.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472585.1_HG00673.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472585.1.2023-03-31/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 178m21.195s + + sed -e 's/^/ # /;' fb.GCA_018472585.1.chainHg38Link.txt + # 2753693241 bases of 2925716157 (94.120%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472585.1.chainSynHg38Link.txt + # 2744516270 bases of 2925716157 (93.807%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/585/GCA_018472585.1/GCA_018472585.1.chrom.sizes.txt" \ + GCA_018472585.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m41.678s + + sed -e 's/^/ # /;' fb.GCA_018472585.1.chainRBest.Hg38.txt + # 2709952963 bases of 2925716157 (92.625%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018506975.1 +# (DONE - 2023-04-01 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018506975.1.2023-04-01 + cd /hive/data/genomes/hg38/bed/lastzGCA_018506975.1.2023-04-01 + + printf '# human GCA_018506975.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# 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_LIMIT=40 + +# QUERY: human 2021-05-26 GCA_018506975.1_HG00733.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018506975.1.2023-04-01 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018506975.1_HG00733.pri.mat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 715m15.369s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018506975.1Link.txt + # 3055939979 bases of 3299210039 (92.626%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018506975.1Link.txt + # 3049122190 bases of 3299210039 (92.420%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.chrom.sizes.txt" \ + hg38 GCA_018506975.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m55.110s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018506975.1.txt + # 2839289049 bases of 3299210039 (86.060%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/506/975/GCA_018506975.1_HG00733.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018506975.1_HG00733.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018506975.1.2023-04-01/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 185m40.016s + + sed -e 's/^/ # /;' fb.GCA_018506975.1.chainHg38Link.txt + # 2881236161 bases of 3026533161 (95.199%) in intersection + sed -e 's/^/ # /;' fb.GCA_018506975.1.chainSynHg38Link.txt + # 2873519502 bases of 3026533161 (94.944%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/506/975/GCA_018506975.1/GCA_018506975.1.chrom.sizes.txt" \ + GCA_018506975.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 83m22.954s + + sed -e 's/^/ # /;' fb.GCA_018506975.1.chainRBest.Hg38.txt + # 2839019594 bases of 3026533161 (93.804%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472765.1 +# (DONE - 2023-04-01 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472765.1.2023-04-01 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472765.1.2023-04-01 + + printf '# human GCA_018472765.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# 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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018472765.1_HG00735.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472765.1.2023-04-01 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472765.1_HG00735.pri.mat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 773m57.328s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472765.1Link.txt + # 3055677509 bases of 3299210039 (92.618%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472765.1Link.txt + # 3048544954 bases of 3299210039 (92.402%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.chrom.sizes.txt" \ + hg38 GCA_018472765.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m29.396s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472765.1.txt + # 2842418915 bases of 3299210039 (86.155%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/765/GCA_018472765.1_HG00735.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472765.1_HG00735.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472765.1.2023-04-01/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 186m20.625s + + sed -e 's/^/ # /;' fb.GCA_018472765.1.chainHg38Link.txt + # 2878517540 bases of 3037795105 (94.757%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472765.1.chainSynHg38Link.txt + # 2870375039 bases of 3037795105 (94.489%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/765/GCA_018472765.1/GCA_018472765.1.chrom.sizes.txt" \ + GCA_018472765.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 86m3.847s + + sed -e 's/^/ # /;' fb.GCA_018472765.1.chainRBest.Hg38.txt + # 2837794728 bases of 3037795105 (93.416%) in intersection + +##############################################################################