0d6e74b5c4f8a5c5aa4465d6fb5551dec1fc3841 hiram Wed Apr 5 16:27:34 2023 -0700 catching up with completed lastz/chain/net refs #30912 diff --git src/hg/makeDb/doc/hg38/hprcLastz.txt src/hg/makeDb/doc/hg38/hprcLastz.txt index d367879..db17523 100644 --- src/hg/makeDb/doc/hg38/hprcLastz.txt +++ src/hg/makeDb/doc/hg38/hprcLastz.txt @@ -1466,15 +1466,1027 @@ sed -e 's/^/ # /;' fb.GCA_018472565.1.chainSynHg38Link.txt # 2869784047 bases of 3053585067 (93.981%) 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 79m55.124s sed -e 's/^/ # /;' fb.GCA_018472565.1.chainRBest.Hg38.txt # 2835964470 bases of 3053585067 (92.873%) in intersection ############################################################################## +# LASTZ Human Hg38 vs. human GCA_018504645.1 +# (DONE - 2023-04-04 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018504645.1.2023-04-04 + cd /hive/data/genomes/hg38/bed/lastzGCA_018504645.1.2023-04-04 + + printf '# human GCA_018504645.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-26 GCA_018504645.1_HG01109.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018504645.1.2023-04-04 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018504645.1_HG01109.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 203m4.556s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018504645.1Link.txt + # 2920217350 bases of 3299210039 (88.513%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018504645.1Link.txt + # 2915634332 bases of 3299210039 (88.374%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.chrom.sizes.txt" \ + hg38 GCA_018504645.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 81m18.405s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018504645.1.txt + # 2712395314 bases of 3299210039 (82.213%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/504/645/GCA_018504645.1_HG01109.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018504645.1_HG01109.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018504645.1.2023-04-04/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 130m58.222s + + sed -e 's/^/ # /;' fb.GCA_018504645.1.chainHg38Link.txt + # 2747539796 bases of 2921876128 (94.033%) in intersection + sed -e 's/^/ # /;' fb.GCA_018504645.1.chainSynHg38Link.txt + # 2742166983 bases of 2921876128 (93.850%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/504/645/GCA_018504645.1/GCA_018504645.1.chrom.sizes.txt" \ + GCA_018504645.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m24.687s + + sed -e 's/^/ # /;' fb.GCA_018504645.1.chainRBest.Hg38.txt + # 2711590537 bases of 2921876128 (92.803%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018471075.1 +# (DONE - 2023-04-04 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018471075.1.2023-04-04 + cd /hive/data/genomes/hg38/bed/lastzGCA_018471075.1.2023-04-04 + + printf '# human GCA_018471075.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018471075.1_HG01106.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018471075.1.2023-04-04 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018471075.1_HG01106.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 209m12.834s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018471075.1Link.txt + # 2920665557 bases of 3299210039 (88.526%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018471075.1Link.txt + # 2915808493 bases of 3299210039 (88.379%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.chrom.sizes.txt" \ + hg38 GCA_018471075.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m53.525s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018471075.1.txt + # 2711607125 bases of 3299210039 (82.190%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/471/075/GCA_018471075.1_HG01106.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018471075.1_HG01106.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018471075.1.2023-04-04/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 132m43.054s + + sed -e 's/^/ # /;' fb.GCA_018471075.1.chainHg38Link.txt + # 2744444887 bases of 2927007346 (93.763%) in intersection + sed -e 's/^/ # /;' fb.GCA_018471075.1.chainSynHg38Link.txt + # 2738739772 bases of 2927007346 (93.568%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/471/075/GCA_018471075.1/GCA_018471075.1.chrom.sizes.txt" \ + GCA_018471075.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 76m15.192s + + sed -e 's/^/ # /;' fb.GCA_018471075.1.chainRBest.Hg38.txt + # 2710147089 bases of 2927007346 (92.591%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018471065.1 +# (DONE - 2023-04-04 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018471065.1.2023-04-04 + cd /hive/data/genomes/hg38/bed/lastzGCA_018471065.1.2023-04-04 + + printf '# human GCA_018471065.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018471065.1_HG01175.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018471065.1.2023-04-04 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018471065.1_HG01175.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 166m0.387s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018471065.1Link.txt + # 3047883175 bases of 3299210039 (92.382%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018471065.1Link.txt + # 3043689722 bases of 3299210039 (92.255%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.chrom.sizes.txt" \ + hg38 GCA_018471065.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 69m45.945s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018471065.1.txt + # 2837540130 bases of 3299210039 (86.007%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/471/065/GCA_018471065.1_HG01175.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018471065.1_HG01175.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018471065.1.2023-04-04/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 115m9.563s + + sed -e 's/^/ # /;' fb.GCA_018471065.1.chainHg38Link.txt + # 2867069552 bases of 3030026811 (94.622%) in intersection + sed -e 's/^/ # /;' fb.GCA_018471065.1.chainSynHg38Link.txt + # 2861422546 bases of 3030026811 (94.436%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/471/065/GCA_018471065.1/GCA_018471065.1.chrom.sizes.txt" \ + GCA_018471065.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 69m34.161s + + sed -e 's/^/ # /;' fb.GCA_018471065.1.chainRBest.Hg38.txt + # 2835565461 bases of 3030026811 (93.582%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018504045.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018504045.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018504045.1.2023-04-05 + + printf '# human GCA_018504045.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-26 GCA_018504045.1_HG01243.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018504045.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018504045.1_HG01243.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 150m59.122s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018504045.1Link.txt + # 2919254671 bases of 3299210039 (88.483%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018504045.1Link.txt + # 2913695572 bases of 3299210039 (88.315%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.chrom.sizes.txt" \ + hg38 GCA_018504045.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 72m53.423s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018504045.1.txt + # 2709479193 bases of 3299210039 (82.125%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/504/045/GCA_018504045.1_HG01243.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018504045.1_HG01243.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018504045.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 119m46.883s + + sed -e 's/^/ # /;' fb.GCA_018504045.1.chainHg38Link.txt + # 2743073817 bases of 2908728425 (94.305%) in intersection + sed -e 's/^/ # /;' fb.GCA_018504045.1.chainSynHg38Link.txt + # 2737254676 bases of 2908728425 (94.105%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/504/045/GCA_018504045.1/GCA_018504045.1.chrom.sizes.txt" \ + GCA_018504045.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 72m42.690s + + sed -e 's/^/ # /;' fb.GCA_018504045.1.chainRBest.Hg38.txt + # 2706781589 bases of 2908728425 (93.057%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469405.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469405.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469405.1.2023-04-05 + + printf '# human GCA_018469405.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469405.1_HG01258.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469405.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469405.1_HG01258.pri.mat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 156m49.282s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469405.1Link.txt + # 3049729340 bases of 3299210039 (92.438%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469405.1Link.txt + # 3045207974 bases of 3299210039 (92.301%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.chrom.sizes.txt" \ + hg38 GCA_018469405.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m50.802s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469405.1.txt + # 2836720842 bases of 3299210039 (85.982%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/405/GCA_018469405.1_HG01258.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469405.1_HG01258.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018469405.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 126m38.759s + + sed -e 's/^/ # /;' fb.GCA_018469405.1.chainHg38Link.txt + # 2873269175 bases of 3032420282 (94.752%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469405.1.chainSynHg38Link.txt + # 2867398349 bases of 3032420282 (94.558%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/405/GCA_018469405.1/GCA_018469405.1.chrom.sizes.txt" \ + GCA_018469405.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m41.856s + + sed -e 's/^/ # /;' fb.GCA_018469405.1.chainRBest.Hg38.txt + # 2835173854 bases of 3032420282 (93.495%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469675.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469675.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469675.1.2023-04-05 + + printf '# human GCA_018469675.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469675.1_HG01258.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469675.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469675.1_HG01258.alt.pat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 162m37.126s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469675.1Link.txt + # 2920623841 bases of 3299210039 (88.525%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469675.1Link.txt + # 2915334531 bases of 3299210039 (88.365%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.chrom.sizes.txt" \ + hg38 GCA_018469675.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 76m17.382s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469675.1.txt + # 2711692640 bases of 3299210039 (82.192%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/675/GCA_018469675.1_HG01258.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469675.1_HG01258.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018469675.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 119m29.520s + + sed -e 's/^/ # /;' fb.GCA_018469675.1.chainHg38Link.txt + # 2742067216 bases of 2915178237 (94.062%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469675.1.chainSynHg38Link.txt + # 2736192130 bases of 2915178237 (93.860%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/675/GCA_018469675.1/GCA_018469675.1.chrom.sizes.txt" \ + GCA_018469675.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 72m13.307s + + sed -e 's/^/ # /;' fb.GCA_018469675.1.chainRBest.Hg38.txt + # 2708251212 bases of 2915178237 (92.902%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469685.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469685.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469685.1.2023-04-05 + + printf '# human GCA_018469685.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469685.1_HG01361.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469685.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469685.1_HG01361.pri.mat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 171m14.537s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469685.1Link.txt + # 3048195466 bases of 3299210039 (92.392%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469685.1Link.txt + # 3043159939 bases of 3299210039 (92.239%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.chrom.sizes.txt" \ + hg38 GCA_018469685.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 73m22.770s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469685.1.txt + # 2833943818 bases of 3299210039 (85.898%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/685/GCA_018469685.1_HG01361.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469685.1_HG01361.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018469685.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 123m21.537s + + sed -e 's/^/ # /;' fb.GCA_018469685.1.chainHg38Link.txt + # 2863544355 bases of 3025313608 (94.653%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469685.1.chainSynHg38Link.txt + # 2858105884 bases of 3025313608 (94.473%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/685/GCA_018469685.1/GCA_018469685.1.chrom.sizes.txt" \ + GCA_018469685.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m30.190s + + sed -e 's/^/ # /;' fb.GCA_018469685.1.chainRBest.Hg38.txt + # 2830977232 bases of 3025313608 (93.576%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469665.1 +# (DONE - 2023-04-04 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469665.1.2023-04-04 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469665.1.2023-04-04 + + printf '# human GCA_018469665.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469665.1_HG01123.pri.mat.f1_v2.1 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469665.1.2023-04-04 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469665.1_HG01123.pri.mat.f1_v2.1 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 213m6.351s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469665.1Link.txt + # 3048844569 bases of 3299210039 (92.411%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469665.1Link.txt + # 3044500979 bases of 3299210039 (92.280%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.chrom.sizes.txt" \ + hg38 GCA_018469665.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 85m45.377s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469665.1.txt + # 2836682774 bases of 3299210039 (85.981%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/665/GCA_018469665.1_HG01123.pri.mat.f1_v2.1/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469665.1_HG01123.pri.mat.f1_v2.1 /hive/data/genomes/hg38/bed/lastzGCA_018469665.1.2023-04-04/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 133m41.257s + + sed -e 's/^/ # /;' fb.GCA_018469665.1.chainHg38Link.txt + # 2865875487 bases of 3012822948 (95.123%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469665.1.chainSynHg38Link.txt + # 2860544697 bases of 3012822948 (94.946%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/665/GCA_018469665.1/GCA_018469665.1.chrom.sizes.txt" \ + GCA_018469665.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m1.738s + + sed -e 's/^/ # /;' fb.GCA_018469665.1.chainRBest.Hg38.txt + # 2834465468 bases of 3012822948 (94.080%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469865.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469865.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469865.1.2023-04-05 + + printf '# human GCA_018469865.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469865.1_HG01358.pri.mat.f1_v2.1 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469865.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469865.1_HG01358.pri.mat.f1_v2.1 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 168m13.600s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469865.1Link.txt + # 3047657353 bases of 3299210039 (92.375%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469865.1Link.txt + # 3043194543 bases of 3299210039 (92.240%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.chrom.sizes.txt" \ + hg38 GCA_018469865.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m3.311s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469865.1.txt + # 2838079272 bases of 3299210039 (86.023%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/865/GCA_018469865.1_HG01358.pri.mat.f1_v2.1/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469865.1_HG01358.pri.mat.f1_v2.1 /hive/data/genomes/hg38/bed/lastzGCA_018469865.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 123m12.696s + + sed -e 's/^/ # /;' fb.GCA_018469865.1.chainHg38Link.txt + # 2865143593 bases of 3029587694 (94.572%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469865.1.chainSynHg38Link.txt + # 2859636823 bases of 3029587694 (94.390%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/865/GCA_018469865.1/GCA_018469865.1.chrom.sizes.txt" \ + GCA_018469865.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 74m43.717s + + sed -e 's/^/ # /;' fb.GCA_018469865.1.chainRBest.Hg38.txt + # 2834353735 bases of 3029587694 (93.556%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469965.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469965.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469965.1.2023-04-05 + + printf '# human GCA_018469965.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018469965.1_HG01358.alt.pat.f1_v2.1 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469965.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469965.1_HG01358.alt.pat.f1_v2.1 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 143m44.220s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469965.1Link.txt + # 2920305964 bases of 3299210039 (88.515%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469965.1Link.txt + # 2915298077 bases of 3299210039 (88.364%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.chrom.sizes.txt" \ + hg38 GCA_018469965.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 76m41.070s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469965.1.txt + # 2712668877 bases of 3299210039 (82.222%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/965/GCA_018469965.1_HG01358.alt.pat.f1_v2.1/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469965.1_HG01358.alt.pat.f1_v2.1 /hive/data/genomes/hg38/bed/lastzGCA_018469965.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 112m18.392s + + sed -e 's/^/ # /;' fb.GCA_018469965.1.chainHg38Link.txt + # 2748397653 bases of 2932540871 (93.721%) in intersection + sed -e 's/^/ # /;' fb.GCA_018469965.1.chainSynHg38Link.txt + # 2742649822 bases of 2932540871 (93.525%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/965/GCA_018469965.1/GCA_018469965.1.chrom.sizes.txt" \ + GCA_018469965.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 76m24.412s + + sed -e 's/^/ # /;' fb.GCA_018469965.1.chainRBest.Hg38.txt + # 2710789449 bases of 2932540871 (92.438%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018467155.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018467155.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018467155.1.2023-04-05 + + printf '# human GCA_018467155.1 vs. Human Hg38 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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_LIMIT=40 + +# QUERY: human 2021-05-24 GCA_018467155.1_HG01891.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018467155.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018467155.1_HG01891.pri.mat.f1_v2 -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 167m43.516s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018467155.1Link.txt + # 3047773145 bases of 3299210039 (92.379%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018467155.1Link.txt + # 3042967052 bases of 3299210039 (92.233%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.chrom.sizes.txt" \ + hg38 GCA_018467155.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 69m46.717s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018467155.1.txt + # 2834653179 bases of 3299210039 (85.919%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/467/155/GCA_018467155.1_HG01891.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018467155.1_HG01891.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018467155.1.2023-04-05/DEF -swapDir=`pwd` \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + + grep -w real swap.log | sed -e 's/^/ # /;' + # real 125m58.945s + + sed -e 's/^/ # /;' fb.GCA_018467155.1.chainHg38Link.txt + # 2866986413 bases of 3022952778 (94.841%) in intersection + sed -e 's/^/ # /;' fb.GCA_018467155.1.chainSynHg38Link.txt + # 2861260988 bases of 3022952778 (94.651%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/467/155/GCA_018467155.1/GCA_018467155.1.chrom.sizes.txt" \ + GCA_018467155.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m35.492s + + sed -e 's/^/ # /;' fb.GCA_018467155.1.chainRBest.Hg38.txt + # 2832748344 bases of 3022952778 (93.708%) in intersection + +##############################################################################