5ed537d9f4f1883a4596f278c9c13cb7816df964 hiram Thu Apr 6 15:07:58 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 bc90392..0d8ff05 100644 --- src/hg/makeDb/doc/hg38/hprcLastz.txt +++ src/hg/makeDb/doc/hg38/hprcLastz.txt @@ -2570,15 +2570,1119 @@ sed -e 's/^/ # /;' fb.GCA_018469705.1.chainSynHg38Link.txt # 2859768016 bases of 3010067136 (95.007%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ \ -target2bit="/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.2bit" \ -targetSizes="/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.chrom.sizes.txt" \ GCA_018469705.1 hg38) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 76m30.039s sed -e 's/^/ # /;' fb.GCA_018469705.1.chainRBest.Hg38.txt # 2835320194 bases of 3010067136 (94.195%) in intersection ############################################################################## +# LASTZ Human Hg38 vs. human GCA_018467165.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018467165.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018467165.1.2023-04-05 + + printf '# human GCA_018467165.1 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_018467165.1_HG01891.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018467165.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018467165.1_HG01891.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 159m31.347s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018467165.1Link.txt + # 3049116083 bases of 3299210039 (92.420%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018467165.1Link.txt + # 3044731829 bases of 3299210039 (92.287%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.chrom.sizes.txt" \ + hg38 GCA_018467165.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m38.348s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018467165.1.txt + # 2838013120 bases of 3299210039 (86.021%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/467/165/GCA_018467165.1_HG01891.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018467165.1_HG01891.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018467165.1.2023-04-05/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 125m4.249s + + sed -e 's/^/ # /;' fb.GCA_018467165.1.chainHg38Link.txt + # 2874312102 bases of 3043232268 (94.449%) in intersection + sed -e 's/^/ # /;' fb.GCA_018467165.1.chainSynHg38Link.txt + # 2868483040 bases of 3043232268 (94.258%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/467/165/GCA_018467165.1/GCA_018467165.1.chrom.sizes.txt" \ + GCA_018467165.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m4.728s + + sed -e 's/^/ # /;' fb.GCA_018467165.1.chainRBest.Hg38.txt + # 2836904281 bases of 3043232268 (93.220%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018505825.1 +# (DONE - 2023-04-06 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 + cd /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 + + printf '# human GCA_018505825.1 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_018505825.1_HG02109.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018505825.1_HG02109.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 159m28.473s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018505825.1Link.txt + # 3048266987 bases of 3299210039 (92.394%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018505825.1Link.txt + # 3044144120 bases of 3299210039 (92.269%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt" \ + hg38 GCA_018505825.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m14.803s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018505825.1.txt + # 2837240177 bases of 3299210039 (85.998%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/505/825/GCA_018505825.1_HG02109.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018505825.1_HG02109.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06/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 130m6.019s + + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainHg38Link.txt + # 2870938986 bases of 3026115826 (94.872%) in intersection + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainSynHg38Link.txt + # 2865131757 bases of 3026115826 (94.680%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt" \ + GCA_018505825.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m15.495s + + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainRBest.Hg38.txt + # 2835084887 bases of 3026115826 (93.687%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472705.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472705.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472705.1.2023-04-05 + + printf '# human GCA_018472705.1 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_018472705.1_HG01928.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472705.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472705.1_HG01928.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 163m14.294s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472705.1Link.txt + # 2920759025 bases of 3299210039 (88.529%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472705.1Link.txt + # 2915870383 bases of 3299210039 (88.381%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.chrom.sizes.txt" \ + hg38 GCA_018472705.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 73m53.132s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472705.1.txt + # 2710751652 bases of 3299210039 (82.164%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/705/GCA_018472705.1_HG01928.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472705.1_HG01928.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472705.1.2023-04-05/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 117m32.936s + + sed -e 's/^/ # /;' fb.GCA_018472705.1.chainHg38Link.txt + # 2743643391 bases of 2923053911 (93.862%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472705.1.chainSynHg38Link.txt + # 2737701220 bases of 2923053911 (93.659%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/705/GCA_018472705.1/GCA_018472705.1.chrom.sizes.txt" \ + GCA_018472705.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 67m3.576s + + sed -e 's/^/ # /;' fb.GCA_018472705.1.chainRBest.Hg38.txt + # 2708545372 bases of 2923053911 (92.661%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018471545.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018471545.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018471545.1.2023-04-05 + + printf '# human GCA_018471545.1 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_018471545.1_HG01952.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018471545.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018471545.1_HG01952.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 168m9.773s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018471545.1Link.txt + # 3048619956 bases of 3299210039 (92.405%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018471545.1Link.txt + # 3044170738 bases of 3299210039 (92.270%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.chrom.sizes.txt" \ + hg38 GCA_018471545.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 76m53.550s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018471545.1.txt + # 2838487930 bases of 3299210039 (86.035%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/471/545/GCA_018471545.1_HG01952.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018471545.1_HG01952.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018471545.1.2023-04-05/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 122m47.581s + + sed -e 's/^/ # /;' fb.GCA_018471545.1.chainHg38Link.txt + # 2872293644 bases of 3020563005 (95.091%) in intersection + sed -e 's/^/ # /;' fb.GCA_018471545.1.chainSynHg38Link.txt + # 2866375735 bases of 3020563005 (94.895%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/471/545/GCA_018471545.1/GCA_018471545.1.chrom.sizes.txt" \ + GCA_018471545.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 69m19.571s + + sed -e 's/^/ # /;' fb.GCA_018471545.1.chainRBest.Hg38.txt + # 2836401226 bases of 3020563005 (93.903%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018471555.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018471555.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018471555.1.2023-04-05 + + printf '# human GCA_018471555.1 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_018471555.1_HG01952.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018471555.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018471555.1_HG01952.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 140m13.734s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018471555.1Link.txt + # 2918848968 bases of 3299210039 (88.471%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018471555.1Link.txt + # 2913549109 bases of 3299210039 (88.311%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.chrom.sizes.txt" \ + hg38 GCA_018471555.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 73m22.011s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018471555.1.txt + # 2707032716 bases of 3299210039 (82.051%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/471/555/GCA_018471555.1_HG01952.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018471555.1_HG01952.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018471555.1.2023-04-05/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 118m59.134s + + sed -e 's/^/ # /;' fb.GCA_018471555.1.chainHg38Link.txt + # 2738500264 bases of 2913263982 (94.001%) in intersection + sed -e 's/^/ # /;' fb.GCA_018471555.1.chainSynHg38Link.txt + # 2732826954 bases of 2913263982 (93.806%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/471/555/GCA_018471555.1/GCA_018471555.1.chrom.sizes.txt" \ + GCA_018471555.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m18.124s + + sed -e 's/^/ # /;' fb.GCA_018471555.1.chainRBest.Hg38.txt + # 2706500715 bases of 2913263982 (92.903%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472865.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472865.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472865.1.2023-04-05 + + printf '# human GCA_018472865.1 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_018472865.1_HG01978.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472865.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472865.1_HG01978.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 171m14.446s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472865.1Link.txt + # 3047365592 bases of 3299210039 (92.367%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472865.1Link.txt + # 3043049700 bases of 3299210039 (92.236%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.chrom.sizes.txt" \ + hg38 GCA_018472865.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m46.282s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472865.1.txt + # 2835747386 bases of 3299210039 (85.952%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/865/GCA_018472865.1_HG01978.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472865.1_HG01978.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472865.1.2023-04-05/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 132m37.621s + + sed -e 's/^/ # /;' fb.GCA_018472865.1.chainHg38Link.txt + # 2867278593 bases of 3051869401 (93.952%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472865.1.chainSynHg38Link.txt + # 2861527125 bases of 3051869401 (93.763%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/865/GCA_018472865.1/GCA_018472865.1.chrom.sizes.txt" \ + GCA_018472865.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m37.229s + + sed -e 's/^/ # /;' fb.GCA_018472865.1.chainRBest.Hg38.txt + # 2834379833 bases of 3051869401 (92.874%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018472845.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018472845.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018472845.1.2023-04-05 + + printf '# human GCA_018472845.1 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_018472845.1_HG01978.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018472845.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018472845.1_HG01978.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 161m59.381s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018472845.1Link.txt + # 3048225496 bases of 3299210039 (92.393%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018472845.1Link.txt + # 3043723937 bases of 3299210039 (92.256%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.chrom.sizes.txt" \ + hg38 GCA_018472845.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m7.625s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018472845.1.txt + # 2836404970 bases of 3299210039 (85.972%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/472/845/GCA_018472845.1_HG01978.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018472845.1_HG01978.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018472845.1.2023-04-05/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 133m43.664s + + sed -e 's/^/ # /;' fb.GCA_018472845.1.chainHg38Link.txt + # 2874258628 bases of 3055071491 (94.082%) in intersection + sed -e 's/^/ # /;' fb.GCA_018472845.1.chainSynHg38Link.txt + # 2868180892 bases of 3055071491 (93.883%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/472/845/GCA_018472845.1/GCA_018472845.1.chrom.sizes.txt" \ + GCA_018472845.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m2.491s + + sed -e 's/^/ # /;' fb.GCA_018472845.1.chainRBest.Hg38.txt + # 2834756457 bases of 3055071491 (92.789%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018506125.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018506125.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018506125.1.2023-04-05 + + printf '# human GCA_018506125.1 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_018506125.1_HG02055.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018506125.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018506125.1_HG02055.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 159m9.601s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018506125.1Link.txt + # 3049130531 bases of 3299210039 (92.420%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018506125.1Link.txt + # 3044658662 bases of 3299210039 (92.284%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.chrom.sizes.txt" \ + hg38 GCA_018506125.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 79m34.779s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018506125.1.txt + # 2837132708 bases of 3299210039 (85.994%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/506/125/GCA_018506125.1_HG02055.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018506125.1_HG02055.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018506125.1.2023-04-05/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 134m43.050s + + sed -e 's/^/ # /;' fb.GCA_018506125.1.chainHg38Link.txt + # 2866177825 bases of 3019590183 (94.919%) in intersection + sed -e 's/^/ # /;' fb.GCA_018506125.1.chainSynHg38Link.txt + # 2860016612 bases of 3019590183 (94.715%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/506/125/GCA_018506125.1/GCA_018506125.1.chrom.sizes.txt" \ + GCA_018506125.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m18.027s + + sed -e 's/^/ # /;' fb.GCA_018506125.1.chainRBest.Hg38.txt + # 2834560427 bases of 3019590183 (93.872%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018505855.1 +# (DONE - 2023-04-06 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 + cd /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 + + printf '# human GCA_018505855.1 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_018505855.1_HG02055.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018505855.1_HG02055.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 160m27.006s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018505855.1Link.txt + # 2920085105 bases of 3299210039 (88.509%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018505855.1Link.txt + # 2915187308 bases of 3299210039 (88.360%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt" \ + hg38 GCA_018505855.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m52.496s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018505855.1.txt + # 2712237293 bases of 3299210039 (82.209%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/505/855/GCA_018505855.1_HG02055.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018505855.1_HG02055.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06/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 122m39.734s + + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainHg38Link.txt + # 2749378239 bases of 2950246117 (93.191%) in intersection + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainSynHg38Link.txt + # 2742930636 bases of 2950246117 (92.973%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt" \ + GCA_018505855.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 84m36.497s + + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainRBest.Hg38.txt + # 2707923188 bases of 2950246117 (91.786%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018505855.1 +# (DONE - 2023-04-06 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 + cd /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 + + printf '# human GCA_018505855.1 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_018505855.1_HG02055.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018505855.1_HG02055.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 160m27.006s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018505855.1Link.txt + # 2920085105 bases of 3299210039 (88.509%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018505855.1Link.txt + # 2915187308 bases of 3299210039 (88.360%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt" \ + hg38 GCA_018505855.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 75m52.496s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018505855.1.txt + # 2712237293 bases of 3299210039 (82.209%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/505/855/GCA_018505855.1_HG02055.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018505855.1_HG02055.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018505855.1.2023-04-06/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 122m39.734s + + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainHg38Link.txt + # 2749378239 bases of 2950246117 (93.191%) in intersection + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainSynHg38Link.txt + # 2742930636 bases of 2950246117 (92.973%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/505/855/GCA_018505855.1/GCA_018505855.1.chrom.sizes.txt" \ + GCA_018505855.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 84m36.497s + + sed -e 's/^/ # /;' fb.GCA_018505855.1.chainRBest.Hg38.txt + # 2707923188 bases of 2950246117 (91.786%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018504055.1 +# (DONE - 2023-04-06 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018504055.1.2023-04-06 + cd /hive/data/genomes/hg38/bed/lastzGCA_018504055.1.2023-04-06 + + printf '# human GCA_018504055.1 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_018504055.1_HG02080.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018504055.1.2023-04-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018504055.1_HG02080.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 172m6.313s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018504055.1Link.txt + # 3048389081 bases of 3299210039 (92.398%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018504055.1Link.txt + # 3043986538 bases of 3299210039 (92.264%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.chrom.sizes.txt" \ + hg38 GCA_018504055.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m21.855s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018504055.1.txt + # 2836952811 bases of 3299210039 (85.989%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/504/055/GCA_018504055.1_HG02080.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018504055.1_HG02080.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018504055.1.2023-04-06/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 124m22.855s + + sed -e 's/^/ # /;' fb.GCA_018504055.1.chainHg38Link.txt + # 2869987747 bases of 3024505444 (94.891%) in intersection + sed -e 's/^/ # /;' fb.GCA_018504055.1.chainSynHg38Link.txt + # 2864430996 bases of 3024505444 (94.707%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/504/055/GCA_018504055.1/GCA_018504055.1.chrom.sizes.txt" \ + GCA_018504055.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 77m53.994s + + sed -e 's/^/ # /;' fb.GCA_018504055.1.chainRBest.Hg38.txt + # 2835545942 bases of 3024505444 (93.752%) in intersection + +############################################################################## +# LASTZ Human Hg38 vs. human GCA_018505825.1 +# (DONE - 2023-04-06 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 + cd /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 + + printf '# human GCA_018505825.1 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_018505825.1_HG02109.pri.mat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018505825.1_HG02109.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 159m28.473s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018505825.1Link.txt + # 3048266987 bases of 3299210039 (92.394%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018505825.1Link.txt + # 3044144120 bases of 3299210039 (92.269%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt" \ + hg38 GCA_018505825.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m14.803s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018505825.1.txt + # 2837240177 bases of 3299210039 (85.998%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/505/825/GCA_018505825.1_HG02109.pri.mat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018505825.1_HG02109.pri.mat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018505825.1.2023-04-06/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 130m6.019s + + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainHg38Link.txt + # 2870938986 bases of 3026115826 (94.872%) in intersection + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainSynHg38Link.txt + # 2865131757 bases of 3026115826 (94.680%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/505/825/GCA_018505825.1/GCA_018505825.1.chrom.sizes.txt" \ + GCA_018505825.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 80m15.495s + + sed -e 's/^/ # /;' fb.GCA_018505825.1.chainRBest.Hg38.txt + # 2835084887 bases of 3026115826 (93.687%) in intersection + +##############################################################################