ca5e96d3ef0bc2d2f995a912dc4f7b5fdf432e4e hiram Wed Apr 5 16:46:20 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 db17523..bc90392 100644 --- src/hg/makeDb/doc/hg38/hprcLastz.txt +++ src/hg/makeDb/doc/hg38/hprcLastz.txt @@ -2478,15 +2478,107 @@ 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 ############################################################################## +# LASTZ Human Hg38 vs. human GCA_018469705.1 +# (DONE - 2023-04-05 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018469705.1.2023-04-05 + cd /hive/data/genomes/hg38/bed/lastzGCA_018469705.1.2023-04-05 + + printf '# human GCA_018469705.1 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_018469705.1_HG01361.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018469705.1.2023-04-05 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018469705.1_HG01361.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 181m59.456s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018469705.1Link.txt + # 3048539612 bases of 3299210039 (92.402%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018469705.1Link.txt + # 3044490947 bases of 3299210039 (92.279%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/469/705/GCA_018469705.1/GCA_018469705.1.chrom.sizes.txt" \ + hg38 GCA_018469705.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 78m20.100s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018469705.1.txt + # 2837562648 bases of 3299210039 (86.007%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/469/705/GCA_018469705.1_HG01361.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018469705.1_HG01361.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018469705.1.2023-04-05/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 127m44.548s + + sed -e 's/^/ # /;' fb.GCA_018469705.1.chainHg38Link.txt + # 2865148414 bases of 3010067136 (95.186%) in intersection + 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 + +##############################################################################