b390872e7b2543685b9bd8e301099c38935bcc1d hiram Mon Apr 10 08:12:30 2023 -0700 last one has completed refs #30912 diff --git src/hg/makeDb/doc/hg38/hprcLastz.txt src/hg/makeDb/doc/hg38/hprcLastz.txt index 410eaf8..bd2e25b 100644 --- src/hg/makeDb/doc/hg38/hprcLastz.txt +++ src/hg/makeDb/doc/hg38/hprcLastz.txt @@ -8274,15 +8274,107 @@ sed -e 's/^/ # /;' fb.GCA_018506965.1.chainSynHg38Link.txt # 2868394773 bases of 3029694013 (94.676%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ \ -target2bit="/hive/data/genomes/asmHubs/GCA/018/506/965/GCA_018506965.1/GCA_018506965.1.2bit" \ -targetSizes="/hive/data/genomes/asmHubs/GCA/018/506/965/GCA_018506965.1/GCA_018506965.1.chrom.sizes.txt" \ GCA_018506965.1 hg38) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 73m28.912s sed -e 's/^/ # /;' fb.GCA_018506965.1.chainRBest.Hg38.txt # 2836696337 bases of 3029694013 (93.630%) in intersection ############################################################################## +# LASTZ Human Hg38 vs. human GCA_018506945.1 +# (DONE - 2023-04-10 - hiram) + + mkdir /hive/data/genomes/hg38/bed/lastzGCA_018506945.1.2023-04-10 + cd /hive/data/genomes/hg38/bed/lastzGCA_018506945.1.2023-04-10 + + printf '# human GCA_018506945.1 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_018506945.1_HG005.alt.pat.f1_v2 +SEQ2_DIR=/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.2bit +SEQ2_LEN=/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.chrom.sizes.txt +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/hg38/bed/lastzGCA_018506945.1.2023-04-10 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -verbose=2 `pwd`/DEF -syntenicNet \ + -qAsmId GCA_018506945.1_HG005.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 145m58.290s + + sed -e 's/^/ # /;' fb.hg38.chainGCA_018506945.1Link.txt + # 2920733867 bases of 3299210039 (88.528%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynGCA_018506945.1Link.txt + # 2915764385 bases of 3299210039 (88.378%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -query2Bit="/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.2bit" \ +-querySizes="/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.chrom.sizes.txt" \ + hg38 GCA_018506945.1) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 69m36.569s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.GCA_018506945.1.txt + # 2711031495 bases of 3299210039 (82.172%) in intersection + + ### and for the swap + + cd /hive/data/genomes/asmHubs/allBuild/GCA/018/506/945/GCA_018506945.1_HG005.alt.pat.f1_v2/trackData/blastz.hg38.swap + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -trackHub -noDbNameCheck -swap -verbose=2 \ + -qAsmId GCA_018506945.1_HG005.alt.pat.f1_v2 /hive/data/genomes/hg38/bed/lastzGCA_018506945.1.2023-04-10/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 108m28.293s + + sed -e 's/^/ # /;' fb.GCA_018506945.1.chainHg38Link.txt + # 2752380759 bases of 2937775295 (93.689%) in intersection + sed -e 's/^/ # /;' fb.GCA_018506945.1.chainSynHg38Link.txt + # 2746722452 bases of 2937775295 (93.497%) in intersection +\ time (~/kent/src/hg/utils/automation/doRecipBest.pl -trackHub -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + -target2bit="/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.2bit" \ +-targetSizes="/hive/data/genomes/asmHubs/GCA/018/506/945/GCA_018506945.1/GCA_018506945.1.chrom.sizes.txt" \ + GCA_018506945.1 hg38) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 66m38.476s + + sed -e 's/^/ # /;' fb.GCA_018506945.1.chainRBest.Hg38.txt + # 2709508288 bases of 2937775295 (92.230%) in intersection + +##############################################################################