86ae147ac68707dcb81a697e5e45f4619465097e hiram Tue Feb 16 08:52:47 2021 -0800 completed lastz/chain/net to mm10 mm39 hg38 for rn7 release refs #26682 diff --git src/hg/makeDb/doc/hg38/lastzRuns.txt src/hg/makeDb/doc/hg38/lastzRuns.txt index bdacd69..b2be5fc 100644 --- src/hg/makeDb/doc/hg38/lastzRuns.txt +++ src/hg/makeDb/doc/hg38/lastzRuns.txt @@ -12910,15 +12910,93 @@ # real 105m30.938s cat fb.calJac4.chainHg38Link.txt # 2256668215 bases of 2859817025 (78.910%) in intersection cat fb.calJac4.chainSynHg38Link.txt # 2183912419 bases of 2859817025 (76.365%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ calJac4 hg38) > rbest.log 2>&1 & # real 467m22.590s cat fb.calJac4.chainRBest.Hg38.txt # 2147250913 bases of 2859817025 (75.084%) in intersection ############################################################################ +# LASTZ MOUSE Rn7 (DONE - 2021-02-04 - Hiram) + # can no longer use the lineage specific repeats with the new lastz + # use a screen to manage this longish job: + screen -S hg38Rn7 + + mkdir /hive/data/genomes/hg38/bed/lastzRn7.2021-02-04 + cd /hive/data/genomes/hg38/bed/lastzRn7.2021-02-04 + + # best to always specify an exact path to lastz so we know which one is used + # lastz default parameters are human-mouse parameters + + printf '# human vs mouse +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: Human Hg38 +SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit +SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes +SEQ1_CTGDIR=/hive/data/genomes/hg38/hg38.contigs.2bit +SEQ1_CTGLEN=/hive/data/genomes/hg38/hg38.contigs.chrom.sizes +SEQ1_LIFT=/hive/data/genomes/hg38/jkStuff/hg38.contigs.lift +SEQ1_CHUNK=40000000 +SEQ1_LAP=10000 + +# QUERY: Mouse Rn7 +SEQ2_DIR=/hive/data/genomes/rn7/rn7.2bit +SEQ2_LEN=/hive/data/genomes/rn7/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 + +BASE=/hive/data/genomes/hg38/bed/lastzRn7.2021-02-04 +TMPDIR=/dev/shm +' > DEF + + # verify files exist: + grep "=" DEF | cut -d= -f2 | xargs ls -ogd + + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -syntenicNet) > do.log 2>&1 + # real 270m41.393s + + sed -e 's/^/ # /;' fb.hg38.chainRn7Link.txt + # 958592205 bases of 3110768607 (30.815%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynRn7Link.txt + # 904066852 bases of 3110768607 (29.062%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + hg38 rn7) > rbest.log 2>&1 & + # real 313m26.149s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.Rn7.txt + # 883775977 bases of 3110768607 (28.410%) in intersection + + # and the swap + mkdir /hive/data/genomes/rn7/bed/blastz.hg38.swap + cd /hive/data/genomes/rn7/bed/blastz.hg38.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg38/bed/lastzRn7.2021-02-04/DEF \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -swap -syntenicNet) > swap.log 2>&1 + # real 74m20.215s + + sed -e 's/^/ # /;' fb.rn7.chainHg38Link.txt + # 928866703 bases of 2626580772 (35.364%) in intersection + + sed -e 's/^/ # /;' fb.rn7.chainSynHg38Link.txt + # 879484562 bases of 2626580772 (33.484%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + rn7 hg38) > rbest.log 2>&1 & + # real 373m6.610s + + sed -e 's/^/ # /;' fb.rn7.chainRBest.Hg38.txt + # 885516265 bases of 2626580772 (33.714%) in intersection + +#########################################################################