3dd09a4b5f9dd8ad5122483b7b040dcec14ac1f4 hiram Mon Dec 14 16:40:51 2020 -0800 lastz chainNet per user request hg19 bosTau9 refs #26638 diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index 3230572..6770282 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -33844,15 +33844,92 @@ # sys 12m0.858s cd .. time cat hg19/genomes/*.bed | ./gnomadVcfBedToBigBed stdin stdout | sort -k1,1 -k2,2n > gnomad.v2.1.1.genomes.bed # real 199m48.619s # user 186m49.769s # sys 29m12.841s # now South Asian variants in the genomes file, change type: time bedToBigBed -type=bed9+47 -tab -as=genomes.as gnomad.v2.1.1.genomes.bed /hive/data/genomes/hg19/chrom.sizes genomes.bb # pass1 - making usageList (23 chroms): 165336 millis # pass2 - checking and writing primary data (253556152 records, 55 fields): 4909106 millis # # real 89m3.165s # user 86m41.554s # sys 2m15.722s + +############################################################################# +# LASTZ Cow bosTau9 (DONE - 2020-12-07 - Hiram) + mkdir /hive/data/genomes/hg19/bed/lastzBosTau9.2020-12-07 + cd /hive/data/genomes/hg19/bed/lastzBosTau9.2020-12-07 + + printf '# human vs Cow +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz +BLASTZ_T=2 +BLASTZ_O=400 +BLASTZ_E=30 +BLASTZ_M=254 +# default BLASTZ_Q score matrix: +# A C G T +# A 91 -114 -31 -123 +# C -114 100 -125 -31 +# G -31 -125 100 -114 +# T -123 -31 -114 91 + +# TARGET: human hg19 +SEQ1_DIR=/hive/data/genomes/hg19/hg19.2bit +SEQ1_LEN=/hive/data/genomes/hg19/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 + +# QUERY: Cow bosTau9 +SEQ2_DIR=/hive/data/genomes/bosTau9/bosTau9.2bit +SEQ2_LEN=/hive/data/genomes/bosTau9/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LIMIT=10 +SEQ2_LAP=0 + +BASE=/hive/data/genomes/hg19/bed/lastzBosTau9.2020-12-07 +TMPDIR=/dev/shm +' > DEF + + time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + -chainMinScore=3000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ + -syntenicNet) > do.log 2>&1 + # real 239m35.175s + + cat fb.hg19.chainBosTau9Link.txt + # 1407432462 bases of 2991710746 (47.044%) in intersection + + cat fb.hg19.chainSynBosTau9Link.txt + # 1354159575 bases of 2991710746 (45.264%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg19 bosTau9) > rbest.log 2>&1 & + # real 274m55.811s + + cat fb.hg19.chainRBest.BosTau9.txt + # 1290531802 bases of 2991710746 (43.137%) in intersection + + # running the swap + mkdir /hive/data/genomes/bosTau9/bed/blastz.hg19.swap + cd /hive/data/genomes/bosTau9/bed/blastz.hg19.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg19/bed/lastzBosTau9.2020-12-07/DEF \ + -swap -syntenicNet -workhorse=hgwdev \ + -smallClusterHub=hgwdev -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 + # real 72m28.826s + + cat fb.bosTau9.chainHg19Link.txt + # 1342159887 bases of 2715853792 (49.419%) in intersection + cat fb.bosTau9.chainSynHg19Link.txt + # 1305558878 bases of 2715853792 (48.072%) in intersection + + time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` bosTau9 hg19) > rbest.log 2>&1 & +XXX - running - Tue Dec 8 09:13:34 PST 2020 + # real 272m15.176s + + cat fb.bosTau9.chainRBest.Hg19.txt + # 1290810412 bases of 2715853792 (47.529%) in intersection + +#############################################################################