7873ad671c469a1c6c8b6d249dc4123e6d82e361 hiram Wed Sep 4 08:35:13 2019 -0700 lastz chainNet hg19 to rheMac10 refs #23771 diff --git src/hg/makeDb/doc/hg19.txt src/hg/makeDb/doc/hg19.txt index e7b0e6c..73f74f2 100644 --- src/hg/makeDb/doc/hg19.txt +++ src/hg/makeDb/doc/hg19.txt @@ -33523,16 +33523,90 @@ # Update human/hg19/wgEncodeGencodeSuper.html and update 'Release Notes' # to describe new release. [ONLY if it's going to be pushed] # edit human/hg19/trackDb.wgEncode.ra to add new .ra file include make DBS=hg19 # edit all.joiner to add ~/tmp/gencodeV32lift37.joiner # verify with: pushd /hive/data/genomes/hg19/bed/gencodeV32lift37 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck # commit all ############################################################################## +# LASTZ human/hg19 Tree chimp/rheMac10 - (DONE - 2019-07-09 - Hiram) + mkdir /hive/data/genomes/hg19/bed/lastzRheMac10.2019-07-09 + cd /hive/data/genomes/hg19/bed/lastzRheMac10.2019-07-09 + printf '# human vs macaca mulatta +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz +# maximum M allowed with lastz is only 254 +BLASTZ_M=254 +BLASTZ_Q=/hive/data/staging/data/blastz/human_chimp.v2.q +BLASTZ_O=600 +BLASTZ_E=150 +# other parameters from panTro2 vs hg18 lastz on advice from Webb +BLASTZ_K=4500 +BLASTZ_Y=15000 +BLASTZ_T=2 + +# 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: Macaca Mulatta RheMac10 +SEQ2_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit +SEQ2_LEN=/hive/data/genomes/rheMac10/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LIMIT=600 +SEQ2_LAP=0 +SEQ2_IN_CONTIGS=0 + +BASE=/hive/data/genomes/hg19/bed/lastzRheMac10.2019-07-09 +TMPDIR=/dev/shm +' > DEF + # << happy emacs + + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -syntenicNet -fileServer=hgwdev \ + -chainMinScore=5000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku) > do.log 2>&1 + # real 85m20.849s + + cat fb.hg19.chainRheMac10Link.txt + # 2604364199 bases of 2991694177 (87.053%) in intersection + cat fb.hg19.chainSynRheMac10Link.txt + # 2570126144 bases of 2991694177 (85.909%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg19 rheMac10) > rbest.log 2>&1 & + # real 112m12.228s + + cat fb.hg19.chainRBest.RheMac10.txt + # 2421810991 bases of 2991694177 (80.951%) in intersection + + # and for the swap: + mkdir /hive/data/genomes/rheMac10/bed/blastz.hg19.swap + cd /hive/data/genomes/rheMac10/bed/blastz.hg19.swap + + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg19/bed/lastzRheMac10.2019-07-09/DEF \ + -swap -chainMinScore=5000 -chainLinearGap=medium \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet) > swap.log 2>&1 + # real 56m29.163s + + cat fb.rheMac10.chainHg19Link.txt + # 2483311773 bases of 2936892733 (84.556%) in intersection + cat fb.rheMac10.chainSynHg19Link.txt + # 2461925388 bases of 2936892733 (83.828%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` rheMac10 hg19) > rbest.log 2>&1 + # real 112m15.825s + + cat fb.rheMac10.chainRBest.Hg19.txt + # 2423781773 bases of 2936892733 (82.529%) in intersection + +#########################################################################