53c0ef5df5bee7978a6d37a401190471e097c689 hiram Mon Jul 8 15:20:16 2019 -0700 lastz chainNet to regenRn0 and rheMac10 refs #23771 #21579 diff --git src/hg/makeDb/doc/mm10.txt src/hg/makeDb/doc/mm10.txt index 5f9dbf9..ef96d4e 100644 --- src/hg/makeDb/doc/mm10.txt +++ src/hg/makeDb/doc/mm10.txt @@ -17944,16 +17944,140 @@ ## only if being pushed to RR: # edit all.joiner to add ~/tmp/gencodeVM22.joiner # verify with: pushd /hive/data/genomes/mm10/bed/gencodeVM22 make -f ~/kent/src/hg/makeDb/outside/gencode/gencodeLoad.mk joinerCheck db=mm10 # commit all and make push request, the file tables.lst will have the # list of tables for the push request. cd ~/kent/src/hg/makeDb/trackDb make alpha DBS=mm10 # commit all # if pushing public, add ticket and MARK QA READY -######################################################################### +############################################################################## +# LASTZ Rat regenRn0 (DONE - 2019-07-01 - Jonathan) + mkdir /hive/data/genomes/mm10/bed/lastzRegenRn0.2019-07-01 + cd /hive/data/genomes/mm10/bed/lastzRegenRn0.2019-07-01 + + printf '# rat vs mouse +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz +# TARGET: Mouse Mm10 +SEQ1_DIR=/scratch/data/mm10/mm10.2bit +SEQ1_LEN=/scratch/data/mm10/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 + +# QUERY: Rat RegenRn0 +SEQ2_DIR=/hive/data/genomes/regenRn0/regenRn0.2bit +SEQ2_LEN=/hive/data/genomes/regenRn0/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=500 + +BASE=/hive/data/genomes/mm10/bed/lastzRegenRn0.2019-07-01 +TMPDIR=/dev/shm +' > DEF + + # establish a screen to control this job + screen -S mm10RegenRn0 + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -noDbNameCheck -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -syntenicNet -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 + # real 196m22.733s + + cat fb.mm10.chainRegenRn0Link.txt + # 1843678500 bases of 2652783500 (69.500%) in intersection + cat fb.mm10.chainSynRegenRn0Link.txt + # 1720395177 bases of 2652783500 (64.852%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` mm10 regenRn0) > rbest.log 2>&1 & + # real 494m43.241s + + cat fb.mm10.chainRBest.RegenRn0.txt + # 1694384084 bases of 2652783500 (63.872%) in intersection + + mkdir /hive/data/genomes/regenRn0/bed/blastz.mm10.swap + cd /hive/data/genomes/regenRn0/bed/blastz.mm10.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/mm10/bed/lastzRegenRn0.2019-07-01/DEF \ + -swap -syntenicNet -noDbNameCheck \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 + # real 106m31.449s + + cat fb.regenRn0.chainMm10Link.txt + # 1803664991 bases of 2534810853 (71.156%) in intersection + cat fb.regenRn0.chainSynMm10Link.txt + # 1712372147 bases of 2534810853 (67.554%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn0 mm10) > rbest.log 2>&1 + # real 536m51.292s + + cat fb.regenRn0.chainRBest.Mm10.txt + # 1695272967 bases of 2534810853 (66.880%) in intersection + +############################################################################## +# LASTZ Rhesus rheMac10 (DONE - 2019-07-03 - Hiram) + mkdir /hive/data/genomes/mm10/bed/lastzRheMac10.2019-07-03 + cd /hive/data/genomes/mm10/bed/lastzRheMac10.2019-07-03 + + printf '# rhesus vs mouse +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz +# TARGET: Mouse Mm10 +SEQ1_DIR=/hive/data/genomes/mm10/mm10.2bit +SEQ1_LEN=/hive/data/genomes/mm10/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 + +# QUERY: Rhesus RheMac10 +SEQ2_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit +SEQ2_LEN=/hive/data/genomes/rheMac10/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=500 + +BASE=/hive/data/genomes/mm10/bed/lastzRheMac10.2019-07-03 +TMPDIR=/dev/shm +' > DEF + + # establish a screen to control this job + screen -S mm10RheMac10 + time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ + -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + # real 211m21.922s + + cat fb.mm10.chainRheMac10Link.txt + # 923559693 bases of 2652783500 (34.815%) in intersection + cat fb.mm10.chainSynRheMac10Link.txt + # 878479553 bases of 2652783500 (33.115%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` mm10 rheMac10) > rbest.log 2>&1 & + # real 315m43.465s + + cat fb.mm10.chainRBest.RheMac10.txt + # 879885863 bases of 2652783500 (33.168%) in intersection + + mkdir /hive/data/genomes/rheMac10/bed/blastz.mm10.swap + cd /hive/data/genomes/rheMac10/bed/blastz.mm10.swap + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/mm10/bed/lastzRheMac10.2019-07-03/DEF \ + -swap -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ + -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 + # real 52m48.045s + + cat fb.rheMac10.chainMm10Link.txt + # 918551088 bases of 2936892733 (31.276%) in intersection + cat fb.rheMac10.chainSynMm10Link.txt + # 876230433 bases of 2936892733 (29.835%) in intersection + + time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` rheMac10 mm10) > rbest.log 2>&1 + # real 303m40.303s + + cat fb.rheMac10.chainRBest.Mm10.txt + # 878542993 bases of 2936892733 (29.914%) in intersection + +##############################################################################