########################################################################### # Gorilla Lastz run (DONE - 2016-08-04 - Hiram) screen -S panTro5GorGor5 # use a screen to manage this longish running job mkdir /hive/data/genomes/panTro5/bed/lastzGorGor5.2016-08-04 cd /hive/data/genomes/panTro5/bed/lastzGorGor5.2016-08-04 # always set the BLASTZ program so we know what version was used printf "# chimp vs. gorilla BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_T=2 BLASTZ_O=600 BLASTZ_E=150 BLASTZ_M=254 BLASTZ_K=4500 BLASTZ_L=4500 BLASTZ_Y=15000 BLASTZ_Q=/scratch/data/blastz/human_chimp.v2.q # A C G T # 90 -330 -236 -356 # -330 100 -318 -236 # -236 -318 100 -330 # -356 -236 -330 90 # TARGET: Chimp panTro5 SEQ1_DIR=/hive/data/genomes/panTro5/panTro5.2bit SEQ1_LEN=/hive/data/genomes/panTro5/chrom.sizes SEQ1_CHUNK=40000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 SEQ1_LIMIT=200 # QUERY: Gorilla gorGor5 SEQ2_DIR=/hive/data/genomes/gorGor5/gorGor5.2bit SEQ2_LEN=/hive/data/genomes/gorGor5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=200 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/panTro5/bed/lastzGorGor5.2016-08-04 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 204m8.839s cat fb.panTro5.chainGorGor5Link.txt # 2899634368 bases of 3132620660 (92.563%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ panTro5 gorGor5) > rbest.log 2>&1 # real 136m0.379s # running the swap mkdir /hive/data/genomes/gorGor5/bed/blastz.panTro5.swap cd /hive/data/genomes/gorGor5/bed/blastz.panTro5.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/panTro5/bed/lastzGorGor5.2016-08-04/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 102m31.679s cat fb.gorGor5.chainPanTro5Link.txt # 2755486334 bases of 3080431298 (89.451%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ gorGor5 panTro5) > rbest.log 2>&1 # real 118m53.869s ############################################################################# # swap hg19 chainNet (DONE - 2017-05-11 - Hiram) # alignment to hg19 cd /hive/data/genomes/hg19/bed/lastzPanTro5.2017-05-04 cat fb.hg19.chainPanTro5Link.txt # 2824333913 bases of 2897316137 (97.481%) in intersection # running the swap mkdir /hive/data/genomes/panTro5/bed/blastz.hg19.swap cd /hive/data/genomes/panTro5/bed/blastz.hg19.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg19/bed/lastzPanTro5.2017-05-04/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 111m15.418s cat fb.panTro5.chainHg19Link.txt # 2929713252 bases of 3132620660 (93.523%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ panTro5 hg19) > rbest.log 2>&1 # real 279m26.262s ############################################################################# # Rhesus lastz/chainNet run (DONE - 2017-08-08 - Hiram) screen -S panTro5RheMac8 # use a screen to manage this longish running job mkdir /hive/data/genomes/panTro5/bed/lastzRheMac8.2017-08-08 cd /hive/data/genomes/panTro5/bed/lastzRheMac8.2017-08-08 # always set the BLASTZ program so we know what version was used printf "# chimp vs. rhesus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_T=2 BLASTZ_O=600 BLASTZ_E=150 BLASTZ_M=254 BLASTZ_K=4500 BLASTZ_L=4500 BLASTZ_Y=15000 BLASTZ_Q=/scratch/data/blastz/human_chimp.v2.q # A C G T # 90 -330 -236 -356 # -330 100 -318 -236 # -236 -318 100 -330 # -356 -236 -330 90 # TARGET: Chimp panTro5 SEQ1_DIR=/hive/data/genomes/panTro5/panTro5.2bit SEQ1_LEN=/hive/data/genomes/panTro5/chrom.sizes SEQ1_CHUNK=40000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 SEQ1_LIMIT=400 # QUERY: Rhesus rheMac8 SEQ2_DIR=/hive/data/genomes/rheMac8/rheMac8.2bit SEQ2_LEN=/hive/data/genomes/rheMac8/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=1000 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/panTro5/bed/lastzRheMac8.2017-08-08 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 187m26.960s cat fb.panTro5.chainRheMac8Link.txt # 2586883104 bases of 3132620660 (82.579%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ panTro5 rheMac8) > rbest.log 2>&1 # real 368m0.695s # running the swap mkdir /hive/data/genomes/rheMac8/bed/blastz.panTro5.swap cd /hive/data/genomes/rheMac8/bed/blastz.panTro5.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/panTro5/bed/lastzRheMac8.2017-08-08/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 214m12.404s cat fb.rheMac8.chainPanTro5Link.txt # 2494854251 bases of 3142093174 (79.401%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ rheMac8 panTro5) > rbest.log 2>&1 # real 567m24.754s #############################################################################