34371bd099e5103a5446e2390d70c67c45711d7b kate Wed Sep 2 11:00:28 2020 -0700 Label tweaks. refs #26129 diff --git src/hg/makeDb/doc/hg38/lastzRuns.txt src/hg/makeDb/doc/hg38/lastzRuns.txt index f2ab9d1..5982e84 100644 --- src/hg/makeDb/doc/hg38/lastzRuns.txt +++ src/hg/makeDb/doc/hg38/lastzRuns.txt @@ -1,12845 +1,12850 @@ # for emacs: -*- mode: sh; -*- ######################################################################### # LASTZ human/hg38 bonobo/panPan1 - (DONE - 2014-12-11 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPanPan1.2014-12-11 cd /hive/data/genomes/hg38/bed/lastzPanPan1.2014-12-11 cat << '_EOF_' > DEF # human vs bonobo # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.panPan1/hg38.panPan1.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzPanPan1.2014-12-11/hg38.panPan1.tuning.Q.txt # A C G T # A 100 -174 -43 -143 # C -174 91 -179 -43 # G -43 -179 91 -174 # T -143 -43 -174 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: bonobo panPan1 SEQ2_DIR=/hive/data/genomes/panPan1/panPan1.2bit SEQ2_LEN=/hive/data/genomes/panPan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPanPan1.2014-12-11 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 197m51.411s cat fb.hg38.chainPanPan1Link.txt # 2833718712 bases of 3049335806 (92.929%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 panPan1) > rbest.log 2>&1 & # real 44m15.208s # and for the swap: mkdir /hive/data/genomes/panPan1/bed/blastz.hg38.swap cd /hive/data/genomes/panPan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPanPan1.2014-12-11/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 117m56.319s cat fb.panPan1.chainHg38Link.txt # 2665801248 bases of 2725905606 (97.795%) in intersection time (doRecipBest.pl -buildDir=`pwd` panPan1 hg38) > rbest.log 2>&1 # real 79m30.931s ######################################################################### # LASTZ human/hg38 Golden snub-nosed monkey/rhiRox1 - (DONE - 2015-02-23 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23 cd /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23 cp -p \ /hive/users/hiram/multiz/100way/hg38.rhiRox1/hg38.rhiRox1.tuning.top300.txt \ ./hg38.rhiRox1.tuning.Q.txt cat << '_EOF_' > DEF # human vs Golden snub-nosed monkey # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.rhiRox1/hg38.rhiRox1.tuning.top300.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23/hg38.rhiRox1.tuning.Q.txt # A C G T # A 100 -176 -44 -147 # C -176 93 -178 -44 # G -44 -178 93 -176 # T -147 -44 -176 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Golden snub-nosed monkey rhiRox1 SEQ2_DIR=/hive/data/genomes/rhiRox1/rhiRox1.2bit SEQ2_LEN=/hive/data/genomes/rhiRox1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 218m48.221s cat fb.hg38.chainRhiRox1Link.txt # 2595256243 bases of 3049335806 (85.109%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 rhiRox1) \ > rbest.log 2>&1 & # real 53m54.908s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 rhiRox1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestRhiRox1Link.txt # 2400873699 bases of 3049335806 (78.734%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23/axtChain netToAxt hg38.rhiRox1.syn.net.gz hg38.rhiRox1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/rhiRox1/rhiRox1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/rhiRox1/chrom.sizes stdout \ | gzip -c > hg38.rhiRox1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynRhiRox1 hg38.rhiRox1.syn.chain.gz netFilter -minGap=10 hg38.rhiRox1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynRhiRox1 stdin cd /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23 featureBits hg38 chainSynRhiRox1Link > fb.hg38.chainSynRhiRox1Link.txt 2>&1 cat fb.hg38.chainSynRhiRox1Link.txt # 2538430248 bases of 3049335806 (83.245%) in intersection # and for the swap: mkdir /hive/data/genomes/rhiRox1/bed/blastz.hg38.swap cd /hive/data/genomes/rhiRox1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRhiRox1.2015-02-23/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 174m27.934s cat fb.rhiRox1.chainHg38Link.txt # 2474156996 bases of 2856044136 (86.629%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` rhiRox1 hg38) \ > rbest.log 2>&1 # real 83m2.776s ######################################################################### # LASTZ human/hg38 Gibbon/nomLeu3 - (DONE - 2014-12-12 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12 cd /hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12 cp -p \ /hive/users/hiram/multiz/100way/hg38.nomLeu3/hg38.nomLeu3.tuning.top200.txt \ ./hg38.nomLeu3.tuning.Q.txt cat << '_EOF_' > DEF # human vs Gibbon # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.nomLeu3/hg38.nomLeu3.tuning.top200.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12/hg38.nomLeu3.tuning.Q.txt # A C G T # A 100 -175 -43 -144 # C -175 92 -180 -43 # G -43 -180 92 -175 # T -144 -43 -175 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Gibbon nomLeu3 SEQ2_DIR=/hive/data/genomes/nomLeu3/nomLeu3.2bit SEQ2_LEN=/hive/data/genomes/nomLeu3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 366m25.258s cat fb.hg38.chainNomLeu3Link.txt # 2633978949 bases of 3049335806 (86.379%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 nomLeu3) > rbest.log 2>&1 & # real 77m44.300s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 nomLeu3) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestNomLeu3Link.txt # 2442160816 bases of 3049335806 (80.088%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12/axtChain netToAxt hg38.nomLeu3.syn.net.gz hg38.nomLeu3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/nomLeu3/nomLeu3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/nomLeu3/chrom.sizes stdout \ | gzip -c > hg38.nomLeu3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynNomLeu3 hg38.nomLeu3.syn.chain.gz netFilter -minGap=10 hg38.nomLeu3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynNomLeu3 stdin cd /hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12 featureBits hg38 chainSynNomLeu3Link > fb.hg38.chainSynNomLeu3Link.txt 2>&1 cat fb.hg38.chainSynNomLeu3Link.txt 2577846437 bases of 3049335806 (84.538%) in intersection real 7m3.732s # and for the swap: mkdir /hive/data/genomes/nomLeu3/bed/blastz.hg38.swap cd /hive/data/genomes/nomLeu3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzNomLeu3.2014-12-12/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 120m35.210s cat fb.nomLeu3.chainHg38Link.txt # 2493897222 bases of 2756609047 (90.470%) in intersection time (doRecipBest.pl -buildDir=`pwd` nomLeu3 hg38) > rbest.log 2>&1 # real 39m37.872s ######################################################################### # LASTZ human/hg38 Squirrel monkey/saiBol1 - (DONE - 2014-12-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13 cd /hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13 cp -p \ /hive/users/hiram/multiz/100way/hg38.saiBol1/hg38.saiBol1.tuning.top300.txt \ ./hg38.saiBol1.tuning.Q.txt cat << '_EOF_' > DEF # human vs Squirrel monkey # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.saiBol1/hg38.saiBol1.tuning.top300.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13/hg38.saiBol1.tuning.Q.txt # A C G T # A 100 -178 -40 -145 # C -178 93 -188 -40 # G -40 -188 93 -178 # T -145 -40 -178 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Squirrel monkey saiBol1 SEQ2_DIR=/hive/data/genomes/saiBol1/saiBol1.2bit SEQ2_LEN=/hive/data/genomes/saiBol1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 321m56.693s cat fb.hg38.chainSaiBol1Link.txt # 2151771087 bases of 3049335806 (70.565%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 saiBol1) > rbest.log 2>&1 & # real 129m56.144s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 saiBol1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestSaiBol1Link.txt # 1986661464 bases of 3049335806 (65.151%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13/axtChain netToAxt hg38.saiBol1.syn.net.gz hg38.saiBol1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/saiBol1/saiBol1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/saiBol1/chrom.sizes stdout \ | gzip -c > hg38.saiBol1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynSaiBol1 hg38.saiBol1.syn.chain.gz netFilter -minGap=10 hg38.saiBol1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynSaiBol1 stdin cd /hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13 featureBits hg38 chainSynSaiBol1Link > fb.hg38.chainSynSaiBol1Link.txt 2>&1 cat fb.hg38.chainSynSaiBol1Link.txt # 2096151749 bases of 3049335806 (68.741%) in intersection # real 10m12.757s # and for the swap: mkdir /hive/data/genomes/saiBol1/bed/blastz.hg38.swap cd /hive/data/genomes/saiBol1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSaiBol1.2014-12-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 102m22.969s cat fb.saiBol1.chainHg38Link.txt # 2018022119 bases of 2477131095 (81.466%) in intersection time (doRecipBest.pl -buildDir=`pwd` saiBol1 hg38) > rbest.log 2>&1 # real 42m24.226s ######################################################################### # LASTZ human/hg38 Crab-eating macaque/macFas5 - (DONE - 2014-12-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13 cd /hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13 cp -p \ /hive/users/hiram/multiz/100way/hg38.macFas5/hg38.macFas5.tuning.top300.txt \ ./hg38.macFas5.tuning.Q.txt cat << '_EOF_' > DEF # human vs Crab-eating macaque # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.macFas5/hg38.macFas5.tuning.top300.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13/hg38.macFas5.tuning.Q.txt # A C G T # A 100 -174 -43 -144 # C -174 93 -176 -43 # G -43 -176 93 -174 # T -144 -43 -174 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Crab-eating macaque macFas5 SEQ2_DIR=/hive/data/genomes/macFas5/macFas5.2bit SEQ2_LEN=/hive/data/genomes/macFas5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 669m24.572s cat fb.hg38.chainMacFas5Link.txt # 2612527708 bases of 3049335806 (85.675%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 macFas5) > rbest.log 2>&1 & # real 47m25.375s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 macFas5) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestMacFas5Link.txt # 2423088291 bases of 3049335806 (79.463%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13/axtChain netToAxt hg38.macFas5.syn.net.gz hg38.macFas5.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/macFas5/macFas5.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/macFas5/chrom.sizes stdout \ | gzip -c > hg38.macFas5.syn.chain.gz hgLoadChain -tIndex hg38 chainSynMacFas5 hg38.macFas5.syn.chain.gz netFilter -minGap=10 hg38.macFas5.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynMacFas5 stdin cd /hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13 featureBits hg38 chainSynMacFas5Link > fb.hg38.chainSynMacFas5Link.txt 2>&1 cat fb.hg38.chainSynMacFas5Link.txt # 2557788563 bases of 3049335806 (83.880%) in intersection # and for the swap: mkdir /hive/data/genomes/macFas5/bed/blastz.hg38.swap cd /hive/data/genomes/macFas5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMacFas5.2014-12-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 120m29.355s cat fb.macFas5.chainHg38Link.txt # 2460372459 bases of 2803866698 (87.749%) in intersection time (doRecipBest.pl -buildDir=`pwd` macFas5 hg38) > rbest.log 2>&1 # real 66m23.284s ######################################################################### # LASTZ human/hg38 Bushbaby/otoGar3 - (DONE - 2015-02-22 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22 cd /hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22 cat << '_EOF_' > DEF # human vs Bushbaby BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Bushbaby otoGar3 SEQ2_DIR=/hive/data/genomes/otoGar3/otoGar3.2bit SEQ2_LEN=/hive/data/genomes/otoGar3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 336m10.091s cat fb.hg38.chainOtoGar3Link.txt # 1622122468 bases of 3049335806 (53.196%) in intersection # replacing previous tuned version: # 1508964214 bases of 3049335806 (49.485%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 otoGar3) \ > rbest.log 2>&1 & # real 59m25.363s # mistakenly destroyed the rbest.log file: time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 otoGar3) > rbest.log 2>&1 & # real 13m9.418s cat fb.hg38.chainRBestOtoGar3Link.txt # 1482204777 bases of 3049335806 (48.607%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22/axtChain netToAxt hg38.otoGar3.syn.net.gz hg38.otoGar3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/otoGar3/otoGar3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/otoGar3/chrom.sizes stdout \ | gzip -c > hg38.otoGar3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynOtoGar3 hg38.otoGar3.syn.chain.gz netFilter -minGap=10 hg38.otoGar3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynOtoGar3 stdin cd /hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22 featureBits hg38 chainSynOtoGar3Link > fb.hg38.chainSynOtoGar3Link.txt 2>&1 cat fb.hg38.chainSynOtoGar3Link.txt # 1547295352 bases of 3049335806 (50.742%) in intersection # and for the swap: mkdir /hive/data/genomes/otoGar3/bed/blastz.hg38.swap cd /hive/data/genomes/otoGar3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOtoGar3.2015-02-22/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 115m47.941s cat fb.otoGar3.chainHg38Link.txt # 1531320942 bases of 2359530453 (64.899%) in intersection # replacing previous tuned version: # 1428944740 bases of 2359530453 (60.561%) in intersection time (doRecipBest.pl -buildDir=`pwd` otoGar3 hg38) > rbest.log 2>&1 # real 46m56.972s ######################################################################### # LASTZ human/hg38 Marmoset/calJac3 - (DONE - 2014-12-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13 cd /hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13 cp -p \ /hive/users/hiram/multiz/100way/hg38.calJac3/hg38.calJac3.tuning.top300.txt \ ./hg38.calJac3.tuning.Q.txt cat << '_EOF_' > DEF # human vs Marmoset # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.calJac3/hg38.calJac3.tuning.top300.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13/hg38.calJac3.tuning.Q.txt # A C G T # A 100 -176 -40 -145 # C -176 94 -186 -40 # G -40 -186 94 -176 # T -145 -40 -176 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Marmoset calJac3 SEQ2_DIR=/hive/data/genomes/calJac3/calJac3.2bit SEQ2_LEN=/hive/data/genomes/calJac3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 486m51.449s cat fb.hg38.chainCalJac3Link.txt # 2186651179 bases of 3049335806 (71.709%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 calJac3) > rbest.log 2>&1 & # real 50m52.928s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 calJac3) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestCalJac3Link.txt # 2019861688 bases of 3049335806 (66.239%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13 netToAxt hg38.calJac3.syn.net.gz hg38.calJac3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/calJac3/calJac3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/calJac3/chrom.sizes stdout \ | gzip -c > hg38.calJac3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynCalJac3 hg38.calJac3.syn.chain.gz netFilter -minGap=10 hg38.calJac3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynCalJac3 stdin cd /hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13 featureBits hg38 chainSynCalJac3Link > fb.hg38.chainSynCalJac3Link.txt 2>&1 cat fb.hg38.chainSynCalJac3Link.txt # 2119273306 bases of 3049335806 (69.500%) in intersection # and for the swap: mkdir /hive/data/genomes/calJac3/bed/blastz.hg38.swap cd /hive/data/genomes/calJac3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCalJac3.2014-12-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 125m9.577s cat fb.calJac3.chainHg38Link.txt # 2112735553 bases of 2752505800 (76.757%) in intersection time (doRecipBest.pl -buildDir=`pwd` calJac3 hg38) > rbest.log 2>&1 ######################################################################### # LASTZ human/hg38 Gorilla/gorGor3 - (DONE - 2014-12-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGorGor3.2014-12-13 cd /hive/data/genomes/hg38/bed/lastzGorGor3.2014-12-13 cat << '_EOF_' > DEF # human vs Gorilla # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.gorGor3/hg38.gorGor3.tuning.top200.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzGorGor3.2014-12-13/hg38.gorGor3.tuning.Q.txt # A C G T # A 100 -177 -41 -144 # C -177 93 -184 -41 # G -41 -184 93 -177 # T -144 -41 -177 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Gorilla gorGor3 SEQ2_DIR=/hive/data/genomes/gorGor3/gorGor3.2bit SEQ2_LEN=/hive/data/genomes/gorGor3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGorGor3.2014-12-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2846m38.709s cat fb.hg38.chainGorGor3Link.txt # 2683571923 bases of 3049335806 (88.005%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 gorGor3) > rbest.log 2>&1 & # real 42m25.526s # and for the swap: mkdir /hive/data/genomes/gorGor3/bed/blastz.hg38.swap cd /hive/data/genomes/gorGor3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGorGor3.2014-12-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 116m45.998s cat fb.gorGor3.chainHg38Link.txt # 2588342923 bases of 2822760080 (91.695%) in intersection time (doRecipBest.pl -buildDir=`pwd` gorGor3 hg38) > rbest.log 2>&1 # real 42m41.291s ######################################################################### # LASTZ human/hg38 Baboon/papAnu2 - (DONE - 2014-12-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPapAnu2.2014-12-13 cd /hive/data/genomes/hg38/bed/lastzPapAnu2.2014-12-13 cp -p \ /hive/users/hiram/multiz/100way/hg38.papAnu2/hg38.papAnu2.tuning.top200.txt \ ./hg38.papAnu2.tuning.Q.txt cat << '_EOF_' > DEF # human vs Baboon # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.papAnu2/hg38.papAnu2.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzPapAnu2.2014-12-13/hg38.papAnu2.tuning.Q.txt # A C G T # A 100 -173 -45 -144 # C -173 92 -175 -45 # G -45 -175 92 -173 # T -144 -45 -173 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Baboon papAnu2 SEQ2_DIR=/hive/data/genomes/papAnu2/papAnu2.2bit SEQ2_LEN=/hive/data/genomes/papAnu2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPapAnu2.2014-12-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 406m41.281s cat fb.hg38.chainPapAnu2Link.txt # 2566899753 bases of 3049335806 (84.179%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 papAnu2) > rbest.log 2>&1 & # real 63m38.539s # and for the swap: mkdir /hive/data/genomes/papAnu2/bed/blastz.hg38.swap cd /hive/data/genomes/papAnu2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPapAnu2.2014-12-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 118m55.487s cat fb.papAnu2.chainHg38Link.txt # 2444845897 bases of 2893250291 (84.502%) in intersection time (doRecipBest.pl -buildDir=`pwd` papAnu2 hg38) > rbest.log 2>&1 # real 57m47.118s ######################################################################### # LASTZ human/hg38 Proboscis monkey/nasLar1 - (DONE - 2014-12-15 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15 cd /hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15 cp -p \ /hive/users/hiram/multiz/100way/hg38.nasLar1/hg38.nasLar1.tuning.top300.txt \ ./hg38.nasLar1.tuning.Q.txt cat << '_EOF_' > DEF # human vs Proboscis monkey # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.nasLar1/hg38.nasLar1.tuning.top300.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15/hg38.nasLar1.tuning.Q.txt # A C G T # A 100 -177 -41 -145 # C -177 94 -181 -41 # G -41 -181 94 -177 # T -145 -41 -177 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Proboscis monkey nasLar1 SEQ2_DIR=/hive/data/genomes/nasLar1/nasLar1.2bit SEQ2_LEN=/hive/data/genomes/nasLar1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=700 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 485m32.959s cat fb.hg38.chainNasLar1Link.txt # 2272993702 bases of 3049335806 (74.541%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 nasLar1) > rbest.log 2>&1 & # real 55m14.954s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 nasLar1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestNasLar1Link.txt # 2091196276 bases of 3049335806 (68.579%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15/axtChain netToAxt hg38.nasLar1.syn.net.gz hg38.nasLar1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/nasLar1/nasLar1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/nasLar1/chrom.sizes stdout \ | gzip -c > hg38.nasLar1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynNasLar1 hg38.nasLar1.syn.chain.gz netFilter -minGap=10 hg38.nasLar1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynNasLar1 stdin cd /hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15 featureBits hg38 chainSynNasLar1Link > fb.hg38.chainSynNasLar1Link.txt 2>&1 cat fb.hg38.chainSynNasLar1Link.txt # 1911545258 bases of 3049335806 (62.687%) in intersection # and for the swap: mkdir /hive/data/genomes/nasLar1/bed/blastz.hg38.swap cd /hive/data/genomes/nasLar1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzNasLar1.2014-12-15/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 616m45.774s cat fb.nasLar1.chainHg38Link.txt # 2157676376 bases of 2398172200 (89.972%) in intersection # did this in two parts when discovered this was running on ku, # stopped it there, then finished it off on hgwdev. time (doRecipBest.pl -buildDir=`pwd` nasLar1 hg38) > rbest.log 2>&1 # real 119m16.828s # real 536m38.397s ######################################################################### # LASTZ human/hg38 Tree shrew/tupBel1 - (DONE - 2014-12-15 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTupBel1.2014-12-15 cd /hive/data/genomes/hg38/bed/lastzTupBel1.2014-12-15 cp -p \ /hive/users/hiram/multiz/100way/hg38.tupBel1/hg38.tupBel1.tuning.top400.txt \ ./hg38.tupBel1.tuning.Q.txt cat << '_EOF_' > DEF # human vs Tree shrew # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.tupBel1/hg38.tupBel1.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=840 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzTupBel1.2014-12-15/hg38.tupBel1.tuning.Q.txt # A C G T # A 84 -203 -96 -292 # C -203 100 -204 -96 # G -96 -204 100 -203 # T -292 -96 -203 84 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Tree shrew tupBel1 SEQ2_DIR=/hive/data/genomes/tupBel1/tupBel1.2bit SEQ2_LEN=/hive/data/genomes/tupBel1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTupBel1.2014-12-15 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 266m34.212s cat fb.hg38.chainTupBel1Link.txt # 753229970 bases of 3049335806 (24.701%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 tupBel1) > rbest.log 2>&1 & # real 29m25.353s # and for the swap: mkdir /hive/data/genomes/tupBel1/bed/blastz.hg38.swap cd /hive/data/genomes/tupBel1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTupBel1.2014-12-15/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 192m16.970s cat fb.tupBel1.chainHg38Link.txt # 749930137 bases of 2137225476 (35.089%) in intersection time (doRecipBest.pl -buildDir=`pwd` tupBel1 hg38) > rbest.log 2>&1 # real 142m10.914s ######################################################################### # LASTZ human/hg38 Mouse lemur/micMur1 - (DONE - 2014-12-19 - Hiram) # for some odd reason, these results were lost # the same procedure was re-run March 2015 in: lastzMicMur1.2015-03-17 mkdir /hive/data/genomes/hg38/bed/lastzMicMur1.2014-12-19 cd /hive/data/genomes/hg38/bed/lastzMicMur1.2014-12-19 cp -p \ /hive/users/hiram/multiz/100way/hg38.micMur1/hg38.micMur1.tuning.top400.txt \ ./hg38.micMur1.tuning.Q.txt cat << '_EOF_' > DEF # human vs Mouse lemur # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.micMur1/hg38.micMur1.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzMicMur1.2014-12-19/hg38.micMur1.tuning.Q.txt # A C G T # A 100 -159 -37 -128 # C -159 93 -186 -37 # G -37 -186 93 -159 # T -128 -37 -159 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Mouse lemur micMur1 SEQ2_DIR=/hive/data/genomes/micMur1/micMur1.2bit SEQ2_LEN=/hive/data/genomes/micMur1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMicMur1.2014-12-19 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -stop=net -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > net.log 2>&1 # real 116m3.143s time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -continue=load -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > load.log 2>&1 # real 50m58.488s cat fb.hg38.chainMicMur1Link.txt # 1300627579 bases of 3049335806 (42.653%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 micMur1) > rbest.log 2>&1 & # real 39m44.440s # the re-run: # real 35m41.014s # and for the swap: mkdir /hive/data/genomes/micMur1/bed/blastz.hg38.swap cd /hive/data/genomes/micMur1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMicMur1.2014-12-19/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 223m37.152s cat fb.micMur1.chainHg38Link.txt # 1253236864 bases of 1852394361 (67.655%) in intersection time (doRecipBest.pl -buildDir=`pwd` micMur1 hg38) > rbest.log 2>&1 # real 182m5.563s ######################################################################### # LASTZ human/hg38 vs. sheep/oviAri3 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOviAri3.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzOviAri3.2015-04-27 cat << '_EOF_' > DEF # human vs sheep BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Sheep oviAri3 SEQ2_DIR=/hive/data/genomes/oviAri3/oviAri3.2bit SEQ2_LEN=/hive/data/genomes/oviAri3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOviAri3.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 527m8.200s cat fb.hg38.chainOviAri3Link.txt # 1382921590 bases of 3049335806 (45.352%) in intersection # replacing the previous tuned version: # 1256101876 bases of 3049335806 (41.193%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 oviAri3) > rbest.log 2>&1 & # real 68m34.171s # and for the swap: mkdir /hive/data/genomes/oviAri3/bed/blastz.hg38.swap cd /hive/data/genomes/oviAri3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOviAri3.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 98m39.757s cat fb.oviAri3.chainHg38Link.txt # 1312457473 bases of 2534335866 (51.787%) in intersection # replacing the previous tuned version: # 1193048482 bases of 2534335866 (47.075%) in intersection time (doRecipBest.pl -buildDir=`pwd` oviAri3 hg38) > rbest.log 2>&1 # real 47m50.965s ######################################################################### # LASTZ human/hg38 vs. medaka/oryLat2 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOryLat2.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzOryLat2.2015-02-06 cat << '_EOF_' > DEF # human vs medaka BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: medaka oryLat2 SEQ2_DIR=/hive/data/genomes/oryLat2/oryLat2.2bit SEQ2_LEN=/hive/data/genomes/oryLat2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=28 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOryLat2.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 59m44.479s cat fb.hg38.chainOryLat2Link.txt # 61061549 bases of 3049335806 (2.002%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 oryLat2) > rbest.log 2>&1 & # real 5m38.658s # and for the swap: mkdir /hive/data/genomes/oryLat2/bed/blastz.hg38.swap cd /hive/data/genomes/oryLat2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOryLat2.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 9m23.499s cat fb.oryLat2.chainHg38Link.txt # 47994675 bases of 700386597 (6.853%) in intersection time (doRecipBest.pl -buildDir=`pwd` oryLat2 hg38) > rbest.log 2>&1 # real 5m47.982s ######################################################################### # LASTZ human/hg38 vs. lizard/anoCar2 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAnoCar2.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzAnoCar2.2015-02-06 cat << '_EOF_' > DEF # human vs lizard BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: lizard anoCar2 SEQ2_DIR=/hive/data/genomes/anoCar2/anoCar2.2bit SEQ2_LEN=/hive/data/genomes/anoCar2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=28 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAnoCar2.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 279m15.159s cat fb.hg38.chainAnoCar2Link.txt # 109575794 bases of 3049335806 (3.593%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 anoCar2) > rbest.log 2>&1 & # real 17m23.686s # and for the swap: mkdir /hive/data/genomes/anoCar2/bed/blastz.hg38.swap cd /hive/data/genomes/anoCar2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAnoCar2.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 19m9.260s cat fb.anoCar2.chainHg38Link.txt # 88838401 bases of 1701353770 (5.222%) in intersection time (doRecipBest.pl -buildDir=`pwd` anoCar2 hg38) > rbest.log 2>&1 # real 7m31.302s ######################################################################### # LASTZ human/hg38 vs. green seaturtle/cheMyd1 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCheMyd1.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzCheMyd1.2015-02-06 cat << '_EOF_' > DEF # human vs green seaturtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: green seaturtle cheMyd1 SEQ2_DIR=/hive/data/genomes/cheMyd1/cheMyd1.2bit SEQ2_LEN=/hive/data/genomes/cheMyd1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=800 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCheMyd1.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 274m42.880s cat fb.hg38.chainCheMyd1Link.txt # 191988160 bases of 3049335806 (6.296%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 cheMyd1) > rbest.log 2>&1 & # real 8m1.248s # and for the swap: mkdir /hive/data/genomes/cheMyd1/bed/blastz.hg38.swap cd /hive/data/genomes/cheMyd1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCheMyd1.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 35m32.831s cat fb.cheMyd1.chainHg38Link.txt # 167987740 bases of 2110381997 (7.960%) in intersection time (doRecipBest.pl -buildDir=`pwd` cheMyd1 hg38) > rbest.log 2>&1 # real 14m38.900s ######################################################################### # LASTZ human/hg38 vs. painted turtle/chrPic2 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzChrPic2.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzChrPic2.2015-02-06 cat << '_EOF_' > DEF # human vs painted turtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: painted turtle chrPic2 SEQ2_DIR=/hive/data/genomes/chrPic2/chrPic2.2bit SEQ2_LEN=/hive/data/genomes/chrPic2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzChrPic2.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 286m29.793s cat fb.hg38.chainChrPic2Link.txt # 204556077 bases of 3049335806 (6.708%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 chrPic2) > rbest.log 2>&1 & # real 9m13.702s # and for the swap: mkdir /hive/data/genomes/chrPic2/bed/blastz.hg38.swap cd /hive/data/genomes/chrPic2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzChrPic2.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 35m11.829s cat fb.chrPic2.chainHg38Link.txt # 185888111 bases of 2173204089 (8.554%) in intersection time (doRecipBest.pl -buildDir=`pwd` chrPic2 hg38) > rbest.log 2>&1 # real 15m17.351s ######################################################################### # LASTZ human/hg38 vs. painted turtle/xipMac1 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzXipMac1.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzXipMac1.2015-02-06 cat << '_EOF_' > DEF # human vs painted turtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: painted turtle xipMac1 SEQ2_DIR=/hive/data/genomes/xipMac1/xipMac1.2bit SEQ2_LEN=/hive/data/genomes/xipMac1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzXipMac1.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 125m46.563s cat fb.hg38.chainXipMac1Link.txt # 57890952 bases of 3049335806 (1.898%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 xipMac1) > rbest.log 2>&1 & # real 3m48.235s # and for the swap: mkdir /hive/data/genomes/xipMac1/bed/blastz.hg38.swap cd /hive/data/genomes/xipMac1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXipMac1.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 9m11.951s cat fb.xipMac1.chainHg38Link.txt # 48535752 bases of 652815383 (7.435%) in intersection time (doRecipBest.pl -buildDir=`pwd` xipMac1 hg38) > rbest.log 2>&1 # real 6m4.065s ######################################################################### # LASTZ human/hg38 vs. Pundamilia nyererei/punNye1 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPunNye1.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzPunNye1.2015-02-06 cat << '_EOF_' > DEF # human vs Pundamilia nyererei BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: Pundamilia nyererei punNye1 SEQ2_DIR=/hive/data/genomes/punNye1/punNye1.2bit SEQ2_LEN=/hive/data/genomes/punNye1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPunNye1.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 134m6.741s cat fb.hg38.chainPunNye1Link.txt # 54487438 bases of 3049335806 (1.787%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 punNye1) > rbest.log 2>&1 & # real 4m39.292s # and for the swap: mkdir /hive/data/genomes/punNye1/bed/blastz.hg38.swap cd /hive/data/genomes/punNye1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPunNye1.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m40.110s cat fb.punNye1.chainHg38Link.txt # 47965851 bases of 698757151 (6.864%) in intersection time (doRecipBest.pl -buildDir=`pwd` punNye1 hg38) > rbest.log 2>&1 # real 5m7.941s ######################################################################### # LASTZ human/hg38 vs. Zebra Mbuna/mayZeb1 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMayZeb1.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzMayZeb1.2015-02-06 cat << '_EOF_' > DEF # human vs Zebra Mbuna BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: Zebra Mbuna mayZeb1 SEQ2_DIR=/hive/data/genomes/mayZeb1/mayZeb1.2bit SEQ2_LEN=/hive/data/genomes/mayZeb1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMayZeb1.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1066m37.973s cat fb.hg38.chainMayZeb1Link.txt # 55052422 bases of 3049335806 (1.805%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 mayZeb1) > rbest.log 2>&1 & # real 4m49.016s # and for the swap: mkdir /hive/data/genomes/mayZeb1/bed/blastz.hg38.swap cd /hive/data/genomes/mayZeb1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMayZeb1.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m24.648s cat fb.mayZeb1.chainHg38Link.txt # 48376552 bases of 713527863 (6.780%) in intersection time (doRecipBest.pl -buildDir=`pwd` mayZeb1 hg38) > rbest.log 2>&1 # real 4m57.850s ######################################################################### # LASTZ human/hg38 vs. zebrafish/danRer10 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzDanRer10.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzDanRer10.2015-02-06 cat << '_EOF_' > DEF # human vs zebrafish BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: zebrafish danRer10 SEQ2_DIR=/hive/data/genomes/danRer10/danRer10.2bit SEQ2_LEN=/hive/data/genomes/danRer10/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzDanRer10.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2785m54.894s cat fb.hg38.chainDanRer10Link.txt # 102378031 bases of 3049335806 (3.357%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 danRer10) > rbest.log 2>&1 & # real 7m50.594s # and for the swap: mkdir /hive/data/genomes/danRer10/bed/blastz.hg38.swap cd /hive/data/genomes/danRer10/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzDanRer10.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 37m50.204s cat fb.danRer10.chainHg38Link.txt # 97391181 bases of 1369683683 (7.110%) in intersection time (doRecipBest.pl -buildDir=`pwd` danRer10 hg38) > rbest.log 2>&1 # real 8m37.556s ######################################################################### # LASTZ human/hg38 vs. lamprey/petMar2 - (DONE - 2015-02-06 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPetMar2.2015-02-06 cd /hive/data/genomes/hg38/bed/lastzPetMar2.2015-02-06 cat << '_EOF_' > DEF # human vs lamprey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: lamprey petMar2 SEQ2_DIR=/hive/data/genomes/petMar2/petMar2.2bit SEQ2_LEN=/hive/data/genomes/petMar2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPetMar2.2015-02-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 120m15.847s cat fb.hg38.chainPetMar2Link.txt # 38581766 bases of 3049335806 (1.265%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 petMar2) > rbest.log 2>&1 & # real 2m51.935s # and for the swap: mkdir /hive/data/genomes/petMar2/bed/blastz.hg38.swap cd /hive/data/genomes/petMar2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPetMar2.2015-02-06/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m48.057s cat fb.petMar2.chainHg38Link.txt # 25633579 bases of 647368134 (3.960%) in intersection time (doRecipBest.pl -buildDir=`pwd` petMar2 hg38) > rbest.log 2>&1 # real 4m46.757s ######################################################################### # LASTZ human/hg38 vs. Aardvark/oryAfe1 - (DONE - 2015-04-23 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOryAfe1.2015-04-23 cd /hive/data/genomes/hg38/bed/lastzOryAfe1.2015-04-23 cat << '_EOF_' > DEF # human vs Aardvark BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Aardvark oryAfe1 SEQ2_DIR=/hive/data/genomes/oryAfe1/oryAfe1.2bit SEQ2_LEN=/hive/data/genomes/oryAfe1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOryAfe1.2015-04-23 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 472m21.083s cat fb.hg38.chainOryAfe1Link.txt # 1236908970 bases of 3049335806 (40.563%) in intersection # replacing previous tuned version: # 1113801383 bases of 3049335806 (36.526%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 oryAfe1) > rbest.log 2>&1 & # real 34m51.856s # and for the swap: mkdir /hive/data/genomes/oryAfe1/bed/blastz.hg38.swap cd /hive/data/genomes/oryAfe1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOryAfe1.2015-04-23/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 105m58.107s cat fb.oryAfe1.chainHg38Link.txt # 1164699059 bases of 3415340621 (34.102%) in intersection # replacing previous tuned version: # 1048528734 bases of 3415340621 (30.701%) in intersection time (doRecipBest.pl -buildDir=`pwd` oryAfe1 hg38) > rbest.log 2>&1 # real 38m36.380s ######################################################################### # LASTZ human/hg38 vs. White rhinoceros/cerSim1 - (DONE - 2015-02-22 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCerSim1.2015-02-22 cd /hive/data/genomes/hg38/bed/lastzCerSim1.2015-02-22 cat << '_EOF_' > DEF # human vs White rhinoceros BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: White rhinoceros cerSim1 SEQ2_DIR=/hive/data/genomes/cerSim1/cerSim1.2bit SEQ2_LEN=/hive/data/genomes/cerSim1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCerSim1.2015-02-22 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1227m14.067s cat fb.hg38.chainCerSim1Link.txt # 1726920355 bases of 3049335806 (56.633%) in intersection # replacing previous tuned version: # 1618425081 bases of 3049335806 (53.075%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 cerSim1) > rbest.log 2>&1 & # real 42m41.811s # and for the swap: mkdir /hive/data/genomes/cerSim1/bed/blastz.hg38.swap cd /hive/data/genomes/cerSim1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCerSim1.2015-02-22/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 117m59.898s cat fb.cerSim1.chainHg38Link.txt # 1638614141 bases of 2366858012 (69.232%) in intersection # replacing previous tuned version: # 1534238724 bases of 2366858012 (64.822%) in intersection time (doRecipBest.pl -buildDir=`pwd` cerSim1 hg38) > rbest.log 2>&1 # real 78m9.790s ######################################################################### # LASTZ human/hg38 vs. Cape golden mole/chrAsi1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzChrAsi1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzChrAsi1.2015-02-17 cat << '_EOF_' > DEF # human vs Cape golden mole BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Cape golden mole chrAsi1 SEQ2_DIR=/hive/data/genomes/chrAsi1/chrAsi1.2bit SEQ2_LEN=/hive/data/genomes/chrAsi1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzChrAsi1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3754m43.142s cat fb.hg38.chainChrAsi1Link.txt # 1015855213 bases of 3049335806 (33.314%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 chrAsi1) \ > rbest.log 2>&1 & # real 42m12.650s # and for the swap: mkdir /hive/data/genomes/chrAsi1/bed/blastz.hg38.swap cd /hive/data/genomes/chrAsi1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzChrAsi1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 103m1.384s cat fb.chrAsi1.chainHg38Link.txt # 977711721 bases of 3363564316 (29.068%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` chrAsi1 hg38) \ > rbest.log 2>&1 # real 47m40.074s ######################################################################### # LASTZ human/hg38 vs. Big brown bat/eptFus1 - (DONE - 2015-04-24 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEptFus1.2015-04-24 cd /hive/data/genomes/hg38/bed/lastzEptFus1.2015-04-24 cat << '_EOF_' > DEF # human vs Big brown bat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Big brown bat eptFus1 SEQ2_DIR=/hive/data/genomes/eptFus1/eptFus1.2bit SEQ2_LEN=/hive/data/genomes/eptFus1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEptFus1.2015-04-24 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 377m2.703s cat fb.hg38.chainEptFus1Link.txt # 1193001967 bases of 3049335806 (39.123%) in intersection # replacing previous tuned version: # 1109543782 bases of 3049335806 (36.386%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 eptFus1) > rbest.log 2>&1 & # real 33m10.892s # and for the swap: mkdir /hive/data/genomes/eptFus1/bed/blastz.hg38.swap cd /hive/data/genomes/eptFus1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEptFus1.2015-04-24/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 91m1.466s cat fb.eptFus1.chainHg38Link.txt # 1127211856 bases of 1811378799 (62.229%) in intersection # replacing previous tuned version: # 1051896885 bases of 1811378799 (58.072%) in intersection time (doRecipBest.pl -buildDir=`pwd` eptFus1 hg38) > rbest.log 2>&1 # real 36m31.110s ######################################################################### # LASTZ human/hg38 vs. Chinese tree shrew/tupChi1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTupChi1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzTupChi1.2015-02-17 cat << '_EOF_' > DEF # human vs Chinese tree shrew BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Chinese tree shrew tupChi1 SEQ2_DIR=/hive/data/genomes/tupChi1/tupChi1.2bit SEQ2_LEN=/hive/data/genomes/tupChi1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=120 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTupChi1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2638m13.806s cat fb.hg38.chainTupChi1Link.txt # 1379994626 bases of 3049335806 (45.256%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 tupChi1) \ > rbest.log 2>&1 & # real 60m22.301s # and for the swap: mkdir /hive/data/genomes/tupChi1/bed/blastz.hg38.swap cd /hive/data/genomes/tupChi1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTupChi1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 119m54.935s cat fb.tupChi1.chainHg38Link.txt # 1362665822 bases of 2706389135 (50.350%) in intersection time (doRecipBest.pl -buildDir=`pwd` tupChi1 hg38) > rbest.log 2>&1 # real 43m38.032s ######################################################################### # LASTZ human/hg38 vs. horse/equCab2 - (DONE - 2015-02-22 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22 cd /hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22 cat << '_EOF_' > DEF # human vs horse BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: horse equCab2 SEQ2_DIR=/hive/data/genomes/equCab2/equCab2.2bit SEQ2_LEN=/hive/data/genomes/equCab2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=10 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 966m54.143s cat fb.hg38.chainEquCab2Link.txt # 1691134629 bases of 3049335806 (55.459%) in intersection # replacing the previous tuned version: # 1588178706 bases of 3049335806 (52.083%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 equCab2) > rbest.log 2>&1 & # real 81m49.399s # load up the recip best chainNet tables time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 equCab2) > loadRBest.log 2>&1 & # real 11m38.247s cat fb.hg38.chainRBestEquCab2Link.txt # 1547949213 bases of 3049335806 (50.763%) in intersection # create and load up the syntenic chainNet tables 2017-10-30 cd /hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22/axtChain netToAxt hg38.equCab2.syn.net.gz hg38.equCab2.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/equCab2/equCab2.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/equCab2/chrom.sizes stdout \ | gzip -c > hg38.equCab2.syn.chain.gz hgLoadChain -tIndex hg38 chainSynEquCab2 hg38.equCab2.syn.chain.gz netFilter -minGap=10 hg38.equCab2.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynEquCab2 stdin cd /hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22 featureBits hg38 chainSynEquCab2Link > fb.hg38.chainSynEquCab2Link.txt 2>&1 cat fb.hg38.chainSynEquCab2Link.txt # 1625260798 bases of 3049335806 (53.299%) in intersection # and for the swap: mkdir /hive/data/genomes/equCab2/bed/blastz.hg38.swap cd /hive/data/genomes/equCab2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEquCab2.2015-02-22/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 123m57.167s cat fb.equCab2.chainHg38Link.txt # 1617562865 bases of 2428790173 (66.600%) in intersection # replacing the previous tuned version: # 1516707888 bases of 2428790173 (62.447%) in intersection time (doRecipBest.pl -buildDir=`pwd` equCab2 hg38) > rbest.log 2>&1 # real 43m47.647s ######################################################################### # LASTZ human/hg38 vs. Bactrian camel/camFer1 - (DONE - 2015-04-24 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCamFer1.2015-04-24 cd /hive/data/genomes/hg38/bed/lastzCamFer1.2015-04-24 cat << '_EOF_' > DEF # human vs Bactrian camel BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Bactrian camel camFer1 SEQ2_DIR=/hive/data/genomes/camFer1/camFer1.2bit SEQ2_LEN=/hive/data/genomes/camFer1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCamFer1.2015-04-24 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 382m39.001s cat fb.hg38.chainCamFer1Link.txt # 1497063551 bases of 3049335806 (49.095%) in intersection # replacing the previous tuned version: # 1408973544 bases of 3049335806 (46.206%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 camFer1) > rbest.log 2>&1 & # real 41m32.785s # and for the swap: mkdir /hive/data/genomes/camFer1/bed/blastz.hg38.swap cd /hive/data/genomes/camFer1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCamFer1.2015-04-24/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 99m10.651s cat fb.camFer1.chainHg38Link.txt # 1414980564 bases of 1985442806 (71.268%) in intersection # replacing the previous tuned version: # 1335694086 bases of 1985442806 (67.274%) in intersection time (doRecipBest.pl -buildDir=`pwd` camFer1 hg38) > rbest.log 2>&1 # real 40m5.483s ######################################################################### # LASTZ human/hg38 vs. alpaca/vicPac2 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzVicPac2.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzVicPac2.2015-04-28 cat << '_EOF_' > DEF # human vs alpaca BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: alpaca vicPac2 SEQ2_DIR=/hive/data/genomes/vicPac2/vicPac2.2bit SEQ2_LEN=/hive/data/genomes/vicPac2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzVicPac2.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1562m13.104s cat fb.hg38.chainVicPac2Link.txt # 1491400921 bases of 3049335806 (48.909%) in intersection # replacing the previous tuned version: # 1399262189 bases of 3049335806 (45.887%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 vicPac2) > rbest.log 2>&1 & # real 39m21.890s # and for the swap: mkdir /hive/data/genomes/vicPac2/bed/blastz.hg38.swap cd /hive/data/genomes/vicPac2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzVicPac2.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 229m47.891s cat fb.vicPac2.chainHg38Link.txt # 1429121865 bases of 2078582856 (68.755%) in intersection # replacing the previous tuned version: # 1342041434 bases of 2078582856 (64.565%) in intersection time (doRecipBest.pl -buildDir=`pwd` vicPac2 hg38) > rbest.log 2>&1 # real 364m14.802s finished manually real 101m13.133s time (doRecipBest.pl -workhorse=hgwdev -continue=download \ -buildDir=`pwd` vicPac2 hg38) > rbestDownload.log 2>&1 # real 0m4.424s ######################################################################### # LASTZ human/hg38 vs. dolphin/turTru2 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTurTru2.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzTurTru2.2015-04-28 cat << '_EOF_' > DEF # human vs dolphin BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: dolphin turTru2 SEQ2_DIR=/hive/data/genomes/turTru2/turTru2.2bit SEQ2_LEN=/hive/data/genomes/turTru2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTurTru2.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1495m0.218s cat fb.hg38.chainTurTru2Link.txt # 1516370469 bases of 3049335806 (49.728%) in intersection # replacing the previous tuned version: # 1404889155 bases of 3049335806 (46.072%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 turTru2) > rbest.log 2>&1 & # real 40m22.097s # and for the swap: mkdir /hive/data/genomes/turTru2/bed/blastz.hg38.swap cd /hive/data/genomes/turTru2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTurTru2.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 253m58.332s cat fb.turTru2.chainHg38Link.txt # 1431921957 bases of 2332402443 (61.393%) in intersection # replacing the previous tuned version: # 1329424627 bases of 2332402443 (56.998%) in intersection time (doRecipBest.pl -buildDir=`pwd` turTru2 hg38) > rbest.log 2>&1 # real 119m47.159s ######################################################################### # LASTZ human/hg38 vs. Killer whale/orcOrc1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOrcOrc1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzOrcOrc1.2015-04-28 cat << '_EOF_' > DEF # human vs Killer whale BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Killer whale orcOrc1 SEQ2_DIR=/hive/data/genomes/orcOrc1/orcOrc1.2bit SEQ2_LEN=/hive/data/genomes/orcOrc1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=5 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOrcOrc1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1874m13.873s cat fb.hg38.chainOrcOrc1Link.txt # 1546274677 bases of 3049335806 (50.709%) in intersection # replacing the previous tuned version: # 1441746760 bases of 3049335806 (47.281%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 orcOrc1) > rbest.log 2>&1 & # real 43m21.901s # and for the swap: mkdir /hive/data/genomes/orcOrc1/bed/blastz.hg38.swap cd /hive/data/genomes/orcOrc1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOrcOrc1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 100m56.186s cat fb.orcOrc1.chainHg38Link.txt # 1447927506 bases of 2249582127 (64.364%) in intersection # replacing the previous tuned version: # 1354015119 bases of 2249582127 (60.190%) in intersection time (doRecipBest.pl -buildDir=`pwd` orcOrc1 hg38) > rbest.log 2>&1 # real 41m38.435s ######################################################################### # LASTZ human/hg38 vs. squirrel/speTri2 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSpeTri2.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzSpeTri2.2015-04-28 cat << '_EOF_' > DEF # human vs squirrel BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: squirrel speTri2 SEQ2_DIR=/hive/data/genomes/speTri2/speTri2.2bit SEQ2_LEN=/hive/data/genomes/speTri2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSpeTri2.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1669m55.874s cat fb.hg38.chainSpeTri2Link.txt # 1472314467 bases of 3049335806 (48.283%) in intersection # replacing the previous tuned version: # 1363949428 bases of 3049335806 (44.729%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 speTri2) > rbest.log 2>&1 & # real 47m19.925s # and for the swap: mkdir /hive/data/genomes/speTri2/bed/blastz.hg38.swap cd /hive/data/genomes/speTri2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSpeTri2.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 114m57.250s cat fb.speTri2.chainHg38Link.txt # 1429491323 bases of 2311060300 (61.854%) in intersection # replacing the previous tuned version: # 1323562747 bases of 2311060300 (57.271%) in intersection time (doRecipBest.pl -buildDir=`pwd` speTri2 hg38) > rbest.log 2>&1 # real 46m47.951s ######################################################################### # LASTZ human/hg38 vs. Black flying fox/pteAle1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPteAle1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzPteAle1.2015-04-28 cat << '_EOF_' > DEF # human vs Black flying fox BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Black flying fox pteAle1 SEQ2_DIR=/hive/data/genomes/pteAle1/pteAle1.2bit SEQ2_LEN=/hive/data/genomes/pteAle1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPteAle1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1615m3.913s cat fb.hg38.chainPteAle1Link.txt # 1472264278 bases of 3049335806 (48.281%) in intersection # replacing the previous tuned version: # 1390855083 bases of 3049335806 (45.612%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 pteAle1) > rbest.log 2>&1 & # real 102m6.597s # and for the swap: mkdir /hive/data/genomes/pteAle1/bed/blastz.hg38.swap cd /hive/data/genomes/pteAle1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPteAle1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 144m41.676s cat fb.pteAle1.chainHg38Link.txt # 1383942731 bases of 1944625202 (71.168%) in intersection # replacing the previous tuned version: # 1310659904 bases of 1944625202 (67.399%) in intersection time (doRecipBest.pl -buildDir=`pwd` pteAle1 hg38) > rbest.log 2>&1 # real 51m1.756s ######################################################################### # LASTZ human/hg38 vs. pig/susScr3 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSusScr3.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzSusScr3.2015-04-28 cat << '_EOF_' > DEF # human vs pig BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: pig susScr3 SEQ2_DIR=/hive/data/genomes/susScr3/susScr3.2bit SEQ2_LEN=/hive/data/genomes/susScr3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSusScr3.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1570m22.537s cat fb.hg38.chainSusScr3Link.txt # 1362333591 bases of 3049335806 (44.676%) in intersection # replacing the previous tuned version: # 1260167798 bases of 3049335806 (41.326%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 susScr3) > rbest.log 2>&1 & # real 49m20.123s # and for the swap: mkdir /hive/data/genomes/susScr3/bed/blastz.hg38.swap cd /hive/data/genomes/susScr3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSusScr3.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 112m33.386s cat fb.susScr3.chainHg38Link.txt # 1446310692 bases of 2525294057 (57.273%) in intersection # replacing the previous tuned version: # 1338540526 bases of 2525294057 (53.005%) in intersection time (doRecipBest.pl -buildDir=`pwd` susScr3 hg38) > rbest.log 2>&1 # real 47m22.984s ######################################################################### # LASTZ human/hg38 vs. elephant/loxAfr3 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzLoxAfr3.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzLoxAfr3.2015-04-28 cat << '_EOF_' > DEF # human vs elephant BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: elephant loxAfr3 SEQ2_DIR=/hive/data/genomes/loxAfr3/loxAfr3.2bit SEQ2_LEN=/hive/data/genomes/loxAfr3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzLoxAfr3.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1717m57.837s cat fb.hg38.chainLoxAfr3Link.txt # 1378739469 bases of 3049335806 (45.214%) in intersection # replacing the previous tuned version: # 1277792660 bases of 3049335806 (41.904%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 loxAfr3) > rbest.log 2>&1 & # real 140m31.966s # and for the swap: mkdir /hive/data/genomes/loxAfr3/bed/blastz.hg38.swap cd /hive/data/genomes/loxAfr3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzLoxAfr3.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 121m44.548s cat fb.loxAfr3.chainHg38Link.txt # 1319251552 bases of 3118565340 (42.303%) in intersection # replacing the previous tuned version: # 1220708619 bases of 3118565340 (39.143%) in intersection time (doRecipBest.pl -buildDir=`pwd` loxAfr3 hg38) > rbest.log 2>&1 # real 45m9.386s ######################################################################### # LASTZ human/hg38 vs. Naked mole rat/hetGla2 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzHetGla2.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzHetGla2.2015-04-28 cat << '_EOF_' > DEF # human vs Naked mole rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Naked mole rat hetGla2 SEQ2_DIR=/hive/data/genomes/hetGla2/hetGla2.2bit SEQ2_LEN=/hive/data/genomes/hetGla2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzHetGla2.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1681m38.688s cat fb.hg38.chainHetGla2Link.txt # 1410266478 bases of 3049335806 (46.248%) in intersection # replacing the previous tuned version: # 1290312728 bases of 3049335806 (42.315%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 hetGla2) > rbest.log 2>&1 & # real 137m40.853s # and for the swap: mkdir /hive/data/genomes/hetGla2/bed/blastz.hg38.swap cd /hive/data/genomes/hetGla2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzHetGla2.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 114m42.322s cat fb.hetGla2.chainHg38Link.txt # 1362365778 bases of 2314771103 (58.855%) in intersection # replacing the previous tuned version: # 1251393586 bases of 2314771103 (54.061%) in intersection time (doRecipBest.pl -buildDir=`pwd` hetGla2 hg38) > rbest.log 2>&1 # real 41m49.099s ######################################################################### # LASTZ human/hg38 vs. megabat/pteVam1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPteVam1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzPteVam1.2015-04-28 cat << '_EOF_' > DEF # human vs megabat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: megabat pteVam1 SEQ2_DIR=/hive/data/genomes/pteVam1/pteVam1.2bit SEQ2_LEN=/hive/data/genomes/pteVam1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=120 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPteVam1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1499m5.523s cat fb.hg38.chainPteVam1Link.txt # 1339387555 bases of 3049335806 (43.924%) in intersection # replacing the previous tuned version: # 1250608381 bases of 3049335806 (41.012%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 pteVam1) > rbest.log 2>&1 & # real 33m53.542s # and for the swap: mkdir /hive/data/genomes/pteVam1/bed/blastz.hg38.swap cd /hive/data/genomes/pteVam1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPteVam1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 135m10.167s cat fb.pteVam1.chainHg38Link.txt # 1279228346 bases of 1839436660 (69.545%) in intersection # replacing the previous tuned version: # 1198492243 bases of 1839436660 (65.155%) in intersection time (doRecipBest.pl -buildDir=`pwd` pteVam1 hg38) > rbest.log 2>&1 # real 152m29.972s ######################################################################### # LASTZ human/hg38 vs. cat/felCat8 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFelCat8.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzFelCat8.2015-04-28 cat << '_EOF_' > DEF # human vs cat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: cat felCat8 SEQ2_DIR=/hive/data/genomes/felCat8/felCat8.2bit SEQ2_LEN=/hive/data/genomes/felCat8/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFelCat8.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2218m28.035s cat fb.hg38.chainFelCat8Link.txt # 1576029345 bases of 3049335806 (51.684%) in intersection # replacing the previous tuned version: # 1454517955 bases of 3049335806 (47.700%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 felCat8) > rbest.log 2>&1 & # real 57m53.174s # and for the swap: mkdir /hive/data/genomes/felCat8/bed/blastz.hg38.swap cd /hive/data/genomes/felCat8/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFelCat8.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 300m16.338s cat fb.felCat8.chainHg38Link.txt # 1527336267 bases of 2599716822 (58.750%) in intersection # replacing the previous tuned version: # 1408124069 bases of 2599716822 (54.165%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` felCat8 hg38) \ > rbest.log 2>&1 # real 113m7.878s # finished broken recipBest run: # real 148m36.100s ######################################################################### # LASTZ human/hg38 vs. panda/ailMel1 - (DONE - 2015-02-11 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAilMel1.2015-02-11 cd /hive/data/genomes/hg38/bed/lastzAilMel1.2015-02-11 # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.ailMel1/hg38.ailMel1.tuning.top400.txt cp -p /hive/users/hiram/multiz/100way/hg38.ailMel1/hg38.ailMel1.tuning.top400.txt \ ./hg38.ailMel1.tuning.Q.txt cat << '_EOF_' > DEF # human vs panda BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_X=740 BLASTZ_Y=3400 BLASTZ_M=50 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzAilMel1.2015-02-11/hg38.ailMel1.tuning.Q.txt # A C G T # A 74 -117 -23 -133 # C -117 100 -112 -23 # G -23 -112 100 -117 # T -133 -23 -117 74 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: panda ailMel1 SEQ2_DIR=/hive/data/genomes/ailMel1/ailMel1.2bit SEQ2_LEN=/hive/data/genomes/ailMel1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=130 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAilMel1.2015-02-11 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 830m30.518s cat fb.hg38.chainAilMel1Link.txt # 1470587412 bases of 3049335806 (48.226%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 ailMel1) > rbest.log 2>&1 & # real 34m53.243s # and for the swap: mkdir /hive/data/genomes/ailMel1/bed/blastz.hg38.swap cd /hive/data/genomes/ailMel1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAilMel1.2015-02-11/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 88m43.119s cat fb.ailMel1.chainHg38Link.txt # 1384233285 bases of 2245312831 (61.650%) in intersection time (doRecipBest.pl -buildDir=`pwd` ailMel1 hg38) > rbest.log 2>&1 # real 41m48.012s ######################################################################### # LASTZ human/hg38 vs. ferret/musFur1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMusFur1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzMusFur1.2015-04-28 cat << '_EOF_' > DEF # human vs ferret BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: ferret musFur1 SEQ2_DIR=/hive/data/genomes/musFur1/musFur1.2bit SEQ2_LEN=/hive/data/genomes/musFur1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMusFur1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 405m30.959s cat fb.hg38.chainMusFur1Link.txt # 1513410953 bases of 3049335806 (49.631%) in intersection # replacing the previous tuned version: # 1396051514 bases of 3049335806 (45.782%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 musFur1) > rbest.log 2>&1 & # real 86m22.214s # and for the swap: mkdir /hive/data/genomes/musFur1/bed/blastz.hg38.swap cd /hive/data/genomes/musFur1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMusFur1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 103m55.044s cat fb.musFur1.chainHg38Link.txt # 1421314098 bases of 2277906570 (62.396%) in intersection # replacing the previous tuned version: # 1313363964 bases of 2277906570 (57.657%) in intersection time (doRecipBest.pl -buildDir=`pwd` musFur1 hg38) > rbest.log 2>&1 # real 40m15.023s ######################################################################### # LASTZ human/hg38 vs. guinea pig/cavPor3 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCavPor3.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzCavPor3.2015-04-27 cat << '_EOF_' > DEF # human vs guinea pig BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: guinea pig cavPor3 SEQ2_DIR=/hive/data/genomes/cavPor3/cavPor3.2bit SEQ2_LEN=/hive/data/genomes/cavPor3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCavPor3.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1456m13.633s cat fb.hg38.chainCavPor3Link.txt # 1292035815 bases of 3049335806 (42.371%) in intersection # replacing the previous tuned version: # 1155740911 bases of 3049335806 (37.901%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 cavPor3) > rbest.log 2>&1 & # real 40m47.501s # and for the swap: mkdir /hive/data/genomes/cavPor3/bed/blastz.hg38.swap cd /hive/data/genomes/cavPor3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCavPor3.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 147m52.206s cat fb.cavPor3.chainHg38Link.txt # 1278427131 bases of 2663369733 (48.000%) in intersection # replacing the previous tuned version: # 1142636457 bases of 2663369733 (42.902%) in intersection time (doRecipBest.pl -buildDir=`pwd` cavPor3 hg38) > rbest.log 2>&1 # real 132m10.182s ######################################################################### # LASTZ human/hg38 vs. armadillo/dasNov3 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28 cat << '_EOF_' > DEF # human vs armadillo BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: armadillo dasNov3 SEQ2_DIR=/hive/data/genomes/dasNov3/dasNov3.2bit SEQ2_LEN=/hive/data/genomes/dasNov3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=80 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1719m25.419s cat fb.hg38.chainDasNov3Link.txt # 1382853067 bases of 3049335806 (45.349%) in intersection # replacing the previous tuned version: # 1287831558 bases of 3049335806 (42.233%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 dasNov3) > rbest.log 2>&1 & # real 491m51.020s # load up the recip best chainNet tables time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 dasNov3) > loadRBest.log 2>&1 & # real 12m39.283s cat fb.hg38.chainRBestDasNov3Link.txt # 1267819323 bases of 3049335806 (41.577%) in intersection # create and load up the syntenic chainNet tables 2017-10-30 cd /hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28/axtChain netToAxt hg38.dasNov3.syn.net.gz hg38.dasNov3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/dasNov3/dasNov3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/dasNov3/chrom.sizes stdout \ | gzip -c > hg38.dasNov3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynDasNov3 hg38.dasNov3.syn.chain.gz netFilter -minGap=10 hg38.dasNov3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynDasNov3 stdin cd /hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28 featureBits hg38 chainSynDasNov3Link > fb.hg38.chainSynDasNov3Link.txt 2>&1 cat fb.hg38.chainSynDasNov3Link.txt # 1302517110 bases of 3049335806 (42.715%) in intersection # and for the swap: mkdir /hive/data/genomes/dasNov3/bed/blastz.hg38.swap cd /hive/data/genomes/dasNov3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzDasNov3.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 139m24.821s cat fb.dasNov3.chainHg38Link.txt # 1382479617 bases of 3299882059 (41.895%) in intersection # replacing the previous tuned version: # 1284164290 bases of 3299882059 (38.915%) in intersection time (doRecipBest.pl -buildDir=`pwd` dasNov3 hg38) > rbest.log 2>&1 # real 78m34.471s ######################################################################### # LASTZ human/hg38 vs. rabbit/oryCun2 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOryCun2.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzOryCun2.2015-04-27 cat << '_EOF_' > DEF # human vs rabbit BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: rabbit oryCun2 SEQ2_DIR=/hive/data/genomes/oryCun2/oryCun2.2bit SEQ2_LEN=/hive/data/genomes/oryCun2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=10 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOryCun2.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1143m17.631s cat fb.hg38.chainOryCun2Link.txt # 1308502981 bases of 3049335806 (42.911%) in intersection # replacing the previous tuned version: # 1177978746 bases of 3049335806 (38.631%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 oryCun2) > rbest.log 2>&1 & # real 39m0.464s # and for the swap: mkdir /hive/data/genomes/oryCun2/bed/blastz.hg38.swap cd /hive/data/genomes/oryCun2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOryCun2.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 107m40.781s cat fb.oryCun2.chainHg38Link.txt # 1259317035 bases of 2604023284 (48.360%) in intersection # replacing the previous tuned version: # 1136478377 bases of 2604023284 (43.643%) in intersection time (doRecipBest.pl -buildDir=`pwd` oryCun2 hg38) > rbest.log 2>&1 # real 74m17.119s ######################################################################### # LASTZ human/hg38 vs. Tibetan antelope/panHod1 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPanHod1.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzPanHod1.2015-04-27 cat << '_EOF_' > DEF # human vs Tibetan antelope BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Tibetan antelope panHod1 SEQ2_DIR=/hive/data/genomes/panHod1/panHod1.2bit SEQ2_LEN=/hive/data/genomes/panHod1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPanHod1.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1194m17.831s cat fb.hg38.chainPanHod1Link.txt # 1391091506 bases of 3049335806 (45.619%) in intersection # replacing the previous tuned version: # 1261119369 bases of 3049335806 (41.357%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 panHod1) > rbest.log 2>&1 & # real 84m43.209s # and for the swap: mkdir /hive/data/genomes/panHod1/bed/blastz.hg38.swap cd /hive/data/genomes/panHod1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPanHod1.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 112m26.689s cat fb.panHod1.chainHg38Link.txt # 1317338279 bases of 2507986438 (52.526%) in intersection # replacing the previous tuned version: # 1196606934 bases of 2507986438 (47.712%) in intersection time (doRecipBest.pl -buildDir=`pwd` panHod1 hg38) > rbest.log 2>&1 # real 441m32.946s finished manually real 53m30.864s time (doRecipBest.pl -workhorse=hgwdev -continue=download \ -buildDir=`pwd` panHod1 hg38) > rbestDownload.log 2>&1 # real 0m4.397s ######################################################################### # LASTZ human/hg38 vs. Weddell seal/lepWed1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzLepWed1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzLepWed1.2015-04-28 cat << '_EOF_' > DEF # human vs Weddell seal BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Weddell seal lepWed1 SEQ2_DIR=/hive/data/genomes/lepWed1/lepWed1.2bit SEQ2_LEN=/hive/data/genomes/lepWed1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzLepWed1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1527m39.249s cat fb.hg38.chainLepWed1Link.txt # 1557394982 bases of 3049335806 (51.073%) in intersection # replacing the previous tuned version: # 1446510291 bases of 3049335806 (47.437%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 lepWed1) > rbest.log 2>&1 & # real 70m0.849s # and for the swap: mkdir /hive/data/genomes/lepWed1/bed/blastz.hg38.swap cd /hive/data/genomes/lepWed1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzLepWed1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 112m55.510s cat fb.lepWed1.chainHg38Link.txt # 1459320253 bases of 2223164129 (65.642%) in intersection # replacing the previous tuned version: # 1358644851 bases of 2223164129 (61.113%) in intersection time (doRecipBest.pl -buildDir=`pwd` lepWed1 hg38) > rbest.log 2>&1 # real 83m25.807s ######################################################################### # LASTZ human/hg38 vs. Pacific walrus/odoRosDiv1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOdoRosDiv1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzOdoRosDiv1.2015-04-28 cat << '_EOF_' > DEF # human vs Pacific walrus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Pacific walrus odoRosDiv1 SEQ2_DIR=/hive/data/genomes/odoRosDiv1/odoRosDiv1.2bit SEQ2_LEN=/hive/data/genomes/odoRosDiv1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=10 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOdoRosDiv1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > do.log 2>&1 # real 1559m56.509s cat fb.hg38.chainOdoRosDiv1Link.txt # 1591525110 bases of 3049335806 (52.193%) in intersection # replacing the previous tuned version: # 1463226456 bases of 3049335806 (47.985%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 odoRosDiv1) > rbest.log 2>&1 & # real 68m19.885s # and for the swap: mkdir /hive/data/genomes/odoRosDiv1/bed/blastz.hg38.swap cd /hive/data/genomes/odoRosDiv1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOdoRosDiv1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 116m42.765s cat fb.odoRosDiv1.chainHg38Link.txt # 1492793949 bases of 2300235512 (64.897%) in intersection # replacing the previous tuned version: # 1376881973 bases of 2300235512 (59.858%) in intersection time (doRecipBest.pl -buildDir=`pwd` odoRosDiv1 hg38) > rbest.log 2>&1 # real 129m15.182s ######################################################################### # LASTZ human/hg38 vs. David's myotis bat/myoDav1 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMyoDav1.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzMyoDav1.2015-04-27 cat << '_EOF_' > DEF # human vs David's myotis bat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: David's myotis bat myoDav1 SEQ2_DIR=/hive/data/genomes/myoDav1/myoDav1.2bit SEQ2_LEN=/hive/data/genomes/myoDav1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=150 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMyoDav1.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1191m1.115s cat fb.hg38.chainMyoDav1Link.txt # 1180503256 bases of 3049335806 (38.713%) in intersection # replacing the previous tuned version: # 1063972348 bases of 3049335806 (34.892%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 myoDav1) > rbest.log 2>&1 & # real 38m14.019s # and for the swap: mkdir /hive/data/genomes/myoDav1/bed/blastz.hg38.swap cd /hive/data/genomes/myoDav1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMyoDav1.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 122m57.687s cat fb.myoDav1.chainHg38Link.txt # 1132451816 bases of 1878461987 (60.286%) in intersection # replacing the previous tuned version: # 1025255929 bases of 1878461987 (54.580%) in intersection time (doRecipBest.pl -buildDir=`pwd` myoDav1 hg38) > rbest.log 2>&1 # real 77m7.749s ######################################################################### # LASTZ human/hg38 vs. goat/capHir1 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCapHir1.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzCapHir1.2015-04-27 cat << '_EOF_' > DEF # human vs goat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: goat capHir1 SEQ2_DIR=/hive/data/genomes/capHir1/capHir1.2bit SEQ2_LEN=/hive/data/genomes/capHir1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=130 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCapHir1.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1473m2.628s cat fb.hg38.chainCapHir1Link.txt # 1380028096 bases of 3049335806 (45.257%) in intersection # replacing the previous tuned version: # 1259921542 bases of 3049335806 (41.318%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 capHir1) > rbest.log 2>&1 & # real 84m49.153s # and for the swap: mkdir /hive/data/genomes/capHir1/bed/blastz.hg38.swap cd /hive/data/genomes/capHir1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCapHir1.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 128m13.474s cat fb.capHir1.chainHg38Link.txt # 1314558467 bases of 2495939845 (52.668%) in intersection # replacing the previous tuned version: # 1201106945 bases of 2495939845 (48.122%) in intersection time (doRecipBest.pl -buildDir=`pwd` capHir1 hg38) > rbest.log 2>&1 # real 432m43.547s finished manually real 65m19.641s time (doRecipBest.pl -workhorse=hgwdev -continue=download \ -buildDir=`pwd` capHir1 hg38) > rbestDownload.log 2>&1 # real 0m4.386s ######################################################################### # LASTZ human/hg38 vs. microbat/myoLuc2 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMyoLuc2.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzMyoLuc2.2015-04-27 cat << '_EOF_' > DEF # human vs microbat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: microbat myoLuc2 SEQ2_DIR=/hive/data/genomes/myoLuc2/myoLuc2.2bit SEQ2_LEN=/hive/data/genomes/myoLuc2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMyoLuc2.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1062m31.557s cat fb.hg38.chainMyoLuc2Link.txt # 1176781597 bases of 3049335806 (38.591%) in intersection # replacing the previous tuned version: # 1071766600 bases of 3049335806 (35.148%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 myoLuc2) > rbest.log 2>&1 & # real 31m49.720s # and for the swap: mkdir /hive/data/genomes/myoLuc2/bed/blastz.hg38.swap cd /hive/data/genomes/myoLuc2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMyoLuc2.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 101m34.047s cat fb.myoLuc2.chainHg38Link.txt # 1174515059 bases of 1966419868 (59.729%) in intersection # replacing the previous tuned version: # 1075118724 bases of 1966419868 (54.674%) in intersection time (doRecipBest.pl -buildDir=`pwd` myoLuc2 hg38) > rbest.log 2>&1 # real 103m44.974s ######################################################################### # LASTZ human/hg38 vs. Cape elephant shrew/eleEdw1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEleEdw1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzEleEdw1.2015-02-17 cat << '_EOF_' > DEF # human vs Cape elephant shrew BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Cape elephant shrew eleEdw1 SEQ2_DIR=/hive/data/genomes/eleEdw1/eleEdw1.2bit SEQ2_LEN=/hive/data/genomes/eleEdw1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEleEdw1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2714m54.678s cat fb.hg38.chainEleEdw1Link.txt # 818423001 bases of 3049335806 (26.839%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eleEdw1) \ > rbest.log 2>&1 & # real 46m7.480s # and for the swap: mkdir /hive/data/genomes/eleEdw1/bed/blastz.hg38.swap cd /hive/data/genomes/eleEdw1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEleEdw1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 81m53.808s cat fb.eleEdw1.chainHg38Link.txt # 801797017 bases of 3315871847 (24.181%) in intersection time (doRecipBest.pl -buildDir=`pwd` eleEdw1 hg38) > rbest.log 2>&1 # real 30m17.282s ######################################################################### # LASTZ human/hg38 vs. manatee/triMan1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTriMan1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzTriMan1.2015-04-28 cat << '_EOF_' > DEF # human vs manatee BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: manatee triMan1 SEQ2_DIR=/hive/data/genomes/triMan1/triMan1.2bit SEQ2_LEN=/hive/data/genomes/triMan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTriMan1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1801m7.775s cat fb.hg38.chainTriMan1Link.txt # 1382747603 bases of 3049335806 (45.346%) in intersection # replacing the previous tuned version: # 1263723305 bases of 3049335806 (41.443%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 triMan1) > rbest.log 2>&1 & # real 73m5.269s # and for the swap: mkdir /hive/data/genomes/triMan1/bed/blastz.hg38.swap cd /hive/data/genomes/triMan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTriMan1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 103m30.816s cat fb.triMan1.chainHg38Link.txt # 1299790980 bases of 2769099677 (46.939%) in intersection # replacing the previous tuned version: # 1188634635 bases of 2769099677 (42.925%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` triMan1 hg38) \ > rbest.log 2>&1 # real 53m44.429s ######################################################################### # LASTZ human/hg38 vs. lesser Egyptian jerboa/jacJac1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzJacJac1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzJacJac1.2015-02-17 cat << '_EOF_' > DEF # human vs lesser Egyptian jerboa BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: lesser Egyptian jerboa jacJac1 SEQ2_DIR=/hive/data/genomes/jacJac1/jacJac1.2bit SEQ2_LEN=/hive/data/genomes/jacJac1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzJacJac1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3282m33.094s cat fb.hg38.chainJacJac1Link.txt # 1041439402 bases of 3049335806 (34.153%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 jacJac1) \ > rbest.log 2>&1 & # real 43m41.722s # and for the swap: mkdir /hive/data/genomes/jacJac1/bed/blastz.hg38.swap cd /hive/data/genomes/jacJac1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzJacJac1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 88m19.593s cat fb.jacJac1.chainHg38Link.txt # 995506956 bases of 2470259869 (40.300%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` jacJac1 hg38) \ > rbest.log 2>&1 # real 46m52.984s ######################################################################### # LASTZ human/hg38 vs. chinchilla/chiLan1 - (DONE - 2015-04-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzChiLan1.2015-04-27 cd /hive/data/genomes/hg38/bed/lastzChiLan1.2015-04-27 cat << '_EOF_' > DEF # human vs chinchilla BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: chinchilla chiLan1 SEQ2_DIR=/hive/data/genomes/chiLan1/chiLan1.2bit SEQ2_LEN=/hive/data/genomes/chiLan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzChiLan1.2015-04-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1099m27.880s cat fb.hg38.chainChiLan1Link.txt # 1392476369 bases of 3049335806 (45.665%) in intersection # replacing the previous tuned version: # 1244377852 bases of 3049335806 (40.808%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 chiLan1) > rbest.log 2>&1 & # real 38m31.373s # and for the swap: mkdir /hive/data/genomes/chiLan1/bed/blastz.hg38.swap cd /hive/data/genomes/chiLan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzChiLan1.2015-04-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 107m42.158s cat fb.chiLan1.chainHg38Link.txt # 1324935425 bases of 2284276400 (58.002%) in intersection # replacing the previous tuned version: # 1188638834 bases of 2284276400 (52.036%) in intersection time (doRecipBest.pl -buildDir=`pwd` chiLan1 hg38) > rbest.log 2>&1 # real 62m47.881s ######################################################################### # LASTZ human/hg38 vs. star nosed mole/conCri1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzConCri1.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzConCri1.2015-04-28 cat << '_EOF_' > DEF # human vs star nosed mole BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: star nosed mole conCri1 SEQ2_DIR=/hive/data/genomes/conCri1/conCri1.2bit SEQ2_LEN=/hive/data/genomes/conCri1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzConCri1.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1423m17.538s cat fb.hg38.chainConCri1Link.txt # 1095032620 bases of 3049335806 (35.911%) in intersection # replacing the previous tuned version: # 1007403174 bases of 3049335806 (33.037%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 conCri1) > rbest.log 2>&1 & # real 99m34.655s # and for the swap: mkdir /hive/data/genomes/conCri1/bed/blastz.hg38.swap cd /hive/data/genomes/conCri1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzConCri1.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 81m47.687s cat fb.conCri1.chainHg38Link.txt # 1026633109 bases of 1682542007 (61.017%) in intersection # replacing the previous tuned version: # 946409492 bases of 1682542007 (56.249%) in intersection time (doRecipBest.pl -buildDir=`pwd` conCri1 hg38) > rbest.log 2>&1 # real 415m57.506s finished manually real 45m44.330s time (doRecipBest.pl -workhorse=hgwdev -continue=download \ -buildDir=`pwd` conCri1 hg38) > rbestDownload.log 2>&1 # real 0m4.444s ######################################################################### # LASTZ human/hg38 vs. brush tailed rat/octDeg1 - (DONE - 2015-04-24 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOctDeg1.2015-04-24 cd /hive/data/genomes/hg38/bed/lastzOctDeg1.2015-04-24 # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.octDeg1/hg38.octDeg.tuning.top400.txt cp -p /hive/users/hiram/multiz/100way/hg38.octDeg1/hg38.octDeg1.tuning.top400.txt ./hg38.octDeg1.tuning.Q.txt cat << '_EOF_' > DEF # human vs brush tailed rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: brush tailed rat octDeg1 SEQ2_DIR=/hive/data/genomes/octDeg1/octDeg1.2bit SEQ2_LEN=/hive/data/genomes/octDeg1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOctDeg1.2015-04-24 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 311m38.376s cat fb.hg38.chainOctDeg1Link.txt # 1226996880 bases of 3049335806 (40.238%) in intersection # replacing the previous tuned version: # 1092487806 bases of 3049335806 (35.827%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 octDeg1) > rbest.log 2>&1 & # real 36m11.781s # and for the swap: mkdir /hive/data/genomes/octDeg1/bed/blastz.hg38.swap cd /hive/data/genomes/octDeg1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOctDeg1.2015-04-24/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 107m48.695s cat fb.octDeg1.chainHg38Link.txt # 1203795092 bases of 2526254702 (47.651%) in intersection # replacing the previous tuned version: # 1076649085 bases of 2526254702 (42.618%) in intersection time (doRecipBest.pl -buildDir=`pwd` octDeg1 hg38) > rbest.log 2>&1 # real 38m52.487s ######################################################################### # LASTZ human/hg38 vs. pika/ochPri3 - (DONE - 2015-04-17 - Hiram) # mistakenly done in directory name 2015-04-17 when it is really 2015-04-27 mkdir /hive/data/genomes/hg38/bed/lastzOchPri3.2015-04-17 cd /hive/data/genomes/hg38/bed/lastzOchPri3.2015-04-17 cat << '_EOF_' > DEF # human vs pika BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: pika ochPri3 SEQ2_DIR=/hive/data/genomes/ochPri3/ochPri3.2bit SEQ2_LEN=/hive/data/genomes/ochPri3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOchPri3.2015-04-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 971m36.115s cat fb.hg38.chainOchPri3Link.txt # 1025119076 bases of 3049335806 (33.618%) in intersection # replacing the previous tuned version: # 922764468 bases of 3049335806 (30.261%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 ochPri3) > rbest.log 2>&1 & # real 35m7.253s # and for the swap: mkdir /hive/data/genomes/ochPri3/bed/blastz.hg38.swap cd /hive/data/genomes/ochPri3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOchPri3.2015-04-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 80m33.697s cat fb.ochPri3.chainHg38Link.txt # 968829838 bases of 1943987870 (49.837%) in intersection # replacing the previous tuned version: # 874404292 bases of 1943987870 (44.980%) in intersection time (doRecipBest.pl -buildDir=`pwd` ochPri3 hg38) > rbest.log 2>&1 # real 46m26.106s ######################################################################### # LASTZ human/hg38 vs. hedgehog/eriEur2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEriEur2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzEriEur2.2015-02-17 cat << '_EOF_' > DEF # human vs hedgehog BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: hedgehog eriEur2 SEQ2_DIR=/hive/data/genomes/eriEur2/eriEur2.2bit SEQ2_LEN=/hive/data/genomes/eriEur2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEriEur2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2763m20.266s cat fb.hg38.chainEriEur2Link.txt # 777213928 bases of 3049335806 (25.488%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eriEur2) \ > rbest.log 2>&1 & # real 32m54.605s # and for the swap: mkdir /hive/data/genomes/eriEur2/bed/blastz.hg38.swap cd /hive/data/genomes/eriEur2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEriEur2.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 75m12.828s cat fb.eriEur2.chainHg38Link.txt # 730172579 bases of 2333073535 (31.297%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eriEur2 hg38) \ > rbest.log 2>&1 # real 34m37.153s ######################################################################### # LASTZ human/hg38 vs. tenrec/echTel2 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEchTel2.2015-04-28 cd /hive/data/genomes/hg38/bed/lastzEchTel2.2015-04-28 cat << '_EOF_' > DEF # human vs tenrec BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: tenrec echTel2 SEQ2_DIR=/hive/data/genomes/echTel2/echTel2.2bit SEQ2_LEN=/hive/data/genomes/echTel2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEchTel2.2015-04-28 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1689m14.948s cat fb.hg38.chainEchTel2Link.txt # 893752189 bases of 3049335806 (29.310%) in intersection # replacing the previous tuned version: # 840080104 bases of 3049335806 (27.550%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 echTel2) > rbest.log 2>&1 & # real 108m5.914s # and for the swap: mkdir /hive/data/genomes/echTel2/bed/blastz.hg38.swap cd /hive/data/genomes/echTel2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEchTel2.2015-04-28/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 87m14.342s cat fb.echTel2.chainHg38Link.txt # 853272550 bases of 2605196361 (32.753%) in intersection # replacing the previous tuned version: # 802302160 bases of 2605196361 (30.796%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` echTel2 hg38) \ > rbest.log 2>&1 # real 42m32.249s ######################################################################### # LASTZ human/hg38 vs. rat/rn6 - (DONE - 2015-02-14 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRn6.2015-02-14 cd /hive/data/genomes/hg38/bed/lastzRn6.2015-02-14 # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.rn6/hg38.octDeg.tuning.top400.txt cp -p /hive/users/hiram/multiz/100way/hg38.rn6/hg38.rn6.tuning.top400.txt ./hg38.rn6.tuning.Q.txt cat << '_EOF_' > DEF # human vs rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: rat rn6 SEQ2_DIR=/hive/data/genomes/rn6/rn6.2bit SEQ2_LEN=/hive/data/genomes/rn6/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzRn6.2015-02-14 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 539m6.068s cat fb.hg38.chainRn6Link.txt # 947631744 bases of 3049335806 (31.077%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 rn6) > rbest.log 2>&1 & # real 61m44.574s # and for the swap: mkdir /hive/data/genomes/rn6/bed/blastz.hg38.swap cd /hive/data/genomes/rn6/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRn6.2015-02-14/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 114m13.019s cat fb.rn6.chainHg38Link.txt # 952700446 bases of 2729860805 (34.899%) in intersection time (doRecipBest.pl -buildDir=`pwd` rn6 hg38) > rbest.log 2>&1 # real 47m8.081s ######################################################################### # LASTZ human/hg38 vs. Chinese hamster/criGri1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCriGri1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzCriGri1.2015-02-17 cat << '_EOF_' > DEF # human vs Chinese hamster BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Chinese hamster criGri1 SEQ2_DIR=/hive/data/genomes/criGri1/criGri1.2bit SEQ2_LEN=/hive/data/genomes/criGri1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCriGri1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3327m39.074s # after a crash in lastz, continuing: time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -continue=cat -syntenicNet) > cat.log 2>&1 # real 399m26.683s cat fb.hg38.chainCriGri1Link.txt # 1011432843 bases of 3049335806 (33.169%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 criGri1) \ > rbest.log 2>&1 & # lost the log file # real 41m11.272s # and for the swap: mkdir /hive/data/genomes/criGri1/bed/blastz.hg38.swap cd /hive/data/genomes/criGri1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCriGri1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 142m31.834s cat fb.criGri1.chainHg38Link.txt # 976365873 bases of 2301325917 (42.426%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` criGri1 hg38) \ > rbest.log 2>&1 # real 44m9.075s ######################################################################### # LASTZ human/hg38 vs. Golden hamster/mesAur1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMesAur1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzMesAur1.2015-02-17 cat << '_EOF_' > DEF # human vs Golden hamster BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Golden hamster mesAur1 SEQ2_DIR=/hive/data/genomes/mesAur1/mesAur1.2bit SEQ2_LEN=/hive/data/genomes/mesAur1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMesAur1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3321m29.849s cat fb.hg38.chainMesAur1Link.txt # 939276772 bases of 3049335806 (30.803%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 mesAur1) \ > rbest.log 2>&1 & # real 40m43.963s # and for the swap: mkdir /hive/data/genomes/mesAur1/bed/blastz.hg38.swap cd /hive/data/genomes/mesAur1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMesAur1.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 97m31.454s cat fb.mesAur1.chainHg38Link.txt # 894722574 bases of 2076176254 (43.095%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` mesAur1 hg38) \ > rbest.log 2>&1 # real 43m18.764s ######################################################################### # LASTZ human/hg38 vs. Prairie vole/micOch1 - (DONE - 2015-02-14 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMicOch1.2015-02-14 cd /hive/data/genomes/hg38/bed/lastzMicOch1.2015-02-14 cat << '_EOF_' > DEF # human vs Prairie vole BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Prairie vole micOch1 SEQ2_DIR=/hive/data/genomes/micOch1/micOch1.2bit SEQ2_LEN=/hive/data/genomes/micOch1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMicOch1.2015-02-14 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 493m1.575s cat fb.hg38.chainMicOch1Link.txt # 960200428 bases of 3049335806 (31.489%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 micOch1) > rbest.log 2>&1 & # real 28m17.738s # and for the swap: mkdir /hive/data/genomes/micOch1/bed/blastz.hg38.swap cd /hive/data/genomes/micOch1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMicOch1.2015-02-14/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 111m26.473s cat fb.micOch1.chainHg38Link.txt # 916196683 bases of 2104321675 (43.539%) in intersection time (doRecipBest.pl -buildDir=`pwd` micOch1 hg38) > rbest.log 2>&1 # real 84m4.019s ######################################################################### # LASTZ human/hg38 vs. shrew/sorAra2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSorAra2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzSorAra2.2015-02-17 cat << '_EOF_' > DEF # human vs shrew BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: shrew sorAra2 SEQ2_DIR=/hive/data/genomes/sorAra2/sorAra2.2bit SEQ2_LEN=/hive/data/genomes/sorAra2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSorAra2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3480m4.393s cat fb.hg38.chainSorAra2Link.txt # 820409269 bases of 3049335806 (26.905%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 sorAra2) \ > rbest.log 2>&1 & # real 37m5.305s # and for the swap: mkdir /hive/data/genomes/sorAra2/bed/blastz.hg38.swap cd /hive/data/genomes/sorAra2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSorAra2.2015-02-17/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 106m55.651s cat fb.sorAra2.chainHg38Link.txt # 783891768 bases of 2192103426 (35.760%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` sorAra2 hg38) \ > rbest.log 2>&1 # real 37m44.557s ######################################################################### # LASTZ human/hg38 vs. wallaby/macEug2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMacEug2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzMacEug2.2015-02-17 cat << '_EOF_' > DEF # human vs wallaby BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: wallaby macEug2 SEQ2_DIR=/hive/data/genomes/macEug2/macEug2.2bit SEQ2_LEN=/hive/data/genomes/macEug2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMacEug2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3321m43.912s cat fb.hg38.chainMacEug2Link.txt # 194475426 bases of 3049335806 (6.378%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 macEug2) \ > rbest.log 2>&1 & # real 17m42.993s # and for the swap: mkdir /hive/data/genomes/macEug2/bed/blastz.hg38.swap cd /hive/data/genomes/macEug2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMacEug2.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 185m57.086s cat fb.macEug2.chainHg38Link.txt # 182916846 bases of 2536076957 (7.213%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` macEug2 hg38) \ > rbest.log 2>&1 # real 143m14.162s ######################################################################### # LASTZ human/hg38 vs. Tasmanian devil/sarHar1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSarHar1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzSarHar1.2015-02-13 cat << '_EOF_' > DEF # human vs Tasmanian devil BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Tasmanian devil sarHar1 SEQ2_DIR=/hive/data/genomes/sarHar1/sarHar1.2bit SEQ2_LEN=/hive/data/genomes/sarHar1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=60 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSarHar1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 862m32.202s cat fb.hg38.chainSarHar1Link.txt # 388903768 bases of 3049335806 (12.754%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 sarHar1) > rbest.log 2>&1 & # real 34m31.714s # and for the swap: mkdir /hive/data/genomes/sarHar1/bed/blastz.hg38.swap cd /hive/data/genomes/sarHar1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSarHar1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 69m33.260s cat fb.sarHar1.chainHg38Link.txt # 378889609 bases of 2931539702 (12.925%) in intersection time (doRecipBest.pl -buildDir=`pwd` sarHar1 hg38) > rbest.log 2>&1 # real 22m1.912s ######################################################################### # LASTZ human/hg38 vs. Spiny softshell turtle/apaSpi1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzApaSpi1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzApaSpi1.2015-02-13 cat << '_EOF_' > DEF # human vs Spiny softshell turtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Spiny softshell turtle apaSpi1 SEQ2_DIR=/hive/data/genomes/apaSpi1/apaSpi1.2bit SEQ2_LEN=/hive/data/genomes/apaSpi1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzApaSpi1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 737m19.211s cat fb.hg38.chainApaSpi1Link.txt # 140617559 bases of 3049335806 (4.611%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 apaSpi1) > rbest.log 2>&1 & # real 19m56.198s # and for the swap: mkdir /hive/data/genomes/apaSpi1/bed/blastz.hg38.swap cd /hive/data/genomes/apaSpi1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzApaSpi1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 47m41.422s cat fb.apaSpi1.chainHg38Link.txt # 118690974 bases of 1877982184 (6.320%) in intersection time (doRecipBest.pl -buildDir=`pwd` apaSpi1 hg38) > rbest.log 2>&1 # real 48m11.487s ######################################################################### # LASTZ human/hg38 vs. Chinese softshell turtle/pelSin1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPelSin1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzPelSin1.2015-02-13 cat << '_EOF_' > DEF # human vs Chinese softshell turtle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Chinese softshell turtle pelSin1 SEQ2_DIR=/hive/data/genomes/pelSin1/pelSin1.2bit SEQ2_LEN=/hive/data/genomes/pelSin1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPelSin1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 749m6.906s cat fb.hg38.chainPelSin1Link.txt # 174304542 bases of 3049335806 (5.716%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 pelSin1) > rbest.log 2>&1 & # real 32m56.986s # and for the swap: mkdir /hive/data/genomes/pelSin1/bed/blastz.hg38.swap cd /hive/data/genomes/pelSin1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPelSin1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 28m15.790s cat fb.pelSin1.chainHg38Link.txt # 151827556 bases of 2106639384 (7.207%) in intersection time (doRecipBest.pl -buildDir=`pwd` pelSin1 hg38) > rbest.log 2>&1 # real 63m22.391s ######################################################################### # LASTZ human/hg38 vs. platypus/ornAna1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOrnAna1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzOrnAna1.2015-02-13 cat << '_EOF_' > DEF # human vs platypus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: platypus ornAna1 SEQ2_DIR=/hive/data/genomes/ornAna1/ornAna1.2bit SEQ2_LEN=/hive/data/genomes/ornAna1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOrnAna1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 714m38.972s cat fb.hg38.chainOrnAna1Link.txt # 236893911 bases of 3049335806 (7.769%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 ornAna1) > rbest.log 2>&1 & # real 38m4.653s # and for the swap: mkdir /hive/data/genomes/ornAna1/bed/blastz.hg38.swap cd /hive/data/genomes/ornAna1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOrnAna1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m45.882s cat fb.ornAna1.chainHg38Link.txt # 217095490 bases of 1842236818 (11.784%) in intersection time (doRecipBest.pl -buildDir=`pwd` ornAna1 hg38) > rbest.log 2>&1 # real 61m34.921s ######################################################################### # LASTZ human/hg38 vs. American alligator/allMis1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAllMis1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzAllMis1.2015-02-13 cat << '_EOF_' > DEF # human vs American alligator BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: American alligator allMis1 SEQ2_DIR=/hive/data/genomes/allMis1/allMis1.2bit SEQ2_LEN=/hive/data/genomes/allMis1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAllMis1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 773m58.250s cat fb.hg38.chainAllMis1Link.txt # 230567044 bases of 3049335806 (7.561%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 allMis1) > rbest.log 2>&1 & # real 32m25.167s # and for the swap: mkdir /hive/data/genomes/allMis1/bed/blastz.hg38.swap cd /hive/data/genomes/allMis1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAllMis1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 41m40.053s cat fb.allMis1.chainHg38Link.txt # 184529544 bases of 2129659933 (8.665%) in intersection time (doRecipBest.pl -buildDir=`pwd` allMis1 hg38) > rbest.log 2>&1 # real 20m37.259s ######################################################################### # LASTZ human/hg38 vs. Rock pigeon/colLiv1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzColLiv1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzColLiv1.2015-02-13 cat << '_EOF_' > DEF # human vs Rock pigeon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Rock pigeon colLiv1 SEQ2_DIR=/hive/data/genomes/colLiv1/colLiv1.2bit SEQ2_LEN=/hive/data/genomes/colLiv1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzColLiv1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 577m9.861s cat fb.hg38.chainColLiv1Link.txt # 143694750 bases of 3049335806 (4.712%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 colLiv1) > rbest.log 2>&1 & # real 39m12.952s # and for the swap: mkdir /hive/data/genomes/colLiv1/bed/blastz.hg38.swap cd /hive/data/genomes/colLiv1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzColLiv1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 17m12.980s cat fb.colLiv1.chainHg38Link.txt # 111080887 bases of 1086925875 (10.220%) in intersection time (doRecipBest.pl -buildDir=`pwd` colLiv1 hg38) > rbest.log 2>&1 # real 57m22.697s ######################################################################### # LASTZ human/hg38 vs. chicken/galGal4 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGalGal4.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzGalGal4.2015-02-13 cat << '_EOF_' > DEF # human vs chicken BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: chicken galGal4 SEQ2_DIR=/hive/data/genomes/galGal4/galGal4.2bit SEQ2_LEN=/hive/data/genomes/galGal4/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGalGal4.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 591m53.978s cat fb.hg38.chainGalGal4Link.txt # 143193682 bases of 3049335806 (4.696%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 galGal4) > rbest.log 2>&1 & # real 22m9.725s # and for the swap: mkdir /hive/data/genomes/galGal4/bed/blastz.hg38.swap cd /hive/data/genomes/galGal4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGalGal4.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 19m26.680s cat fb.galGal4.chainHg38Link.txt # 112454237 bases of 1032854810 (10.888%) in intersection time (doRecipBest.pl -buildDir=`pwd` galGal4 hg38) > rbest.log 2>&1 # real 16m49.158s ######################################################################### # LASTZ human/hg38 vs. Mallard duck/anaPla1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAnaPla1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzAnaPla1.2015-02-13 cat << '_EOF_' > DEF # human vs Mallard duck BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Mallard duck anaPla1 SEQ2_DIR=/hive/data/genomes/anaPla1/anaPla1.2bit SEQ2_LEN=/hive/data/genomes/anaPla1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAnaPla1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 548m49.861s cat fb.hg38.chainAnaPla1Link.txt # 130130831 bases of 3049335806 (4.268%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 anaPla1) > rbest.log 2>&1 & # real 40m39.914s # and for the swap: mkdir /hive/data/genomes/anaPla1/bed/blastz.hg38.swap cd /hive/data/genomes/anaPla1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAnaPla1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 18m52.863s cat fb.anaPla1.chainHg38Link.txt # 103561071 bases of 1069972754 (9.679%) in intersection time (doRecipBest.pl -buildDir=`pwd` anaPla1 hg38) > rbest.log 2>&1 # real 68m35.285s ######################################################################### # LASTZ human/hg38 vs. turkey/melGal1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMelGal1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzMelGal1.2015-02-13 cat << '_EOF_' > DEF # human vs turkey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: turkey melGal1 SEQ2_DIR=/hive/data/genomes/melGal1/melGal1.2bit SEQ2_LEN=/hive/data/genomes/melGal1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMelGal1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 655m4.317s cat fb.hg38.chainMelGal1Link.txt # 131975070 bases of 3049335806 (4.328%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 melGal1) > rbest.log 2>&1 & # real 14m2.560s # and for the swap: mkdir /hive/data/genomes/melGal1/bed/blastz.hg38.swap cd /hive/data/genomes/melGal1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMelGal1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 12m24.021s cat fb.melGal1.chainHg38Link.txt # 102272881 bases of 935922386 (10.927%) in intersection time (doRecipBest.pl -buildDir=`pwd` melGal1 hg38) > rbest.log 2>&1 # real 7m21.946s ######################################################################### # LASTZ human/hg38 vs. Saker falcon/falChe1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFalChe1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzFalChe1.2015-02-13 cat << '_EOF_' > DEF # human vs Saker falcon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Saker falcon falChe1 SEQ2_DIR=/hive/data/genomes/falChe1/falChe1.2bit SEQ2_LEN=/hive/data/genomes/falChe1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFalChe1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 542m16.464s cat fb.hg38.chainFalChe1Link.txt # 147225031 bases of 3049335806 (4.828%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 falChe1) > rbest.log 2>&1 & # real 8m23.849s # and for the swap: mkdir /hive/data/genomes/falChe1/bed/blastz.hg38.swap cd /hive/data/genomes/falChe1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFalChe1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 14m3.049s cat fb.falChe1.chainHg38Link.txt # 113693444 bases of 1150993769 (9.878%) in intersection time (doRecipBest.pl -buildDir=`pwd` falChe1 hg38) > rbest.log 2>&1 # real 18m4.600s ######################################################################### # LASTZ human/hg38 vs. Peregrine falcon/falPer1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFalPer1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzFalPer1.2015-02-13 cat << '_EOF_' > DEF # human vs Peregrine falcon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Peregrine falcon falPer1 SEQ2_DIR=/hive/data/genomes/falPer1/falPer1.2bit SEQ2_LEN=/hive/data/genomes/falPer1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFalPer1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 551m19.392s cat fb.hg38.chainFalPer1Link.txt # 150205756 bases of 3049335806 (4.926%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 falPer1) > rbest.log 2>&1 & # real 6m7.675s # and for the swap: mkdir /hive/data/genomes/falPer1/bed/blastz.hg38.swap cd /hive/data/genomes/falPer1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFalPer1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 14m47.580s cat fb.falPer1.chainHg38Link.txt # 115649151 bases of 1153404357 (10.027%) in intersection time (doRecipBest.pl -buildDir=`pwd` falPer1 hg38) > rbest.log 2>&1 # real 25m36.021s ######################################################################### # LASTZ human/hg38 vs. parrot/amaVit1 - (DONE - 2015-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAmaVit1.2015-02-13 cd /hive/data/genomes/hg38/bed/lastzAmaVit1.2015-02-13 cat << '_EOF_' > DEF # human vs parrot BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: parrot amaVit1 SEQ2_DIR=/hive/data/genomes/amaVit1/amaVit1.2bit SEQ2_LEN=/hive/data/genomes/amaVit1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAmaVit1.2015-02-13 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 657m27.659s cat fb.hg38.chainAmaVit1Link.txt # 127630825 bases of 3049335806 (4.186%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 amaVit1) > rbest.log 2>&1 & # real 9m2.061s # and for the swap: mkdir /hive/data/genomes/amaVit1/bed/blastz.hg38.swap cd /hive/data/genomes/amaVit1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAmaVit1.2015-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 76m6.072s cat fb.amaVit1.chainHg38Link.txt # 106957200 bases of 1128255752 (9.480%) in intersection time (doRecipBest.pl -buildDir=`pwd` amaVit1 hg38) > rbest.log 2>&1 # real 107m34.617s ######################################################################### # LASTZ human/hg38 vs. Scarlet macaw/araMac1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAraMac1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzAraMac1.2015-02-17 cat << '_EOF_' > DEF # human vs Scarlet macaw BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Scarlet macaw araMac1 SEQ2_DIR=/hive/data/genomes/araMac1/araMac1.2bit SEQ2_LEN=/hive/data/genomes/araMac1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAraMac1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 246m48.471s cat fb.hg38.chainAraMac1Link.txt # 115478631 bases of 3049335806 (3.787%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 araMac1) > rbest.log 2>&1 & # real 9m59.145s # lost rbest.log # and for the swap: mkdir /hive/data/genomes/araMac1/bed/blastz.hg38.swap cd /hive/data/genomes/araMac1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAraMac1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 70m16.338s cat fb.araMac1.chainHg38Link.txt # 90173740 bases of 997636166 (9.039%) in intersection time (doRecipBest.pl -buildDir=`pwd` araMac1 hg38) > rbest.log 2>&1 # real 42m44.255s ######################################################################### # LASTZ human/hg38 vs. Tibetan ground jay/pseHum1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPseHum1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzPseHum1.2015-02-17 cat << '_EOF_' > DEF # human vs Tibetan ground jay BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Tibetan ground jay pseHum1 SEQ2_DIR=/hive/data/genomes/pseHum1/pseHum1.2bit SEQ2_LEN=/hive/data/genomes/pseHum1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPseHum1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 70m22.110s # continuing after cluster trouble: time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -continue=cat -syntenicNet) > cat.log 2>&1 # real 34m11.495s cat fb.hg38.chainPseHum1Link.txt # 156923153 bases of 3049335806 (5.146%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 pseHum1) \ > rbest.log 2>&1 & # real 11m52.623s # and for the swap: mkdir /hive/data/genomes/pseHum1/bed/blastz.hg38.swap cd /hive/data/genomes/pseHum1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPseHum1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 14m38.524s cat fb.pseHum1.chainHg38Link.txt # 122950927 bases of 1030030436 (11.937%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` pseHum1 hg38) \ > rbest.log 2>&1 # real 11m38.841s ######################################################################### # LASTZ human/hg38 vs. budgerigar/melUnd1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMelUnd1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzMelUnd1.2015-02-17 cat << '_EOF_' > DEF # human vs budgerigar BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: budgerigar melUnd1 SEQ2_DIR=/hive/data/genomes/melUnd1/melUnd1.2bit SEQ2_LEN=/hive/data/genomes/melUnd1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMelUnd1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2082m35.909s cat fb.hg38.chainMelUnd1Link.txt # 136423508 bases of 3049335806 (4.474%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 melUnd1) \ > rbest.log 2>&1 & # real 9m33.306s # and for the swap: mkdir /hive/data/genomes/melUnd1/bed/blastz.hg38.swap cd /hive/data/genomes/melUnd1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMelUnd1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 12m38.168s cat fb.melUnd1.chainHg38Link.txt # 107164699 bases of 1086614815 (9.862%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` melUnd1 hg38) \ > rbest.log 2>&1 # real 9m40.749s ######################################################################### # LASTZ human/hg38 vs. Collard flycatcher/ficAlb2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFicAlb2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzFicAlb2.2015-02-17 cat << '_EOF_' > DEF # human vs Collard flycatcher BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Collard flycatcher ficAlb2 SEQ2_DIR=/hive/data/genomes/ficAlb2/ficAlb2.2bit SEQ2_LEN=/hive/data/genomes/ficAlb2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFicAlb2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1978m13.358s cat fb.hg38.chainFicAlb2Link.txt # 147048785 bases of 3049335806 (4.822%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 ficAlb2) > rbest.log 2>&1 & # real 10m49.556s # and for the swap: mkdir /hive/data/genomes/ficAlb2/bed/blastz.hg38.swap cd /hive/data/genomes/ficAlb2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFicAlb2.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 15m26.251s cat fb.ficAlb2.chainHg38Link.txt # 118476285 bases of 1102325870 (10.748%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` ficAlb2 hg38) \ > rbest.log 2>&1 # real 12m43.894s ######################################################################### # LASTZ human/hg38 vs. White throaqted sparrow/zonAlb1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzZonAlb1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzZonAlb1.2015-02-17 cat << '_EOF_' > DEF # human vs White throaqted sparrow BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: White throaqted sparrow zonAlb1 SEQ2_DIR=/hive/data/genomes/zonAlb1/zonAlb1.2bit SEQ2_LEN=/hive/data/genomes/zonAlb1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzZonAlb1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1615m23.324s cat fb.hg38.chainZonAlb1Link.txt # 137040575 bases of 3049335806 (4.494%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 zonAlb1) > rbest.log 2>&1 & # real 6m4.340s # and for the swap: mkdir /hive/data/genomes/zonAlb1/bed/blastz.hg38.swap cd /hive/data/genomes/zonAlb1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzZonAlb1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 12m59.040s cat fb.zonAlb1.chainHg38Link.txt # 106367271 bases of 1006303327 (10.570%) in intersection time (doRecipBest.pl -buildDir=`pwd` zonAlb1 hg38) > rbest.log 2>&1 # real 6m51.403s ######################################################################### # LASTZ human/hg38 vs. Medium ground finch/geoFor1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGeoFor1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzGeoFor1.2015-02-17 cat << '_EOF_' > DEF # human vs Medium ground finch BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Medium ground finch geoFor1 SEQ2_DIR=/hive/data/genomes/geoFor1/geoFor1.2bit SEQ2_LEN=/hive/data/genomes/geoFor1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGeoFor1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2097m14.874s cat fb.hg38.chainGeoFor1Link.txt # 135529241 bases of 3049335806 (4.445%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 geoFor1) \ > rbest.log 2>&1 & # real 9m9.547s # and for the swap: mkdir /hive/data/genomes/geoFor1/bed/blastz.hg38.swap cd /hive/data/genomes/geoFor1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGeoFor1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 13m19.205s cat fb.geoFor1.chainHg38Link.txt # 107944681 bases of 1041286029 (10.366%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` geoFor1 hg38) \ > rbest.log 2>&1 # real 9m35.765s ######################################################################### # LASTZ human/hg38 vs. Zebra finch/taeGut2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTaeGut2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzTaeGut2.2015-02-17 cat << '_EOF_' > DEF # human vs Zebra finch BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Zebra finch taeGut2 SEQ2_DIR=/hive/data/genomes/taeGut2/taeGut2.2bit SEQ2_LEN=/hive/data/genomes/taeGut2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTaeGut2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 3301m5.574s cat fb.hg38.chainTaeGut2Link.txt # 179692554 bases of 3049335806 (5.893%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 taeGut2) \ > rbest.log 2>&1 & # real 14m16.442s # and for the swap: mkdir /hive/data/genomes/taeGut2/bed/blastz.hg38.swap cd /hive/data/genomes/taeGut2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTaeGut2.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 37m48.256s cat fb.taeGut2.chainHg38Link.txt # 151099393 bases of 1222864691 (12.356%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` taeGut2 hg38) \ > rbest.log 2>&1 # real 20m21.580s ######################################################################### # LASTZ human/hg38 vs. Atlantic cod/gadMor1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGadMor1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzGadMor1.2015-02-17 cat << '_EOF_' > DEF # human vs Atlantic cod BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Atlantic cod gadMor1 SEQ2_DIR=/hive/data/genomes/gadMor1/gadMor1.2bit SEQ2_LEN=/hive/data/genomes/gadMor1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=500 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGadMor1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1588m35.829s cat fb.hg38.chainGadMor1Link.txt # 50624248 bases of 3049335806 (1.660%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 gadMor1) > rbest.log 2>&1 & # real 4m28.029s # and for the swap: mkdir /hive/data/genomes/gadMor1/bed/blastz.hg38.swap cd /hive/data/genomes/gadMor1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGadMor1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 74m26.591s cat fb.gadMor1.chainHg38Link.txt # 42019467 bases of 608038597 (6.911%) in intersection time (doRecipBest.pl -buildDir=`pwd` gadMor1 hg38) > rbest.log 2>&1 # real 35m52.207s ######################################################################### # LASTZ human/hg38 vs. Stickleback/gasAcu1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGasAcu1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzGasAcu1.2015-02-17 cat << '_EOF_' > DEF # human vs Stickleback BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Stickleback gasAcu1 SEQ2_DIR=/hive/data/genomes/gasAcu1/gasAcu1.2bit SEQ2_LEN=/hive/data/genomes/gasAcu1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=1 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGasAcu1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1053m23.074s cat fb.hg38.chainGasAcu1Link.txt # 63437294 bases of 3049335806 (2.080%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 gasAcu1) > rbest.log 2>&1 & # about 6 minutes - lost rbest.log # and for the swap: mkdir /hive/data/genomes/gasAcu1/bed/blastz.hg38.swap cd /hive/data/genomes/gasAcu1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGasAcu1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 9m14.802s cat fb.gasAcu1.chainHg38Link.txt # 53397634 bases of 446627861 (11.956%) in intersection time (doRecipBest.pl -buildDir=`pwd` gasAcu1 hg38) > rbest.log 2>&1 # real 10m7.401s ######################################################################### # LASTZ human/hg38 vs. Nile tilapia/oreNil2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOreNil2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzOreNil2.2015-02-17 cat << '_EOF_' > DEF # human vs Nile tilapia BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Nile tilapia oreNil2 SEQ2_DIR=/hive/data/genomes/oreNil2/oreNil2.2bit SEQ2_LEN=/hive/data/genomes/oreNil2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOreNil2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1380m11.717s cat fb.hg38.chainOreNil2Link.txt # 56961010 bases of 3049335806 (1.868%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 oreNil2) \ > rbest.log 2>&1 & # real 8m9.098s # and for the swap: mkdir /hive/data/genomes/oreNil2/bed/blastz.hg38.swap cd /hive/data/genomes/oreNil2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOreNil2.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m56.062s cat fb.oreNil2.chainHg38Link.txt # 50933712 bases of 816084674 (6.241%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` oreNil2 hg38) \ > rbest.log 2>&1 # real 7m54.354s ######################################################################### # LASTZ human/hg38 vs. Tetraodon/tetNig2 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTetNig2.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzTetNig2.2015-02-17 cat << '_EOF_' > DEF # human vs Tetraodon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Tetraodon tetNig2 SEQ2_DIR=/hive/data/genomes/tetNig2/tetNig2.2bit SEQ2_LEN=/hive/data/genomes/tetNig2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=1 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTetNig2.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 537m38.314s cat fb.hg38.chainTetNig2Link.txt # 53138885 bases of 3049335806 (1.743%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 tetNig2) > rbest.log 2>&1 & # real 8m12.538s # and for the swap: mkdir /hive/data/genomes/tetNig2/bed/blastz.hg38.swap cd /hive/data/genomes/tetNig2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTetNig2.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 6m31.168s cat fb.tetNig2.chainHg38Link.txt # 43299390 bases of 302314788 (14.323%) in intersection time (doRecipBest.pl -buildDir=`pwd` tetNig2 hg38) > rbest.log 2>&1 # real 5m5.399s ######################################################################### # LASTZ human/hg38 vs. Princess of Burundi/neoBri1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzNeoBri1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzNeoBri1.2015-02-17 cat << '_EOF_' > DEF # human vs Princess of Burundi BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Princess of Burundi neoBri1 SEQ2_DIR=/hive/data/genomes/neoBri1/neoBri1.2bit SEQ2_LEN=/hive/data/genomes/neoBri1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzNeoBri1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1316m55.223s cat fb.hg38.chainNeoBri1Link.txt # 53868820 bases of 3049335806 (1.767%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 neoBri1) > rbest.log 2>&1 & # real 4m18.813s # and for the swap: mkdir /hive/data/genomes/neoBri1/bed/blastz.hg38.swap cd /hive/data/genomes/neoBri1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzNeoBri1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m59.125s cat fb.neoBri1.chainHg38Link.txt # 46915356 bases of 685897281 (6.840%) in intersection time (doRecipBest.pl -buildDir=`pwd` neoBri1 hg38) > rbest.log 2>&1 # real 6m25.911s ######################################################################### # LASTZ human/hg38 vs. Yellowbelly pufferfish/takFla1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTakFla1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzTakFla1.2015-02-17 cat << '_EOF_' > DEF # human vs Yellowbelly pufferfish BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Yellowbelly pufferfish takFla1 SEQ2_DIR=/hive/data/genomes/takFla1/takFla1.2bit SEQ2_LEN=/hive/data/genomes/takFla1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTakFla1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1193m52.421s cat fb.hg38.chainTakFla1Link.txt # 47205001 bases of 3049335806 (1.548%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 takFla1) > rbest.log 2>&1 & # real 2m58.484s # and for the swap: mkdir /hive/data/genomes/takFla1/bed/blastz.hg38.swap cd /hive/data/genomes/takFla1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTakFla1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 7m24.854s cat fb.takFla1.chainHg38Link.txt # 35632361 bases of 314848639 (11.317%) in intersection time (doRecipBest.pl -buildDir=`pwd` takFla1 hg38) > rbest.log 2>&1 # real 8m20.901s ######################################################################### # LASTZ human/hg38 vs. Burton's mouthbreeder/hapBur1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzHapBur1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzHapBur1.2015-02-17 cat << '_EOF_' > DEF # human vs Burton's mouthbreeder BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Burton's mouthbreeder hapBur1 SEQ2_DIR=/hive/data/genomes/hapBur1/hapBur1.2bit SEQ2_LEN=/hive/data/genomes/hapBur1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzHapBur1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1288m42.717s cat fb.hg38.chainHapBur1Link.txt # 54379915 bases of 3049335806 (1.783%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 hapBur1) > rbest.log 2>&1 & # real 3m45.453s # and for the swap: mkdir /hive/data/genomes/hapBur1/bed/blastz.hg38.swap cd /hive/data/genomes/hapBur1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzHapBur1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 9m18.063s cat fb.hapBur1.chainHg38Link.txt # 47956127 bases of 698936397 (6.861%) in intersection time (doRecipBest.pl -buildDir=`pwd` hapBur1 hg38) > rbest.log 2>&1 # real 6m53.796s ######################################################################### # LASTZ human/hg38 vs. Fugu/fr3 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFr3.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzFr3.2015-02-17 cat << '_EOF_' > DEF # human vs Fugu BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Fugu fr3 SEQ2_DIR=/hive/data/genomes/fr3/fr3.2bit SEQ2_LEN=/hive/data/genomes/fr3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFr3.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 906m48.419s cat fb.hg38.chainFr3Link.txt # 54409247 bases of 3049335806 (1.784%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 fr3) > rbest.log 2>&1 & # real 4m4.720s # and for the swap: mkdir /hive/data/genomes/fr3/bed/blastz.hg38.swap cd /hive/data/genomes/fr3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFr3.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 6m35.968s cat fb.fr3.chainHg38Link.txt # 43496560 bases of 350961831 (12.394%) in intersection time (doRecipBest.pl -buildDir=`pwd` fr3 hg38) > rbest.log 2>&1 # real 11m12.304s ######################################################################### # LASTZ human/hg38 vs. Mexican tetra cavefish/astMex1 - (DONE - 2015-02-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAstMex1.2015-02-17 cd /hive/data/genomes/hg38/bed/lastzAstMex1.2015-02-17 cat << '_EOF_' > DEF # human vs Mexican tetra cavefish BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Mexican tetra cavefish astMex1 SEQ2_DIR=/hive/data/genomes/astMex1/astMex1.2bit SEQ2_LEN=/hive/data/genomes/astMex1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAstMex1.2015-02-17 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1566m37.808s cat fb.hg38.chainAstMex1Link.txt # 67854134 bases of 3049335806 (2.225%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 astMex1) > rbest.log 2>&1 & # real 4m58.664s # and for the swap: mkdir /hive/data/genomes/astMex1/bed/blastz.hg38.swap cd /hive/data/genomes/astMex1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAstMex1.2015-02-17/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 13m50.072s cat fb.astMex1.chainHg38Link.txt # 61379040 bases of 964264884 (6.365%) in intersection time (doRecipBest.pl -buildDir=`pwd` astMex1 hg38) > rbest.log 2>&1 # real 6m31.123s ######################################################################### # LASTZ human/hg38 vs. X. tropicalis/xenTro7 - (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzXenTro7.2015-02-18 cd /hive/data/genomes/hg38/bed/lastzXenTro7.2015-02-18 cat << '_EOF_' > DEF # human vs X. tropicalis BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: X. tropicalis xenTro7 SEQ2_DIR=/hive/data/genomes/xenTro7/xenTro7.2bit SEQ2_LEN=/hive/data/genomes/xenTro7/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzXenTro7.2015-02-18 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1991m40.229s cat fb.hg38.chainXenTro7Link.txt # 116213822 bases of 3049335806 (3.811%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 xenTro7) \ > rbest.log 2>&1 & # real 15m54.917s # and for the swap: mkdir /hive/data/genomes/xenTro7/bed/blastz.hg38.swap cd /hive/data/genomes/xenTro7/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXenTro7.2015-02-18/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 53m28.988s cat fb.xenTro7.chainHg38Link.txt # 108823737 bases of 1365936747 (7.967%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro7 hg38) \ > rbest.log 2>&1 # real 16m4.622s ######################################################################### # LASTZ human/hg38 vs. Coelacanth/latCha1 - (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzLatCha1.2015-02-18 cd /hive/data/genomes/hg38/bed/lastzLatCha1.2015-02-18 cat << '_EOF_' > DEF # human vs Coelacanth BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Coelacanth latCha1 SEQ2_DIR=/hive/data/genomes/latCha1/latCha1.2bit SEQ2_LEN=/hive/data/genomes/latCha1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzLatCha1.2015-02-18 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 2036m36.030s cat fb.hg38.chainLatCha1Link.txt # 87594238 bases of 3049335806 (2.873%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 latCha1) \ > rbest.log 2>&1 & # real 8m36.393s # and for the swap: mkdir /hive/data/genomes/latCha1/bed/blastz.hg38.swap cd /hive/data/genomes/latCha1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzLatCha1.2015-02-18/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 19m14.665s cat fb.latCha1.chainHg38Link.txt # 75312106 bases of 2183592768 (3.449%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` latCha1 hg38) \ > rbest.log 2>&1 # real 10m14.893s ######################################################################### # LASTZ human/hg38 vs. Spotted gar/lepOcu1 - (DONE - 2015-02-18 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzLepOcu1.2015-02-18 cd /hive/data/genomes/hg38/bed/lastzLepOcu1.2015-02-18 cat << '_EOF_' > DEF # human vs Spotted gar BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Spotted gar lepOcu1 SEQ2_DIR=/hive/data/genomes/lepOcu1/lepOcu1.2bit SEQ2_LEN=/hive/data/genomes/lepOcu1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzLepOcu1.2015-02-18 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 917m10.105s cat fb.hg38.chainLepOcu1Link.txt # 76570858 bases of 3049335806 (2.511%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 lepOcu1) \ > rbest.log 2>&1 & # real 11m4.401s # and for the swap: mkdir /hive/data/genomes/lepOcu1/bed/blastz.hg38.swap cd /hive/data/genomes/lepOcu1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzLepOcu1.2015-02-18/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m52.863s cat fb.lepOcu1.chainHg38Link.txt # 57676637 bases of 869414361 (6.634%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` lepOcu1 hg38) \ > rbest.log 2>&1 # real 8m31.395s ######################################################################### # LASTZ human/hg38 Tree shrew/tupBel1 - (DONE - 2015-03-27 - Hiram) # re-running with default parameters, this provides more coverage mkdir /hive/data/genomes/hg38/bed/lastzTupBel1.2015-03-27 cd /hive/data/genomes/hg38/bed/lastzTupBel1.2015-03-27 cat << '_EOF_' > DEF # human vs Tree shrew BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_M=254 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Tree shrew tupBel1 SEQ2_DIR=/hive/data/genomes/tupBel1/tupBel1.2bit SEQ2_LEN=/hive/data/genomes/tupBel1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTupBel1.2015-03-27 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku) > do.log 2>&1 # real 372m50.142s cat fb.hg38.chainTupBel1Link.txt # 1067849727 bases of 3049335806 (35.019%) in intersection # replacing the previous tuned version: # 753229970 bases of 3049335806 (24.701%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 tupBel1) > rbest.log 2>&1 & # real 33m33.647s # and for the swap: mkdir /hive/data/genomes/tupBel1/bed/blastz.hg38.swap cd /hive/data/genomes/tupBel1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTupBel1.2015-03-27/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 256m18.000s cat fb.tupBel1.chainHg38Link.txt # 1056254191 bases of 2137225476 (49.422%) in intersection # replacing the previous tuned version: # 749930137 bases of 2137225476 (35.089%) in intersection time (doRecipBest.pl -buildDir=`pwd` tupBel1 hg38) > rbest.log 2>&1 # real 112m44.439s ######################################################################### # LASTZ human/hg38 Tree mouse/mm10 - (DONE - 2015-04-10 - Hiram) # re-running to correct missing contig alignments from canFam3 mkdir /hive/data/genomes/hg38/bed/lastzMm10.2015-04-08 cd /hive/data/genomes/hg38/bed/lastzMm10.2015-04-08 cat << '_EOF_' > DEF # human vs mouse BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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 Mm10 SEQ2_DIR=/scratch/data/mm10/mm10.2bit SEQ2_LEN=/scratch/data/mm10/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMm10.2015-04-08 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -fileServer=hgwdev -chainMinScore=3000 -chainLinearGap=medium) \ > do.log 2>&1 # real 323m51.165s cat fb.hg38.chainMm10Link.txt # 965211935 bases of 3049335806 (31.653%) in intersection # replacing the broken run from Jan 2014: # 964465044 bases of 3049335806 (31.629%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 mm10) > rbest.log 2>&1 & # real 32m22.990s # load up the recip best chainNet tables time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 mm10) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestMm10Link.txt # 891562094 bases of 3049335806 (29.238%) in intersection # create and load up the syntenic chainNet tables 2017-10-30 cd /hive/data/genomes/hg38/bed/lastzMm10.2015-04-08/axtChain netToAxt hg38.mm10.syn.net.gz hg38.mm10.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/mm10/mm10.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/mm10/chrom.sizes stdout \ | gzip -c > hg38.mm10.syn.chain.gz hgLoadChain -tIndex hg38 chainSynMm10 hg38.mm10.syn.chain.gz netFilter -minGap=10 hg38.mm10.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynMm10 stdin cd /hive/data/genomes/hg38/bed/lastzMm10.2015-04-08 featureBits hg38 chainSynMm10Link > fb.hg38.chainSynMm10Link.txt 2>&1 cat fb.hg38.chainSynMm10Link.txt # 913707143 bases of 3049335806 (29.964%) in intersection # and for the swap: mkdir /hive/data/genomes/mm10/bed/blastz.hg38.swap cd /hive/data/genomes/mm10/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMm10.2015-04-08/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 74m49.827s cat fb.mm10.chainHg38Link.txt # 938348519 bases of 2652783500 (35.372%) in intersection # replacing the broken run from Jan 2014: # 937030766 bases of 2652783500 (35.323%) in intersection time (doRecipBest.pl -buildDir=`pwd` mm10 hg38) > rbest.log 2>&1 # real 32m38.549s ######################################################################### # LASTZ human/hg38 Tree dog/canFam3 - (DONE - 2015-04-10 - Hiram) # re-running to correct missing contig alignments from canFam3 mkdir /hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08 cd /hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08 cat << '_EOF_' > DEF # human vs dog BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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=20000000 SEQ1_LAP=10000 # QUERY: Dog CanFam3 SEQ2_DIR=/hive/data/genomes/canFam3/canFam3.2bit SEQ2_LEN=/hive/data/genomes/canFam3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -fileServer=hgwdev -chainMinScore=3000 -chainLinearGap=medium) \ > do.log 2>&1 # real 821m15.144s cat fb.hg38.chainCanFam3Link.txt # 1536721546 bases of 3049335806 (50.395%) in intersection # replacing the broken one from Jan 2014: # 1523987456 bases of 3049335806 (49.978%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 canFam3) > rbest.log 2>&1 & # real 42m21.276s # load up the recip best chainNet tables time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 canFam3) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestCanFam3Link.txt # 1415877801 bases of 3049335806 (46.432%) in intersection # create and load up the syntenic chainNet tables 2017-10-30 cd /hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08/axtChain netToAxt hg38.canFam3.syn.net.gz hg38.canFam3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/canFam3/canFam3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/canFam3/chrom.sizes stdout \ | gzip -c > hg38.canFam3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynCanFam3 hg38.canFam3.syn.chain.gz netFilter -minGap=10 hg38.canFam3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynCanFam3 stdin cd /hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08 featureBits hg38 chainSynCanFam3Link > fb.hg38.chainSynCanFam3Link.txt 2>&1 cat fb.hg38.chainSynCanFam3Link.txt # 1478843439 bases of 3049335806 (48.497%) in intersection # and for the swap: mkdir /hive/data/genomes/canFam3/bed/blastz.hg38.swap cd /hive/data/genomes/canFam3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCanFam3.2015-04-08/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 105m19.994s cat fb.canFam3.chainHg38Link.txt # 1456224911 bases of 2392715236 (60.861%) in intersection # replacing the broken one from Jan 2014: # 1437624815 bases of 2392715236 (60.083%) in intersection time (doRecipBest.pl -buildDir=`pwd` canFam3 hg38) > rbest.log 2>&1 # real 43m54.042s ######################################################################### # LASTZ human/hg38 Tree dog/rheMac3 - (DONE - 2015-04-10 - Hiram) # re-running to correct missing contig alignments from rheMac3 mkdir /hive/data/genomes/hg38/bed/lastzRheMac3.2015-04-08 cd /hive/data/genomes/hg38/bed/lastzRheMac3.2015-04-08 cat << '_EOF_' > DEF # human vs macaca mulatta BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: Macaca Mulatta RheMac3 SEQ2_DIR=/scratch/data/rheMac3/rheMac3.2bit SEQ2_LEN=/scratch/data/rheMac3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzRheMac3.2015-04-08 TMPDIR=/dev/shm '_EOF_' # << 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 193m23.828s cat fb.hg38.chainRheMac3Link.txt # 2464716257 bases of 3049335806 (80.828%) in intersection # replacing the broken one from Jan 2014: # 2431208700 bases of 3049335806 (79.729%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 rheMac3) > rbest.log 2>&1 & # real 38m25.112s # and for the swap: mkdir /hive/data/genomes/rheMac3/bed/blastz.hg38.swap cd /hive/data/genomes/rheMac3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRheMac3.2015-04-08/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 83m14.955s cat fb.rheMac3.chainHg38Link.txt # 2328257435 bases of 2639145830 (88.220%) in intersection # replacing the broken one from Jan 2014: # 2288533769 bases of 2639145830 (86.715%) in intersection time (doRecipBest.pl -buildDir=`pwd` rheMac3 hg38) > rbest.log 2>&1 # real 39m52.256s ######################################################################### # LASTZ human/hg38 Tree mouse/mm10 - (DONE - 2015-04-30 - Hiram) # experiment to see if lineage specific repeats does more coverage mkdir /hive/data/genomes/hg38/bed/lastzMm10.2015-04-30 cd /hive/data/genomes/hg38/bed/lastzMm10.2015-04-30 cat << '_EOF_' > DEF # human vs mouse BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_ABRIDGE_REPEATS=1 # TARGET: Human Hg38 SEQ1_DIR=/scratch/data/hg38/nib SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes SEQ1_SMSK=/hive/data/genomes/hg38/bed/linSpecRep/humanSpecific SEQ1_CHUNK=40000000 SEQ1_LAP=10000 # QUERY: Mouse Mm10 SEQ2_DIR=/scratch/data/mm10/nib SEQ2_SMSK=/scratch/data/mm10/notInOthers SEQ2_LEN=/scratch/data/mm10/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMm10.2015-04-30 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl -stop=net -verbose=2 `pwd`/DEF \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -fileServer=hgwdev -chainMinScore=3000 -chainLinearGap=medium) \ > net.log 2>&1 # real 323m51.165s # test load, -debug to generate loadUp.csh, then modify the table names doBlastzChainNet.pl -stop=net -verbose=2 `pwd`/DEF -continue=load -debug \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -stop=load -fileServer=hgwdev -chainMinScore=3000 -chainLinearGap=medium > net.log 2>&1 # real 167m38.082s cat fb.hg38.chainMm10Link.txt # 1044599372 bases of 3049335806 (34.257%) in intersection # this procedure does produce more coverage cat fb.hg38.chainMm10Link.txt # 965211935 bases of 3049335806 (31.653%) in intersection # replacing the broken run from Jan 2014: # 964465044 bases of 3049335806 (31.629%) in intersection # XXX experiment concluded, not continued from here time (doRecipBest.pl -buildDir=`pwd` hg38 mm10) > rbest.log 2>&1 & # real 32m22.990s # and for the swap: mkdir /hive/data/genomes/mm10/bed/blastz.hg38.swap cd /hive/data/genomes/mm10/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMm10.2015-04-30/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 74m49.827s cat fb.mm10.chainHg38Link.txt # 938348519 bases of 2652783500 (35.372%) in intersection # replacing the broken run from Jan 2014: # 937030766 bases of 2652783500 (35.323%) in intersection time (doRecipBest.pl -buildDir=`pwd` mm10 hg38) > rbest.log 2>&1 # real 32m38.549s ######################################################################### # LASTZ human/hg38 Mouse lemur/micMur2 - (DONE - 2015-05-05 - Hiram) # for some odd reason, these results were lost # the same procedure was re-run March 2015 in: lastzMicMur2.2015-03-17 mkdir /hive/data/genomes/hg38/bed/lastzMicMur2.2015-05-06 cd /hive/data/genomes/hg38/bed/lastzMicMur2.2015-05-06 cp -p \ /hive/users/hiram/multiz/100way/hg38.micMur2/hg38.micMur2.tuning.top400.txt \ ./hg38.micMur2.tuning.Q.txt cat << '_EOF_' > DEF # human vs Mouse lemur # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.micMur2/hg38.micMur2.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=254 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzMicMur2.2015-05-06/hg38.micMur2.tuning.Q.txt # A C G T # A 100 -164 -34 -127 # C -164 93 -186 -34 # G -34 -186 93 -164 # T -127 -34 -164 100 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Mouse lemur micMur2 SEQ2_DIR=/hive/data/genomes/micMur2/micMur2.2bit SEQ2_LEN=/hive/data/genomes/micMur2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMicMur2.2015-05-06 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -syntenicNet) > do.log 2>&1 # real 286m0.829s cat fb.hg38.chainMicMur2Link.txt # 1632306331 bases of 3049335806 (53.530%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 micMur2) > rbest.log 2>&1 & # real 37m38.749s # and for the swap: mkdir /hive/data/genomes/micMur2/bed/blastz.hg38.swap cd /hive/data/genomes/micMur2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMicMur2.2015-05-06/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 108m50.264s cat fb.micMur2.chainHg38Link.txt # 1587083892 bases of 2377775715 (66.747%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` micMur2 hg38) \ > rbest.log 2>&1 # real 59m8.207s ######################################################################### # LASTZ human/hg38 Tree chimp/rheMac8 - (DONE - 2016-02-05 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05 cd /hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05 printf '# human vs macaca mulatta BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: Macaca Mulatta RheMac8 SEQ2_DIR=/hive/data/genomes/rheMac8/rheMac8.2bit SEQ2_LEN=/hive/data/genomes/rheMac8/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=600 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05 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 4099m2.582s # broken cluster run, continuing: time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -continue=cat -syntenicNet -fileServer=hgwdev \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku) > cat.log 2>&1 # real 101m51.644s cat fb.hg38.chainRheMac8Link.txt # 2576861166 bases of 3049335806 (84.506%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 rheMac8) > rbest.log 2>&1 & # real 182m11.216s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 rheMac8) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestRheMac8Link.txt # 2401566032 bases of 3049335806 (78.757%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05/axtChain netToAxt hg38.rheMac8.syn.net.gz hg38.rheMac8.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/rheMac8/rheMac8.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/rheMac8/chrom.sizes stdout \ | gzip -c > hg38.rheMac8.syn.chain.gz hgLoadChain -tIndex hg38 chainSynRheMac8 hg38.rheMac8.syn.chain.gz netFilter -minGap=10 hg38.rheMac8.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynRheMac8 stdin cd /hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05 featureBits hg38 chainSynRheMac8Link > fb.hg38.chainSynRheMac8Link.txt 2>&1 cat fb.hg38.chainSynRheMac8Link.txt # 2535752862 bases of 3049335806 (83.158%) in intersection # and for the swap: mkdir /hive/data/genomes/rheMac8/bed/blastz.hg38.swap cd /hive/data/genomes/rheMac8/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRheMac8.2016-02-05/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 234m24.287s cat fb.rheMac8.chainHg38Link.txt # 2499211352 bases of 3142093174 (79.540%) in intersection time (doRecipBest.pl -buildDir=`pwd` rheMac8 hg38) > rbest.log 2>&1 # real 355m16.431s ######################################################################### # LASTZ human/hg38 vs. chicken/galGal5 - (DONE - 2016-04-19 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGalGal5.2016-04-19 cd /hive/data/genomes/hg38/bed/lastzGalGal5.2016-04-19 printf "# human vs chicken BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: chicken galGal5 SEQ2_DIR=/hive/data/genomes/galGal5/galGal5.2bit SEQ2_LEN=/hive/data/genomes/galGal5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGalGal5.2016-04-19 TMPDIR=/dev/shm " > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 341m2.910s cat fb.hg38.chainGalGal5Link.txt # 155942333 bases of 3049335806 (5.114%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 galGal5) > rbest.log 2>&1 & # real 235m31.028s # and for the swap: mkdir /hive/data/genomes/galGal5/bed/blastz.hg38.swap cd /hive/data/genomes/galGal5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGalGal5.2016-04-19/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 17m45.055s cat fb.galGal5.chainHg38Link.txt # 131657596 bases of 1218501075 (10.805%) in intersection time (doRecipBest.pl -buildDir=`pwd` galGal5 hg38) > rbest.log 2>&1 # real 196m46.991s ######################################################################### # LASTZ human/hg38 vs. Malayan flying lemur/galVar1 - (DONE - 2016-04-25 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGalVar1.2016-04-25 cd /hive/data/genomes/hg38/bed/lastzGalVar1.2016-04-25 printf "# human vs Malayan flying lemur BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Malayan flying lemur galVar1 SEQ2_DIR=/hive/data/genomes/galVar1/galVar1.2bit SEQ2_LEN=/hive/data/genomes/galVar1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=400 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGalVar1.2016-04-25 TMPDIR=/dev/shm " > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 916m34.893s cat fb.hg38.chainGalVar1Link.txt # 1739210426 bases of 3049335806 (57.036%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 galVar1) \ > rbest.log 2>&1 & # real 1055m58.835s # and for the swap: mkdir /hive/data/genomes/galVar1/bed/blastz.hg38.swap cd /hive/data/genomes/galVar1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGalVar1.2016-04-25/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 357m45.647s cat fb.galVar1.chainHg38Link.txt # 1818567752 bases of 2802917674 (64.881%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` galVar1 hg38) \ > rbest.log 2>&1 # real 1774m42.560s ######################################################################### # LASTZ human/hg38 Gorilla/panPan2 - (DONE - 2016-05-24 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24 cd /hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24 cp -p \ /hive/users/hiram/multiz/100way/hg38.panPan2/hg38.panPan2.tuning.top200.txt \ ./hg38.panPan2.tuning.Q.txt printf '# human vs bonobo 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 # A 90 -330 -236 -356 # C -330 100 -318 -236 # G -236 -318 100 -330 # T -356 -236 -330 90 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: bonobo panPan2 SEQ2_DIR=/hive/data/genomes/panPan2/panPan2.2bit SEQ2_LEN=/hive/data/genomes/panPan2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24 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 203m58.095s cat fb.hg38.chainPanPan2Link.txt # 2826289232 bases of 3049335806 (92.685%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 panPan2) \ > rbest.log 2>&1 & # real 184m43.685s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 panPan2) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestPanPan2Link.txt # 2653262611 bases of 3049335806 (87.011%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24/axtChain netToAxt hg38.panPan2.syn.net.gz hg38.panPan2.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/panPan2/panPan2.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/panPan2/chrom.sizes stdout \ | gzip -c > hg38.panPan2.syn.chain.gz hgLoadChain -tIndex hg38 chainSynPanPan2 hg38.panPan2.syn.chain.gz netFilter -minGap=10 hg38.panPan2.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynPanPan2 stdin cd /hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24 featureBits hg38 chainSynPanPan2Link > fb.hg38.chainSynPanPan2Link.txt 2>&1 cat fb.hg38.chainSynPanPan2Link.txt # 2790018893 bases of 3049335806 (91.496%) in intersection # and for the swap: mkdir /hive/data/genomes/panPan2/bed/blastz.hg38.swap cd /hive/data/genomes/panPan2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPanPan2.2016-05-24/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 127m16.000s cat fb.panPan2.chainHg38Link.txt # 2664377492 bases of 2725937399 (97.742%) in intersection time (doRecipBest.pl -buildDir=`pwd` panPan2 hg38) > rbest.log 2>&1 # real 84m33.540s ######################################################################### # LASTZ human/hg38 vs. Killer whale/orcOrc1 - (DONE - 2015-04-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOrcOrc1.2016-06-03 cd /hive/data/genomes/hg38/bed/lastzOrcOrc1.2016-06-03 printf '# human vs Killer whale BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Killer whale orcOrc1 SEQ2_DIR=/hive/data/genomes/orcOrc1/orcOrc1.2bit SEQ2_LEN=/hive/data/genomes/orcOrc1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=5 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOrcOrc1.2016-06-03 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 772m18.962s cat fb.hg38.chainOrcOrc1Link.txt # 1544655174 bases of 3049335806 (50.655%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 orcOrc1) \ > rbest.log 2>&1 & # real 529m17.865s # and for the swap: mkdir /hive/data/genomes/orcOrc1/bed/blastz.hg38.swap cd /hive/data/genomes/orcOrc1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOrcOrc1.2016-06-03/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 128m38.587s cat fb.orcOrc1.chainHg38Link.txt # 1447157896 bases of 2249582125 (64.330%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` orcOrc1 hg38) \ > rbest.log 2>&1 # real 467m24.661s ######################################################################### # LASTZ human/hg38 Gorilla/gorGor5 - (DONE - 2016-06-24 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24 cd /hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24 printf '# human 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_Y=15000 BLASTZ_Q=/scratch/data/blastz/human_chimp.v2.q # A C G T # A 90 -330 -236 -356 # C -330 100 -318 -236 # G -236 -318 100 -330 # T -356 -236 -330 90 # TARGET: human hg38 SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 # 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=50 BASE=/hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24 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 830m35.387s cat fb.hg38.chainGorGor5Link.txt # 2887457436 bases of 3049335806 (94.691%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 gorGor5) \ > rbest.log 2>&1 & # real 101m55.329s # load up the recip best chainNet tables time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 gorGor5) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestGorGor5Link.txt # 2708011335 bases of 3049335806 (88.807%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24/axtChain netToAxt hg38.gorGor5.syn.net.gz hg38.gorGor5.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/gorGor5/gorGor5.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/gorGor5/chrom.sizes stdout \ | gzip -c > hg38.gorGor5.syn.chain.gz hgLoadChain -tIndex hg38 chainSynGorGor5 hg38.gorGor5.syn.chain.gz netFilter -minGap=10 hg38.gorGor5.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynGorGor5 stdin cd /hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24 featureBits hg38 chainSynGorGor5Link > fb.hg38.chainSynGorGor5Link.txt 2>&1 cat fb.hg38.chainSynGorGor5Link.txt # 2868720234 bases of 3049335806 (94.077%) in intersection # and for the swap: mkdir /hive/data/genomes/gorGor5/bed/blastz.hg38.swap cd /hive/data/genomes/gorGor5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGorGor5.2016-06-24/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 101m50.285s cat fb.gorGor5.chainHg38Link.txt # 2766345777 bases of 3080431298 (89.804%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` gorGor5 hg38) \ > rbest.log 2>&1 # real 125m35.459s ########################################################################### # Chimp Lastz run (DONE - 2016-08-03 - Hiram) screen -S hg38PanTro5 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03 cd /hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03 # always set the BLASTZ program so we know what version was used printf "# human vs chimp 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: Human Hg38 SEQ1_DIR=/scratch/data/hg38/hg38.2bit SEQ1_LEN=/scratch/data/hg38/chrom.sizes SEQ1_CHUNK=40000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 # QUERY: Chimp PanTro5 SEQ2_DIR=/hive/data/genomes/panTro5/panTro5.2bit SEQ2_LEN=/hive/data/genomes/panTro5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=100 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 209m31.431s cat fb.hg38.chainPanTro5Link.txt # 2907702790 bases of 3049335806 (95.355%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ hg38 panTro5) > rbest.log 2>&1 # real 195m53.750s time ($HOME/kent/src/hg/utils/automation/doRecipBest.pl -load -continue=load -workhorse=hgwdev -buildDir=`pwd` hg38 panTro5) \ > loadRBest.log 2>&1 # real 2m36.993s cat fb.hg38.chainRBestPanTro5Link.txt # 2737882959 bases of 3049335806 (89.786%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03/axtChain netToAxt hg38.panTro5.syn.net.gz hg38.panTro5.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/panTro5/panTro5.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/panTro5/chrom.sizes stdout \ | gzip -c > hg38.panTro5.syn.chain.gz # real 3m23.632s hgLoadChain -tIndex hg38 chainSynPanTro5 hg38.panTro5.syn.chain.gz netFilter -minGap=10 hg38.panTro5.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynPanTro5 stdin # real 1m13.380s cd /hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03 featureBits hg38 chainSynPanTro5Link >&fb.hg38.chainSynPanTro5Link.txt cat fb.hg38.chainSynPanTro5Link.txt # 2878970238 bases of 3049335806 (94.413%) in intersection # running the swap mkdir /hive/data/genomes/panTro5/bed/blastz.hg38.swap cd /hive/data/genomes/panTro5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzPanTro5.2016-08-03/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 126m8.214s cat fb.panTro5.chainHg38Link.txt # 2935702060 bases of 3132620660 (93.714%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ panTro5 hg38) > rbest.log 2>&1 # real 240m25.264s ############################################################################# # Chlorocebus sabaeus/Green monkey Lastz run (DONE - 2014-07-11 - Hiram) screen -S hg38ChlSab2 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11 cd /hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11 # always set the BLASTZ program so we know what version was used printf "# human vs Chlorocebus sabaeus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.52/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY Chlorocebus sabaeus chlSab2 SEQ2_DIR=/hive/data/genomes/chlSab2/chlSab2.2bit SEQ2_LEN=/hive/data/genomes/chlSab2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # Elapsed time: 142m4s cat fb.hg38.chainChlSab2Link.txt # 2573435303 bases of 3049335806 (84.393%) in intersection # filter with doRecipBest.pl doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ hg38 chlSab2 time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 chlSab2) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestChlSab2Link.txt # 2397287473 bases of 3049335806 (78.617%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11/axtChain netToAxt hg38.chlSab2.syn.net.gz hg38.chlSab2.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/chlSab2/chlSab2.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/chlSab2/chrom.sizes stdout \ | gzip -c > hg38.chlSab2.syn.chain.gz hgLoadChain -tIndex hg38 chainSynChlSab2 hg38.chlSab2.syn.chain.gz netFilter -minGap=10 hg38.chlSab2.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynChlSab2 stdin cd /hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11 featureBits hg38 chainSynChlSab2Link > fb.hg38.chainSynChlSab2Link.txt 2>&1 cat fb.hg38.chainSynChlSab2Link.txt # 2537786701 bases of 3049335806 (83.224%) in intersection # running the swap mkdir /hive/data/genomes/chlSab2/bed/blastz.hg38.swap cd /hive/data/genomes/chlSab2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzChlSab2.2014-07-11/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # Elapsed time: 88m48s cat fb.chlSab2.chainHg38Link.txt # 2429053010 bases of 2752019208 (88.264%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ chlSab2 hg38) > rbest.log 2>&1 # real 240m25.264s ############################################################################# # LASTZ human/hg38 vs. turkey/melGal5 - (DONE - 2017-01-20 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMelGal5.2017-01-20 cd /hive/data/genomes/hg38/bed/lastzMelGal5.2017-01-20 printf '# human vs turkey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: turkey melGal5 SEQ2_DIR=/hive/data/genomes/melGal5/melGal5.2bit SEQ2_LEN=/hive/data/genomes/melGal5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMelGal5.2017-01-20 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 190m58.492s cat fb.hg38.chainMelGal5Link.txt # 135950364 bases of 3049335806 (4.458%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 melGal5) \ > rbest.log 2>&1 & # real 492m55.893s # and for the swap: mkdir /hive/data/genomes/melGal5/bed/blastz.hg38.swap cd /hive/data/genomes/melGal5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMelGal5.2017-01-20/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 36m37.471s cat fb.melGal5.chainHg38Link.txt # 107549251 bases of 1093044709 (9.839%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` melGal5 hg38) \ > rbest.log 2>&1 # real 456m25.214s ######################################################################### # LASTZ human/hg38 vs. brown kiwi/aptMan1 - (DONE - 2017-02-21 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAptMan1.2017-02-21 cd /hive/data/genomes/hg38/bed/lastzAptMan1.2017-02-21 printf '# human vs brown kiwi BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: brown kiwi aptMan1 SEQ2_DIR=/hive/data/genomes/aptMan1/aptMan1.2bit SEQ2_LEN=/hive/data/genomes/aptMan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAptMan1.2017-02-21 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 368m59.939s cat fb.hg38.chainAptMan1Link.txt # 150901346 bases of 3049335806 (4.949%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 aptMan1) \ > rbest.log 2>&1 & # real 300m28.333s # and for the swap: mkdir /hive/data/genomes/aptMan1/bed/blastz.hg38.swap cd /hive/data/genomes/aptMan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAptMan1.2017-02-21/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 16m9.761s cat fb.aptMan1.chainHg38Link.txt # 125964464 bases of 1311306859 (9.606%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` aptMan1 hg38) \ > rbest.log 2>&1 # real 269m10.012s ######################################################################### # LASTZ human/hg38 Tree dolphin/turTru2 - (DONE - 2017-02-21 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTurTru2.2017-02-21 cd /hive/data/genomes/hg38/bed/lastzTurTru2.2017-02-21 printf '# human vs dolphin BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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=20000000 SEQ1_LAP=10000 # QUERY: Dog TurTru2 SEQ2_DIR=/hive/data/genomes/turTru2/turTru2.2bit SEQ2_LEN=/hive/data/genomes/turTru2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=600 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTurTru2.2017-02-21 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku \ -bigClusterHub=ku -fileServer=hgwdev \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 # real 572m54.888s cat fb.hg38.chainTurTru2Link.txt # 1516482527 bases of 3049335806 (49.732%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 turTru2) \ > rbest.log 2>&1 & # real 1079m31.677s # and for the swap: mkdir /hive/data/genomes/turTru2/bed/blastz.hg38.swap cd /hive/data/genomes/turTru2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTurTru2.2017-02-21/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 228m9.744s cat fb.turTru2.chainHg38Link.txt # 1432042877 bases of 2332402443 (61.398%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` turTru2 hg38) \ > rbest.log 2>&1 # real 1295m48.357s ######################################################################### # LASTZ human/hg38 vs. platypus/ornAna2 - (DONE - 2017-02-21 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOrnAna2.2017-02-21 cd /hive/data/genomes/hg38/bed/lastzOrnAna2.2017-02-21 printf '# human vs platypus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: platypus ornAna2 SEQ2_DIR=/hive/data/genomes/ornAna2/ornAna2.2bit SEQ2_LEN=/hive/data/genomes/ornAna2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=300 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOrnAna2.2017-02-21 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 445m13.234s cat fb.hg38.chainOrnAna2Link.txt # 256721472 bases of 3049335806 (8.419%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 ornAna2) \ > rbest.log 2>&1 & # real 788m25.199s # and for the swap: mkdir /hive/data/genomes/ornAna2/bed/blastz.hg38.swap cd /hive/data/genomes/ornAna2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOrnAna2.2017-02-21/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 130m42.942s cat fb.ornAna2.chainHg38Link.txt # 232286308 bases of 1842252119 (12.609%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` ornAna2 hg38) \ > rbest.log 2>&1 # real 821m10.828s ############################################################################# # Colobus angolensis palliatus/Angolan colobus lastz run (DONE - 2017-02-27 - Hiram) screen -S hg38ColAng1 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27 cd /hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27 # always set the BLASTZ program so we know what version was used printf "# human vs Angolan colobus BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY Angolan colobus colAng1 SEQ2_DIR=/hive/data/genomes/colAng1/colAng1.2bit SEQ2_LEN=/hive/data/genomes/colAng1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=40 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 123m41.958s cat fb.hg38.chainColAng1Link.txt # 2489504237 bases of 3049335806 (81.641%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ hg38 colAng1) > rbest.log 2>&1 # real 240m0.041s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 colAng1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestColAng1Link.txt # 2323958368 bases of 3049335806 (76.212%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27/axtChain netToAxt hg38.colAng1.syn.net.gz hg38.colAng1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/colAng1/colAng1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/colAng1/chrom.sizes stdout \ | gzip -c > hg38.colAng1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynColAng1 hg38.colAng1.syn.chain.gz netFilter -minGap=10 hg38.colAng1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynColAng1 stdin cd /hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27 featureBits hg38 chainSynColAng1Link > fb.hg38.chainSynColAng1Link.txt 2>&1 cat fb.hg38.chainSynColAng1Link.txt # 2439773865 bases of 3049335806 (80.010%) in intersection # running the swap mkdir /hive/data/genomes/colAng1/bed/blastz.hg38.swap cd /hive/data/genomes/colAng1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzColAng1.2017-02-27/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 80m23.924s cat fb.colAng1.chainHg38Link.txt # 2355021477 bases of 2679973137 (87.875%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ colAng1 hg38) > rbest.log 2>&1 # real 224m29.002s ############################################################################# # Macaca nemestrina/pig-tailed macaque lastz run (DONE - 2017-02-27 - Hiram) screen -S hg38MacNem1 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27 cd /hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27 # always set the BLASTZ program so we know what version was used printf "# human vs pig-tailed macaque BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY pig-tailed macaque macNem1 SEQ2_DIR=/hive/data/genomes/macNem1/macNem1.2bit SEQ2_LEN=/hive/data/genomes/macNem1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=40 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 122m14.198s cat fb.hg38.chainMacNem1Link.txt # 2546912844 bases of 3049335806 (83.524%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ hg38 macNem1) > rbest.log 2>&1 # real 201m54.795s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 macNem1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestMacNem1Link.txt # 2376010543 bases of 3049335806 (77.919%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27/axtChain netToAxt hg38.macNem1.syn.net.gz hg38.macNem1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/macNem1/macNem1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/macNem1/chrom.sizes stdout \ | gzip -c > hg38.macNem1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynMacNem1 hg38.macNem1.syn.chain.gz netFilter -minGap=10 hg38.macNem1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynMacNem1 stdin cd /hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27 featureBits hg38 chainSynMacNem1Link > fb.hg38.chainSynMacNem1Link.txt 2>&1 cat fb.hg38.chainSynMacNem1Link.txt # 2505548649 bases of 3049335806 (82.167%) in intersection # running the swap mkdir /hive/data/genomes/macNem1/bed/blastz.hg38.swap cd /hive/data/genomes/macNem1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzMacNem1.2017-02-27/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 82m42.545s cat fb.macNem1.chainHg38Link.txt # 2424148087 bases of 2838503083 (85.402%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ macNem1 hg38) > rbest.log 2>&1 # real 239m15.997s ############################################################################# # LASTZ human/hg38 Mouse lemur/micMur3 - (DONE - 2017-03-03 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03 cd /hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03 printf '# human vs Mouse lemur BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Mouse lemur micMur3 SEQ2_DIR=/hive/data/genomes/micMur3/micMur3.2bit SEQ2_LEN=/hive/data/genomes/micMur3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03 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 1149m34.034s cat fb.hg38.chainMicMur3Link.txt # 906521007 bases of 3049335806 (29.728%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 micMur3) \ > rbest.log 2>&1 & # real 265m38.806s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 micMur3) > rbest.log 2>&1 & cat fb.hg38.chainRBestMicMur3Link.txt # 857684217 bases of 3049335806 (28.127%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03/axtChain netToAxt hg38.micMur3.syn.net.gz hg38.micMur3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/micMur3/micMur3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/micMur3/chrom.sizes stdout \ | gzip -c > hg38.micMur3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynMicMur3 hg38.micMur3.syn.chain.gz netFilter -minGap=10 hg38.micMur3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynMicMur3 stdin cd /hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03 featureBits hg38 chainSynMicMur3Link > fb.hg38.chainSynMicMur3Link.txt 2>&1 cat fb.hg38.chainSynMicMur3Link.txt # 874918179 bases of 3049335806 (28.692%) in intersection # and for the swap: mkdir /hive/data/genomes/micMur3/bed/blastz.hg38.swap cd /hive/data/genomes/micMur3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzMicMur3.2017-03-03/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 42m21.629s cat fb.micMur3.chainHg38Link.txt # 880636728 bases of 2386321975 (36.904%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` micMur3 hg38) \ > rbest.log 2>&1 # real 296m23.384s ######################################################################### # LASTZ human/hg38 Chinese pangolin/manPen1 - (DONE - 2017-03-15 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzManPen1.2017-03-15 cd /hive/data/genomes/hg38/bed/lastzManPen1.2017-03-15 printf '# human vs Chinese pangolin BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Chinese pangolin manPen1 SEQ2_DIR=/hive/data/genomes/manPen1/manPen1.2bit SEQ2_LEN=/hive/data/genomes/manPen1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=120 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzManPen1.2017-03-15 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet -fileServer=hgwdev \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku) > do.log 2>&1 # real 495m29.451s cat fb.hg38.chainManPen1Link.txt # 1373891126 bases of 3049335806 (45.055%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 manPen1) \ > rbest.log 2>&1 & # real 672m29.761s # and for the swap: mkdir /hive/data/genomes/manPen1/bed/blastz.hg38.swap cd /hive/data/genomes/manPen1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 -swap \ /hive/data/genomes/hg38/bed/lastzManPen1.2017-03-15/DEF \ -syntenicNet -fileServer=hgwdev \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku) > swap.log 2>&1 # real 122m34.841s cat fb.manPen1.chainHg38Link.txt # 1305035790 bases of 1999066070 (65.282%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` manPen1 hg38) \ > rbest.log 2>&1 # real 729m45.645s ######################################################################### # LASTZ human/hg38 vs. Golden eagle/aquChr2 - (DONE - 2017-03-16 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAquChr2.2017-03-16 cd /hive/data/genomes/hg38/bed/lastzAquChr2.2017-03-16 printf "# human vs Golden eagle BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Golden eagle aquChr2 SEQ2_DIR=/hive/data/genomes/aquChr2/aquChr2.2bit SEQ2_LEN=/hive/data/genomes/aquChr2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAquChr2.2017-03-16 TMPDIR=/dev/shm " > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 249m22.348s cat fb.hg38.chainAquChr2Link.txt # 168168136 bases of 3049335806 (5.515%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 aquChr2) \ > rbest.log 2>&1 & # real 288m36.217s # and for the swap: mkdir /hive/data/genomes/aquChr2/bed/blastz.hg38.swap cd /hive/data/genomes/aquChr2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAquChr2.2017-03-16/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 14m18.710s cat fb.aquChr2.chainHg38Link.txt # 127935996 bases of 1180019022 (10.842%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` aquChr2 hg38) \ > rbest.log 2>&1 # real 180m40.655s ######################################################################### # LASTZ Cow bisBis1 (DONE - 2017-03-17 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzBisBis1.2017-03-17 cd /hive/data/genomes/hg38/bed/lastzBisBis1.2017-03-17 printf '# human vs bison BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Bison bisBis1 SEQ2_DIR=/hive/data/genomes/bisBis1/bisBis1.2bit SEQ2_LEN=/hive/data/genomes/bisBis1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=100 BASE=/hive/data/genomes/hg38/bed/lastzBisBis1.2017-03-17 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 \ `pwd`/DEF \ -syntenicNet -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 # real 686m35.655s cat fb.hg38.chainBisBis1Link.txt # 1392131211 bases of 3049335806 (45.654%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 bisBis1) \ > rbest.log 2>&1 & # real 585m14.200s # running the swap mkdir /hive/data/genomes/bisBis1/bed/blastz.hg38.swap cd /hive/data/genomes/bisBis1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzBisBis1.2017-03-17/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 374m22.343s cat fb.bisBis1.chainHg38Link.txt # 1344953854 bases of 2757854331 (48.768%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` bisBis1 hg38) \ > rbest.log 2>&1 # real 828m16.502s ############################################################################ # Rhinopithecus bieti/Black snub-nosed monkey lastz run # (DONE - 2017-03-23 - Hiram) screen -S hg38RhiBie1 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23 cd /hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23 # always set the BLASTZ program so we know what version was used printf "# human vs black snub-nosed monkey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY black snub-nosed monkey rhiBie1 SEQ2_DIR=/hive/data/genomes/rhiBie1/rhiBie1.2bit SEQ2_LEN=/hive/data/genomes/rhiBie1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=300 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 156m11.384s cat fb.hg38.chainRhiBie1Link.txt # 2532928717 bases of 3049335806 (83.065%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ hg38 rhiBie1) > rbest.log 2>&1 # real 457m19.209s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 rhiBie1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestRhiBie1Link.txt # 2356179781 bases of 3049335806 (77.269%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23/axtChain netToAxt hg38.rhiBie1.syn.net.gz hg38.rhiBie1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/rhiBie1/rhiBie1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/rhiBie1/chrom.sizes stdout \ | gzip -c > hg38.rhiBie1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynRhiBie1 hg38.rhiBie1.syn.chain.gz netFilter -minGap=10 hg38.rhiBie1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynRhiBie1 stdin cd /hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23 featureBits hg38 chainSynRhiBie1Link > fb.hg38.chainSynRhiBie1Link.txt 2>&1 cat fb.hg38.chainSynRhiBie1Link.txt # 2453690582 bases of 3049335806 (80.466%) in intersection # running the swap mkdir /hive/data/genomes/rhiBie1/bed/blastz.hg38.swap cd /hive/data/genomes/rhiBie1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzRhiBie1.2017-03-23/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 125m54.338s cat fb.rhiBie1.chainHg38Link.txt # 2420545520 bases of 2977074741 (81.306%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` \ rhiBie1 hg38) > rbest.log 2>&1 # real 595m32.110s ############################################################################# # LASTZ human/hg38 vs. X. tropicalis/xenTro9 - (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29 cd /hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29 printf '# human vs X. tropicalis BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: X. tropicalis xenTro9 SEQ2_DIR=/hive/data/genomes/xenTro9/xenTro9.2bit SEQ2_LEN=/hive/data/genomes/xenTro9/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 911m54.869s # download failed due to hgwdev home directory problem time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -continue=download -syntenicNet) > download.log 2>&1 & # real 3m53.808s cat fb.hg38.chainXenTro9Link.txt # 117720401 bases of 3049335806 (3.861%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 xenTro9) \ > rbest.log 2>&1 & # real 813m7.491s # and for the swap: mkdir /hive/data/genomes/xenTro9/bed/blastz.hg38.swap cd /hive/data/genomes/xenTro9/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXenTro9.2017-03-29/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 61m0.707s cat fb.xenTro9.chainHg38Link.txt # 108900066 bases of 1369865365 (7.950%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenTro9 hg38) \ > rbest.log 2>&1 # real 749m24.229s ############################################################################# # LASTZ human/hg38 vs. X. laevis/xenLae2 - (DONE - 2017-03-29 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29 cd /hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29 printf '# human vs X. laevis BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=50 SEQ1_LAP=10000 # QUERY: X. laevis xenLae2 SEQ2_DIR=/hive/data/genomes/xenLae2/xenLae2.2bit SEQ2_LEN=/hive/data/genomes/xenLae2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 952m1.703s cat fb.hg38.chainXenLae2Link.txt # 97526523 bases of 3049335806 (3.198%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 xenLae2) \ > rbest.log 2>&1 & # real 650m25.803s # and for the swap: mkdir /hive/data/genomes/xenLae2/bed/blastz.hg38.swap cd /hive/data/genomes/xenLae2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzXenLae2.2017-03-29/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 28m54.570s cat fb.xenLae2.chainHg38Link.txt # 114726989 bases of 2408724787 (4.763%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` xenLae2 hg38) \ > rbest.log 2>&1 # real 712m34.326s ######################################################################### # LASTZ human/hg38 vs. Chinese hamster CHO-K1 cell line/criGriChoV1 # (DONE - 2017-04-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCriGriChoV1.2017-04-13 cd /hive/data/genomes/hg38/bed/lastzCriGriChoV1.2017-04-13 printf '# human vs Chinese hamster ovary CHO-K1 cell line BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Chinese hamster ovary CHO-K1 cell line criGriChoV1 SEQ2_DIR=/hive/data/genomes/criGriChoV1/criGriChoV1.2bit SEQ2_LEN=/hive/data/genomes/criGriChoV1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCriGriChoV1.2017-04-13 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > do.log 2>&1 # real 3327m39.074s cat fb.hg38.chainCriGriChoV1Link.txt # 973293331 bases of 3049335806 (31.918%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 criGriChoV1) \ > rbest.log 2>&1 & # real 408m18.202s # and for the swap: mkdir /hive/data/genomes/criGriChoV1/bed/blastz.hg38.swap cd /hive/data/genomes/criGriChoV1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCriGriChoV1.2017-04-13/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 91m19.847s cat fb.criGriChoV1.chainHg38Link.txt # 935724011 bases of 2318132242 (40.365%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` criGriChoV1 hg38) \ > rbest.log 2>&1 & # real 436m55.979s ######################################################################### # LASTZ human/hg38 Baboon/papAnu3 - (DONE - 2017-06-21 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21 cd /hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21 printf '# human vs baboon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_M=254 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Baboon papAnu3 SEQ2_DIR=/hive/data/genomes/papAnu3/papAnu3.2bit SEQ2_LEN=/hive/data/genomes/papAnu3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=150 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21 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 1034m57.244s cat fb.hg38.chainPapAnu3Link.txt # 2632683317 bases of 3049335806 (86.336%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 papAnu3) \ > rbest.log 2>&1 & # real 488m59.447s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 papAnu3) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestPapAnu3Link.txt # 2430072678 bases of 3049335806 (79.692%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21/axtChain netToAxt hg38.papAnu3.syn.net.gz hg38.papAnu3.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/papAnu3/papAnu3.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/papAnu3/chrom.sizes stdout \ | gzip -c > hg38.papAnu3.syn.chain.gz hgLoadChain -tIndex hg38 chainSynPapAnu3 hg38.papAnu3.syn.chain.gz netFilter -minGap=10 hg38.papAnu3.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynPapAnu3 stdin cd /hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21 featureBits hg38 chainSynPapAnu3Link > fb.hg38.chainSynPapAnu3Link.txt 2>&1 cat fb.hg38.chainSynPapAnu3Link.txt # 2570312354 bases of 3049335806 (84.291%) in intersection # and for the swap: mkdir /hive/data/genomes/papAnu3/bed/blastz.hg38.swap cd /hive/data/genomes/papAnu3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPapAnu3.2017-06-21/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 232m5.391s cat fb.papAnu3.chainHg38Link.txt # 2501550280 bases of 2893270787 (86.461%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` papAnu3 hg38) \ > rbest.log 2>&1 # real 446m1.402s ######################################################################### # LASTZ human/hg38 vs. pig/susScr11 - (DONE - 2017-07-31 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzSusScr11.2017-07-31 cd /hive/data/genomes/hg38/bed/lastzSusScr11.2017-07-31 printf '# human vs pig BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: pig susScr11 SEQ2_DIR=/hive/data/genomes/susScr11/susScr11.2bit SEQ2_LEN=/hive/data/genomes/susScr11/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=5 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzSusScr11.2017-07-31 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 638m46.019s cat fb.hg38.chainSusScr11Link.txt # 1463754915 bases of 3049335806 (48.002%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 susScr11) \ > rbest.log 2>&1 & # real 664m31.094s # and for the swap: mkdir /hive/data/genomes/susScr11/bed/blastz.hg38.swap cd /hive/data/genomes/susScr11/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzSusScr11.2017-07-31/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 107m7.364s cat fb.susScr11.chainHg38Link.txt # 1387973267 bases of 2472073034 (56.146%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` susScr11 hg38) \ > rbest.log 2>&1 # real 598m8.675s ######################################################################### # LASTZ human/hg38 vs. Nile tilapia/oreNil3 - (DONE - 2017-07-31 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzOreNil3.2017-07-31 cd /hive/data/genomes/hg38/bed/lastzOreNil3.2017-07-31 printf '# human vs Nile tilapia BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Nile tilapia oreNil3 SEQ2_DIR=/hive/data/genomes/oreNil3/oreNil3.2bit SEQ2_LEN=/hive/data/genomes/oreNil3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=10 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOreNil3.2017-07-31 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 318m42.840s cat fb.hg38.chainOreNil3Link.txt # 59963651 bases of 3049335806 (1.966%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 oreNil3) \ > rbest.log 2>&1 & # real 275m9.491s # and for the swap: mkdir /hive/data/genomes/oreNil3/bed/blastz.hg38.swap cd /hive/data/genomes/oreNil3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOreNil3.2017-07-31/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m59.810s cat fb.oreNil3.chainHg38Link.txt # 56298016 bases of 1009856516 (5.575%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` oreNil3 hg38) \ > rbest.log 2>&1 # real 263m17.904s ######################################################################### # LASTZ human/hg38 drill/manLeu1 - (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25 cd /hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25 printf '# human vs drill BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: Drill/Mandrillus leucophaeus manLeu1 SEQ2_DIR=/hive/data/genomes/manLeu1/manLeu1.2bit SEQ2_LEN=/hive/data/genomes/manLeu1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25 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 121m0.485s cat fb.hg38.chainManLeu1Link.txt # 2515634714 bases of 3049335806 (82.498%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 manLeu1) \ > rbest.log 2>&1 & # real 287m28.553s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 manLeu1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestManLeu1Link.txt # 2346062769 bases of 3049335806 (76.937%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25/axtChain netToAxt hg38.manLeu1.syn.net.gz hg38.manLeu1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/manLeu1/manLeu1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/manLeu1/chrom.sizes stdout \ | gzip -c > hg38.manLeu1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynManLeu1 hg38.manLeu1.syn.chain.gz netFilter -minGap=10 hg38.manLeu1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynManLeu1 stdin cd /hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25 featureBits hg38 chainSynManLeu1Link > fb.hg38.chainSynManLeu1Link.txt 2>&1 cat fb.hg38.chainSynManLeu1Link.txt # 2472880015 bases of 3049335806 (81.096%) in intersection # and for the swap: mkdir /hive/data/genomes/manLeu1/bed/blastz.hg38.swap cd /hive/data/genomes/manLeu1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzManLeu1.2017-09-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 79m34.951s cat fb.manLeu1.chainHg38Link.txt # 2409820927 bases of 2721424086 (88.550%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` manLeu1 hg38) \ > rbest.log 2>&1 # real 388m23.086s ######################################################################### # LASTZ human/hg38 vs. Ma's night monkey/aotNan1 - (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25 cd /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25 printf '# human vs Ma_s night monkey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: aotNan1 - Ma_s night monkey - Aotus nancymaae SEQ2_DIR=/hive/data/genomes/aotNan1/aotNan1.2bit SEQ2_LEN=/hive/data/genomes/aotNan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25 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 205m4.426s cat fb.hg38.chainAotNan1Link.txt # 2153726630 bases of 3049335806 (70.629%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 aotNan1) \ > rbest.log 2>&1 & # real 269m4.216s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 aotNan1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestAotNan1Link.txt # 2013684675 bases of 3049335806 (66.037%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25/axtChain netToAxt hg38.aotNan1.syn.net.gz hg38.aotNan1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/aotNan1/aotNan1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/aotNan1/chrom.sizes stdout \ | gzip -c > hg38.aotNan1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynAotNan1 hg38.aotNan1.syn.chain.gz netFilter -minGap=10 hg38.aotNan1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynAotNan1 stdin cd /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25 featureBits hg38 chainSynAotNan1Link > fb.hg38.chainSynAotNan1Link.txt 2>&1 cat fb.hg38.chainSynAotNan1Link.txt # 2098197465 bases of 3049335806 (68.808%) in intersection # and for the swap: mkdir /hive/data/genomes/aotNan1/bed/blastz.hg38.swap cd /hive/data/genomes/aotNan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAotNan1.2017-09-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m8.440s cat fb.aotNan1.chainHg38Link.txt # 2111600029 bases of 2714439490 (77.791%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` aotNan1 hg38) \ > rbest.log 2>&1 # real 427m26.453s ######################################################################### # LASTZ human/hg38 vs. Hawaiian monk seal/neoSch1 - (DONE - 2017-09-25 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzNeoSch1.2017-09-25 cd /hive/data/genomes/hg38/bed/lastzNeoSch1.2017-09-25 printf '# human vs Hawaiian monk seal BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Hawaiian monk seal - neoSch1 SEQ2_DIR=/hive/data/genomes/neoSch1/neoSch1.2bit SEQ2_LEN=/hive/data/genomes/neoSch1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzNeoSch1.2017-09-25 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 512m6.939s cat fb.hg38.chainNeoSch1Link.txt # 1586260720 bases of 3049335806 (52.020%) in intersection cat fb.hg38.chainSynNeoSch1Link.txt # 1515015853 bases of 3049335806 (49.683%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 neoSch1) \ > rbest.log 2>&1 & # real 475m3.278s cat fb.hg38.chainRBestNeoSch1Link.txt # 1455520429 bases of 3049335806 (47.732%) in intersection # and for the swap: mkdir /hive/data/genomes/neoSch1/bed/blastz.hg38.swap cd /hive/data/genomes/neoSch1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzNeoSch1.2017-09-25/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 108m21.523s cat fb.neoSch1.chainHg38Link.txt # 1483929997 bases of 2400839308 (61.809%) in intersection cat fb.neoSch1.chainSynHg38Link.txt # 1446564285 bases of 2400839308 (60.252%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` neoSch1 hg38) \ > rbest.log 2>&1 # real 404m14.530s cat fb.neoSch1.chainRBestHg38Link.txt # 1455431042 bases of 2400839308 (60.622%) in intersection ######################################################################### # LASTZ human/hg38 vs. Sooty mangabey/cerAty1 - (DONE - 2017-09-27 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27 cd /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27 printf '# human vs Sooty mangabey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: cerAty1 - Sooty mangabey - Cercocebus atys SEQ2_DIR=/hive/data/genomes/cerAty1/cerAty1.2bit SEQ2_LEN=/hive/data/genomes/cerAty1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27 TMPDIR=/dev/shm ' > DEF 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 202m34.990s cat fb.hg38.chainCerAty1Link.txt # 2556764791 bases of 3049335806 (83.847%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 cerAty1) \ > rbest.log 2>&1 & # real 188m38.348s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 cerAty1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestCerAty1Link.txt # 2383692825 bases of 3049335806 (78.171%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27/axtChain netToAxt hg38.cerAty1.syn.net.gz hg38.cerAty1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/cerAty1/cerAty1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/cerAty1/chrom.sizes stdout \ | gzip -c > hg38.cerAty1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynCerAty1 hg38.cerAty1.syn.chain.gz netFilter -minGap=10 hg38.cerAty1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynCerAty1 stdin cd /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27 featureBits hg38 chainSynCerAty1Link > fb.hg38.chainSynCerAty1Link.txt 2>&1 cat fb.hg38.chainSynCerAty1Link.txt # 2516680168 bases of 3049335806 (82.532%) in intersection # and for the swap: mkdir /hive/data/genomes/cerAty1/bed/blastz.hg38.swap cd /hive/data/genomes/cerAty1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCerAty1.2017-09-27/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 84m53.559s cat fb.cerAty1.chainHg38Link.txt # 2424226994 bases of 2787289397 (86.974%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` cerAty1 hg38) \ > rbest.log 2>&1 # real 226m2.420s ######################################################################### # LASTZ human/hg38 vs. Sooty mangabey/proCoq1 - (DONE - 2017-09-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28 cd /hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28 printf '# human vs Coquerel_s sifaka BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: proCoq1 - Coquerel_s sifaka - Propithecus coquereli SEQ2_DIR=/hive/data/genomes/proCoq1/proCoq1.2bit SEQ2_LEN=/hive/data/genomes/proCoq1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=70 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28 TMPDIR=/dev/shm ' > DEF 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 110m38.813s cat fb.hg38.chainProCoq1Link.txt # 990017370 bases of 3049335806 (32.467%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 proCoq1) \ > rbest.log 2>&1 & # real 330m51.520s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 proCoq1) > rbest.log 2>&1 & cat fb.hg38.chainRBestProCoq1Link.txt # 935801596 bases of 3049335806 (30.689%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28/axtChain netToAxt hg38.proCoq1.syn.net.gz hg38.proCoq1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/proCoq1/proCoq1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/proCoq1/chrom.sizes stdout \ | gzip -c > hg38.proCoq1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynProCoq1 hg38.proCoq1.syn.chain.gz netFilter -minGap=10 hg38.proCoq1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynProCoq1 stdin cd /hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28 featureBits hg38 chainSynProCoq1Link > fb.hg38.chainSynProCoq1Link.txt 2>&1 cat fb.hg38.chainSynProCoq1Link.txt # 943897639 bases of 3049335806 (30.954%) in intersection # and for the swap: mkdir /hive/data/genomes/proCoq1/bed/blastz.hg38.swap cd /hive/data/genomes/proCoq1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzProCoq1.2017-09-28/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 44m29.295s cat fb.proCoq1.chainHg38Link.txt # 953092997 bases of 2083764538 (45.739%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` proCoq1 hg38) \ > rbest.log 2>&1 # real 334m45.550s ######################################################################### # LASTZ human/hg38 vs. White-faced sapajou/cebCap1 - (DONE - 2017-09-28 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28 cd /hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28 printf '# human vs White-faced sapajou BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: cebCap1 - White-faced sapajou - Cebus capucinus imitator SEQ2_DIR=/hive/data/genomes/cebCap1/cebCap1.2bit SEQ2_LEN=/hive/data/genomes/cebCap1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28 TMPDIR=/dev/shm ' > DEF 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 169m20.421s cat fb.hg38.chainCebCap1Link.txt # 2155370668 bases of 3049335806 (70.683%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 cebCap1) \ > rbest.log 2>&1 & # real 210m50.610s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 cebCap1) > loadRBest.log 2>&1 & cat fb.hg38.chainRBestCebCap1Link.txt # 2011508311 bases of 3049335806 (65.965%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28/axtChain netToAxt hg38.cebCap1.syn.net.gz hg38.cebCap1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/cebCap1/cebCap1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/cebCap1/chrom.sizes stdout \ | gzip -c > hg38.cebCap1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynCebCap1 hg38.cebCap1.syn.chain.gz netFilter -minGap=10 hg38.cebCap1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynCebCap1 stdin cd /hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28 featureBits hg38 chainSynCebCap1Link > fb.hg38.chainSynCebCap1Link.txt 2>&1 cat fb.hg38.chainSynCebCap1Link.txt # 2113665551 bases of 3049335806 (69.316%) in intersection # and for the swap: mkdir /hive/data/genomes/cebCap1/bed/blastz.hg38.swap cd /hive/data/genomes/cebCap1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCebCap1.2017-09-28/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 76m58.704s cat fb.cebCap1.chainHg38Link.txt # 2053319068 bases of 2610518382 (78.656%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` cebCap1 hg38) \ > rbest.log 2>&1 # real 227m7.064s ######################################################################### # LASTZ human/hg38 vs. Sclater's lemur/eulFla1 - (DONE - 2017-10-03 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03 cd /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03 printf '# human vs Sclater_s lemur BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: eulFla1 - Sclater_s lemur - Eulemur flavifrons SEQ2_DIR=/hive/data/genomes/eulFla1/eulFla1.2bit SEQ2_LEN=/hive/data/genomes/eulFla1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03 TMPDIR=/dev/shm ' > DEF 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 130m37.028s cat fb.hg38.chainEulFla1Link.txt # 1016209837 bases of 3049335806 (33.326%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eulFla1) \ > rbest.log 2>&1 & # real 214m11.636s # loading the recip best results time (doRecipBest.pl -load -continue=load -workhorse=hgwdev -buildDir=`pwd` hg38 eulFla1) \ > loadRBest.log 2>&1 & # real 5m38.039s cat fb.hg38.chainRBestEulFla1Link.txt # 961423111 bases of 3049335806 (31.529%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03/axtChain netToAxt hg38.eulFla1.syn.net.gz hg38.eulFla1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/eulFla1/eulFla1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/eulFla1/chrom.sizes stdout \ | gzip -c > hg38.eulFla1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynEulFla1 hg38.eulFla1.syn.chain.gz netFilter -minGap=10 hg38.eulFla1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynEulFla1 stdin cd /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03 featureBits hg38 chainSynEulFla1Link > fb.hg38.chainSynEulFla1Link.txt 2>&1 # real 7m20.440s cat fb.hg38.chainSynEulFla1Link.txt # 973484798 bases of 3049335806 (31.924%) in intersection # and for the swap: mkdir /hive/data/genomes/eulFla1/bed/blastz.hg38.swap cd /hive/data/genomes/eulFla1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEulFla1.2017-10-03/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 48m20.179s cat fb.eulFla1.chainHg38Link.txt # 969761746 bases of 2094103399 (46.309%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulFla1 hg38) \ > rbest.log 2>&1 # real 199m39.734s time ($HOME/kent/src/hg/utils/automation/doRecipBest.pl -load -continue=load -workhorse=hgwdev -buildDir=`pwd` eulFla1 hg38) \ > loadRBest.log 2>&1 # real 6m23.578s cat fb.eulFla1.chainRBestHg38Link.txt # 961226273 bases of 2094103399 (45.902%) in intersection ######################################################################### # LASTZ human/hg38 vs. Black lemur/eulMac1 - (DONE - 2017-10-04 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04 cd /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04 printf '# human vs Black lemur BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz # maximum M allowed with lastz is only 254 BLASTZ_M=254 BLASTZ_Q=/scratch/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 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=20000000 SEQ1_LAP=10000 # QUERY: eulMac1 - Black lemur - Eulemur macaco SEQ2_DIR=/hive/data/genomes/eulMac1/eulMac1.2bit SEQ2_LEN=/hive/data/genomes/eulMac1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04 TMPDIR=/dev/shm ' > DEF 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 66m41.057s cat fb.hg38.chainEulMac1Link.txt # 1027856175 bases of 3049335806 (33.708%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` hg38 eulMac1) \ > rbest.log 2>&1 & # real 220m20.185s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 eulMac1) > rbest.log 2>&1 & # real 6m20.657s cat fb.hg38.chainRBestEulMac1Link.txt 972709793 bases of 3049335806 (31.899%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04/axtChain netToAxt hg38.eulMac1.syn.net.gz hg38.eulMac1.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/eulMac1/eulMac1.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/eulMac1/chrom.sizes stdout \ | gzip -c > hg38.eulMac1.syn.chain.gz hgLoadChain -tIndex hg38 chainSynEulMac1 hg38.eulMac1.syn.chain.gz netFilter -minGap=10 hg38.eulMac1.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynEulMac1 stdin cd /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04 featureBits hg38 chainSynEulMac1Link > fb.hg38.chainSynEulMac1Link.txt 2>&1 cat fb.hg38.chainSynEulMac1Link.txt # 983839076 bases of 3049335806 (32.264%) in intersection # and for the swap: mkdir /hive/data/genomes/eulMac1/bed/blastz.hg38.swap cd /hive/data/genomes/eulMac1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEulMac1.2017-10-04/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 47m2.650s cat fb.eulMac1.chainHg38Link.txt # 979925982 bases of 2101039320 (46.640%) in intersection time (doRecipBest.pl -workhorse=hgwdev -buildDir=`pwd` eulMac1 hg38) \ > rbest.log 2>&1 # real 200m34.710s ######################################################################### # LASTZ Human/hg38 - Tarsier TarSyr2 (DONE - 2014-12-11 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11 cd /hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11 cat << '_EOF_' > DEF # human vs tarsier # parameters obtained from a tuning run of lastz_D # /hive/users/hiram/multiz/100way/hg38.tarSyr2/hg38.tarSyr2.tuning.top400.txt BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.54/bin/lastz BLASTZ_T=2 BLASTZ_O=400 BLASTZ_E=30 BLASTZ_M=50 BLASTZ_X=1000 BLASTZ_Y=3400 BLASTZ_Q=/hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11/hg38.tarSyr2.tuning.Q.txt # A C G T # A 100 -172 -29 -118 # C -172 98 -170 -29 # G -29 -170 98 -172 # T -118 -29 -172 100 # TARGET: Human hg38 SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LIMIT=80 SEQ1_LAP=10000 # QUERY: Tarsier tarSyr2 SEQ2_DIR=/hive/data/genomes/tarSyr2/tarSyr2.2bit SEQ2_LEN=/hive/data/genomes/tarSyr2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=500 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11 TMPDIR=/dev/shm '_EOF_' # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 1223m11.846s cat fb.hg38.chainTarSyr2Link.txt # 1708294423 bases of 3049335806 (56.022%) in intersection time (doRecipBest.pl -buildDir=`pwd` hg38 tarSyr2) > rbest.log 2>&1 & # real 46m29.975s time (doRecipBest.pl -load -continue=load -workhorse=hgwdev \ -buildDir=`pwd` hg38 tarSyr2) > loadRBest.log 2>&1 & # real 12m28.565s cat fb.hg38.chainRBestTarSyr2Link.txt # 1563421915 bases of 3049335806 (51.271%) in intersection # create and load up syntenic chainNet: 2017-10-27 cd /hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11/axtChain netToAxt hg38.tarSyr2.syn.net.gz hg38.tarSyr2.all.chain.gz \ /scratch/data/hg38/hg38.2bit /hive/data/genomes/tarSyr2/tarSyr2.2bit stdout \ | axtSort stdin stdout \ | axtToChain stdin /hive/data/genomes/hg38/chrom.sizes \ /hive/data/genomes/tarSyr2/chrom.sizes stdout \ | gzip -c > hg38.tarSyr2.syn.chain.gz hgLoadChain -tIndex hg38 chainSynTarSyr2 hg38.tarSyr2.syn.chain.gz netFilter -minGap=10 hg38.tarSyr2.syn.net.gz \ | hgLoadNet -verbose=0 hg38 netSynTarSyr2 stdin cd /hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11 featureBits hg38 chainSynTarSyr2Link > fb.hg38.chainSynTarSyr2Link.txt 2>&1 cat fb.hg38.chainSynTarSyr2Link.txt # 1622913627 bases of 3049335806 (53.222%) in intersection # and for the swap: mkdir /hive/data/genomes/tarSyr2/bed/blastz.hg38.swap cd /hive/data/genomes/tarSyr2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzTarSyr2.2014-12-11/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 452m27.264s cat fb.tarSyr2.chainHg38Link.txt # 1781378574 bases of 3405755564 (52.305%) in intersection time (doRecipBest.pl -buildDir=`pwd` tarSyr2 hg38) > rbest.log 2>&1 # real 115m47.619s ############################################################################## # LASTZ Kangaroo Rat DipOrd2 (DONE - 2018-01-01 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzDipOrd2.2018-01-01 cd /hive/data/genomes/hg38/bed/lastzDipOrd2.2018-01-01 printf '# Human vs. Kangaroo Rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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=20000000 SEQ1_LAP=10000 # QUERY: Kangaroo Rat SEQ2_DIR=/hive/data/genomes/dipOrd2/dipOrd2.2bit SEQ2_LEN=/hive/data/genomes/dipOrd2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=180 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzDipOrd2.2018-01-01 TMPDIR=/dev/shm ' > DEF # establish a screen to control this job screen time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 435m37.638s cat fb.hg38.chainDipOrd2Link.txt # 1001007354 bases of 3049335806 (32.827%) in intersection cat fb.hg38.chainSynDipOrd2Link.txt # 934602735 bases of 3049335806 (30.649%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` hg38 dipOrd2) > rbest.log 2>&1 & # real 424m7.155s cat fb.hg38.chainRBestDipOrd2Link.txt # 921538020 bases of 3049335806 (30.221%) in intersection # and for the swap: mkdir /hive/data/genomes/dipOrd2/bed/blastz.hg38.swap cd /hive/data/genomes/dipOrd2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzDipOrd2.2018-01-01/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -syntenicNet) > swap.log 2>&1 & # real 97m8.750s cat fb.dipOrd2.chainHg38Link.txt # 957281496 bases of 2065314047 (46.350%) in intersection cat fb.dipOrd2.chainSynHg38Link.txt # 905805640 bases of 2065314047 (43.858%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` dipOrd2 hg38) > rbest.log 2>&1 & # real 431m28.226s cat fb.dipOrd2.chainRBestHg38Link.txt # 923041001 bases of 2065314047 (44.693%) in intersection ############################################################################## # LASTZ Damara mole rat - Fukomys damarensis (DONE - 2018-01-01 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFukDam1.2018-01-01 cd /hive/data/genomes/hg38/bed/lastzFukDam1.2018-01-01 printf '# Human vs. Damara mole rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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=20000000 SEQ1_LAP=10000 # QUERY: Damara mole rat SEQ2_DIR=/hive/data/genomes/fukDam1/fukDam1.2bit SEQ2_LEN=/hive/data/genomes/fukDam1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=200 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFukDam1.2018-01-01 TMPDIR=/dev/shm ' > DEF # establish a screen to control this job screen time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 504m13.875s cat fb.hg38.chainFukDam1Link.txt # 1340852960 bases of 3049335806 (43.972%) in intersection cat fb.hg38.chainSynFukDam1Link.txt # 1276966958 bases of 3049335806 (41.877%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` hg38 fukDam1) > rbest.log 2>&1 & # real 391m20.373s cat fb.hg38.chainRBestFukDam1Link.txt # 1236966410 bases of 3049335806 (40.565%) in intersection # and for the swap: mkdir /hive/data/genomes/fukDam1/bed/blastz.hg38.swap cd /hive/data/genomes/fukDam1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFukDam1.2018-01-01/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -syntenicNet) > swap.log 2>&1 & # real 122m19.689s cat fb.fukDam1.chainHg38Link.txt # 1290829351 bases of 2285984782 (56.467%) in intersection cat fb.fukDam1.chainSynHg38Link.txt # 1233187886 bases of 2285984782 (53.946%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` fukDam1 hg38) > rbest.log 2>&1 & # real 456m33.399s cat fb.fukDam1.chainRBestHg38Link.txt # 1238697651 bases of 2285984782 (54.187%) in intersection ############################################################################## # Chimp Lastz run (DONE - 2018-01-03 - Hiram) screen -S hg38PanTro3 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzPanTro3.2018-01-03 cd /hive/data/genomes/hg38/bed/lastzPanTro3.2018-01-03 # always set the BLASTZ program so we know what version was used printf "# human vs chimp 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: Human Hg38 SEQ1_DIR=/scratch/data/hg38/hg38.2bit SEQ1_LEN=/scratch/data/hg38/chrom.sizes SEQ1_CHUNK=40000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 # QUERY: Chimp PanTro3 SEQ2_DIR=/hive/data/genomes/panTro3/panTro3.2bit SEQ2_LEN=/hive/data/genomes/panTro3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=100 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzPanTro3.2018-01-03 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 170m54.660s cat fb.hg38.chainPanTro3Link.txt # 2839373050 bases of 3049335806 (93.114%) in intersection cat fb.hg38.chainSynPanTro3Link.txt # 2805471052 bases of 3049335806 (92.003%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 panTro3) > rbest.log 2>&1 # real 122m48.608s cat fb.hg38.chainRBestPanTro3Link.txt # 2677897807 bases of 3049335806 (87.819%) in intersection # running the swap mkdir /hive/data/genomes/panTro3/bed/blastz.hg38.swap cd /hive/data/genomes/panTro3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzPanTro3.2018-01-03/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 92m7.154s cat fb.panTro3.chainHg38Link.txt # 2775323749 bases of 2900529764 (95.683%) in intersection cat fb.panTro3.chainSynHg38Link.txt # 2733818111 bases of 2900529764 (94.252%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ panTro3 hg38) > rbest.log 2>&1 # real 173m38.562s cat fb.panTro3.chainRBestHg38Link.txt # 2685706565 bases of 2900529764 (92.594%) in intersection ############################################################################# # LASTZ human/hg38 vs. Chinese hamster CHO-K1 cell line/criGriChoV2 # (DONE - 2018-01-05 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCriGriChoV2.2018-01-05 cd /hive/data/genomes/hg38/bed/lastzCriGriChoV2.2018-01-05 printf '# human vs Chinese hamster ovary CHO-K1 cell line BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Chinese hamster ovary CHO-K1 cell line criGriChoV2 SEQ2_DIR=/hive/data/genomes/criGriChoV2/criGriChoV2.2bit SEQ2_LEN=/hive/data/genomes/criGriChoV2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCriGriChoV2.2018-01-05 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > do.log 2>&1 # real 527m7.679s cat fb.hg38.chainCriGriChoV2Link.txt # 1016328250 bases of 3049335806 (33.329%) in intersection cat fb.hg38.chainSynCriGriChoV2Link.txt # 961641546 bases of 3049335806 (31.536%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 criGriChoV2) > rbest.log 2>&1 & # real 443m50.337s cat fb.hg38.chainRBestCriGriChoV2Link.txt # 936450028 bases of 3049335806 (30.710%) in intersection # and for the swap: mkdir /hive/data/genomes/criGriChoV2/bed/blastz.hg38.swap cd /hive/data/genomes/criGriChoV2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCriGriChoV2.2018-01-05/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 123m38.716s cat fb.criGriChoV2.chainHg38Link.txt # 983638905 bases of 2323924942 (42.327%) in intersection cat fb.criGriChoV2.chainSynHg38Link.txt # 932774807 bases of 2323924942 (40.138%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ criGriChoV2 hg38) > rbest.log 2>&1 & # real 489m43.438s cat fb.criGriChoV2.chainRBestHg38Link.txt # 938325634 bases of 2323924942 (40.377%) in intersection ######################################################################### # LASTZ human/hg38 Baboon/papAnu4 - (DONE - 2018-01-08 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPapAnu4.2018-01-08 cd /hive/data/genomes/hg38/bed/lastzPapAnu4.2018-01-08 printf '# human vs baboon BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_M=254 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: Baboon papAnu4 SEQ2_DIR=/hive/data/genomes/papAnu4/papAnu4.2bit SEQ2_LEN=/hive/data/genomes/papAnu4/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=150 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPapAnu4.2018-01-08 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 1300m59.182s cat fb.hg38.chainPapAnu4Link.txt # 2665048631 bases of 3049335806 (87.398%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 papAnu4) \ > rbest.log 2>&1 & # real 394m33.277s cat fb.hg38.chainRBestPapAnu4Link.txt # 2462004619 bases of 3049335806 (80.739%) in intersection # and for the swap: mkdir /hive/data/genomes/papAnu4/bed/blastz.hg38.swap cd /hive/data/genomes/papAnu4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPapAnu4.2018-01-08/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 166m16.865s cat fb.papAnu4.chainHg38Link.txt # 2539481835 bases of 2937004939 (86.465%) in intersection cat fb.papAnu4.chainSynHg38Link.txt # 2485777123 bases of 2937004939 (84.636%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` papAnu4 hg38) \ > rbest.log 2>&1 & # real 483m48.216s cat fb.papAnu4.chainRBestHg38Link.txt # 2465241931 bases of 2937004939 (83.937%) in intersection ######################################################################### # LASTZ human/hg38 vs. guinea pig/cavApe1 - (DONE - 2018-01-08 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCavApe1.2018-01-08 cd /hive/data/genomes/hg38/bed/lastzCavApe1.2018-01-08 printf '# human vs guinea pig BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: guinea pig cavApe1 SEQ2_DIR=/hive/data/genomes/cavApe1/cavApe1.2bit SEQ2_LEN=/hive/data/genomes/cavApe1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCavApe1.2018-01-08 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 502m28.460s cat fb.hg38.chainCavApe1Link.txt # 804449430 bases of 3049335806 (26.381%) in intersection cat fb.hg38.chainSynCavApe1Link.txt # 746370799 bases of 3049335806 (24.477%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 cavApe1) > rbest.log 2>&1 & # real 386m40.434s cat fb.hg38.chainRBestCavApe1Link.txt # 735739254 bases of 3049335806 (24.128%) in intersection # and for the swap: mkdir /hive/data/genomes/cavApe1/bed/blastz.hg38.swap cd /hive/data/genomes/cavApe1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCavApe1.2018-01-08/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 61m35.236s cat fb.cavApe1.chainHg38Link.txt # 767670846 bases of 1749140834 (43.888%) in intersection cat fb.cavApe1.chainSynHg38Link.txt # 734822213 bases of 1749140834 (42.010%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ cavApe1 hg38) > rbest.log 2>&1 # real 327m9.529s cat fb.cavApe1.chainRBestHg38Link.txt # 737288411 bases of 1749140834 (42.151%) in intersection ######################################################################### # LASTZ human/hg38 vs. Collard flycatcher/ficAlb1 - (DONE - 2018-01-08 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFicAlb1.2018-01-08 cd /hive/data/genomes/hg38/bed/lastzFicAlb1.2018-01-08 cat << '_EOF_' > DEF printf '# human vs Collard flycatcher BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Collard flycatcher ficAlb1 SEQ2_DIR=/hive/data/genomes/ficAlb1/ficAlb1.2bit SEQ2_LEN=/hive/data/genomes/ficAlb1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFicAlb1.2018-01-08 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 605m22.594s cat fb.hg38.chainFicAlb1Link.txt # 147048785 bases of 3049335806 (4.822%) in intersection cat fb.hg38.chainSynFicAlb1Link.txt # 88694039 bases of 3049335806 (2.909%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 ficAlb1) > rbest.log 2>&1 & # real 324m34.953s cat fb.hg38.chainRBestFicAlb1Link.txt # 103439671 bases of 3049335806 (3.392%) in intersection # and for the swap: mkdir /hive/data/genomes/ficAlb1/bed/blastz.hg38.swap cd /hive/data/genomes/ficAlb1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFicAlb1.2018-01-08/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 14m32.727s cat fb.ficAlb1.chainHg38Link.txt # 118476285 bases of 1102325870 (10.748%) in intersection cat fb.ficAlb1.chainSynHg38Link.txt # 86852014 bases of 1102325870 (7.879%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ ficAlb1 hg38) > rbest.log 2>&1 # real 265m12.990s cat fb.ficAlb1.chainRBestHg38Link.txt # 103174487 bases of 1102325870 (9.360%) in intersection ######################################################################### # LASTZ human/hg38 vs. lamprey/petMar3 - (DONE - 2018-01-25 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPetMar3.2018-01-25 cd /hive/data/genomes/hg38/bed/lastzPetMar3.2018-01-25 printf '# human vs lamprey BLASTZ=/cluster/bin/penn/lastz-distrib-1.03.66/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: lamprey petMar3 SEQ2_DIR=/hive/data/genomes/petMar3/petMar3.2bit SEQ2_LEN=/hive/data/genomes/petMar3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPetMar3.2018-01-25 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 117m35.788s cat fb.hg38.chainPetMar3Link.txt # 52661859 bases of 3049335806 (1.727%) in intersection cat fb.hg38.chainSynPetMar3Link.txt # 1508338 bases of 3049335806 (0.049%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 petMar3) \ > rbest.log 2>&1 & # real 259m50.083s cat fb.hg38.chainRBestPetMar3Link.txt # 25411380 bases of 3049335806 (0.833%) in intersection # and for the swap: mkdir /hive/data/genomes/petMar3/bed/blastz.hg38.swap cd /hive/data/genomes/petMar3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPetMar3.2018-01-25/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 12m51.092s cat fb.petMar3.chainHg38Link.txt # 51300303 bases of 1043181598 (4.918%) in intersection cat fb.petMar3.chainSynHg38Link.txt # 1425757 bases of 1043181598 (0.137%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` petMar3 hg38) \ > rbest.log 2>&1 & # real 264m26.880s cat fb.petMar3.chainRBestHg38Link.txt # 25154743 bases of 1043181598 (2.411%) in intersection ######################################################################### # LASTZ human/hg38 vs. garter snake/thaSir1 - (DONE - 2018-02-13 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzThaSir1.2018-02-13 cd /hive/data/genomes/hg38/bed/lastzThaSir1.2018-02-13 # note: first time with this new 1.04.00 version of lastz printf '# human vs garter snake BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=3 SEQ1_LAP=10000 # QUERY: garter snake thaSir1 SEQ2_DIR=/hive/data/genomes/thaSir1/thaSir1.2bit SEQ2_LEN=/hive/data/genomes/thaSir1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=28 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzThaSir1.2018-02-13 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 124m58.650s cat fb.hg38.chainThaSir1Link.txt # 99838535 bases of 3049335806 (3.274%) in intersection cat fb.hg38.chainSynThaSir1Link.txt # 29432396 bases of 3049335806 (0.965%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 thaSir1)\ > rbest.log 2>&1 & # real 315m43.227s cat fb.hg38.chainRBestThaSir1Link.txt # 66452884 bases of 3049335806 (2.179%) in intersection # and for the swap: mkdir /hive/data/genomes/thaSir1/bed/blastz.hg38.swap cd /hive/data/genomes/thaSir1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzThaSir1.2018-02-13/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 16m52.956s cat fb.thaSir1.chainHg38Link.txt # 75915958 bases of 1122701795 (6.762%) in intersection cat fb.thaSir1.chainSynHg38Link.txt # 28865261 bases of 1122701795 (2.571%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` thaSir1 hg38)\ > rbest.log 2>&1 # real 269m56.160s cat fb.thaSir1.chainRBestHg38Link.txt # 66545073 bases of 1122701795 (5.927%) in intersection ######################################################################### # LASTZ human/hg38 vs. cat/felCat9 - (DONE - 2018-03-14 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzFelCat9.2018-03-14 cd /hive/data/genomes/hg38/bed/lastzFelCat9.2018-03-14 # note: first time with this new 1.04.00 version of lastz printf '# human vs cat BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz 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 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: cat felCat9 SEQ2_DIR=/hive/data/genomes/felCat9/felCat9.2bit SEQ2_LEN=/hive/data/genomes/felCat9/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=100 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzFelCat9.2018-03-14 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 1256m48.240s cat fb.hg38.chainFelCat9Link.txt # 1579231929 bases of 3049335806 (51.789%) in intersection cat fb.hg38.chainSynFelCat9Link.txt # 1516804589 bases of 3049335806 (49.742%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 \ felCat9) > rbest.log 2>&1 & # real 704m43.342s cat fb.hg38.chainRBestFelCat9Link.txt # 1449222744 bases of 3049335806 (47.526%) in intersection # and for the swap: mkdir /hive/data/genomes/felCat9/bed/blastz.hg38.swap cd /hive/data/genomes/felCat9/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzFelCat9.2018-03-14/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 142m37.100s cat fb.felCat9.chainHg38Link.txt # 1486134443 bases of 2476453204 (60.011%) in intersection cat fb.felCat9.chainSynHg38Link.txt # 1452577988 bases of 2476453204 (58.656%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ felCat9 hg38) > rbest.log 2>&1 & # real 623m28.676s cat fb.felCat9.chainRBestHg38Link.txt # 1449521349 bases of 2476453204 (58.532%) in intersection ############################################################################## # LASTZ Beaver casCan1 (DONE - 2018-03-19 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCasCan1.2018-03-19 cd /hive/data/genomes/hg38/bed/lastzCasCan1.2018-03-19 # note: first time with this new 1.04.00 version of lastz printf '# Human vs. Beaver BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz 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 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=20000000 SEQ1_LIMIT=80 SEQ1_LAP=10000 # QUERY: Beaver SEQ2_DIR=/hive/data/genomes/casCan1/casCan1.2bit SEQ2_LEN=/hive/data/genomes/casCan1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=80 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCasCan1.2018-03-19 TMPDIR=/dev/shm ' > DEF # establish a screen to control this job screen time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 568m56.951s cat fb.hg38.chainCasCan1Link.txt # 1440538496 bases of 3049335806 (47.241%) in intersection cat fb.hg38.chainSynCasCan1Link.txt # 1348638697 bases of 3049335806 (44.227%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` hg38 casCan1) > rbest.log 2>&1 & # real 903m29.785s cat fb.hg38.chainRBestCasCan1Link.txt # 1318039475 bases of 3049335806 (43.224%) in intersection # and for the swap: mkdir /hive/data/genomes/casCan1/bed/blastz.hg38.swap cd /hive/data/genomes/casCan1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCasCan1.2018-03-19/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -swap -syntenicNet) > swap.log 2>&1 & # real 141m44.555s cat fb.casCan1.chainHg38Link.txt # 1440839903 bases of 2517974654 (57.222%) in intersection cat fb.casCan1.chainSynHg38Link.txt # 1348477433 bases of 2517974654 (53.554%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev \ -buildDir=`pwd` casCan1 hg38) > rbest.log 2>&1 & # real 1199m30.336s cat fb.casCan1.chainRBestHg38Link.txt # 1321240715 bases of 2517974654 (52.472%) in intersection ############################################################################## # Chimp Lastz run (DONE - 2018-03-24 - Hiram) screen -S hg38PanTro6 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzPanTro6.2018-03-24 cd /hive/data/genomes/hg38/bed/lastzPanTro6.2018-03-24 # always set the BLASTZ program so we know what version was used printf "# human vs chimp BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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: 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=20000000 SEQ1_LIMIT=50 SEQ1_LAP=10000 # QUERY: Chimp PanTro6 SEQ2_DIR=/hive/data/genomes/panTro6/panTro6.2bit SEQ2_LEN=/hive/data/genomes/panTro6/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=50 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzPanTro6.2018-03-24 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 239m0.367s cat fb.hg38.chainPanTro6Link.txt # 2910625246 bases of 3049335806 (95.451%) in intersection cat fb.hg38.chainSynPanTro6Link.txt # 2890994068 bases of 3049335806 (94.807%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 panTro6) > rbest.log 2>&1 # real 103m42.148s cat fb.hg38.chainRBestPanTro6Link.txt # 2743876160 bases of 3049335806 (89.983%) in intersection # running the swap mkdir /hive/data/genomes/panTro6/bed/blastz.hg38.swap cd /hive/data/genomes/panTro6/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzPanTro6.2018-03-24/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 101m29.782s cat fb.panTro6.chainHg38Link.txt # 2814507414 bases of 3018592990 (93.239%) in intersection cat fb.panTro6.chainSynHg38Link.txt # 2800642800 bases of 3018592990 (92.780%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ panTro6 hg38) > rbest.log 2>&1 & # real 102m47.533s cat fb.panTro6.chainRBestHg38Link.txt # 2748571185 bases of 3018592990 (91.055%) in intersection ############################################################################## # Orangutan Lastz run (DONE - 2018-03-26 - Hiram) screen -S hg38PonAbe3 # use a screen to manage this longish running job mkdir /hive/data/genomes/hg38/bed/lastzPonAbe3.2018-03-26 cd /hive/data/genomes/hg38/bed/lastzPonAbe3.2018-03-26 # always set the BLASTZ program so we know what version was used printf "# human vs orangutan BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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: 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=20000000 SEQ1_LIMIT=20 SEQ1_LAP=10000 # QUERY: Orangutan PonAbe3 SEQ2_DIR=/hive/data/genomes/ponAbe3/ponAbe3.2bit SEQ2_LEN=/hive/data/genomes/ponAbe3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=20 SEQ2_IN_CONTIGS=0 BASE=/hive/data/genomes/hg38/bed/lastzPonAbe3.2018-03-26 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 282m16.272s cat fb.hg38.chainPonAbe3Link.txt # 2823472924 bases of 3049335806 (92.593%) in intersection cat fb.hg38.chainSynPonAbe3Link.txt # 2800840721 bases of 3049335806 (91.851%) in intersection # filter with doRecipBest.pl time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 ponAbe3) > rbest.log 2>&1 & # real 129m13.848s cat fb.hg38.chainRBestPonAbe3Link.txt # 2640015618 bases of 3049335806 (86.577%) in intersection # running the swap mkdir /hive/data/genomes/ponAbe3/bed/blastz.hg38.swap cd /hive/data/genomes/ponAbe3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ -swap /hive/data/genomes/hg38/bed/lastzPonAbe3.2018-03-26/DEF \ -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 92m31.689s cat fb.ponAbe3.chainHg38Link.txt # 2693373164 bases of 3043444524 (88.498%) in intersection cat fb.ponAbe3.chainSynHg38Link.txt # 2679121264 bases of 3043444524 (88.029%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ ponAbe3 hg38) > rbest.log 2>&1 & # real 141m23.715s cat fb.ponAbe3.chainRBestHg38Link.txt # 2641871600 bases of 3043444524 (86.805%) in intersection ############################################################################# # LASTZ human/hg38 vs. sheep/oviAri4 - (DONE - 2018-04-25 - ChrisL) mkdir /hive/data/genomes/hg38/bed/lastzOviAri4.2018-04-25 cd /hive/data/genomes/hg38/bed/lastzOviAri4.2018-04-25 printf '# human vs sheep BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Sheep oviAri4 SEQ2_DIR=/hive/data/genomes/oviAri4/oviAri4.2bit SEQ2_LEN=/hive/data/genomes/oviAri4/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzOviAri4.2018-04-25 TMPDIR=/dev/shm ' > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # lineCount: Undefined variable. # Command failed: # ssh -x -o 'StrictHostKeyChecking = no' -o 'BatchMode = yes' hgwdev \ # nice /hive/data/genomes/hg38/bed/lastzOviAri4.2018-04-25/axtChain/netSynteny.csh # # real 1423m22.844s # this took forever because the final job was stuck all night # and the syntenic net step failed, so remove the files and run # again, just like what happened for mm10: rm hg38.oviAri4.syn.chain.gz rm hg38.oviAri4.syn.net.gz time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -continue=syntenicNet \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > syntenicNet.log 2>&1 & # real 34m23.191s cat fb.hg38.chainOviAri4Link.txt # 1388649593 bases of 3049335806 (45.539%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 oviAri4) > rbest.log 2>&1 & # real 612m50.394s # and for the swap: mkdir /hive/data/genomes/oviAri4/bed/blastz.hg38.swap cd /hive/data/genomes/oviAri4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzOviAri4.2018-04-25/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 104m31.748s cat fb.oviAri4.chainHg38Link.txt # 1319553403 bases of 2587515673 (50.997%) in intersection # replacing the previous tuned version: # 1193048482 bases of 2534335866 (47.075%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` oviAri4 hg38) > rbest.log 2>&1 & # real 638m15.603s ############################################################################# # LASTZ human/hg38 vs. horse/equCab3 - (DONE - 2018-05-25 - ChrisL) mkdir /hive/data/genomes/hg38/bed/lastzEquCab3.2018-05-25 cd /hive/data/genomes/hg38/bed/lastzEquCab3.2018-05-25 printf '# human vs horse BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: horse equCab3 SEQ2_DIR=/hive/data/genomes/equCab3/equCab3.2bit SEQ2_LEN=/hive/data/genomes/equCab3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEquCab3.2018-05-25 TMPDIR=/dev/shm ' > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 519m22.432s cat fb.hg38.chainEquCab3Link.txt # 1705190736 bases of 3049335806 (55.920%) in intersection cat fb.hg38.chainSynEquCab3Link.txt # 1642798373 bases of 3049335806 (53.874%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 equCab3) > rbest.log 2>&1 & # real 553m32.545s cat fb.hg38.chainRBest.EquCab3.txt # 1563820848 bases of 3049335806 (51.284%) in intersection # and for the swap: mkdir /hive/data/genomes/equCab3/bed/blastz.hg38.swap cd /hive/data/genomes/equCab3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEquCab3.2018-05-25/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 122m26.771s cat fb.equCab3.chainHg38Link.txt # 1666879638 bases of 2497530654 (66.741%) in intersection cat fb.equCab3.chainSynHg38Link.txt # 1624977128 bases of 2497530654 (65.063%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` equCab3 hg38) > rbest.log 2>&1 & # real 473m11.347s cat fb.equCab3.chainRBest.Hg38.txt ############################################################################# # LASTZ human/hg38 vs. Minke whale/balAcu1 - (DONE - 2018-06-11 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzBalAcu1.2018-06-11 cd /hive/data/genomes/hg38/bed/lastzBalAcu1.2018-06-11 printf '# human vs Minke whale BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Minke whale balAcu1 SEQ2_DIR=/hive/data/genomes/balAcu1/balAcu1.2bit SEQ2_LEN=/hive/data/genomes/balAcu1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=40 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzBalAcu1.2018-06-11 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 226m14.103s cat fb.hg38.chainBalAcu1Link.txt # 1571134497 bases of 3049335806 (51.524%) in intersection cat fb.hg38.chainSynBalAcu1Link.txt # 1509091721 bases of 3049335806 (49.489%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 balAcu1) > rbest.log 2>&1 & # real 426m33.828s cat fb.hg38.chainRBest.BalAcu1.txt # 1443423443 bases of 3049335806 (47.336%) in intersection # and for the swap: mkdir /hive/data/genomes/balAcu1/bed/blastz.hg38.swap cd /hive/data/genomes/balAcu1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzBalAcu1.2018-06-11/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 105m38.443s cat fb.balAcu1.chainHg38Link.txt # 1485701363 bases of 2286657046 (64.973%) in intersection cat fb.balAcu1.chainSynHg38Link.txt # 1444079345 bases of 2286657046 (63.152%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` balAcu1 hg38) > rbest.log 2>&1 & # real 422m43.817s cat fb.balAcu1.chainRBest.Hg38.txt # 1443200492 bases of 2286657046 (63.114%) in intersection ############################################################################# # LASTZ human/hg38 vs. Axolotl/ambMex1 - (DONE - 2018-07-09 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzAmbMex1.2018-07-09 cd /hive/data/genomes/hg38/bed/lastzAmbMex1.2018-07-09 printf '# human vs Axolotl BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 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_LIMIT=5 SEQ1_LAP=10000 # QUERY: Axolotl ambMex1 SEQ2_DIR=/hive/data/genomes/ambMex1/ambMex1.2bit SEQ2_LEN=/hive/data/genomes/ambMex1/chrom.sizes SEQ2_CHUNK=80000000 SEQ2_LIMIT=800 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzAmbMex1.2018-07-09 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 226m14.103s cat fb.hg38.chainAmbMex1Link.txt # 54520910 bases of 3049335806 (1.788%) in intersection cat fb.hg38.chainSynAmbMex1Link.txt # 3343407 bases of 3049335806 (0.110%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 ambMex1) > rbest.log 2>&1 & # real 497m40.060s cat fb.hg38.chainRBest.AmbMex1.txt # 37383183 bases of 3049335806 (1.226%) in intersection # and for the swap: mkdir /hive/data/genomes/ambMex1/bed/blastz.hg38.swap cd /hive/data/genomes/ambMex1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzAmbMex1.2018-07-09/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 & # real 39m37.460s cat fb.ambMex1.chainHg38Link.txt # 59846443 bases of 28366694468 (0.211%) in intersection cat fb.ambMex1.chainSynHg38Link.txt # 3456707 bases of 28366694468 (0.012%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` ambMex1 hg38) > rbest.log 2>&1 & # real 555m51.873s cat fb.ambMex1.chainRBest.Hg38.txt # 38573370 bases of 28366694468 (0.136%) in intersection ############################################################################# # LASTZ human/hg38 vs. chicken/galGal6 - (DONE - 2018-10-12 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGalGal6.2018-10-12 cd /hive/data/genomes/hg38/bed/lastzGalGal6.2018-10-12 printf "# human vs chicken BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: chicken galGal6 SEQ2_DIR=/hive/data/genomes/galGal6/galGal6.2bit SEQ2_LEN=/hive/data/genomes/galGal6/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGalGal6.2018-10-12 TMPDIR=/dev/shm " > DEF # << happy emacs time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 83m10.878s cat fb.hg38.chainGalGal6Link.txt # 154079940 bases of 3095998939 (4.977%) in intersection cat fb.hg38.chainSynGalGal6Link.txt # 95877644 bases of 3095998939 (3.097%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 galGal6) > rbest.log 2>&1 & # real 154m32.367s cat fb.hg38.chainRBest.GalGal6.txt # 106665747 bases of 3095998939 (3.445%) in intersection # and for the swap: mkdir /hive/data/genomes/galGal6/bed/blastz.hg38.swap cd /hive/data/genomes/galGal6/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGalGal6.2018-10-12/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 9m45.514s cat fb.galGal6.chainHg38Link.txt # 120955955 bases of 1055588482 (11.459%) in intersection cat fb.galGal6.chainSynHg38Link.txt # 92597630 bases of 1055588482 (8.772%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` galGal6 hg38) > rbest.log 2>&1 & # real 139m24.408s cat fb.galGal6.chainRBest.Hg38.txt # 106294585 bases of 1055588482 (10.070%) in intersection ############################################################################# # LASTZ Cow bosTau9 (DONE - 2018-11-08 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzBosTau9.2018-11-08 cd /hive/data/genomes/hg38/bed/lastzBosTau9.2018-11-08 printf '# human vs Cow BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 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_LIMIT=5 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/hg38/bed/lastzBosTau9.2018-11-08 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev-101 -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 393m17.228s cat fb.hg38.chainBosTau9Link.txt # 1402568450 bases of 3095998939 (45.303%) in intersection cat fb.hg38.chainSynBosTau9Link.txt # 1345897937 bases of 3095998939 (43.472%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 bosTau9) > rbest.log 2>&1 & # real 273m2.085s cat fb.hg38.chainRBest.BosTau9.txt # 1290064468 bases of 3095998939 (41.669%) in intersection # running the swap mkdir /hive/data/genomes/bosTau9/bed/blastz.hg38.swap cd /hive/data/genomes/bosTau9/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzBosTau9.2018-11-08/DEF \ -swap -syntenicNet -workhorse=hgwdev \ -smallClusterHub=hgwdev-101 -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 69m11.226s cat fb.bosTau9.chainHg38Link.txt # 1342860432 bases of 2715853792 (49.445%) in intersection cat fb.bosTau9.chainSynHg38Link.txt # 1306095676 bases of 2715853792 (48.092%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` bosTau9 hg38) > rbest.log 2>&1 & # real 272m15.176s cat fb.bosTau9.chainRBest.Hg38.txt # 1290810412 bases of 2715853792 (47.529%) in intersection ############################################################################# # LASTZ human/hg38 vs. Japanese quail/cotJap2 - (DONE - 2018-11-15 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCotJap2.2018-11-15 cd /hive/data/genomes/hg38/bed/lastzCotJap2.2018-11-15 printf "# human vs Japanese quail BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_O=400 BLASTZ_E=30 BLASTZ_Y=3400 BLASTZ_L=6000 BLASTZ_K=2200 BLASTZ_M=50 BLASTZ_Q=/scratch/data/blastz/HoxD55.q # A C G T # 91 -90 -25 -100 # -90 100 -100 -25 # -25 -100 100 -90 # -100 -25 -90 91 # 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_LIMIT=30 SEQ1_LAP=10000 # QUERY: Japanese quail cotJap2 SEQ2_DIR=/hive/data/genomes/cotJap2/cotJap2.2bit SEQ2_LEN=/hive/data/genomes/cotJap2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCotJap2.2018-11-15 TMPDIR=/dev/shm " > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 # real 81m22.929s cat fb.hg38.chainCotJap2Link.txt # 139668231 bases of 3095998939 (4.511%) in intersection cat fb.hg38.chainSynCotJap2Link.txt # 90319008 bases of 3095998939 (2.917%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 cotJap2) > rbest.log 2>&1 & # real 136m44.926s cat fb.hg38.chainRBest.CotJap2.txt # 99806762 bases of 3095998939 (3.224%) in intersection # and for the swap: mkdir /hive/data/genomes/cotJap2/bed/blastz.hg38.swap cd /hive/data/genomes/cotJap2/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCotJap2.2018-11-15/DEF \ -swap -chainMinScore=5000 -chainLinearGap=loose \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 8m9.892s cat fb.cotJap2.chainHg38Link.txt # 108800437 bases of 917263224 (11.861%) in intersection cat fb.cotJap2.chainSynHg38Link.txt # 87569432 bases of 917263224 (9.547%) in intersection # mistakenly started this on ku, it failed at the download step since # it could not see the /gbdb/mm10/ hierarchy: time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` cotJap2 hg38) > rbest.log 2>&1 & # real 99m33.362s # continue on hgwdev time (doRecipBest.pl -load -workhorse=hgwdev -continue=download -buildDir=`pwd` cotJap2 hg38) > rbest.download.log 2>&1 & # real 1m53.130s cat fb.cotJap2.chainRBest.Hg38.txt # 99417593 bases of 917263224 (10.839%) in intersection ############################################################################# # LASTZ human/hg38 mouse/GRCm38B - (DONE - 2019-03-01 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGRCm38B.2019-03-01 cd /hive/data/genomes/hg38/bed/lastzGRCm38B.2019-03-01 printf '# human vs mouse BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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 GRCm38B SEQ2_DIR=/hive/data/genomes/GRCm38B/GRCm38B.2bit SEQ2_LEN=/hive/data/genomes/GRCm38B/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzGRCm38B.2019-03-01 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF -noDbNameCheck \ -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev-101 \ -fileServer=hgwdev \ -bigClusterHub=ku -chainMinScore=3000 -chainLinearGap=medium) \ > do.log 2>&1 # real 171m59.392s cat fb.hg38.chainGRCm38BLink.txt # 967404497 bases of 3095998939 (31.247%) in intersection cat fb.hg38.chainSynGRCm38BLink.txt # 913717211 bases of 3095998939 (29.513%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 GRCm38B) \ > rbest.log 2>&1 & # real 284m45.623s cat fb.hg38.chainRBest.GRCm38B.txt # 891970056 bases of 3095998939 (28.810%) in intersection # and for the swap: mkdir /hive/data/genomes/GRCm38B/bed/blastz.hg38.swap cd /hive/data/genomes/GRCm38B/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGRCm38B.2019-03-01/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev-101 -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 60m31.849s cat fb.GRCm38B.chainHg38Link.txt # 941205213 bases of 2655285420 (35.446%) in intersection cat fb.GRCm38B.chainSynHg38Link.txt # 891450770 bases of 2655285420 (33.573%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` GRCm38B hg38) \ > rbest.log 2>&1 & # real 331m35.578s cat fb.GRCm38B.chainRBest.Hg38.txt # 893587236 bases of 2655285420 (33.653%) in intersection ######################################################################### # LASTZ human/hg38 vs. rat/regenRn0 - (DONE - 2019-07-01 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRegenRn0.2019-07-01 cd /hive/data/genomes/hg38/bed/lastzRegenRn0.2019-07-01 printf '# human vs rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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_LIMIT=30 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_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzRegenRn0.2019-07-01 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 256m8.479s cat fb.hg38.chainRegenRn0Link.txt # 930788096 bases of 3095998939 (30.064%) in intersection cat fb.hg38.chainSynRegenRn0Link.txt # 870556908 bases of 3095998939 (28.119%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 regenRn0) > rbest.log 2>&1 & # real 328m4.069s cat fb.hg38.chainRBest.RegenRn0.txt # 857127621 bases of 3095998939 (27.685%) in intersection # and for the swap: mkdir /hive/data/genomes/regenRn0/bed/blastz.hg38.swap cd /hive/data/genomes/regenRn0/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRegenRn0.2019-07-01/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 64m34.515s cat fb.regenRn0.chainHg38Link.txt # 906790361 bases of 2534810853 (35.773%) in intersection cat fb.regenRn0.chainSynHg38Link.txt # 849997639 bases of 2534810853 (33.533%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn0 hg38) > rbest.log 2>&1 # real 300m30.411s cat fb.regenRn0.chainRBest.Hg38.txt # 858923025 bases of 2534810853 (33.885%) in intersection ######################################################################### # LASTZ human/hg38 Tree chimp/rheMac10 - (DONE - 2019-07-03 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRheMac10.2019-07-03 cd /hive/data/genomes/hg38/bed/lastzRheMac10.2019-07-03 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 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=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/hg38/bed/lastzRheMac10.2019-07-03 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 97m36.383s cat fb.hg38.chainRheMac10Link.txt # 2596157811 bases of 3095998939 (83.855%) in intersection cat fb.hg38.chainSynRheMac10Link.txt # 2564291936 bases of 3095998939 (82.826%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 rheMac10) > rbest.log 2>&1 & # real 120m8.526s cat fb.hg38.chainRBest.RheMac10.txt # 2422981614 bases of 3095998939 (78.262%) in intersection # and for the swap: mkdir /hive/data/genomes/rheMac10/bed/blastz.hg38.swap cd /hive/data/genomes/rheMac10/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRheMac10.2019-07-03/DEF \ -swap -chainMinScore=5000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 61m39.505s cat fb.rheMac10.chainHg38Link.txt # 2485840115 bases of 2936892733 (84.642%) in intersection cat fb.rheMac10.chainSynHg38Link.txt # 2465210442 bases of 2936892733 (83.939%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` rheMac10 hg38) > rbest.log 2>&1 # real 126m29.919s cat fb.rheMac10.chainRBest.Hg38.txt # 2424028492 bases of 2936892733 (82.537%) in intersection ######################################################################### # LASTZ human/hg38 vs. rat/regenRn1 - (DONE - 2019-09-12 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 cd /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 printf '# human vs rat BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/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_LIMIT=30 SEQ1_LAP=10000 # QUERY: rat regenRn1 SEQ2_DIR=/hive/data/genomes/regenRn1/regenRn1.2bit SEQ2_LEN=/hive/data/genomes/regenRn1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=30 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > do.log 2>&1 & # real 162m40.237s cat fb.hg38.chainRegenRn1Link.txt # 863041482 bases of 3095998939 (27.876%) in intersection cat fb.hg38.chainSynRegenRn1Link.txt # 809332351 bases of 3095998939 (26.141%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` hg38 regenRn1) > rbest.log 2>&1 & # real 261m19.645s cat fb.hg38.chainRBest.RegenRn1.txt # 792532873 bases of 3095998939 (25.599%) in intersection # and for the swap: mkdir /hive/data/genomes/regenRn1/bed/blastz.hg38.swap cd /hive/data/genomes/regenRn1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRegenRn1.2019-09-12/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium -noDbNameCheck \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 63m47.773s cat fb.regenRn1.chainHg38Link.txt # 827167139 bases of 2282482188 (36.240%) in intersection cat fb.regenRn1.chainSynHg38Link.txt # 788025130 bases of 2282482188 (34.525%) in intersection time (doRecipBest.pl -workhorse=hgwdev -load -buildDir=`pwd` regenRn1 hg38) > rbest.log 2>&1 # real 300m50.570s cat fb.regenRn1.chainRBest.Hg38.txt # 793987134 bases of 2282482188 (34.786%) in intersection ######################################################################### # LASTZ human/hg38 Gorilla/gorGor6 - (DONE - 2019-11-20 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 cd /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 printf '# human vs gorilla BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_T=2 BLASTZ_O=600 BLASTZ_E=150 BLASTZ_M=254 BLASTZ_K=4500 BLASTZ_Y=15000 BLASTZ_Q=/hive/data/staging/data/blastz/human_chimp.v2.q # A C G T # A 90 -330 -236 -356 # C -330 100 -318 -236 # G -236 -318 100 -330 # T -356 -236 -330 90 # TARGET: human hg38 SEQ1_DIR=/hive/data/genomes/hg38/hg38.2bit SEQ1_LEN=/hive/data/genomes/hg38/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_IN_CONTIGS=0 # QUERY: gorilla gorGor6 SEQ2_DIR=/hive/data/genomes/gorGor6/gorGor6.2bit SEQ2_LEN=/hive/data/genomes/gorGor6/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=50 BASE=/hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20 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 # broken cluster run due to path name for BLASTZ_Q, continuing: time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -continue=cat -syntenicNet) > cat.log 2>&1 # real 77m19.538s cat fb.hg38.chainGorGor6Link.txt # 2908900659 bases of 3095998939 (93.957%) in intersection cat fb.hg38.chainSynGorGor6Link.txt # 2885980361 bases of 3095998939 (93.216%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` hg38 gorGor6) \ > rbest.log 2>&1 & # real 65m39.724s cat fb.hg38.chainRBest.GorGor6.txt # 2693876207 bases of 3095998939 (87.012%) in intersection # and for the swap: mkdir /hive/data/genomes/gorGor6/bed/blastz.hg38.swap cd /hive/data/genomes/gorGor6/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzGorGor6.2019-11-20/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 63m46.473s cat fb.gorGor6.chainHg38Link.txt # 2738870921 bases of 2999027915 (91.325%) in intersection cat fb.gorGor6.chainSynHg38Link.txt # 2728591501 bases of 2999027915 (90.983%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` gorGor6 hg38) \ > rbest.log 2>&1 # real 62m14.470s cat fb.gorGor6.chainRBest.Hg38.txt # 2697792568 bases of 2999027915 (89.956%) in intersection ############################################################################# # LASTZ human/hg38 vs. Chinese hamster CHO-K1 cell line/regenCho1 # (DONE - 2019-11-26 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzRegenCho1.2019-11-26 cd /hive/data/genomes/hg38/bed/lastzRegenCho1.2019-11-26 printf '# human vs Chinese hamster ovary CHO-K1 cell line BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Chinese hamster ovary CHO-K1 cell line regenCho1 SEQ2_DIR=/hive/data/genomes/regenCho1/regenCho1.2bit SEQ2_LEN=/hive/data/genomes/regenCho1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzRegenCho1.2019-11-26 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > do.log 2>&1 # real 376m47.828s cat fb.hg38.chainRegenCho1Link.txt # 979733899 bases of 3095998939 (31.645%) in intersection cat fb.hg38.chainSynRegenCho1Link.txt # 917104031 bases of 3095998939 (29.622%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 regenCho1) > rbest.log 2>&1 & # real 259m42.688s cat fb.hg38.chainRBest.RegenCho1.txt # 901006295 bases of 3095998939 (29.102%) in intersection # and for the swap: mkdir /hive/data/genomes/regenCho1/bed/blastz.hg38.swap cd /hive/data/genomes/regenCho1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzRegenCho1.2019-11-26/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 79m18.904s cat fb.regenCho1.chainHg38Link.txt # 956720146 bases of 2266312740 (42.215%) in intersection cat fb.regenCho1.chainSynHg38Link.txt # 895755077 bases of 2266312740 (39.525%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ regenCho1 hg38) > rbest.log 2>&1 & # real 289m24.440s cat fb.regenCho1.chainRBest.Hg38.txt # 902782523 bases of 2266312740 (39.835%) in intersection ############################################################################# # LASTZ human/hg38 vs. Southern Sea Otter/enhLutNer1 # (DONE - 2019-12-22 - Jonathan) mkdir /hive/data/genomes/hg38/bed/lastzEnhLutNer1.2019-12-20 cd /hive/data/genomes/hg38/bed/lastzEnhLutNer1.2019-12-20 printf '# human vs Southern sea otter BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.00/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Southern sea otter enhLutNer1 SEQ2_DIR=/hive/data/genomes/enhLutNer1/enhLutNer1.2bit SEQ2_LEN=/hive/data/genomes/enhLutNer1/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzEnhLutNer1.2019-12-20 TMPDIR=/dev/shm ' > DEF time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > do.log 2>&1 # real 336m47.917s cat fb.hg38.chainEnhLutNer1Link.txt # 1537745313 bases of 3095998939 (49.669%) in intersection cat fb.hg38.chainSynEnhLutNer1Link.txt # 1454400074 bases of 3095998939 (46.977%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 enhLutNer1) > rbest.log 2>&1 & # real 336m47.917s cat fb.hg38.chainRBest.EnhLutNer1.txt # 1413203552 bases of 3095998939 (45.646%) in intersection # and for the swap: mkdir /hive/data/genomes/enhLutNer1/bed/blastz.hg38.swap cd /hive/data/genomes/enhLutNer1/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzEnhLutNer1.2019-12-20/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -noDbNameCheck -syntenicNet) > swap.log 2>&1 # real 88m38.087s cat fb.enhLutNer1.chainHg38Link.txt # 1526639908 bases of 2413653822 (63.250%) in intersection cat fb.enhLutNer1.chainSynHg38Link.txt # 1403546142 bases of 2413653822 (58.150%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ enhLutNer1 hg38) > rbest.log 2>&1 & # real 319m54.030s cat fb.enhLutNer1.chainRBest.Hg38.txt # 1414347523 bases of 2413653822 (58.598%) in intersection ######################################################################### # LASTZ human/hg38 vs. German shepard/canFam4 # (DONE - 2020-04-02 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCanFam4.2020-04-02 cd /hive/data/genomes/hg38/bed/lastzCanFam4.2020-04-02 printf '# human vs. German shepard BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: German shepard Mischka/canFam4 SEQ2_DIR=/hive/data/genomes/canFam4/canFam4.2bit SEQ2_LEN=/hive/data/genomes/canFam4/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCanFam4.2020-04-02 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 904m29.420s cat fb.hg38.chainCanFam4Link.txt # 1549397508 bases of 3110768607 (49.808%) in intersection cat fb.hg38.chainSynCanFam4Link.txt # 1488468205 bases of 3110768607 (47.849%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 canFam4) > rbest.log 2>&1 & # real 310m32.196s cat fb.hg38.chainRBest.CanFam4.txt # 1425406620 bases of 3110768607 (45.822%) in intersection # and for the swap: mkdir /hive/data/genomes/canFam4/bed/blastz.hg38.swap cd /hive/data/genomes/canFam4/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCanFam4.2020-04-02/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 99m10.990s cat fb.canFam4.chainHg38Link.txt # 1493209286 bases of 2481941580 (60.163%) in intersection cat fb.canFam4.chainSynHg38Link.txt # 1448164376 bases of 2481941580 (58.348%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ canFam4 hg38) > rbest.log 2>&1 & # real 257m59.713s cat fb.canFam4.chainRBest.Hg38.txt # 1425296830 bases of 2481941580 (57.427%) in intersection ######################################################################### # LASTZ human/hg38 bonobo/panPan3 - (DONE - 2020-06-15 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzPanPan3.2020-06-15 cd /hive/data/genomes/hg38/bed/lastzPanPan3.2020-06-15 printf '# human vs bonobo BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/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=/hive/data/staging/data/blastz/human_chimp.v2.q # A C G T # A 90 -330 -236 -356 # C -330 100 -318 -236 # G -236 -318 100 -330 # T -356 -236 -330 90 # 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_LIMIT=10 SEQ1_LAP=10000 # QUERY: bonobo panPan3 SEQ2_DIR=/hive/data/genomes/panPan3/panPan3.2bit SEQ2_LEN=/hive/data/genomes/panPan3/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=50 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzPanPan3.2020-06-15 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 117m56.403s cat fb.hg38.chainPanPan3Link.txt # 2897225010 bases of 3110768607 (93.135%) in intersection cat fb.hg38.chainSynPanPan3Link.txt # 2880116277 bases of 3110768607 (92.585%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 panPan3) > rbest.log 2>&1 & # real 68m45.187s cat fb.hg38.chainRBest.PanPan3.txt # 2727319248 bases of 3110768607 (87.673%) in intersection # and for the swap: mkdir /hive/data/genomes/panPan3/bed/blastz.hg38.swap cd /hive/data/genomes/panPan3/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzPanPan3.2020-06-15/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 73m50.456s cat fb.panPan3.chainHg38Link.txt # 2777869191 bases of 3015350297 (92.124%) in intersection cat fb.panPan3.chainSynHg38Link.txt # 2768018012 bases of 3015350297 (91.798%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ panPan3 hg38) > rbest.log 2>&1 & # real 66m52.340s cat fb.panPan3.chainRBest.Hg38.txt # 2732415393 bases of 3015350297 (90.617%) in intersection ######################################################################### # LASTZ human/hg38 vs. Great Dane/canFam5 # (DONE - 2020-07-29 - Hiram) mkdir /hive/data/genomes/hg38/bed/lastzCanFam5.2020-07-29 cd /hive/data/genomes/hg38/bed/lastzCanFam5.2020-07-29 printf '# human vs. Great Dane BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz BLASTZ_M=254 # 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_LIMIT=20 SEQ1_LAP=10000 # QUERY: Great Dane Zoey/canFam5 SEQ2_DIR=/hive/data/genomes/canFam5/canFam5.2bit SEQ2_LEN=/hive/data/genomes/canFam5/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LIMIT=20 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzCanFam5.2020-07-29 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 1038m20.721s cat fb.hg38.chainCanFam5Link.txt # 1545648756 bases of 3110768607 (49.687%) in intersection cat fb.hg38.chainSynCanFam5Link.txt # 1484758745 bases of 3110768607 (47.730%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 canFam5) > rbest.log 2>&1 & # real 283m55.399s cat fb.hg38.chainRBest.CanFam5.txt # 1422619513 bases of 3110768607 (45.732%) in intersection # and for the swap: mkdir /hive/data/genomes/canFam5/bed/blastz.hg38.swap cd /hive/data/genomes/canFam5/bed/blastz.hg38.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/hg38/bed/lastzCanFam5.2020-07-29/DEF \ -swap -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=ku -bigClusterHub=ku \ -syntenicNet) > swap.log 2>&1 # real 78m37.078s cat fb.canFam5.chainHg38Link.txt # 1460025525 bases of 2337131234 (62.471%) in intersection cat fb.canFam5.chainSynHg38Link.txt # 1423305734 bases of 2337131234 (60.900%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ canFam5 hg38) > rbest.log 2>&1 & # real 255m9.076s cat fb.canFam5.chainRBest.Hg38.txt # 1422612399 bases of 2337131234 (60.870%) in intersection ############################################################################ # LASTZ MOUSE Mm39 (DONE - 2020-08-17 - Hiram) # can no longer use the lineage specific repeats with the new lastz # use a screen to manage this longish job: screen -S hg38Mm39 mkdir /hive/data/genomes/hg38/bed/lastzMm39.2020-08-17 cd /hive/data/genomes/hg38/bed/lastzMm39.2020-08-17 # 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 Mm39 SEQ2_DIR=/hive/data/genomes/mm39/mm39.2bit SEQ2_LEN=/hive/data/genomes/mm39/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 BASE=/hive/data/genomes/hg38/bed/lastzMm39.2020-08-17 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 -XXX - running - Mon Aug 17 13:12:52 PDT 2020 + # real 209m17.257s - cat fb.hg38.chainMm39Link.txt - # 964465044 bases of 3049335806 (31.629%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainMm39Link.txt + # 966592868 bases of 3110768607 (31.072%) in intersection - cat fb.hg38.chainSynMm39Link.txt - # 1484758745 bases of 3110768607 (47.730%) in intersection + sed -e 's/^/ # /;' fb.hg38.chainSynMm39Link.txt + # 913448433 bases of 3110768607 (29.364%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ hg38 mm39) > rbest.log 2>&1 & + # real 267m52.694s + + sed -e 's/^/ # /;' fb.hg38.chainRBest.Mm39.txt + # 891660271 bases of 3110768607 (28.664%) in intersection # and the swap mkdir /hive/data/genomes/mm39/bed/blastz.hg38.swap cd /hive/data/genomes/mm39/bed/blastz.hg38.swap - time (doBlastzChainNet.pl `pwd`/DEF -verbose=2 \ + time (doBlastzChainNet.pl -verbose=2 \ + /hive/data/genomes/hg38/bed/lastzMm39.2020-08-17/DEF \ -chainMinScore=3000 -chainLinearGap=medium \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -swap -syntenicNet) > swap.log 2>&1 - # real 83m28.397s + # real 47m57.164s - cat fb.mm39.chainHg38Link.txt - # 1493209286 bases of 2481941580 (60.163%) in intersection - cat fb.mm39.chainSynHg38Link.txt - # 1448164376 bases of 2481941580 (58.348%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainHg38Link.txt + # 939000954 bases of 2654624157 (35.372%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainSynHg38Link.txt + # 891050480 bases of 2654624157 (33.566%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ mm39 hg38) > rbest.log 2>&1 & # real 257m59.713s - cat fb.mm39.chainRBest.Hg38.txt - # 1425296830 bases of 2481941580 (57.427%) in intersection + sed -e 's/^/ # /;' fb.mm39.chainRBest.Hg38.txt + # 893176796 bases of 2654624157 (33.646%) in intersection #########################################################################