7d0bd2b7d089f94c9a8260c417246d4dbfce2523 mspeir Sat Mar 29 18:51:22 2025 -0700 adding make docs for several lastz runs from the last 6 months or so diff --git src/hg/makeDb/doc/rheMac10/lastzRuns.txt src/hg/makeDb/doc/rheMac10/lastzRuns.txt index d70a6cc514e..f287339960b 100644 --- src/hg/makeDb/doc/rheMac10/lastzRuns.txt +++ src/hg/makeDb/doc/rheMac10/lastzRuns.txt @@ -1,267 +1,369 @@ ############################################################################## # LASTZ Rat rn6 (DONE - 2020-10-20 - Hiram) mkdir /hive/data/genomes/rheMac10/bed/lastzRn6.2020-10-20 cd /hive/data/genomes/rheMac10/bed/lastzRn6.2020-10-20 printf '# rat vs rhesus BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz # TARGET: Rhesus RheMac10 SEQ1_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit SEQ1_LEN=/hive/data/genomes/rheMac10/chrom.sizes SEQ1_CHUNK=20000000 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_LAP=0 SEQ2_LIMIT=500 BASE=/hive/data/genomes/rheMac10/bed/lastzRn6.2020-10-20 TMPDIR=/dev/shm ' > DEF # establish a screen to control this job screen -S rheMac10Rn6 time (doBlastzChainNet.pl -verbose=2 `pwd`/DEF \ -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 & # real 278m29.024s cat fb.rheMac10.chainRn6Link.txt # 901231172 bases of 2936892733 (30.687%) in intersection cat fb.rheMac10.chainSynRn6Link.txt # 854008376 bases of 2936892733 (29.079%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ rheMac10 rn6) > rbest.log 2>&1 & # real 293m29.540s cat fb.rheMac10.chainRBest.Rn6.txt # 860406990 bases of 2936892733 (29.297%) in intersection mkdir /hive/data/genomes/rn6/bed/blastz.rheMac10.swap cd /hive/data/genomes/rn6/bed/blastz.rheMac10.swap time (doBlastzChainNet.pl -verbose=2 \ /hive/data/genomes/rheMac10/bed/lastzRn6.2020-10-20/DEF \ -swap -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=3000 -chainLinearGap=medium) > swap.log 2>&1 # real 61m59.379s cat fb.rn6.chainRheMac10Link.txt # 938991388 bases of 2729860805 (34.397%) in intersection cat fb.rn6.chainSynRheMac10Link.txt # 873546846 bases of 2729860805 (32.000%) in intersection time (doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ rn6 rheMac10) > rbest.log 2>&1 # real 358m51.937s cat fb.rn6.chainRBest.RheMac10.txt # 861947799 bases of 2729860805 (31.575%) in intersection ############################################################################## # LASTZ Rhesus RheMac10 vs. Crab-eating macaque MacFas5 # (DONE - 2021-10-12 - hiram) cd /cluster/home/hiram/kent/src/hg/makeDb/doc/rheMac10 time (~/kent/src/hg/utils/automation/pairLastz.sh rheMac10 macFas5 \ primate primate) > rheMac10.macFas5.log 2>&1 & # real 422m56.515s # user 0m1.550s # sys 0m1.626s # the following make doc is in that log file, copied here: mkdir /hive/data/genomes/rheMac10/bed/lastzMacFas5.2021-10-12 cd /hive/data/genomes/rheMac10/bed/lastzMacFas5.2021-10-12 printf '# Crab-eating macaque MacFas5 vs. Rhesus RheMac10 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_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: Rhesus RheMac10 SEQ1_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit SEQ1_LEN=/hive/data/genomes/rheMac10/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=40 # 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_LAP=0 SEQ2_LIMIT=100 BASE=/hive/data/genomes/rheMac10/bed/lastzMacFas5.2021-10-12 TMPDIR=/dev/shm ' > DEF time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -verbose=2 `pwd`/DEF -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 grep -w real do.log | sed -e 's/^/ # /;' # real 188m26.969s sed -e 's/^/ # /;' fb.rheMac10.chainMacFas5Link.txt # 2784170031 bases of 2936892733 (94.800%) in intersection sed -e 's/^/ # /;' fb.rheMac10.chainSynMacFas5Link.txt # 2760382026 bases of 2936892733 (93.990%) in intersection time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ \ \ rheMac10 macFas5) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 96m55.151s sed -e 's/^/ # /;' fb.rheMac10.chainRBest.MacFas5.txt # 2728786009 bases of 2936892733 (92.914%) in intersection ### and for the swap cd /hive/data/genomes/macFas5/bed/blastz.rheMac10.swap time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -swap -verbose=2 \ /hive/data/genomes/rheMac10/bed/lastzMacFas5.2021-10-12/DEF -swapDir=`pwd` \ -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 grep -w real swap.log | sed -e 's/^/ # /;' # real 71m1.507s sed -e 's/^/ # /;' fb.macFas5.chainRheMac10Link.txt # 2739714634 bases of 2803866698 (97.712%) in intersection sed -e 's/^/ # /;' fb.macFas5.chainSynRheMac10Link.txt # 2729711862 bases of 2803866698 (97.355%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ \ \ macFas5 rheMac10) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 66m32.559s sed -e 's/^/ # /;' fb.macFas5.chainRBest.RheMac10.txt # 2730109619 bases of 2803866698 (97.369%) in intersection ############################################################################## # LASTZ Rhesus RheMac10 vs. Baboon PapAnu2 # (DONE - 2022-03-17 - Jairo Navarro) mkdir /hive/data/genomes/rheMac10/bed/lastzPapAnu2.2022-03-09 cd /hive/data/genomes/rheMac10/bed/lastzPapAnu2.2022-03-09 printf '# Baboon PapAnu2 vs. Rhesus RheMac10 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_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: Rhesus RheMac10 SEQ1_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit SEQ1_LEN=/hive/data/genomes/rheMac10/chrom.sizes SEQ1_CHUNK=20000000 SEQ1_LAP=10000 SEQ1_LIMIT=40 # QUERY: Baboon PapAnu2 SEQ2_DIR=/hive/data/genomes/papAnu2/papAnu2.2bit SEQ2_LEN=/hive/data/genomes/papAnu2/chrom.sizes SEQ2_CHUNK=20000000 SEQ2_LAP=0 SEQ2_LIMIT=500 BASE=/hive/data/genomes/rheMac10/bed/lastzPapAnu2.2022-03-09 TMPDIR=/dev/shm ' > DEF time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -verbose=2 `pwd`/DEF -syntenicNet \ -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=medium) > do.log 2>&1 grep -w real do.log | sed -e 's/^/ # /;' sed -e 's/^/ # /;' fb.rheMac10.chainPapAnu2Link.txt # 2661233289 bases of 2936892733 (90.614%) in intersection sed -e 's/^/ # /;' fb.rheMac10.chainSynPapAnu2Link.txt # 2637780437 bases of 2936892733 (89.815%) in intersection time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ \ \ rheMac10 papAnu2) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 92m15.570s sed -e 's/^/ # /;' fb.rheMac10.chainRBest.PapAnu2.txt # 2603944831 bases of 2936892733 (88.663%) in intersection ### and for the swap cd /hive/data/genomes/papAnu2/bed/blastz.rheMac10.swap time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -swap -verbose=2 \ /hive/data/genomes/rheMac10/bed/lastzPapAnu2.2022-03-09/DEF -swapDir=`pwd` \ -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 grep -w real swap.log | sed -e 's/^/ # /;' sed -e 's/^/ # /;' fb.papAnu2.chainRheMac10Link.txt # 2643316405 bases of 2893250291 (91.361%) in intersection sed -e 's/^/ # /;' fb.papAnu2.chainSynRheMac10Link.txt cd /hive/data/genomes/papAnu2/bed/blastz.rheMac10.swap time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -swap -verbose=2 \ /hive/data/genomes/rheMac10/bed/lastzPapAnu2.2022-03-09/DEF -swapDir=`pwd` \ -syntenicNet -workhorse=hgwdev -smallClusterHub=hgwdev -bigClusterHub=ku \ -chainMinScore=5000 -chainLinearGap=medium) > swap.log 2>&1 grep -w real swap.log | sed -e 's/^/ # /;' # real 70m47.109s sed -e 's/^/ # /;' fb.papAnu2.chainRheMac10Link.txt # 2643316405 bases of 2893250291 (91.361%) in intersection sed -e 's/^/ # /;' fb.papAnu2.chainSynRheMac10Link.txt # 2615443297 bases of 2893250291 (90.398%) in intersection \ time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ \ \ papAnu2 rheMac10) > rbest.log 2>&1 grep -w real rbest.log | sed -e 's/^/ # /;' # real 109m15.780s sed -e 's/^/ # /;' fb.papAnu2.chainRBest.RheMac10.txt # 2607952215 bases of 2893250291 (90.139%) in intersection ############################################################################## +# LASTZ Rhesus RheMac10 vs. Cow BosTau9 +# (DONE - 2025-03-23 - mspeir) + + mkdir /hive/data/genomes/rheMac10/bed/lastzBosTau9.2025-03-23 + cd /hive/data/genomes/rheMac10/bed/lastzBosTau9.2025-03-23 + + printf '# Cow BosTau9 vs. Rhesus RheMac10 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: Rhesus rheMac10 +SEQ1_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit +SEQ1_LEN=/hive/data/genomes/rheMac10/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=40 + +# QUERY: Cow bosTau9 +SEQ2_DIR=/hive/data/genomes/bosTau9/bosTau9.2bit +SEQ2_LEN=/hive/data/genomes/bosTau9/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/rheMac10/bed/lastzBosTau9.2025-03-23 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -verbose=2 `pwd`/DEF -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -fileServer=hgwdev -bigClusterHub=hgwdev \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 796m10.530s + + sed -e 's/^/ # /;' fb.rheMac10.chainBosTau9Link.txt + # 1345771048 bases of 2936892733 (45.823%) in intersection + sed -e 's/^/ # /;' fb.rheMac10.chainSynBosTau9Link.txt + # 1293982344 bases of 2936892733 (44.060%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + \ + rheMac10 bosTau9) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 229m21.039s + + sed -e 's/^/ # /;' fb.rheMac10.chainRBest.BosTau9.txt + # 1282431413 bases of 2936892733 (43.666%) in intersection + +############################################################################## +# LASTZ Rhesus RheMac10 vs. Horse EquCab3 +# (DONE - 2025-03-23 - mspeir) + + mkdir /hive/data/genomes/rheMac10/bed/lastzEquCab3.2025-03-23 + cd /hive/data/genomes/rheMac10/bed/lastzEquCab3.2025-03-23 + + printf '# Horse EquCab3 vs. Rhesus RheMac10 +BLASTZ=/cluster/bin/penn/lastz-distrib-1.04.03/bin/lastz + +# TARGET: Rhesus rheMac10 +SEQ1_DIR=/hive/data/genomes/rheMac10/rheMac10.2bit +SEQ1_LEN=/hive/data/genomes/rheMac10/chrom.sizes +SEQ1_CHUNK=20000000 +SEQ1_LAP=10000 +SEQ1_LIMIT=40 + +# QUERY: Horse equCab3 +SEQ2_DIR=/hive/data/genomes/equCab3/equCab3.2bit +SEQ2_LEN=/hive/data/genomes/equCab3/chrom.sizes +SEQ2_CHUNK=20000000 +SEQ2_LAP=0 +SEQ2_LIMIT=100 + +BASE=/hive/data/genomes/rheMac10/bed/lastzEquCab3.2025-03-23 +TMPDIR=/dev/shm + +' > DEF + + time (~/kent/src/hg/utils/automation/doBlastzChainNet.pl -verbose=2 `pwd`/DEF -syntenicNet \ + -workhorse=hgwdev -smallClusterHub=hgwdev -fileServer=hgwdev -bigClusterHub=hgwdev \ + -chainMinScore=3000 -chainLinearGap=medium) > do.log 2>&1 + grep -w real do.log | sed -e 's/^/ # /;' + # real 757m43.917s + + sed -e 's/^/ # /;' fb.rheMac10.chainEquCab3Link.txt + # 1631389178 bases of 2936892733 (55.548%) in intersection + sed -e 's/^/ # /;' fb.rheMac10.chainSynEquCab3Link.txt + # 1576810063 bases of 2936892733 (53.690%) in intersection + + time (~/kent/src/hg/utils/automation/doRecipBest.pl -load -workhorse=hgwdev -buildDir=`pwd` \ + \ + \ + rheMac10 equCab3) > rbest.log 2>&1 + + grep -w real rbest.log | sed -e 's/^/ # /;' + # real 230m53.590s + + sed -e 's/^/ # /;' fb.rheMac10.chainRBest.EquCab3.txt + # 1553000153 bases of 2936892733 (52.879%) in intersection + +##############################################################################