src/hg/makeDb/doc/rn4.txt 1.36
1.36 2010/01/25 19:16:11 hiram
panda aligned to dog,rat,mouse,human,opossum pig aligned to mouse,human,opossum,cow bosTau4 to rn4, rabbit to rat,mouse,opossum,guineaPig
Index: src/hg/makeDb/doc/rn4.txt
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/makeDb/doc/rn4.txt,v
retrieving revision 1.35
retrieving revision 1.36
diff -b -B -U 4 -r1.35 -r1.36
--- src/hg/makeDb/doc/rn4.txt 6 Nov 2009 23:18:06 -0000 1.35
+++ src/hg/makeDb/doc/rn4.txt 25 Jan 2010 19:16:11 -0000 1.36
@@ -4962,5 +4962,117 @@
hgsql rn4 -e \
'load data local infile "GN_rat_RefSeq.txt" into table geneNetworkId'
#########################################################################
+# BLASTZ/CHAIN/NET BOSTAU4 (DONE - 2010-01-19,22 - Hiram)
+ ssh hgwdev
+ screen # use a screen to manage this multi-day job
+ mkdir /hive/data/genomes/rn4/bed/blastzBosTau4.2010-01-19
+ cd /hive/data/genomes/rn4/bed/blastzBosTau4.2010-01-19
+ cat << '_EOF_' > DEF
+# Rat vs. Cow
+BLASTZ_M=50
+
+# TARGET: Rat Rn4
+SEQ1_DIR=/scratch/data/rn4/nib
+SEQ1_LEN=/cluster/data/rn4/chrom.sizes
+SEQ1_CHUNK=10000000
+SEQ1_LAP=10000
+
+# QUERY: Cow bosTau4
+SEQ2_DIR=/scratch/data/bosTau4/bosTau4.2bit
+SEQ2_LEN=/cluster/data/bosTau4/chrom.sizes
+# Maximum number of scaffolds that can be lumped together
+SEQ2_LIMIT=100
+SEQ2_CHUNK=20000000
+SEQ2_LAP=0
+
+BASE=/cluster/data/rn4/bed/blastzBosTau4.2010-01-19
+TMPDIR=/scratch/tmp
+'_EOF_'
+ # << this line keeps emacs coloring happy
+
+ time nice -n +19 doBlastzChainNet.pl -verbose=2 \
+ `pwd`/DEF \
+ -workhorse=hgwdev -bigClusterHub=pk -chainMinScore=3000 \
+ -chainLinearGap=medium -noLoadChainSplit -syntenicNet > do.log 2>&1 &
+ # interrupted by storm induced power failures, the finish lastz batch
+ # then continuing:
+ time nice -n +19 doBlastzChainNet.pl -verbose=2 \
+ `pwd`/DEF \
+ -continue=cat -workhorse=hgwdev -bigClusterHub=pk -chainMinScore=3000 \
+ -smallClusterHub=memk -chainLinearGap=medium -noLoadChainSplit \
+ -syntenicNet > cat.log 2>&1 &
+ # real 107m32.779s
+ cat fb.rn4.chainBosTau4Link.txt
+ # 649931321 bases of 2571531505 (25.274%) in intersection
+
+ mkdir /cluster/data/bosTau4/bed/blastz.rn4.swap
+ cd /cluster/data/bosTau4/bed/blastz.rn4.swap
+ time nice -n +19 doBlastzChainNet.pl -verbose=2 \
+ /cluster/data/rn4/bed/blastzBosTau4.2010-01-19/DEF \
+ -noLoadChainSplit -workhorse=hgwdev -smallClusterHub=memk \
+ -bigClusterHub=pk -chainMinScore=3000 -chainLinearGap=medium \
+ -swap -syntenicNet > swap.log 2>&1 &
+ # real 77m18.645s
+ cat fb.bosTau4.chainRn4Link.txt
+ # 664253901 bases of 2731830700 (24.315%) in intersection
+
+#########################################################################
+# ailMel1 Panda alignment (DONE - 2010-01-21 - Hiram)
+ mkdir /hive/data/genomes/rn4/bed/lastzAilMel1.2010-01-21
+ cd /hive/data/genomes/rn4/bed/lastzAilMel1.2010-01-21
+
+ cat << '_EOF_' > DEF
+# Rat vs. Panda
+# parameters from the Panda paper supplemental where they describe
+# their lastz parameters
+BLASTZ_K=2200
+BLASTZ_Y=3400
+BLASTZ_L=6000
+BLASTZ_H=2000
+BLASTZ_C=2
+BLASTZ_T=2
+
+# our usual M
+BLASTZ_M=50
+
+# TARGET: Rat Rn4
+SEQ1_DIR=/scratch/data/rn4/nib
+SEQ1_LEN=/scratch/data/rn4/chrom.sizes
+SEQ1_CHUNK=10000000
+SEQ1_LAP=10000
+
+# QUERY: Panda
+SEQ2_DIR=/scratch/data/ailMel1/ailMel1.2bit
+SEQ2_LEN=/scratch/data/ailMel1/chrom.sizes
+SEQ2_CHUNK=10000000
+SEQ2_LIMIT=50
+SEQ2_LAP=0
+
+BASE=/hive/data/genomes/rn4/bed/lastzAilMel1.2010-01-21
+TMPDIR=/scratch/tmp
+'_EOF_'
+ # << happy emacs
+
+ time nice -n +19 doBlastzChainNet.pl -verbose=2 \
+ `pwd`/DEF \
+ -noLoadChainSplit -syntenicNet \
+ -workhorse=hgwdev -smallClusterHub=pk -bigClusterHub=swarm \
+ -chainMinScore=3000 -chainLinearGap=medium > do.log 2>&1 &
+ # real 129m23.300s
+ cat fb.rn4.chainAilMel1Link.txt
+ # 707335282 bases of 2571531505 (27.506%) in intersection
+
+ mkdir /hive/data/genomes/ailMel1/bed/blastz.rn4.swap
+ cd /hive/data/genomes/ailMel1/bed/blastz.rn4.swap
+ time nice -n +19 doBlastzChainNet.pl -verbose=2 \
+ /hive/data/genomes/rn4/bed/lastzAilMel1.2010-01-21/DEF \
+ -swap -noLoadChainSplit -syntenicNet \
+ -workhorse=hgwdev -smallClusterHub=memk -bigClusterHub=swarm \
+ -chainMinScore=3000 -chainLinearGap=medium > swap.log 2>&1 &
+ # real 65m7.728s
+ cat fb.ailMel1.chainRn4Link.txt
+ # 693099721 bases of 2225124764 (31.149%) in intersection
+
+############################################################################