src/hg/makeDb/doc/aplCal1.txt 1.2

Index: src/hg/makeDb/doc/aplCal1.txt
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/makeDb/doc/aplCal1.txt,v
retrieving revision 1.1
retrieving revision 1.2
diff -b -B -U 1000000 -r1.1 -r1.2
--- src/hg/makeDb/doc/aplCal1.txt	13 May 2009 20:56:14 -0000	1.1
+++ src/hg/makeDb/doc/aplCal1.txt	14 May 2009 00:26:13 -0000	1.2
@@ -1,52 +1,68 @@
 #########################################
 #
 # aplCal1 = Aplysia californica 
 #
 #
 
 # set up main genome directory
 
 ssh hgwdev
 cd /hive/data/genomes
 mkdir aplCal1
 cd aplCal1
 
 mkdir download
 cd download
 
 # get sequence from BROAD
 # http://www.broad.mit.edu/ftp/pub/assemblies/invertebrates/aplysia/
 vi fetch.sh
 chmod +x fetch.sh
 ./fetch.sh
 
 
 # fixup ids for super fasta and quals
 #  change ">scaffold_0.1-1784514 (Draft_v1)" 
 #    to   ">scaffold_0"
 #  sed 's/\(>scaffold_[0-9]*\)[.].*/\1/'
 vi fix.csh
 chmod +x fix.csh
 ./fix.csh
 
 totalKinds assembly.unplaced 2 > unplaced.types
 cat unplaced.types
 #unplaced 4270994
 #low_quality 945330
 #other 1781
 #deliberate 273497
 #vector_or_host 63932
 #multiple_instance 27153
 
 vi aplCal1.config.ra
 
 time makeGenomeDb.pl aplCal1.config.ra > & makeGenomeDb.pl.out &
 # took less than 10 minutes
 
 # Organism Image
 wget -O /usr/local/apache/htdocs/images/Aplysia_californica.jpg \
  'http://upload.wikimedia.org/wikipedia/commons/thumb/e/ef/Aplysia_californica.jpg/250px-Aplysia_californica.jpg'
 
 # Edit and check-in templates for description.html, gold.html, gap.html, aplCal1/trackDb.ra
 
 
+# repeat mask
+time doRepeatMasker.pl aplCal1 > & doRepeatMasker.pl.out &
+
+
+# simple repeat masker trf
+time doSimpleRepeat.pl aplCal1 > & doSimpleRepeat.pl.out &
+
+# make final masked .2bit
+[hgwdev:aplCal1> twoBitMask aplCal1.rmsk.2bit -add bed/simpleRepeat.2009-05-13/trfMask.bed aplCal1.2bit
+#Warning: BED file bed/simpleRepeat.2009-05-13/trfMask.bed has >=13 fields
+#which means it might contain block coordinates, but this program uses only the
+#first three fields (the entire span -- no support for blocks).
+
+ln -s /cluster/data/aplCal1/aplCal1.2bit /gbdb/aplCal1/
+
+