src/hg/makeDb/doc/sacCer2.txt 1.17
1.17 2010/02/05 06:54:06 kuhn
grammar
Index: src/hg/makeDb/doc/sacCer2.txt
===================================================================
RCS file: /projects/compbio/cvsroot/kent/src/hg/makeDb/doc/sacCer2.txt,v
retrieving revision 1.16
retrieving revision 1.17
diff -b -B -U 4 -r1.16 -r1.17
--- src/hg/makeDb/doc/sacCer2.txt 2 Feb 2010 18:56:32 -0000 1.16
+++ src/hg/makeDb/doc/sacCer2.txt 5 Feb 2010 06:54:06 -0000 1.17
@@ -189,9 +189,9 @@
ldHgGene -gtf sacCer2 sgdGene sacCer2.sgdGene.gtf
hgLoadBed sacCer2 sgdOther otherFeatures.bed \
-tab -sqlTable=$HOME/kent/src/hg/lib/sgdOther.sql
- # this perl script will fixup the fasta header lines for
+ # this perl script will fix up the fasta header lines for
# the chr*.peptides.fsa files to run into hgSgdPep
cat << '_EOF_' > filter.pl
#!/usr/bin/env perl
@@ -205,9 +205,9 @@
while (my $line=<>) {
if ($line =~ m/^>Annotated\|/) {
$inAnnotation = 1;
my (@words) = split('\s+', $line);
- die "can not find four fields in\n'$line'" if (scalar(@words) < 4);
+ die "cannot find four fields in\n'$line'" if (scalar(@words) < 4);
my $name = $words[3];
$name =~ s/;.*//;
$name =~ s#/.*##;
printf ">ORFP:%s\n", $name;
@@ -302,8 +302,11 @@
hgsql sacCer2 -e 'load data local infile "sgdToSwissProt.txt" \
into table sgdToSwissProt;'
hgProtIdToGenePred sacCer2 sgdGene sgdToSwissProt name value
+# interesting to note that sgdTOSwissProt has one accession not
+# in sgdGene.name: KHS1 (BK 2009-07-14)
+
############################################################################
# CREATE SGD-BASED CLONE TRACK (DONE - 2009-02-10 - Hiram)
mkdir /hive/data/genomes/sacCer2/bed/sgdClone
cd /hive/data/genomes/sacCer2/bed/sgdClone