Hello!

To see the file structure, click on "tree".

Note that updates take place every 10 minutes, commits may not be seen immediately.
Fixes the gene headers in the fasta files so that they are correctly parsed by blast...
authorelserj <elserj@localhost>
Fri, 17 Sep 2010 23:09:10 +0000 (23:09 +0000)
committerelserj <elserj@localhost>
Fri, 17 Sep 2010 23:09:10 +0000 (23:09 +0000)
svn path=/; revision=37

interactome_scripts/fasta_header_fix.pl [new file with mode: 0755]

diff --git a/interactome_scripts/fasta_header_fix.pl b/interactome_scripts/fasta_header_fix.pl
new file mode 100755 (executable)
index 0000000..eaaa1a8
--- /dev/null
@@ -0,0 +1,35 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+
+require "$ENV{HOME}/scripts/jaiswallab/interactome_scripts/find_species.pl";
+
+my @files;
+
+if($#ARGV == 0) {
+       @files = $ARGV[0];
+}else{
+       @files = glob("*.fa");
+}
+
+foreach my $input_file (@files) {
+       open(in_file, $input_file)  || die "Error: File $input_file can not be opened";
+       my $output_file = $input_file . "_fixed.fa";
+       open(out_file, ">$output_file");
+       
+       my $species = find_species($input_file);
+
+       while(<in_file>) {
+               my $line = $_;
+               chomp $line;
+               if ($line =~ /^>/) {
+                       my $gene = find_gene($line,$species);
+                       $line = ">" . "$gene";
+               }
+               print out_file "$line\n";
+       }
+
+       close(in_file);
+       close(out_file);
+}