Convert the TRANSFAC matrix into a matrix readable by TESS (Transcription Element Search System).

transfac_to_tess.pl

#!/bin/env perl

use strict;
use warnings;

my $usage = "Usage: $0 <matrix.dat>\n";
my $infile = shift or die $usage;

my $accession = '';
my $start = 0;
my @entry = ();

open(IN, '<', $infile) || die "Could not open $infile: $!\n";
while(<IN>){
   chomp;
   if (/^AC\s+(.*)$/){
      $accession = $1;
   }
   if (/^NA\s+(.*)$/){
      $accession .= "_$1";
   }
   if (/^P0/){
      $start = 1;
      $entry[0] = ">$accession";
      next;
   } elsif (/^XX/ && $start == 1){
      $start = 0;
      foreach my $line (@entry){
         print "$line\n";
      }
      print "<\n";
      @entry = ();
   }
   if ($start == 1){
      my ($junk, $a, $c, $g, $t, $junk2) = split(/\s+/);
      $entry[scalar(@entry)] = join("\t", $a, $c, $g, $t);
   }

}
close(IN);

exit(0);