This script has been updated to extract the third column, the CGC_id, for use...

This script has been updated to extract the third column, the CGC_id, for use in as the display_label in xref table. Not all genes will have an entry in the 3rd column (see wormpep.table file).

misc-scripts/xref_mapping/XrefParser/WormPepParser.pm

@@ -33,14 +33,19 @@ sub run {
 
   while (<PEP>) {
 
-    my ($transcript, $wb)  = (split(/\t/,substr($_,1)))[0,1];
+    my ($transcript, $wb, $display)  = (split(/\t/,substr($_,1)))[0,1,2];
+
+    #check if the CGC_id is present in wormpep.table
+    if ($display !~ m/\w/){ # or if ($display == '')
+      $display = $wb;
+    }
 
     # reuse or create xref
     my $xref_id;
     $xref_sth->execute($wb);
     my $xref_id = ($xref_sth->fetchrow_array())[0];
     if (!$xref_id) {
-      $xref_id = $self->add_xref($wb, undef, $wb, "", $worm_source_id, $species_id);
+      $xref_id = $self->add_xref($wb, undef, $display, "", $worm_source_id, $species_id);
       $x_count++;
     }