Ignore transcripts with biotypes 'nonsense_mediated_decay' and

processed_transcript', if gene biotype is protein_coding.

misc-scripts/canonical_transcripts/set_canonical_transcripts.pl

@@ -30,91 +30,99 @@ my $write = 0;
 my $include_non_ref = 1;
 my $verbose = 0;
 
-&GetOptions( 
-            'dbhost:s'      => \$host,
-            'dbport:n'      => \$port,
-            'dbname:s'    => \$dbname,
-            'dbuser:s'    => \$user,
-            'dbpass:s'      => \$pass,
-            'coord_system_name:s' => \$coord_system,
-            'seq_region_name:s' => \$seq_region_name,
-            'write!' => \$write,
-            'include_non_ref!' => \$include_non_ref,
-            'verbose!' => \$verbose,
-           );
-
-unless ( $write ) {  
-   print " you've not used the -write option so results will not be written into the database\n" ; 
-} 
-
-my $db = new Bio::EnsEMBL::DBSQL::DBAdaptor(
-                                              -host   => $host,
-                                              -user   => $user,
-                                              -port   => $port,
-                                              -dbname => $dbname,
-                                              -pass => $pass,
-                                             );
+&GetOptions( 'dbhost:s'            => \$host,
+             'dbport:n'            => \$port,
+             'dbname:s'            => \$dbname,
+             'dbuser:s'            => \$user,
+             'dbpass:s'            => \$pass,
+             'coord_system_name:s' => \$coord_system,
+             'seq_region_name:s'   => \$seq_region_name,
+             'write!'              => \$write,
+             'include_non_ref!'    => \$include_non_ref,
+             'verbose!'            => \$verbose, );
+
+unless ($write) {
+  print
+" you've not used the -write option so results will not be written into the database\n";
+}
+
+my $db =
+  new Bio::EnsEMBL::DBSQL::DBAdaptor( -host   => $host,
+                                      -user   => $user,
+                                      -port   => $port,
+                                      -dbname => $dbname,
+                                      -pass   => $pass, );
 
 
 my $sa = $db->get_SliceAdaptor;
 my $slices;
 
-if($seq_region_name){
-  my $slice = $sa->fetch_by_region($coord_system, $seq_region_name, $include_non_ref);
-  push(@$slices, $slice);
-}else{
-  $slices = $sa->fetch_all($coord_system, '', $include_non_ref);
+if ($seq_region_name) {
+  my $slice =
+    $sa->fetch_by_region( $coord_system, $seq_region_name, $include_non_ref );
+  push( @$slices, $slice );
+} else {
+  $slices = $sa->fetch_all( $coord_system, '', $include_non_ref );
 }
 
+my $update_to_null = "update gene set canonical_transcript_id = NULL, canonical_annotation = NULL";
+$db->dbc->do($update_to_null);
+# get $db->dbc->db_handle->do($update_to_null) instead if above not working
+
 my $gene_update_sql = "update gene set canonical_transcript_id = ? where gene_id = ?";
 my $sth = $db->dbc->prepare($gene_update_sql);
-SLICE:foreach my $slice(@$slices){
-  print "Getting genes for ".$slice->name."\n" if($verbose);
-  my $genes = $slice->get_all_Genes(undef, undef, 1);
+SLICE: foreach my $slice (@$slices) {
+  print "Getting genes for " . $slice->name . "\n" if ($verbose);
+  my $genes = $slice->get_all_Genes( undef, undef, 1 );
   my %canonical;
- GENE:foreach my $gene(@$genes){
-    print "Updating gene: ",$gene->dbID,"\n";
+GENE: foreach my $gene (@$genes) {
+    print "Updating gene: ", $gene->dbID, "\n";
     my $transcripts = $gene->get_all_Transcripts;
-    if(@$transcripts == 1){
-      $canonical{$gene->dbID} = $transcripts->[0]->dbID;
+    if ( @$transcripts == 1 ) {
+      $canonical{ $gene->dbID } = $transcripts->[0]->dbID;
       next GENE;
     }
-    my $has_translation =0;
-    my $count = 0;
+    my $has_translation = 0;
+    my $count           = 0;
     my @with_translation;
     my @no_translation;
-    foreach my $transcript(@$transcripts){
-      if($transcript->translation && ($gene->biotype ne 'processed_transcript') 
-         && ($gene->biotype ne 'pseudogene')){
-				unless($transcript->translation->seq =~ /\*/){
-          push(@with_translation, $transcript);
-				}
-      }else{
-        push(@no_translation, $transcript);
+
+    foreach my $transcript (@$transcripts) {
+      if (    $transcript->translation
+           && ( $gene->biotype       ne 'processed_transcript' )
+           && ( $gene->biotype       ne 'pseudogene' )
+           && ( $transcript->biotype ne 'nonsense_mediated_decay' )
+           && ( $transcript->biotype ne 'processed_transcript' ) )
+      {
+        unless ( $transcript->translation->seq =~ /\*/ ) {
+          push( @with_translation, $transcript );
+        }
+      } else {
+        push( @no_translation, $transcript );
       }
     }
 
     my @sorted;
-    if(@with_translation){
+    if (@with_translation) {
       my @len_and_trans;
       foreach my $trans (@with_translation) {
         my $h = { trans => $trans, len => $trans->translate->length };
-        push @len_and_trans,$h;
+        push @len_and_trans, $h;
       }
       my @tmp_sorted = sort { $b->{len} <=> $a->{len} } @len_and_trans;
 
       foreach my $h (@tmp_sorted) {
         #print "Adding to sorted " . $h->{trans}->dbID . "\n";
-        push @sorted,$h->{trans};
+        push @sorted, $h->{trans};
       }
-    }else{
-      @sorted = sort {$b->length <=> $a->length} @no_translation;
+    } else {
+      @sorted = sort { $b->length <=> $a->length } @no_translation;
     }
-    $canonical{$gene->dbID} = $sorted[0]->dbID;
-  }
-  foreach my $gene_id (keys(%canonical)){
+    $canonical{ $gene->dbID } = $sorted[0]->dbID;
+  } ## end foreach my $gene (@$genes)
+  foreach my $gene_id ( keys(%canonical) ) {
     my $transcript_id = $canonical{$gene_id};
-    $sth->execute($transcript_id, $gene_id) if($write);
+    $sth->execute( $transcript_id, $gene_id ) if ($write);
   }
-}
+} ## end foreach my $slice (@$slices)