now generating density features for three biotype groups

replaces old method of known/novel 'coding' groups

modules/Bio/EnsEMBL/Pipeline/Production/CodingDensity.pm

+package Bio::EnsEMBL::Pipeline::Production::CodingDensity;
+
+use base qw/Bio::EnsEMBL::Pipeline::Production::DensityGenerator/;
+
+
+use strict;
+use warnings;
+
+
+sub get_density {
+  my ($self, $block) = @_;
+  my @biotypes = $self->get_biotype_group("coding");
+  my $count = 0;
+  foreach my $biotype (@biotypes) {
+    $count += scalar(@{ $block->get_all_Genes_by_type($biotype) });
+  }
+  return $count;
+}
+
+1;
+
+

modules/Bio/EnsEMBL/Pipeline/Production/DensityGenerator.pm

@@ -162,5 +162,20 @@ sub get_analysis {
   return $analysis;
 }
 
+sub get_biotype_group {
+  my ($self, $biotype) = @_;
+  my $prod_dba = $self->get_production_DBAdaptor();
+  my $helper = $prod_dba->dbc()->sql_helper();
+  my $sql = q{
+     SELECT name
+     FROM biotype
+     WHERE object_type = 'gene'
+     AND is_current = 1
+     AND biotype_group = ?
+     AND db_type like '%core%' };
+  my @biotypes = @{ $helper->execute_simple(-SQL => $sql, -PARAMS => [$biotype]) };
+  return @biotypes;
+}
+
 
 1;

modules/Bio/EnsEMBL/Pipeline/Production/EmailSummaryCore.pm

@@ -14,6 +14,10 @@ sub fetch_input {
   my $gene_gc = $self->jobs('GeneGC');
   my $percent_gc = $self->jobs('PercentGC');
   my $percent_repeat = $self->jobs('PercentRepeat');
+  my $coding_density = $self->jobs('CodingDensity');
+  my $pseudogene_density = $self->jobs('PseudogeneDensity');
+  my $non_coding_density = $self->jobs('NonCodingDensity');
+
     
   my @args = (
     $pep_stats->{successful_jobs},
@@ -24,11 +28,20 @@ sub fetch_input {
     $percent_gc->{failed_jobs},
     $percent_repeat->{successful_jobs},
     $percent_repeat->{failed_jobs},
+    $coding_density->{successful_jobs},
+    $coding_density->{failed_jobs},
+    $pseudogene_density->{successful_jobs},
+    $pseudogene_density->{failed_jobs},
+    $non_coding_density->{successful_jobs},
+    $non_coding_density->{failed_jobs},
     $self->failed(),
     $self->summary($pep_stats),
     $self->summary($gene_gc),
     $self->summary($percent_gc),
     $self->summary($percent_repeat),
+    $self->summary($coding_density),
+    $self->summary($pseudogene_density),
+    $self->summary($non_coding_density),
   );
   
   my $msg = sprintf(<<'MSG', @args);
@@ -38,6 +51,9 @@ Your FASTA Pipeline has finished. We have:
   * %d species with gene gc (%d failed)
   * %d species with percent gc (%d failed)
   * %d species with percent repeat (%d failed)
+  * %d species with coding density (%d failed)
+  * %d species with pseudogene density (%d failed)
+  * %d species with non coding density (%d failed)
 
 %s
 

modules/Bio/EnsEMBL/Pipeline/Production/NonCodingDensity.pm

+package Bio::EnsEMBL::Pipeline::Production::NonCodingDensity;
+
+use base qw/Bio::EnsEMBL::Pipeline::Production::DensityGenerator/;
+
+
+use strict;
+use warnings;
+
+
+sub get_density {
+  my ($self, $block) = @_;
+  my @biotypes = $self->get_biotype_group("non-coding");
+  my $count = 0;
+  foreach my $biotype (@biotypes) {
+    $count += scalar(@{ $block->get_all_Genes_by_type($biotype) });
+  }
+  return $count;
+}
+
+1;
+
+

modules/Bio/EnsEMBL/Pipeline/Production/PepStats.pm

@@ -122,8 +122,7 @@ sub dump_translation {
     WHERE tr.transcript_id = tl.transcript_id
     AND tr.seq_region_id = s.seq_region_id
     AND s.coord_system_id = cs.coord_system_id
-    AND cs.species_id = ?
-    ORDER by tl.translation_id };
+    AND cs.species_id = ? };
   my @translation_ids = @{ $helper->execute_simple(-SQL => $sql, -PARAMS => [$dba->species_id()]) };
   for my $dbid (@translation_ids) {
     my $translation = $ta->fetch_by_dbID($dbid);

modules/Bio/EnsEMBL/Pipeline/Production/PseudogeneDensity.pm

+package Bio::EnsEMBL::Pipeline::Production::PseudogeneDensity;
+
+use base qw/Bio::EnsEMBL::Pipeline::Production::DensityGenerator/;
+
+
+use strict;
+use warnings;
+
+
+sub get_density {
+  my ($self, $block) = @_;
+  my @biotypes = $self->get_biotype_group("pseudogene");
+  my $count = 0;
+  foreach my $biotype (@biotypes) {
+    $count += scalar(@{ $block->get_all_Genes_by_type($biotype) });
+  }
+  return $count;
+}
+
+1;
+
+