Updates to add projection parent as attributes in gtf and gff dumps - ENSCORESW-2003

modules/Bio/EnsEMBL/Gene.pm

@@ -1524,6 +1524,12 @@ sub summary_as_hash {
   my $havana_gene = $self->havana_gene();
   $summary_ref->{'havana_gene'} = $havana_gene->display_id() if defined $havana_gene;
   $summary_ref->{'havana_version'} = $havana_gene->version() if defined $havana_gene;
+
+  ## Stable identifier of the parent gene this gene was projected from
+   my $proj_parent_attributes = $self->get_all_Attributes("proj_parent_g");
+    if (@{$proj_parent_attributes}) {
+      $summary_ref->{'projection_parent_gene'} = $proj_parent_attributes->[0]->value;
+    }
   return $summary_ref;
 }
 

modules/Bio/EnsEMBL/Transcript.pm

@@ -3139,6 +3139,12 @@ sub summary_as_hash {
   $summary_ref->{'ccdsid'} = $self->ccds->display_id() if $self->ccds();
   $summary_ref->{'transcript_support_level'} = $self->tsl() if $self->tsl();
   $summary_ref->{'tag'} = 'basic' if $self->gencode_basic();
+
+  ## Stable identifier of the parent transcript this transcript was projected from
+  my $proj_parent_attributes = $self->get_all_Attributes("proj_parent_t");
+  if (@{$proj_parent_attributes}) {
+    $summary_ref->{'projection_parent_transcript'} = $proj_parent_attributes->[0]->value;
+  }
   return $summary_ref;
 }
 

modules/Bio/EnsEMBL/Utils/IO/GTFSerializer.pm

@@ -458,7 +458,7 @@ sub _print_attribs {
   }
 
   #add projection parent
-  my $proj_parent_attributes = $transcript->get_all_Attributes("proj_parent_g");
+  my $proj_parent_attributes = $gene->get_all_Attributes("proj_parent_g");
     if (@{$proj_parent_attributes}) {
       my $value = $proj_parent_attributes->[0]->value;
       print $fh qq{ projection_parent_gene "${value}";};

modules/t/gffSerialiser.t

@@ -76,7 +76,7 @@ OUT
   #Have to do this outside of the HERETO thanks to tabs
   $expected .= join("\t", 
     qw/20  ensembl region 30274334  30300924  . + ./,
-    'ID=gene:ENSG00000131044;Name=C20orf125;biotype=protein_coding;gene_id=ENSG00000131044;logic_name=ensembl;version=1' 
+    'ID=gene:ENSG00000131044;Name=C20orf125;biotype=protein_coding;gene_id=ENSG00000131044;logic_name=ensembl;projection_parent_gene=ENSG_PARENT_GENE;version=1'
   );
   $expected .= "\n";
 
@@ -122,7 +122,7 @@ OUT
   #Have to do this outside of the HERETO thanks to tabs
   $expected .= join("\t", 
     qw/20  wibble region 30274334  30300924  . + ./,
-    'ID=gene:ENSG00000131044;Name=C20orf125;biotype=protein_coding;description=DJ310O13.1.2 (NOVEL PROTEIN SIMILAR DROSOPHILA PROTEIN CG7474%2C ISOFORM 2 ) (FRAGMENT). [Source:SPTREMBL%3BAcc:Q9BR18];gene_id=ENSG00000131044;logic_name=ensembl;version=1' 
+    'ID=gene:ENSG00000131044;Name=C20orf125;biotype=protein_coding;description=DJ310O13.1.2 (NOVEL PROTEIN SIMILAR DROSOPHILA PROTEIN CG7474%2C ISOFORM 2 ) (FRAGMENT). [Source:SPTREMBL%3BAcc:Q9BR18];gene_id=ENSG00000131044;logic_name=ensembl;projection_parent_gene=ENSG_PARENT_GENE;version=1'
   );
   $expected .= "\n";
   assert_gff3($gene, $expected, 'Gene with custom source serialises to GFF3 as expected. Source is wibble');
@@ -132,7 +132,7 @@ OUT
 OUT
   $expected .= join("\t", 
   qw/20      ensembl region  30274334        30298904        .       +       ./,
-  'ID=transcript:ENST00000310998;Name=C20orf125;Parent=gene:ENSG00000131044;biotype=protein_coding;logic_name=ensembl;transcript_id=ENST00000310998;version=1'
+  'ID=transcript:ENST00000310998;Name=C20orf125;Parent=gene:ENSG00000131044;biotype=protein_coding;logic_name=ensembl;projection_parent_transcript=ENSG_PARENT_TRANSCRIPT;transcript_id=ENST00000310998;version=1'
   );
   $expected .= "\n";
   assert_gff3($gene->canonical_transcript(), $expected, 'Transcript with custom source serialises to GFF3 as expected. Source is wibble');
@@ -206,7 +206,7 @@ OUT
   #Have to do this outside of the HERETO thanks to tabs
   $expected .= join("\t", 
     qw/20  ensembl region 30274334  30300924  . + ./,
-    'ID=gene:ENSG00000131044;Name=C20orf125;Dbxref=bibble,fibble;Ontology_term=GO:0001612;biotype=protein_coding;description=DJ310O13.1.2 (NOVEL PROTEIN SIMILAR DROSOPHILA PROTEIN CG7474%2C ISOFORM 2 ) (FRAGMENT). [Source:SPTREMBL%3BAcc:Q9BR18];gene_id=ENSG00000131044;logic_name=ensembl;version=1' 
+    'ID=gene:ENSG00000131044;Name=C20orf125;Dbxref=bibble,fibble;Ontology_term=GO:0001612;biotype=protein_coding;description=DJ310O13.1.2 (NOVEL PROTEIN SIMILAR DROSOPHILA PROTEIN CG7474%2C ISOFORM 2 ) (FRAGMENT). [Source:SPTREMBL%3BAcc:Q9BR18];gene_id=ENSG00000131044;logic_name=ensembl;projection_parent_gene=ENSG_PARENT_GENE;version=1'
   );
   $expected .= "\n";
 

modules/t/test-genome-DBs/homo_sapiens/core/attrib_type.txt

@@ -17,3 +17,5 @@
 17	codon_table	Codon Table	Alternate codon table
 18	non_ref	Non Reference	Non Reference Sequence Region
 19	karyotype_rank	Rank in the karyotype	For a given seq_region, if it is part of the species karyotype, will indicate its rank
+20	proj_parent_g	projection parent gene	Stable identifier of the parent gene this gene was projected from (projection between different species and/or assemblies).
+21	proj_parent_t	projection parent transcript	Stable identifier of the parent transcript this transcript was projected from (projection between different species and/or assemblies).

modules/t/test-genome-DBs/homo_sapiens/core/gene_attrib.txt

 18256	10	This is a note on gene 18256
 18259	10	Another note on gene 18259
+18256	20	ENSG_PARENT_GENE

modules/t/test-genome-DBs/homo_sapiens/core/transcript_attrib.txt

+21716	21	ENSG_PARENT_TRANSCRIPT