diff --git a/modules/Bio/EnsEMBL/Biotype.pm b/modules/Bio/EnsEMBL/Biotype.pm
new file mode 100644
index 0000000000000000000000000000000000000000..636b6430c0aba3fa188270ab3f6c0669910d7ca4
--- /dev/null
+++ b/modules/Bio/EnsEMBL/Biotype.pm
@@ -0,0 +1,276 @@
+=head1 LICENSE
+
+Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
+Copyright [2016-2018] EMBL-European Bioinformatics Institute
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+=cut
+
+
+=head1 CONTACT
+
+ Please email comments or questions to the public Ensembl
+ developers list at <http://lists.ensembl.org/mailman/listinfo/dev>.
+
+ Questions may also be sent to the Ensembl help desk at
+ <http://www.ensembl.org/Help/Contact>.
+
+=cut
+
+=head1 NAME
+
+Bio::EnsEMBL::Biotype
+
+=head1 SYNOPSIS
+
+ my $biotype = new Bio::EnsEMBL::Biotype(
+ -name => 'new_biotype,
+ -object_type => 'gene',
+ -biotype_group => 'a_biotype_group',
+ -so_acc => 'SO::1234567',
+ -description => 'New biotype'
+ );
+
+ my $name = $biotype->name();
+ my $biotype_group = $biotype->biotype_group();
+ my $so_acc = $biotype->so_acc();
+
+=head1 DESCRIPTION
+
+ This is the Biotype object class.
+ Gene and Transcript objects used to have a biotype() method that returned the biotype name
+ (the biotype field in the gene and transcript tables).
+ From e93 a new biotype table was added. However because of legacy code using direct sql
+ queries on the biotype column of gene and transcript tables, that column that contains the
+ biotype name was not replaced by biotype_id containing a foreign key to the new biotype table.
+ Gene and Transcripts can still link to a Biotype through the key (name, object_type).
+
+=head1 METHODS
+
+=cut
+
+
+package Bio::EnsEMBL::Biotype;
+
+use strict;
+use warnings;
+
+use Bio::EnsEMBL::Storable;
+use Bio::EnsEMBL::Utils::Exception qw(throw deprecate warning);
+use Bio::EnsEMBL::Utils::Scalar qw(check_ref assert_ref);
+use Bio::EnsEMBL::Utils::Argument qw(rearrange);
+use Scalar::Util qw(weaken isweak);
+
+use parent qw(Bio::EnsEMBL::Storable);
+
+=head2 new
+
+ Arg [-BIOTYPE_ID] :
+ int - dbID of the biotype
+ Arg [-NAME] :
+ string - the name of the biotype (for ensembl)
+ Arg [-OBJECT_TYPE] :
+ string - the object type this biotype applies to (gene or transcript)
+ Arg [-BIOTYPE_GROUP] :
+ string - the name of the biotype group (for ensembl)
+ Arg [-SO_ACC] :
+ string - the Sequence Ontology accession of this biotype
+ Arg [-DESCRIPTION] :
+ string - the biotype description
+ Arg [-DB_TYPE] :
+ string - the database type for this biotype
+ Arg [-ATTRIB_TYPE_ID] :
+ int - attrib_type_id
+
+ Example : $biotype = Bio::EnsEMBL::Biotype->new(...);
+ Description: Creates a new biotype object
+ Returntype : Bio::EnsEMBL::Biotype
+ Exceptions : none
+
+=cut
+
+sub new {
+ my ( $caller, @args ) = @_;
+
+ my $class = ref($caller) || $caller;
+
+ my $self = $class->SUPER::new();
+
+ my($dbID, $name, $object_type, $biotype_group, $so_acc, $description, $db_type, $attrib_type_id) =
+ rearrange([qw(BIOTYPE_ID NAME OBJECT_TYPE BIOTYPE_GROUP SO_ACC DESCRIPTION DB_TYPE ATTRIB_TYPE_ID)], @args);
+
+ $self->{'dbID'} = $dbID;
+ $self->{'name'} = $name;
+ $self->{'object_type'} = $object_type;
+ $self->{'biotype_group'} = $biotype_group;
+ $self->{'so_acc'} = $so_acc;
+ $self->{'description'} = $description;
+ $self->{'db_type'} = $db_type;
+ $self->{'attrib_type_id'} = $attrib_type_id;
+
+ return $self;
+}
+
+=head2 new_fast
+
+ Arg [1] : hashref to be blessed
+ Description: Construct a new Bio::EnsEMBL::Biotype using the hashref.
+ Exceptions : none
+ Returntype : Bio::EnsEMBL::Biotype
+
+=cut
+
+
+sub new_fast {
+ my ( $class, $hashref ) = @_;
+
+ my $self = bless $hashref, $class;
+
+ if ( !isweak($self->{adaptor}) ) {
+ weaken($self->{adaptor})
+ }
+
+ return $self;
+}
+
+=head2 name
+
+ Arg [1] : (optional) string $name
+ The name of this biotype according to ensembl.
+ Example : $name = $biotype->name()
+ Description: Getter/Setter for the name of this biotype.
+ Returntype : string
+ Exceptions : none
+
+=cut
+
+sub name {
+ my ( $self, $name ) = @_;
+
+ if ( defined($name) ) {
+ $self->{'name'} = $name;
+ }
+
+ return $self->{'name'};
+}
+
+=head2 biotype_group
+
+ Arg [1] : (optional) string $biotype_group
+ Example : $biotype_group = $biotype->biotype_group();
+ Description: Getter/Setter for the biotype_group of this biotype.
+ Biotype groups are used internally at ensembl pipelines
+ and consist on few defined categories.
+ Returntype : string
+ Exceptions : none
+ Caller : general
+ Status : Stable
+
+=cut
+
+sub biotype_group {
+ my ( $self, $biotype_group ) = @_;
+
+ if ( defined($biotype_group) ) {
+ $self->{'biotype_group'} = $biotype_group;
+ }
+
+ return $self->{'biotype_group'};
+}
+
+=head2 so_acc
+
+ Arg [1] : (optional) string $so_acc
+ Example : $feat->so_acc();
+ Description: Getter/Setter for the Sequence Ontology accession of this biotype.
+ It must be a SO like accession.
+ Returntype : string
+ Exceptions : thrown if an invalid so_acc argument is passed
+
+=cut
+
+sub so_acc {
+ my ( $self, $so_acc ) = @_;
+
+ if ( defined($so_acc) ) {
+ # throw an error if setting something that does not look like an SO acc
+ unless ( $so_acc =~ m/\ASO:\d+\z/x ) {
+ throw("so_acc must be a Sequence Ontology accession. '$so_acc' does not look like one.")
+ }
+
+ $self->{'so_acc'} = $so_acc;
+ }
+
+ return $self->{'so_acc'};
+}
+
+=head2 object_type
+
+ Arg [1] : (optional) string $object_type
+ Example : $object_type = $biotype->object_type();
+ Description: Getter/Setter for the object_type of this biotype.
+ Biotypes can be assigned to either genes or transcripts,
+ object_type refers to which of them.
+ Returntype : string
+ Exceptions : thrown if an invalid object_type argument is passed (not gene or transcript)
+
+=cut
+
+sub object_type {
+ my ( $self, $object_type ) = @_;
+
+ if ( defined($object_type) ) {
+ $object_type = lc $object_type;
+ # throw an error if setting something that does not look like an SO acc
+ unless ( $object_type eq 'gene' || $object_type eq 'transcript' ) {
+ throw("object_type must be gene or transcript. Got '$object_type'.")
+ }
+
+ $self->{'object_type'} = $object_type;
+ }
+
+ return $self->{'object_type'};
+}
+
+=for Rationale:
+
+ Gene and Transcript objects used to have a biotype() method that returned the string biotype name.
+ From e93 those methods were replaced and a Biotype object is now returned.
+ To maintain legacy code functioning, overload was used to return the string biotype name when
+ the object is not used as such.
+ New code should explicitly call biotype->name() if the string biotype name is what is required.
+
+=cut
+
+use overload
+ 'fallback' => 1,
+ '""' => \&as_string;
+
+=head2 as_string
+
+ Example : $biotype_str = $biotype->as_string();
+ $biotype_str = $biotype();
+ Description : Retrieves a printable string of the biotype object.
+ At the moment this is the biotype ensembl name.
+ If Biotype object is called this is what is returned to maintain compatibility
+ with legacy biotype() methods in Gene and Transcript objects.
+ Returns : string for the biotype.
+
+=cut
+
+sub as_string {
+ return shift->name;
+}
+
+1;
diff --git a/modules/Bio/EnsEMBL/DBSQL/BiotypeAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/BiotypeAdaptor.pm
new file mode 100644
index 0000000000000000000000000000000000000000..66693733fd7fbf46c4b4cb36ef986da83a44158d
--- /dev/null
+++ b/modules/Bio/EnsEMBL/DBSQL/BiotypeAdaptor.pm
@@ -0,0 +1,197 @@
+=head1 LICENSE
+
+Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
+Copyright [2016-2018] EMBL-European Bioinformatics Institute
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+
+=cut
+
+
+=head1 CONTACT
+
+ Please email comments or questions to the public Ensembl
+ developers list at <http://lists.ensembl.org/mailman/listinfo/dev>.
+
+ Questions may also be sent to the Ensembl help desk at
+ <http://www.ensembl.org/Help/Contact>.
+
+=cut
+
+=head1 NAME
+
+ Bio::EnsEMBL::DBSQL::BiotypeAdaptor - An adaptor which performs database
+ interaction relating to the storage and retrieval of Biotypes
+
+=head1 SYNOPSIS
+
+ my $biotype = $db_adaptor->fetch_by_name_object_type('protein_coding', 'gene');
+
+=head1 DESCRIPTION
+
+ This adaptor provides a means to retrieve and store information related
+ to Biotypes. Primarily this involves the retrieval or storage of
+ Bio::EnsEMBL::Biotype objects from a database.
+
+ See Bio::EnsEMBL::Biotype for details of the Biotype class.
+
+=head1 METHODS
+
+=cut
+
+package Bio::EnsEMBL::DBSQL::BiotypeAdaptor;
+
+use Bio::EnsEMBL::DBSQL::BaseAdaptor;
+use Bio::EnsEMBL::Utils::Exception qw(throw deprecate warning);
+use Bio::EnsEMBL::Biotype;
+
+use strict;
+use warnings;
+
+use parent qw(Bio::EnsEMBL::DBSQL::BaseAdaptor);
+
+=head2 _tables
+
+ Arg [1] : none
+ Description: PROTECTED implementation of superclass abstract method.
+ Returns the names, aliases of the tables to use for queries.
+ Returntype : list of arrays of strings
+ Exceptions : none
+
+=cut
+
+sub _tables {
+ my $self = shift;
+
+ return (['biotype', 'b']);
+}
+
+=head2 _columns
+
+ Arg [1] : none
+ Example : none
+ Description: PROTECTED implementation of superclass abstract method.
+ Returns a list of columns to use for queries.
+ Returntype : list of strings
+ Exceptions : none
+
+=cut
+
+sub _columns {
+ my $self = shift;
+
+ return ('b.biotype_id', 'b.name', 'b.object_type', 'b.db_type', 'b.attrib_type_id', 'b.description', 'b.biotype_group', 'b.so_acc');
+}
+
+=head2 _objs_from_sth
+
+ Arg [1] : StatementHandle $sth
+ Example : none
+ Description: PROTECTED implementation of abstract superclass method.
+ responsible for the creation of ProteinFeatures
+ Returntype : arrayref of Bio::EnsEMBL::Biotype objects
+ Exceptions : none
+
+=cut
+
+sub _objs_from_sth {
+ my ($self, $sth) = @_;
+
+ my ($dbID, $name, $object_type, $db_type, $attrib_type_id, $description, $biotype_group, $so_acc);
+
+ $sth->bind_columns(\$dbID, \$name, \$object_type, \$db_type, \$attrib_type_id, \$description, \$biotype_group, \$so_acc);
+
+ my @biotypes;
+
+ while($sth->fetch()) {
+ push( @biotypes,
+ my $feat = Bio::EnsEMBL::Biotype->new_fast( {
+ 'dbID' => $dbID,
+ 'name' => $name,
+ 'object_type' => $object_type,
+ 'db_type' => $db_type,
+ 'attrib_type_id' => $attrib_type_id,
+ 'description' => $description,
+ 'biotype_group' => $biotype_group,
+ 'so_acc' => $so_acc,
+ } )
+ );
+ }
+
+ return \@biotypes;
+}
+
+
+=head2 fetch_by_name_object_type
+
+ Arg [1] : String $name
+ The name of the biotype to retrieve
+ Arg [2] : String $object_type
+ The object type of the biotype to retrieve (gene or transcript)
+ Example : $biotype = $biotype_adaptor->fetch_by_name_object_type('gene', 'protein_coding');
+ Description: Retrieves a biotype object from the database via its combined key (name, object_type).
+ If the Biotype requested does not exist in the database, a new Biotype object is
+ created with the provided name and object_type to be returned.
+ Returntype : Bio::EnsEMBL::Biotype
+ Exceptions : none
+
+=cut
+
+sub fetch_by_name_object_type {
+ my ($self, $name, $object_type) = @_;
+
+ my $constraint = "b.name = ? AND b.object_type = ?";
+ $self->bind_param_generic_fetch($name, SQL_VARCHAR);
+ $self->bind_param_generic_fetch($object_type, SQL_VARCHAR);
+ my ($biotype) = @{$self->generic_fetch($constraint)};
+
+ # If request biotype does not exist in the table
+ # create a new biotype object containing name and object_type only
+ # this is required by genebuild in pipelines
+ if (!defined $biotype) {
+ $biotype = Bio::EnsEMBL::Biotype->new(
+ -NAME => $name,
+ -OBJECT_TYPE => $object_type,
+ )
+ }
+
+ return $biotype;
+}
+
+=head2 fetch_all_by_object_type
+
+ Arg [1] : String $object_type
+ The object_type of the biotypes to retrieve (gene or transcript).
+ Example : $biotypes = $biotype_adaptor->fetch_all_by_object_type('gene');
+ Description: Retrieves an array reference of biotype objects from the database.
+ Returntype : arrayref of Bio::EnsEMBL::Biotype objects or empty arrayref
+ Warning : If empty arrayref is to be returned
+ Exceptions : none
+
+=cut
+
+sub fetch_all_by_object_type {
+ my ($self, $object_type) = @_;
+
+ my $constraint = "b.object_type = ?";
+ $self->bind_param_generic_fetch($object_type, SQL_VARCHAR);
+ my @biotypes = @{$self->generic_fetch($constraint)};
+
+ if ( !@biotypes ) {
+ warning("No objects retrieved. Check if object_type '$object_type' is correct.")
+ }
+
+ return \@biotypes;
+}
+
+1;
\ No newline at end of file
diff --git a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
index 8396036e4b0ce04598967d72ae74773c4fd1b722..62000866518c51392f6c4d5c6c5ce559da7b2193 100755
--- a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
@@ -402,6 +402,7 @@ sub get_available_adaptors {
AssemblyMapper => 'Bio::EnsEMBL::DBSQL::AssemblyMapperAdaptor',
AssemblySlice => 'Bio::EnsEMBL::DBSQL::AssemblySliceAdaptor',
Attribute => 'Bio::EnsEMBL::DBSQL::AttributeAdaptor',
+ Biotype => 'Bio::EnsEMBL::DBSQL::BiotypeAdaptor',
CoordSystem => 'Bio::EnsEMBL::DBSQL::CoordSystemAdaptor',
DataFile => 'Bio::EnsEMBL::DBSQL::DataFileAdaptor',
DBEntry => 'Bio::EnsEMBL::DBSQL::DBEntryAdaptor',
@@ -518,7 +519,7 @@ sub _each_DASFeatureFactory{
features to be obtained from Slices and from RawContigs.
The external feature adaptor which is passed to this method
- will have its db attribuite set to this DBAdaptor object via
+ will have its db attribute set to this DBAdaptor object via
the db accessor method.
ExternalFeatureAdaptors passed to this method are stored
@@ -636,7 +637,7 @@ sub add_ExternalFeatureFactory{
Caller : external
Status : Medium Risk
: please use the Registry method, as at some time this
- : may no longer be supprted.
+ : may no longer be supported.
=cut
@@ -660,7 +661,7 @@ sub get_adaptor {
Caller : external
Status : Medium Risk
: please use the Registry method, as at some time this
- : may no longer be supprted.
+ : may no longer be supported.
=cut
@@ -1068,7 +1069,7 @@ sub switch_adaptor {
Arg [1] : String name of the adaptor type to switch back in
Example : $dba->has_switchable_adaptor("sequence"); #explicit switching back
- Returntype : Boolean indicating if the given adaptor is being activly switched
+ Returntype : Boolean indicating if the given adaptor is being actively switched
Description : Provides a wrapper around the Registry has_switchable_adaptor() method
defaulting both species and group to the current DBAdaptor. This will
inform if the specified adaptor is being switched out
diff --git a/modules/Bio/EnsEMBL/Gene.pm b/modules/Bio/EnsEMBL/Gene.pm
index eba0228adde96299805182534b5d0a071ef92bd6..17045ec1a40f6336a3211c8d5b7a9f44295acf75 100755
--- a/modules/Bio/EnsEMBL/Gene.pm
+++ b/modules/Bio/EnsEMBL/Gene.pm
@@ -66,12 +66,12 @@ use strict;
use POSIX;
use Bio::EnsEMBL::Feature;
use Bio::EnsEMBL::Intron;
+use Bio::EnsEMBL::Biotype;
use Bio::EnsEMBL::Utils::Argument qw(rearrange);
use Bio::EnsEMBL::Utils::Exception qw(throw warning);
use Bio::EnsEMBL::Utils::Scalar qw(assert_ref);
-use vars qw(@ISA);
-@ISA = qw(Bio::EnsEMBL::Feature);
+use parent qw(Bio::EnsEMBL::Feature);
=head2 new
@@ -171,8 +171,9 @@ sub new {
$self->external_status($external_status)
if ( defined $external_status );
$self->display_xref($display_xref) if ( defined $display_xref );
- $self->biotype($type) if ( defined $type );
- $self->biotype($biotype) if ( defined $biotype );
+
+ $self->{'biotype'} = $biotype || $type;
+
$self->description($description);
$self->source($source);
@@ -896,27 +897,6 @@ sub _clear_homologues {
delete $self->{homologues};
}
-
-=head2 biotype
-
- Arg [1] : (optional) String - the biotype to set
- Example : $gene->biotype("protein_coding");
- Description: Getter/setter for the attribute biotype
- Returntype : String
- Exceptions : none
- Caller : general
- Status : Stable
-
-=cut
-
-sub biotype {
- my $self = shift;
-
- $self->{'biotype'} = shift if( @_ );
- return ( $self->{'biotype'} || "protein_coding" );
-}
-
-
=head2 add_Transcript
Arg [1] : Bio::EnsEMBL::Transcript $trans
@@ -1521,6 +1501,50 @@ sub havana_gene {
return $ott;
}
+=head2 biotype
-1;
+ Arg [1] : Arg [1] : (optional) String - the biotype to set
+ Example : my $biotype = $gene->biotype;
+ my $biotype = $gene->biotype('protin_coding');
+ Description: Returns the Biotype object of this gene.
+ When no biotype exists, defaults to 'protein_coding'.
+ When used to set to a biotype that does not exist in
+ the biotype table, a biotype object is created with
+ the provided argument as name and object_type gene.
+ Returntype : Bio::EnsEMBL::Biotype
+ Exceptions : none
+
+=cut
+
+sub biotype {
+ my ( $self, $new_value) = @_;
+
+ # have a biotype object and not setting new one, return it
+ if ( ref $self->{'biotype'} eq 'Bio::EnsEMBL::Biotype' && !defined $new_value ) {
+ return $self->{'biotype'};
+ }
+ # biotype is first set as a string retrieved from the gene table
+ # there is no biotype object in the gene object, retrieve it using the biotype string
+ # if no string, default to protein_coding. this is legacy behaviour and should probably be revisited
+ if ( ref $self->{'biotype'} ne 'Bio::EnsEMBL::Biotype' && !defined $new_value) {
+ $new_value = $self->{'biotype'} // 'protein_coding';
+ }
+
+ # retrieve biotype object from the biotype adaptor
+ if( defined $self->adaptor() ) {
+ my $ba = $self->adaptor()->db()->get_BiotypeAdaptor();
+ $self->{'biotype'} = $ba->fetch_by_name_object_type( $new_value, 'gene' );
+ }
+ # if $self->adaptor is unavailable, create a new biotype object containing name and object_type only
+ else {
+ $self->{'biotype'} = Bio::EnsEMBL::Biotype->new(
+ -NAME => $new_value,
+ -OBJECT_TYPE => 'gene',
+ )
+ }
+
+ return $self->{'biotype'} ;
+}
+
+1;
diff --git a/modules/Bio/EnsEMBL/Transcript.pm b/modules/Bio/EnsEMBL/Transcript.pm
index 31b33e8d06a36c861257199fd400b2e39c15b846..c9fdc5c466d5ae310915a6c6eb725d92260a2524 100755
--- a/modules/Bio/EnsEMBL/Transcript.pm
+++ b/modules/Bio/EnsEMBL/Transcript.pm
@@ -70,13 +70,12 @@ use Bio::EnsEMBL::ExonTranscript;
use Bio::EnsEMBL::CDS;
use Bio::EnsEMBL::TranscriptMapper;
use Bio::EnsEMBL::SeqEdit;
-
+use Bio::EnsEMBL::Biotype;
use Bio::EnsEMBL::Utils::Argument qw( rearrange );
use Bio::EnsEMBL::Utils::Exception qw(warning throw );
use Bio::EnsEMBL::Utils::Scalar qw( assert_ref );
-use vars qw(@ISA);
-@ISA = qw(Bio::EnsEMBL::Feature);
+use parent qw(Bio::EnsEMBL::Feature);
=head2 new
@@ -172,7 +171,9 @@ sub new {
$self->edits_enabled(1);
$self->description($description);
- $self->biotype($biotype);
+
+ $self->{'biotype'} = $biotype;
+
$self->source($source);
# Default version
@@ -597,24 +598,6 @@ sub external_name {
}
}
-
-=head2 biotype
-
- Arg [1] : string $biotype
- Description: get/set for attribute biotype
- Returntype : string
- Exceptions : none
- Caller : general
- Status : Stable
-
-=cut
-
-sub biotype {
- my $self = shift;
- $self->{'biotype'} = shift if( @_ );
- return ( $self->{'biotype'} || "protein_coding" );
-}
-
=head2 source
Arg [1] : (optional) String - the source to set
@@ -3212,6 +3195,52 @@ sub get_Gene {
return $parent_gene;
}
+=head2 biotype
+
+ Arg [1] : Arg [1] : (optional) String - the biotype to set
+ Example : my $biotype = $transcript->biotype;
+ my $biotype = $transcript->biotype('protin_coding');
+ Description: Returns the Biotype object of this transcript.
+ When no biotype exists, defaults to 'protein_coding'.
+ When used to set to a biotype that does not exist in
+ the biotype table, a biotype object is created with
+ the provided argument as name and object_type transcript.
+ Returntype : Bio::EnsEMBL::Biotype
+ Exceptions : none
+
+=cut
+
+sub biotype {
+ my ( $self, $new_value) = @_;
+
+ # have a biotype object and not setting new one, return it
+ if ( ref $self->{'biotype'} eq 'Bio::EnsEMBL::Biotype' && !defined $new_value ) {
+ return $self->{'biotype'};
+ }
+
+ # biotype is first set as a string retrieved from the transcript table
+ # there is no biotype object in the transcript object, retrieve it using the biotype string
+ # if no string, default to protein_coding. this is legacy behaviour and should probably be revisited
+ if ( ref $self->{'biotype'} ne 'Bio::EnsEMBL::Biotype' && !defined $new_value) {
+ $new_value = $self->{'biotype'} // 'protein_coding';
+ }
+
+ # retrieve biotype object from the biotype adaptor
+ if( defined $self->adaptor() ) {
+ my $ba = $self->adaptor()->db()->get_BiotypeAdaptor();
+ $self->{'biotype'} = $ba->fetch_by_name_object_type( $new_value, 'transcript' );
+ }
+ # if $self->adaptor is unavailable, create a new biotype object containing name and object_type only
+ else {
+ $self->{'biotype'} = Bio::EnsEMBL::Biotype->new(
+ -NAME => $new_value,
+ -OBJECT_TYPE => 'transcript',
+ )
+ }
+
+ return $self->{'biotype'} ;
+}
+
1;
diff --git a/modules/Bio/EnsEMBL/Utils/SequenceOntologyMapper.pm b/modules/Bio/EnsEMBL/Utils/SequenceOntologyMapper.pm
index aa8d1cfc0b7805bd8ce4ae7a9d549fbe499b5fb1..f1dd02faedf526a4b2983845e5e2e59e336b3759 100644
--- a/modules/Bio/EnsEMBL/Utils/SequenceOntologyMapper.pm
+++ b/modules/Bio/EnsEMBL/Utils/SequenceOntologyMapper.pm
@@ -28,7 +28,7 @@ SequenceOntologyMapper - Translates EnsEMBL objects into Sequence Ontology terms
use Bio::EnsEMBL::Utils::SequenceOntologyMapper
-# get an Ensembl feature somehow in scalar $feature
+# get an Ensembl feature somehow in scalar $feature
...
...
@@ -40,9 +40,14 @@ print $mapper->to_name($feature), "\n";
=head1 DESCRIPTION
-Basic mapper from Ensembl feature or related objects to Sequence Ontology
+Basic mapper from Ensembl feature or related objects to Sequence Ontology
(http://www.sequenceontology.org) terms.
+Gene and Transcript objects contain a biotype() that will return a Biotype object.
+This object contains several methods, including so_acc() that provides the
+corresponding SO accession. It is thus recommended to use the Biotype object
+if dealing with Gene or Transcript objects.
+
The interface allows to map to SO accessions and names.
=cut
@@ -55,206 +60,205 @@ use warnings;
use Bio::EnsEMBL::Utils::Cache;
use Bio::EnsEMBL::Utils::Exception;
-my %gene_so_mapping =
+my %gene_so_mapping =
(
# Protein coding gene biotype
- 'protein_coding' => 'SO:0001217',
- 'IG_C_gene' => 'SO:0001217',
- 'IG_D_gene' => 'SO:0001217',
- 'IG_gene' => 'SO:0001217',
- 'IG_J_gene' => 'SO:0001217',
- 'IG_LV_gene' => 'SO:0001217',
- 'IG_M_gene' => 'SO:0001217',
- 'IG_V_gene' => 'SO:0001217',
- 'IG_Z_gene' => 'SO:0001217',
- 'mRNA' => 'SO:0001217',
- 'nontranslating_CDS' => 'SO:0001217',
- 'polymorphic' => 'SO:0001217',
- 'polymorphic_pseudogene' => 'SO:0001217',
- 'TR_C_gene' => 'SO:0001217',
- 'TR_D_gene' => 'SO:0001217',
- 'TR_gene' => 'SO:0001217',
- 'TR_J_gene' => 'SO:0001217',
- 'TR_V_gene' => 'SO:0001217',
-
+ 'protein_coding' => 'SO:0001217',
+ 'IG_C_gene' => 'SO:0001217',
+ 'IG_D_gene' => 'SO:0001217',
+ 'IG_gene' => 'SO:0001217',
+ 'IG_J_gene' => 'SO:0001217',
+ 'IG_LV_gene' => 'SO:0001217',
+ 'IG_M_gene' => 'SO:0001217',
+ 'IG_V_gene' => 'SO:0001217',
+ 'IG_Z_gene' => 'SO:0001217',
+ 'mRNA' => 'SO:0001217',
+ 'nontranslating_CDS' => 'SO:0001217',
+ 'polymorphic' => 'SO:0001217',
+ 'polymorphic_pseudogene' => 'SO:0001217',
+ 'TR_C_gene' => 'SO:0001217',
+ 'TR_D_gene' => 'SO:0001217',
+ 'TR_gene' => 'SO:0001217',
+ 'TR_J_gene' => 'SO:0001217',
+ 'TR_V_gene' => 'SO:0001217',
+
# Pseudogene biotype
- 'IG_C_pseudogene' => 'SO:0000336',
- 'IG_D_pseudogene' => 'SO:0000336',
- 'IG_J_pseudogene' => 'SO:0000336',
- 'IG_pseudogene' => 'SO:0000336',
- 'IG_V_pseudogene' => 'SO:0000336',
- 'miRNA_pseudogene' => 'SO:0000336',
- 'misc_RNA_pseudogene' => 'SO:0000336',
- 'Mt_tRNA_pseudogene' => 'SO:0000336',
- 'ncbi_pseudogene' => 'SO:0000336',
- 'ncRNA_pseudogene' => 'SO:0000336',
- 'processed_pseudogene' => 'SO:0000336',
- 'pseudogene' => 'SO:0000336',
- 'rRNA_pseudogene' => 'SO:0000336',
- 'scRNA_pseudogene' => 'SO:0000336',
- 'snoRNA_pseudogene' => 'SO:0000336',
- 'snRNA_pseudogene' => 'SO:0000336',
- 'transcribed_processed_pseudogene' => 'SO:0000336',
- 'transcribed_unitary_pseudogene' => 'SO:0000336',
+ 'IG_C_pseudogene' => 'SO:0000336',
+ 'IG_D_pseudogene' => 'SO:0000336',
+ 'IG_J_pseudogene' => 'SO:0000336',
+ 'IG_pseudogene' => 'SO:0000336',
+ 'IG_V_pseudogene' => 'SO:0000336',
+ 'miRNA_pseudogene' => 'SO:0000336',
+ 'misc_RNA_pseudogene' => 'SO:0000336',
+ 'Mt_tRNA_pseudogene' => 'SO:0000336',
+ 'ncbi_pseudogene' => 'SO:0000336',
+ 'ncRNA_pseudogene' => 'SO:0000336',
+ 'processed_pseudogene' => 'SO:0000336',
+ 'pseudogene' => 'SO:0000336',
+ 'rRNA_pseudogene' => 'SO:0000336',
+ 'scRNA_pseudogene' => 'SO:0000336',
+ 'snoRNA_pseudogene' => 'SO:0000336',
+ 'snRNA_pseudogene' => 'SO:0000336',
+ 'transcribed_processed_pseudogene' => 'SO:0000336',
+ 'transcribed_unitary_pseudogene' => 'SO:0000336',
'transcribed_unprocessed_pseudogene' => 'SO:0000336',
- 'translated_processed_pseudogene' => 'SO:0000336',
- 'translated_unprocessed_pseudogene' => 'SO:0000336',
- 'tRNA_pseudogene' => 'SO:0000336',
- 'TR_J_pseudogene' => 'SO:0000336',
- 'TR_pseudogene' => 'SO:0000336',
- 'TR_V_pseudogene' => 'SO:0000336',
- 'unitary_pseudogene' => 'SO:0000336',
- 'unprocessed_pseudogene' => 'SO:0000336',
+ 'translated_processed_pseudogene' => 'SO:0000336',
+ 'translated_unprocessed_pseudogene' => 'SO:0000336',
+ 'tRNA_pseudogene' => 'SO:0000336',
+ 'TR_J_pseudogene' => 'SO:0000336',
+ 'TR_pseudogene' => 'SO:0000336',
+ 'TR_V_pseudogene' => 'SO:0000336',
+ 'unitary_pseudogene' => 'SO:0000336',
+ 'unprocessed_pseudogene' => 'SO:0000336',
# ncRNA gene biotypes
- '3prime_overlapping_ncrna' => 'SO:0001263',
- 'ambiguous_orf' => 'SO:0001263',
- 'antisense' => 'SO:0001263',
- 'antisense_RNA' => 'SO:0001263',
- 'antitoxin' => 'SO:0001263',
- 'bidirectional_promoter_lncrna' => 'SO:0001263',
- 'class_II_RNA' => 'SO:0001263',
- 'class_I_RNA' => 'SO:0001263',
- 'CRISPR' => 'SO:0001263',
- 'guide_RNA' => 'SO:0001263',
- 'known_ncrna' => 'SO:0001263',
- 'lincRNA' => 'SO:0001263',
- 'lncRNA' => 'SO:0001263',
- 'macro_lncRNA' => 'SO:0001263',
- 'miRNA' => 'SO:0001263',
- 'misc_RNA' => 'SO:0001263',
- 'Mt_rRNA' => 'SO:0001263',
- 'Mt_tRNA' => 'SO:0001263',
- 'ncRNA' => 'SO:0001263',
- 'ncrna_host' => 'SO:0001263',
- 'non_coding' => 'SO:0001263',
- 'piRNA' => 'SO:0001263',
- 'pre_miRNA' => 'SO:0001263',
- 'processed_transcript' => 'SO:0001263',
- 'retained_intron' => 'SO:0001263',
- 'ribozyme' => 'SO:0001263',
- 'RNase_MRP_RNA' => 'SO:0001263',
- 'RNase_P_RNA' => 'SO:0001263',
- 'rRNA' => 'SO:0001263',
- 'scaRNA' => 'SO:0001263',
- 'scRNA' => 'SO:0001263',
- 'sense_intronic' => 'SO:0001263',
- 'sense_overlapping' => 'SO:0001263',
- 'snlRNA' => 'SO:0001263',
- 'snoRNA' => 'SO:0001263',
- 'snRNA' => 'SO:0001263',
- 'sRNA' => 'SO:0001263',
- 'SRP_RNA' => 'SO:0001263',
- 'telomerase_RNA' => 'SO:0001263',
- 'tmRNA' => 'SO:0001263',
- 'tRNA' => 'SO:0001263',
- 'vaultRNA' => 'SO:0001263',
- 'Y_RNA' => 'SO:0001263'
+ '3prime_overlapping_ncrna' => 'SO:0001263',
+ 'ambiguous_orf' => 'SO:0001263',
+ 'antisense' => 'SO:0001263',
+ 'antisense_RNA' => 'SO:0001263',
+ 'antitoxin' => 'SO:0001263',
+ 'bidirectional_promoter_lncrna' => 'SO:0001263',
+ 'class_II_RNA' => 'SO:0001263',
+ 'class_I_RNA' => 'SO:0001263',
+ 'CRISPR' => 'SO:0001263',
+ 'guide_RNA' => 'SO:0001263',
+ 'known_ncrna' => 'SO:0001263',
+ 'lincRNA' => 'SO:0001263',
+ 'lncRNA' => 'SO:0001263',
+ 'macro_lncRNA' => 'SO:0001263',
+ 'miRNA' => 'SO:0001263',
+ 'misc_RNA' => 'SO:0001263',
+ 'Mt_rRNA' => 'SO:0001263',
+ 'Mt_tRNA' => 'SO:0001263',
+ 'ncRNA' => 'SO:0001263',
+ 'ncrna_host' => 'SO:0001263',
+ 'non_coding' => 'SO:0001263',
+ 'piRNA' => 'SO:0001263',
+ 'pre_miRNA' => 'SO:0001263',
+ 'processed_transcript' => 'SO:0001263',
+ 'retained_intron' => 'SO:0001263',
+ 'ribozyme' => 'SO:0001263',
+ 'RNase_MRP_RNA' => 'SO:0001263',
+ 'RNase_P_RNA' => 'SO:0001263',
+ 'rRNA' => 'SO:0001263',
+ 'scaRNA' => 'SO:0001263',
+ 'scRNA' => 'SO:0001263',
+ 'sense_intronic' => 'SO:0001263',
+ 'sense_overlapping' => 'SO:0001263',
+ 'snlRNA' => 'SO:0001263',
+ 'snoRNA' => 'SO:0001263',
+ 'snRNA' => 'SO:0001263',
+ 'sRNA' => 'SO:0001263',
+ 'SRP_RNA' => 'SO:0001263',
+ 'telomerase_RNA' => 'SO:0001263',
+ 'tmRNA' => 'SO:0001263',
+ 'tRNA' => 'SO:0001263',
+ 'vaultRNA' => 'SO:0001263',
+ 'Y_RNA' => 'SO:0001263'
);
-my %transcript_so_mapping =
+my %transcript_so_mapping =
(
# mRNA biotypes
- 'protein_coding' => 'SO:0000234',
- 'mRNA' => 'SO:0000234',
- 'nonsense_mediated_decay' => 'SO:0000234',
- 'nontranslating_CDS' => 'SO:0000234',
- 'non_stop_decay' => 'SO:0000234',
- 'polymorphic_pseudogene' => 'SO:0000234',
-
+ 'protein_coding' => 'SO:0000234',
+ 'mRNA' => 'SO:0000234',
+ 'nonsense_mediated_decay' => 'SO:0000234',
+ 'nontranslating_CDS' => 'SO:0000234',
+ 'non_stop_decay' => 'SO:0000234',
+ 'polymorphic_pseudogene' => 'SO:0000234',
+
# IG biotypes (SO:3000000 gene_segment)
- 'IG_C_gene' => 'SO:0000478', # C_gene_segment
- 'TR_C_gene' => 'SO:0000478', # C_gene_segment
- 'IG_D_gene' => 'SO:0000458', # D_gene_segment
- 'TR_D_gene' => 'SO:0000458', # D_gene_segment
- 'IG_gene' => 'SO:3000000', # gene_segment
- 'TR_gene' => 'SO:3000000', # gene_segment
- 'IG_J_gene' => 'SO:0000470', # J_gene_segment
- 'TR_J_gene' => 'SO:0000470', # J_gene_segment
- 'IG_LV_gene' => 'SO:3000000', # gene_segment
- 'IG_M_gene' => 'SO:3000000', # gene_segment
- 'IG_V_gene' => 'SO:0000466', # V_gene_segment
- 'TR_V_gene' => 'SO:0000466', # V_gene_segment
- 'IG_Z_gene' => 'SO:3000000', # gene_segment
+ 'IG_C_gene' => 'SO:0000478', # C_gene_segment
+ 'TR_C_gene' => 'SO:0000478', # C_gene_segment
+ 'IG_D_gene' => 'SO:0000458', # D_gene_segment
+ 'TR_D_gene' => 'SO:0000458', # D_gene_segment
+ 'IG_gene' => 'SO:3000000', # gene_segment
+ 'TR_gene' => 'SO:3000000', # gene_segment
+ 'IG_J_gene' => 'SO:0000470', # J_gene_segment
+ 'TR_J_gene' => 'SO:0000470', # J_gene_segment
+ 'IG_LV_gene' => 'SO:3000000', # gene_segment
+ 'IG_M_gene' => 'SO:3000000', # gene_segment
+ 'IG_V_gene' => 'SO:0000466', # V_gene_segment
+ 'TR_V_gene' => 'SO:0000466', # V_gene_segment
+ 'IG_Z_gene' => 'SO:3000000', # gene_segment
# Pseudogenic_transcript biotypes
- 'pseudogene' => 'SO:0000516',
- 'disrupted_domain' => 'SO:0000516',
- 'IG_C_pseudogene' => 'SO:0000516',
- 'IG_D_pseudogene' => 'SO:0000516',
- 'IG_J_pseudogene' => 'SO:0000516',
- 'IG_pseudogene' => 'SO:0000516',
- 'IG_V_pseudogene' => 'SO:0000516',
- 'miRNA_pseudogene' => 'SO:0000516',
- 'misc_RNA_pseudogene' => 'SO:0000516',
- 'Mt_tRNA_pseudogene' => 'SO:0000516',
- 'ncbi_pseudogene' => 'SO:0000516',
- 'ncRNA_pseudogene' => 'SO:0000516',
- 'processed_pseudogene' => 'SO:0000516',
- 'rRNA_pseudogene' => 'SO:0000516',
- 'scRNA_pseudogene' => 'SO:0000516',
- 'snoRNA_pseudogene' => 'SO:0000516',
- 'snRNA_pseudogene' => 'SO:0000516',
- 'transcribed_processed_pseudogene' => 'SO:0000516',
- 'transcribed_unitary_pseudogene' => 'SO:0000516',
- 'transcribed_unprocessed_pseudogene' => 'SO:0000516',
- 'translated_processed_pseudogene' => 'SO:0000516',
- 'translated_unprocessed_pseudogene' => 'SO:0000516',
- 'tRNA_pseudogene' => 'SO:0000516',
- 'TR_J_pseudogene' => 'SO:0000516',
- 'TR_pseudogene' => 'SO:0000516',
- 'TR_V_pseudogene' => 'SO:0000516',
- 'unitary_pseudogene' => 'SO:0000516',
- 'unprocessed_pseudogene' => 'SO:0000516',
+ 'pseudogene' => 'SO:0000516',
+ 'disrupted_domain' => 'SO:0000516',
+ 'IG_C_pseudogene' => 'SO:0000516',
+ 'IG_D_pseudogene' => 'SO:0000516',
+ 'IG_J_pseudogene' => 'SO:0000516',
+ 'IG_pseudogene' => 'SO:0000516',
+ 'IG_V_pseudogene' => 'SO:0000516',
+ 'miRNA_pseudogene' => 'SO:0000516',
+ 'misc_RNA_pseudogene' => 'SO:0000516',
+ 'Mt_tRNA_pseudogene' => 'SO:0000516',
+ 'ncbi_pseudogene' => 'SO:0000516',
+ 'ncRNA_pseudogene' => 'SO:0000516',
+ 'processed_pseudogene' => 'SO:0000516',
+ 'rRNA_pseudogene' => 'SO:0000516',
+ 'scRNA_pseudogene' => 'SO:0000516',
+ 'snoRNA_pseudogene' => 'SO:0000516',
+ 'snRNA_pseudogene' => 'SO:0000516',
+ 'transcribed_processed_pseudogene' => 'SO:0000516',
+ 'transcribed_unitary_pseudogene' => 'SO:0000516',
+ 'transcribed_unprocessed_pseudogene' => 'SO:0000516',
+ 'translated_processed_pseudogene' => 'SO:0000516',
+ 'translated_unprocessed_pseudogene' => 'SO:0000516',
+ 'tRNA_pseudogene' => 'SO:0000516',
+ 'TR_J_pseudogene' => 'SO:0000516',
+ 'TR_pseudogene' => 'SO:0000516',
+ 'TR_V_pseudogene' => 'SO:0000516',
+ 'unitary_pseudogene' => 'SO:0000516',
+ 'unprocessed_pseudogene' => 'SO:0000516',
# ncRNA transcript biotypes
## Long non coding RNAs
- '3prime_overlapping_ncrna' => 'SO:0001877',
- 'ambiguous_orf' => 'SO:0001877',
- 'antisense' => 'SO:0001877',
- 'antisense_RNA' => 'SO:0001877',
- 'antitoxin' => 'SO:0001877',
- 'bidirectional_promoter_lncrna' => 'SO:0001877',
- 'lincRNA' => 'SO:0001877',
- 'macro_lncRNA' => 'SO:0001877',
- 'ncrna_host' => 'SO:0001877',
- 'non_coding' => 'SO:0001877',
- 'processed_transcript' => 'SO:0001877',
- 'retained_intron' => 'SO:0001877',
- 'ribozyme' => 'SO:0001877',
- 'sense_intronic' => 'SO:0001877',
- 'sense_overlapping' => 'SO:0001877',
-
+ '3prime_overlapping_ncrna' => 'SO:0001877',
+ 'ambiguous_orf' => 'SO:0001877',
+ 'antisense' => 'SO:0001877',
+ 'antisense_RNA' => 'SO:0001877',
+ 'antitoxin' => 'SO:0001877',
+ 'bidirectional_promoter_lncrna' => 'SO:0001877',
+ 'lincRNA' => 'SO:0001877',
+ 'macro_lncRNA' => 'SO:0001877',
+ 'ncrna_host' => 'SO:0001877',
+ 'non_coding' => 'SO:0001877',
+ 'processed_transcript' => 'SO:0001877',
+ 'retained_intron' => 'SO:0001877',
+ 'ribozyme' => 'SO:0001877',
+ 'sense_intronic' => 'SO:0001877',
+ 'sense_overlapping' => 'SO:0001877',
+
## Short non coding RNAs
- 'class_II_RNA' => 'SO:0000989', # class_II_RNA
- 'class_I_RNA' => 'SO:0000990', # class_I_RNA
- 'guide_RNA' => 'SO:0000602', # guide_RNA
- 'miRNA' => 'SO:0000276', # miRNA
- 'known_ncRNA' => 'SO:0000655', # ncRNA
- 'misc_RNA' => 'SO:0000655', # ncRNA
- 'ncRNA' => 'SO:0000655', # ncRNA
- 'piRNA' => 'SO:0001035', # piRNA
- 'pre_miRNA' => 'SO:0001244', # pre_miRNA
- 'RNase_MRP_RNA' => 'SO:0000385', # RNase_MRP_RNA
- 'RNase_P_RNA' => 'SO:0000386', # RNase_P_RNA
- 'rRNA' => 'SO:0000252', # rRNA
- 'Mt_rRNA' => 'SO:0000252', # rRNA
- 'scaRNA' => 'SO:0000013', # scRNA
- 'scRNA' => 'SO:0000013', # scRNA
- 'snoRNA' => 'SO:0000275', # snoRNA
- 'sRNA' => 'SO:0000274', # snRNA
- 'snlRNA' => 'SO:0000274', # snRNA
- 'snRNA' => 'SO:0000274', # snRNA
- 'SRP_RNA' => 'SO:0000590', # SRP_RNA
- 'telomerase_RNA' => 'SO:0000390', # telomerase_RNA
- 'tmRNA' => 'SO:0000584', # tmRNA
- 'tRNA' => 'SO:0000253', # tRNA
- 'Mt_tRNA' => 'SO:0000253', # tRNA
- 'vaultRNA' => 'SO:0002040', # vaultRNA_primary_transcript
- 'vault_RNA' => 'SO:0002040', # vaultRNA_primary_transcript
- 'Y_RNA' => 'SO:0000405', # Y_RNA
-
+ 'class_II_RNA' => 'SO:0000989', # class_II_RNA
+ 'class_I_RNA' => 'SO:0000990', # class_I_RNA
+ 'guide_RNA' => 'SO:0000602', # guide_RNA
+ 'miRNA' => 'SO:0000276', # miRNA
+ 'known_ncRNA' => 'SO:0000655', # ncRNA
+ 'misc_RNA' => 'SO:0000655', # ncRNA
+ 'ncRNA' => 'SO:0000655', # ncRNA
+ 'piRNA' => 'SO:0001035', # piRNA
+ 'pre_miRNA' => 'SO:0001244', # pre_miRNA
+ 'RNase_MRP_RNA' => 'SO:0000385', # RNase_MRP_RNA
+ 'RNase_P_RNA' => 'SO:0000386', # RNase_P_RNA
+ 'rRNA' => 'SO:0000252', # rRNA
+ 'Mt_rRNA' => 'SO:0000252', # rRNA
+ 'scaRNA' => 'SO:0000013', # scRNA
+ 'scRNA' => 'SO:0000013', # scRNA
+ 'snoRNA' => 'SO:0000275', # snoRNA
+ 'sRNA' => 'SO:0000274', # snRNA
+ 'snlRNA' => 'SO:0000274', # snRNA
+ 'snRNA' => 'SO:0000274', # snRNA
+ 'SRP_RNA' => 'SO:0000590', # SRP_RNA
+ 'telomerase_RNA' => 'SO:0000390', # telomerase_RNA
+ 'tmRNA' => 'SO:0000584', # tmRNA
+ 'tRNA' => 'SO:0000253', # tRNA
+ 'Mt_tRNA' => 'SO:0000253', # tRNA
+ 'vaultRNA' => 'SO:0002040', # vaultRNA_primary_transcript
+ 'vault_RNA' => 'SO:0002040', # vaultRNA_primary_transcript
+ 'Y_RNA' => 'SO:0000405', # Y_RNA
);
my %utr_so_mapping =
@@ -272,28 +276,28 @@ my %region_so_mapping =
'contig' => 'SO:0000149' # contig
);
-my %feature_so_mapping =
+my %feature_so_mapping =
(
- 'Bio::EnsEMBL::Feature' => 'SO:0000001', # region
- 'Bio::EnsEMBL::Gene' => 'SO:0000704', # gene
- 'Bio::EnsEMBL::Transcript' => 'SO:0000673', # transcript
- 'Bio::EnsEMBL::PredictionTranscript' => 'SO:0000673', # transcript
- 'Bio::EnsEMBL::Exon' => 'SO:0000147', # exon
- 'Bio::EnsEMBL::PredictionExon' => 'SO:0000147', # exon
- 'Bio::EnsEMBL::UTR' => 'SO:0000203', # UTR
- 'Bio::EnsEMBL::ExonTranscript' => 'SO:0000147', # Exon
- 'Bio::EnsEMBL::CDS' => 'SO:0000316', # CDS
- 'Bio::EnsEMBL::Slice' => 'SO:0000001', # region
- 'Bio::EnsEMBL::SimpleFeature' => 'SO:0001411', # biological_region
- 'Bio::EnsEMBL::MiscFeature' => 'SO:0001411', # biological_region
- 'Bio::EnsEMBL::RepeatFeature' => 'SO:0000657', # repeat region
- 'Bio::EnsEMBL::Variation::VariationFeature' => 'SO:0001060', # sequence variant
+ 'Bio::EnsEMBL::Feature' => 'SO:0000001', # region
+ 'Bio::EnsEMBL::Gene' => 'SO:0000704', # gene
+ 'Bio::EnsEMBL::Transcript' => 'SO:0000673', # transcript
+ 'Bio::EnsEMBL::PredictionTranscript' => 'SO:0000673', # transcript
+ 'Bio::EnsEMBL::Exon' => 'SO:0000147', # exon
+ 'Bio::EnsEMBL::PredictionExon' => 'SO:0000147', # exon
+ 'Bio::EnsEMBL::UTR' => 'SO:0000203', # UTR
+ 'Bio::EnsEMBL::ExonTranscript' => 'SO:0000147', # Exon
+ 'Bio::EnsEMBL::CDS' => 'SO:0000316', # CDS
+ 'Bio::EnsEMBL::Slice' => 'SO:0000001', # region
+ 'Bio::EnsEMBL::SimpleFeature' => 'SO:0001411', # biological_region
+ 'Bio::EnsEMBL::MiscFeature' => 'SO:0001411', # biological_region
+ 'Bio::EnsEMBL::RepeatFeature' => 'SO:0000657', # repeat region
+ 'Bio::EnsEMBL::Variation::VariationFeature' => 'SO:0001060', # sequence variant
'Bio::EnsEMBL::Variation::StructuralVariationFeature' => 'SO:0001537', # structural variant
- 'Bio::EnsEMBL::Compara::ConstrainedElement' => 'SO:0001009', #DNA_constraint_sequence ????
- 'Bio::EnsEMBL::Funcgen::RegulatoryFeature' => 'SO:0005836', # regulatory_region
- 'Bio::EnsEMBL::DnaDnaAlignFeature' => 'SO:0000347', # nucleotide_match
- 'Bio::EnsEMBL::DnaPepAlignFeature' => 'SO:0000349', # protein_match
- 'Bio::EnsEMBL::KaryotypeBand' => 'SO:0000341', # chromosome_band
+ 'Bio::EnsEMBL::Compara::ConstrainedElement' => 'SO:0001009', #DNA_constraint_sequence ????
+ 'Bio::EnsEMBL::Funcgen::RegulatoryFeature' => 'SO:0005836', # regulatory_region
+ 'Bio::EnsEMBL::DnaDnaAlignFeature' => 'SO:0000347', # nucleotide_match
+ 'Bio::EnsEMBL::DnaPepAlignFeature' => 'SO:0000349', # protein_match
+ 'Bio::EnsEMBL::KaryotypeBand' => 'SO:0000341', # chromosome_band
);
@@ -312,8 +316,8 @@ sub new {
my ($class, $oa) = @_;
defined $oa or throw "No ontology term adaptor specified";
- my $self =
- {
+ my $self =
+ {
ontology_adaptor => $oa,
feat_to_acc => \%feature_so_mapping,
gene_to_acc => \%gene_so_mapping,
@@ -321,8 +325,8 @@ sub new {
region_to_acc => \%region_so_mapping,
tran_to_acc => \%transcript_so_mapping
};
-
- $self->{ontology_adaptor}->isa('Bio::EnsEMBL::DBSQL::OntologyTermAdaptor') or
+
+ $self->{ontology_adaptor}->isa('Bio::EnsEMBL::DBSQL::OntologyTermAdaptor') or
throw "Argument is not an OntologyTermAdaptor object";
tie my %cache, 'Bio::EnsEMBL::Utils::Cache', 100;
@@ -348,15 +352,15 @@ sub to_accession {
my $so_accession;
my $ref = ref($feature);
-
- my ($gene_to_acc, $tran_to_acc, $feat_to_acc, $utr_to_acc, $region_to_acc) =
+
+ my ($gene_to_acc, $tran_to_acc, $feat_to_acc, $utr_to_acc, $region_to_acc) =
($self->{gene_to_acc}, $self->{tran_to_acc}, $self->{feat_to_acc}, $self->{utr_to_acc}, $self->{region_to_acc});
-
- if ($feature->isa('Bio::EnsEMBL::Gene') and
+
+ if ($feature->isa('Bio::EnsEMBL::Gene') and
exists $gene_to_acc->{$feature->biotype}) {
$so_accession = $gene_to_acc->{$feature->biotype};
- } elsif ($feature->isa('Bio::EnsEMBL::Transcript') and
- exists $tran_to_acc->{$feature->biotype}) {
+ } elsif ($feature->isa('Bio::EnsEMBL::Transcript') and
+ exists $tran_to_acc->{$feature->biotype}) {
$so_accession = $tran_to_acc->{$feature->biotype};
} elsif ($feature->isa('Bio::EnsEMBL::UTR') and
exists $utr_to_acc->{$feature->type}) {
@@ -375,7 +379,7 @@ sub to_accession {
throw sprintf "%s: mapping to sequence ontology accession not found", $ref
unless $so_accession;
-
+
return $so_accession;
}
diff --git a/modules/t/biotype.t b/modules/t/biotype.t
new file mode 100644
index 0000000000000000000000000000000000000000..2de5367999ea40ddd8e25a3bebc1885f59ddca11
--- /dev/null
+++ b/modules/t/biotype.t
@@ -0,0 +1,104 @@
+# Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
+# Copyright [2016-2018] EMBL-European Bioinformatics Institute
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+use strict;
+use warnings;
+
+use Test::More;
+use Test::Warnings qw( warning );
+use Test::Exception;
+
+use Bio::EnsEMBL::Test::MultiTestDB;
+use Bio::EnsEMBL::Test::TestUtils;
+
+our $verbose = 0; #set to 1 to turn on debug printouts
+
+
+# Get a DBAdaptor to from the test system
+my $multi = Bio::EnsEMBL::Test::MultiTestDB->new;
+ok($multi, "Test DB loaded successfully");
+my $db = $multi->get_DBAdaptor("core");
+ok($db, "Core DB adaptor loaded successfully");
+
+# Should get meaningful type back
+debug("get biotype adaptor");
+my $biotype_adaptor = $db->get_BiotypeAdaptor();
+ok($biotype_adaptor->isa("Bio::EnsEMBL::DBSQL::BiotypeAdaptor"), "Biotype adaptor loaded successfully");
+
+# fetch a protein_coding gene object
+debug("fetch gene");
+my $ga = $db->get_GeneAdaptor();
+my $gene = $ga->fetch_by_stable_id("ENSG00000171456");
+ok($gene, "Gene object loaded successfully");
+
+# test gene biotype object
+debug("gene biotype");
+is($gene->biotype, 'protein_coding', "Gene biotype is protein_coding");
+my $biotype1 = $gene->biotype;
+ok($biotype1->isa("Bio::EnsEMBL::Biotype"), "Biotype object retrieved successfully");
+is($biotype1->object_type, 'gene', 'Biotype is from Gene object');
+is($biotype1->name, 'protein_coding', 'Biotype name is protein_coding');
+is($biotype1->biotype_group, 'coding', 'Biotype group is coding');
+is($biotype1->so_acc, 'SO:0001217', 'Biotype protein_coding refers to SO:0001217');
+throws_ok { $biotype1->so_acc('test') } qr/so_acc must be a Sequence Ontology accession/, 'so_acc() requires a SO acc like string';
+throws_ok { $biotype1->object_type('test') } qr/object_type must be gene or transcript/, 'object_type() must be gene or transcript';
+
+# test transcript biotype object
+my $transcript = $gene->canonical_transcript;
+debug("transcript biotype");
+is($transcript->biotype, 'protein_coding', "Trancript biotype is protein_coding");
+my $biotype2 = $transcript->biotype;
+ok($biotype2->isa("Bio::EnsEMBL::Biotype"), "Biotype object retrieved successfully");
+is($biotype2->object_type, 'transcript', 'Biotype is from Transcript object');
+is($biotype2->name, 'protein_coding', 'Biotype name is protein_coding');
+is($biotype2->biotype_group, 'coding', 'Biotype group is coding');
+is($biotype2->so_acc, 'SO:0000234', 'Biotype protein_coding refers to SO:0000234');
+
+# set biotype with database term
+debug("set biotype with db term");
+ok($gene->biotype('tRNA'), "Can successfully set biotype to tRNA");
+my $biotype3 = $gene->biotype;
+ok($biotype3->isa("Bio::EnsEMBL::Biotype"), "Biotype object retrieved successfully");
+is($biotype3->object_type, 'gene', 'Biotype is from Gene object');
+is($biotype3->name, 'tRNA', 'Biotype name is tRNA');
+is($biotype3->biotype_group, 'snoncoding', 'Biotype group is snoncoding');
+is($biotype3->so_acc, 'SO:0001263', 'Biotype tRNA refers to SO:0001263');
+
+# set biotype with term not in database
+debug("set biotype with term not in db");
+ok($gene->biotype('dummy'), "Can successfully set biotype to dummy");
+my $biotype4 = $gene->biotype;
+ok($biotype4->isa("Bio::EnsEMBL::Biotype"), "Biotype object retrieved successfully");
+is($biotype4->object_type, 'gene', 'Biotype is from Gene object');
+is($biotype4->name, 'dummy', 'Biotype name is dummy');
+is($biotype4->biotype_group, undef, 'Biotype group is not set');
+is($biotype4->so_acc, undef, 'Biotype SO acc is not set');
+
+# test fetch biotypes of object_type gene
+debug("fetch biotypes by object_type");
+my $biotypes = $biotype_adaptor->fetch_all_by_object_type('gene');
+is(ref $biotypes, 'ARRAY', 'Got an array');
+is(scalar @{$biotypes}, '2', 'of size 2');
+is_deeply($biotypes, [$biotype1, $biotype3], 'with the correct objects');
+my $warning = warning { $biotypes = $biotype_adaptor->fetch_all_by_object_type('none') };
+like( $warning,
+ qr/No objects retrieved. Check if object_type 'none' is correct./,
+ "Got a warning from fetch_all_by_object_type('none') ",
+) or diag 'Got warning: ', explain($warning);
+is(ref $biotypes, 'ARRAY', 'Got an array');
+is(scalar @{$biotypes}, '0', 'of size 0');
+is_deeply($biotypes, [], 'totally empty');
+
+done_testing();
diff --git a/modules/t/test-genome-DBs/circ/core/SQLite/table.sql b/modules/t/test-genome-DBs/circ/core/SQLite/table.sql
index 4bbbcd81f92d8b5ac820cc51e032063e59e7a08b..17afb48698e6cd27b96e5f881da2a86855d425cd 100644
--- a/modules/t/test-genome-DBs/circ/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/circ/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:37:14 2018
+-- Created on Fri Feb 16 15:28:14 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/circ/core/meta.txt b/modules/t/test-genome-DBs/circ/core/meta.txt
index 28cac25569ab9802c89e8ebac825d9e0d7618a80..dffcb8c90f536ec4389b86a24851caaf906f25cf 100644
--- a/modules/t/test-genome-DBs/circ/core/meta.txt
+++ b/modules/t/test-genome-DBs/circ/core/meta.txt
@@ -117,3 +117,4 @@
117 \N patch patch_91_92_a.sql|schema_version
118 \N patch patch_91_92_b.sql|add_cigar_line_align_type
119 \N patch patch_92_93_a.sql|schema_version
+120 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/circ/core/table.sql b/modules/t/test-genome-DBs/circ/core/table.sql
index 471b8dd62e30de9d4fdbfaad2848de8430a63c7b..3c91030a518346f7c73a37cb94856e4f7b8e544f 100644
--- a/modules/t/test-genome-DBs/circ/core/table.sql
+++ b/modules/t/test-genome-DBs/circ/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=391 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=120 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=121 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/homo_sapiens/core/SQLite/table.sql b/modules/t/test-genome-DBs/homo_sapiens/core/SQLite/table.sql
index c3d9b866d9cb08d1a8767b594db048764a403e07..17fb6115b7009a238f6d17c006b4b3d9c4200b9e 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:37:26 2018
+-- Created on Fri Feb 16 15:28:17 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/homo_sapiens/core/biotype.txt b/modules/t/test-genome-DBs/homo_sapiens/core/biotype.txt
new file mode 100644
index 0000000000000000000000000000000000000000..b268b7031417fb127ebd3f8d00312e09285b4a40
--- /dev/null
+++ b/modules/t/test-genome-DBs/homo_sapiens/core/biotype.txt
@@ -0,0 +1,3 @@
+64 protein_coding gene core,otherfeatures,rnaseq,vega,presite \N \N coding SO:0001217
+65 protein_coding transcript core,otherfeatures,rnaseq,vega,presite \N \N coding SO:0000234
+87 tRNA gene core,otherfeatures,presite 76 \N snoncoding SO:0001263
diff --git a/modules/t/test-genome-DBs/homo_sapiens/core/meta.txt b/modules/t/test-genome-DBs/homo_sapiens/core/meta.txt
index 0955043ba26b88e88208acf8735d9c3852d3134c..ce0c68d889e0beaca3a9aa2f7941640d9e0e00d1 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/core/meta.txt
+++ b/modules/t/test-genome-DBs/homo_sapiens/core/meta.txt
@@ -96,3 +96,4 @@
163 \N patch patch_91_92_a.sql|schema_version
164 \N patch patch_91_92_b.sql|add_cigar_line_align_type
165 \N patch patch_92_93_a.sql|schema_version
+166 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/homo_sapiens/core/table.sql b/modules/t/test-genome-DBs/homo_sapiens/core/table.sql
index 17285d829505143bba54e17b39920c05e3a93624..74c697e37c6a1ffdff5e4bf9edcf3a5e04f7455d 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/core/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=392 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=166 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=167 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/homo_sapiens/empty/SQLite/table.sql b/modules/t/test-genome-DBs/homo_sapiens/empty/SQLite/table.sql
index 22153c14926c4b10d17e6056bbed845e4867325f..1c4537079819a5f862d39eadd33f28e8fb843a76 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/empty/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/empty/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:37:38 2018
+-- Created on Fri Feb 16 15:28:20 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/homo_sapiens/empty/meta.txt b/modules/t/test-genome-DBs/homo_sapiens/empty/meta.txt
index 83f1c3852f28ebfbfe975b0d2d9f1756be9970e8..b278b9a9434745b59dfcaa2e5b70cd2a0ef4f94e 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/empty/meta.txt
+++ b/modules/t/test-genome-DBs/homo_sapiens/empty/meta.txt
@@ -96,3 +96,4 @@
145 \N patch patch_91_92_a.sql|schema_version
146 \N patch patch_91_92_b.sql|add_cigar_line_align_type
147 \N patch patch_92_93_a.sql|schema_version
+148 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/homo_sapiens/empty/table.sql b/modules/t/test-genome-DBs/homo_sapiens/empty/table.sql
index 4cf4d739071929b41c70253ee02b2c7cbecfe6d1..74e6dce2fbc8c25343f73feb4e49fe5c13fcd088 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/empty/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/empty/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=391 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=148 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=149 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/homo_sapiens/patch/SQLite/table.sql b/modules/t/test-genome-DBs/homo_sapiens/patch/SQLite/table.sql
index 349936ad5ad702ad784401e9d829e1128ff807e4..e2a3a8a6962ac58d6997c4e73606ca2c3d6c39b7 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/patch/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/patch/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:37:50 2018
+-- Created on Fri Feb 16 15:28:23 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/homo_sapiens/patch/meta.txt b/modules/t/test-genome-DBs/homo_sapiens/patch/meta.txt
index 2469440ef6f48e949ea97c6ea396f679f5691913..38b3c829d04b02a6b3f6875c1c3a36bdad7b21ed 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/patch/meta.txt
+++ b/modules/t/test-genome-DBs/homo_sapiens/patch/meta.txt
@@ -101,3 +101,4 @@
2108 \N patch patch_91_92_a.sql|schema_version
2109 \N patch patch_91_92_b.sql|add_cigar_line_align_type
2110 \N patch patch_92_93_a.sql|schema_version
+2111 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/homo_sapiens/patch/table.sql b/modules/t/test-genome-DBs/homo_sapiens/patch/table.sql
index 1e5f50227fca4970fb8bba8eed0cb4be52bd93ba..296a1fc8d92384c7968dcf09281e9313a3a6082b 100644
--- a/modules/t/test-genome-DBs/homo_sapiens/patch/table.sql
+++ b/modules/t/test-genome-DBs/homo_sapiens/patch/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=407 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=2111 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=2112 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/mapping/core/SQLite/table.sql b/modules/t/test-genome-DBs/mapping/core/SQLite/table.sql
index 0db2d3854365064020270df91d1b4b41e8fc7f8b..cb493e4fb5c42d297903ee27d529e2c31c69c02d 100644
--- a/modules/t/test-genome-DBs/mapping/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/mapping/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:03 2018
+-- Created on Fri Feb 16 15:28:26 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/mapping/core/meta.txt b/modules/t/test-genome-DBs/mapping/core/meta.txt
index 1d0729ea246dea8469e631201d9b3e67f00192e3..821b22a77d83746d22f863cf0398f8bd786a232a 100644
--- a/modules/t/test-genome-DBs/mapping/core/meta.txt
+++ b/modules/t/test-genome-DBs/mapping/core/meta.txt
@@ -57,3 +57,4 @@
150 \N patch patch_91_92_a.sql|schema_version
151 \N patch patch_91_92_b.sql|add_cigar_line_align_type
152 \N patch patch_92_93_a.sql|schema_version
+153 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/mapping/core/table.sql b/modules/t/test-genome-DBs/mapping/core/table.sql
index 908015077cdb646b5ba66b411ed26ff78d15f42f..eb478505b7e8030fa573aa4a88f64a2241ed828d 100644
--- a/modules/t/test-genome-DBs/mapping/core/table.sql
+++ b/modules/t/test-genome-DBs/mapping/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=391 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=153 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=154 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/multi/compara/SQLite/table.sql b/modules/t/test-genome-DBs/multi/compara/SQLite/table.sql
index 36c17b641cc7887bc1db37dce350a4098b34e26a..ebb012cd1cfbdc5a87d395f6b73bb30c9549c4f3 100644
--- a/modules/t/test-genome-DBs/multi/compara/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/multi/compara/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:11 2018
+-- Created on Fri Feb 16 15:28:28 2018
--
BEGIN TRANSACTION;
diff --git a/modules/t/test-genome-DBs/mus_musculus/core/SQLite/table.sql b/modules/t/test-genome-DBs/mus_musculus/core/SQLite/table.sql
index 2c76e6cffc8ffa25a4db0801306c6642a75f9ceb..2665152efbd1531ac1937384f49afd5bcabbe5dc 100644
--- a/modules/t/test-genome-DBs/mus_musculus/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/mus_musculus/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:22 2018
+-- Created on Fri Feb 16 15:28:31 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/mus_musculus/core/meta.txt b/modules/t/test-genome-DBs/mus_musculus/core/meta.txt
index d816a2a67fb8dbdd5983508cec77ca674099f1cc..ff86c58769022661cafa1837043a8746dde06cea 100644
--- a/modules/t/test-genome-DBs/mus_musculus/core/meta.txt
+++ b/modules/t/test-genome-DBs/mus_musculus/core/meta.txt
@@ -174,3 +174,4 @@
1686 \N patch patch_91_92_a.sql|schema_version
1687 \N patch patch_91_92_b.sql|add_cigar_line_align_type
1688 \N patch patch_92_93_a.sql|schema_version
+1689 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/mus_musculus/core/table.sql b/modules/t/test-genome-DBs/mus_musculus/core/table.sql
index 2236b585330ebea7636cf605477960cf6541949f..d9f10455113302da903c98078434459e60c2e6cf 100644
--- a/modules/t/test-genome-DBs/mus_musculus/core/table.sql
+++ b/modules/t/test-genome-DBs/mus_musculus/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=508 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=1689 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=1690 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/nameless/core/SQLite/table.sql b/modules/t/test-genome-DBs/nameless/core/SQLite/table.sql
index 892c8e39122c737a6602491c511321982e745517..fd07f4343e34a059108a0b3c168e6ff6ba1153ee 100644
--- a/modules/t/test-genome-DBs/nameless/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/nameless/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:33 2018
+-- Created on Fri Feb 16 15:28:34 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/nameless/core/meta.txt b/modules/t/test-genome-DBs/nameless/core/meta.txt
index 9d6ec55e30b071db49964c2f0c69150b77c93832..212944a0daccf81172655ba76b1a656f428ba803 100644
--- a/modules/t/test-genome-DBs/nameless/core/meta.txt
+++ b/modules/t/test-genome-DBs/nameless/core/meta.txt
@@ -95,3 +95,4 @@
149 \N patch patch_91_92_a.sql|schema_version
150 \N patch patch_91_92_b.sql|add_cigar_line_align_type
151 \N patch patch_92_93_a.sql|schema_version
+152 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/nameless/core/table.sql b/modules/t/test-genome-DBs/nameless/core/table.sql
index caa481fe87238dbd267da2872e300a83e49f6176..5205f74b4320519bcb13da92eb61db2f31446ca1 100644
--- a/modules/t/test-genome-DBs/nameless/core/table.sql
+++ b/modules/t/test-genome-DBs/nameless/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=391 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -466,7 +479,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=152 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=153 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/ontology/ontology/SQLite/table.sql b/modules/t/test-genome-DBs/ontology/ontology/SQLite/table.sql
index 75c3743a884c86a99a0f312280883a7b75e26246..da737bcf2def51421f73b8ab25dfb20520819f98 100644
--- a/modules/t/test-genome-DBs/ontology/ontology/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/ontology/ontology/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:37 2018
+-- Created on Fri Feb 16 15:28:35 2018
--
BEGIN TRANSACTION;
diff --git a/modules/t/test-genome-DBs/polyploidy/core/SQLite/table.sql b/modules/t/test-genome-DBs/polyploidy/core/SQLite/table.sql
index 48e15c0fcf510d796ee436137c89f6c99d92045e..c0a1547915b024740bde290ea22a64a319bc13e4 100644
--- a/modules/t/test-genome-DBs/polyploidy/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/polyploidy/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:48 2018
+-- Created on Fri Feb 16 15:28:38 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/polyploidy/core/meta.txt b/modules/t/test-genome-DBs/polyploidy/core/meta.txt
index 4bfae9f1880fd70bb529a702734d9fcfeaff3f83..e9a2779ee13cec84a47f0e1f35a277413c433eb2 100644
--- a/modules/t/test-genome-DBs/polyploidy/core/meta.txt
+++ b/modules/t/test-genome-DBs/polyploidy/core/meta.txt
@@ -150,3 +150,4 @@
230 \N patch patch_91_92_a.sql|schema_version
231 \N patch patch_91_92_b.sql|add_cigar_line_align_type
232 \N patch patch_92_93_a.sql|schema_version
+233 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/polyploidy/core/table.sql b/modules/t/test-genome-DBs/polyploidy/core/table.sql
index 60080e68ef3d34f0aac878f1b164d4b5423791f6..026969d58e10b54181d5e68d258a1ad6ddf4b995 100644
--- a/modules/t/test-genome-DBs/polyploidy/core/table.sql
+++ b/modules/t/test-genome-DBs/polyploidy/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=437 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -476,7 +489,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=233 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=234 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/modules/t/test-genome-DBs/test_collection/core/SQLite/table.sql b/modules/t/test-genome-DBs/test_collection/core/SQLite/table.sql
index c778813752fcc507bcdc6a2bb3ace327bb43eaba..30e34243b3d6ed21ca8726af1e0ca13f605dd48c 100644
--- a/modules/t/test-genome-DBs/test_collection/core/SQLite/table.sql
+++ b/modules/t/test-genome-DBs/test_collection/core/SQLite/table.sql
@@ -1,6 +1,6 @@
--
-- Created by SQL::Translator::Producer::SQLite
--- Created on Fri Jan 12 13:38:59 2018
+-- Created on Fri Feb 16 15:28:41 2018
--
BEGIN TRANSACTION;
@@ -131,6 +131,22 @@ CREATE TABLE attrib_type (
CREATE UNIQUE INDEX code_idx ON attrib_type (code);
+--
+-- Table: biotype
+--
+CREATE TABLE biotype (
+ biotype_id INTEGER PRIMARY KEY AUTOINCREMENT NOT NULL,
+ name varchar(64) NOT NULL,
+ object_type enum NOT NULL DEFAULT 'gene',
+ db_type varchar NOT NULL DEFAULT 'core',
+ attrib_type_id integer,
+ description text,
+ biotype_group enum,
+ so_acc varchar(64)
+);
+
+CREATE UNIQUE INDEX name_type_idx ON biotype (name, object_type);
+
--
-- Table: coord_system
--
diff --git a/modules/t/test-genome-DBs/test_collection/core/meta.txt b/modules/t/test-genome-DBs/test_collection/core/meta.txt
index 08490b7da9f8f8206bce3ff575468ebfebf85103..dfb025ae25824290a13fcebf3914e18f391c05f7 100644
--- a/modules/t/test-genome-DBs/test_collection/core/meta.txt
+++ b/modules/t/test-genome-DBs/test_collection/core/meta.txt
@@ -170,3 +170,4 @@
212 \N patch patch_91_92_a.sql|schema_version
213 \N patch patch_91_92_b.sql|add_cigar_line_align_type
214 \N patch patch_92_93_a.sql|schema_version
+215 \N patch patch_92_93_b.sql|biotype_table
diff --git a/modules/t/test-genome-DBs/test_collection/core/table.sql b/modules/t/test-genome-DBs/test_collection/core/table.sql
index a83c8221fad827c8540d83171fd0f582a0a93d3d..4b4bdca6fe5bdd44b61b733822c1cb75849bd0ec 100644
--- a/modules/t/test-genome-DBs/test_collection/core/table.sql
+++ b/modules/t/test-genome-DBs/test_collection/core/table.sql
@@ -105,6 +105,19 @@ CREATE TABLE `attrib_type` (
UNIQUE KEY `code_idx` (`code`)
) ENGINE=MyISAM AUTO_INCREMENT=391 DEFAULT CHARSET=latin1 COLLATE=latin1_bin;
+CREATE TABLE `biotype` (
+ `biotype_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
+ `name` varchar(64) NOT NULL,
+ `object_type` enum('gene','transcript') NOT NULL DEFAULT 'gene',
+ `db_type` set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ `attrib_type_id` int(11) DEFAULT NULL,
+ `description` text,
+ `biotype_group` enum('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ `so_acc` varchar(64) DEFAULT NULL,
+ PRIMARY KEY (`biotype_id`),
+ UNIQUE KEY `name_type_idx` (`name`,`object_type`)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
CREATE TABLE `coord_system` (
`coord_system_id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`species_id` int(10) unsigned NOT NULL DEFAULT '1',
@@ -466,7 +479,7 @@ CREATE TABLE `meta` (
PRIMARY KEY (`meta_id`),
UNIQUE KEY `species_key_value_idx` (`species_id`,`meta_key`,`meta_value`),
KEY `species_value_idx` (`species_id`,`meta_value`)
-) ENGINE=MyISAM AUTO_INCREMENT=215 DEFAULT CHARSET=latin1;
+) ENGINE=MyISAM AUTO_INCREMENT=216 DEFAULT CHARSET=latin1;
CREATE TABLE `meta_coord` (
`table_name` varchar(40) COLLATE latin1_bin NOT NULL DEFAULT '',
diff --git a/sql/patch_92_93_b.sql b/sql/patch_92_93_b.sql
new file mode 100644
index 0000000000000000000000000000000000000000..1fee232a2e1d791383823fac5e89c2e0b6d0a084
--- /dev/null
+++ b/sql/patch_92_93_b.sql
@@ -0,0 +1,38 @@
+-- Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
+-- Copyright [2016-2018] EMBL-European Bioinformatics Institute
+--
+-- Licensed under the Apache License, Version 2.0 (the "License");
+-- you may not use this file except in compliance with the License.
+-- You may obtain a copy of the License at
+--
+-- http://www.apache.org/licenses/LICENSE-2.0
+--
+-- Unless required by applicable law or agreed to in writing, software
+-- distributed under the License is distributed on an "AS IS" BASIS,
+-- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+-- See the License for the specific language governing permissions and
+-- limitations under the License.
+
+# patch_92_93_b.sql
+#
+# Title: Added biotype table
+#
+# Description:
+# Added new table biotype
+
+CREATE TABLE biotype (
+ biotype_id INTEGER UNSIGNED NOT NULL AUTO_INCREMENT,
+ name VARCHAR(64) NOT NULL,
+ object_type ENUM('gene','transcript') NOT NULL DEFAULT 'gene',
+ db_type set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ attrib_type_id INTEGER DEFAULT NULL,
+ description TEXT,
+ biotype_group ENUM('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ so_acc VARCHAR(64),
+ PRIMARY KEY (biotype_id),
+ UNIQUE KEY name_type_idx (name, object_type)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
+# patch identifier
+INSERT INTO meta (species_id, meta_key, meta_value)
+ VALUES (NULL, 'patch', 'patch_92_93_b.sql|biotype_table');
diff --git a/sql/table.sql b/sql/table.sql
index 18e6b1f44d9c37dab3e32bd7ca2d2646bca6ba8e..0dfb201ba1b535281f3f4c701ffc50fb07898ea5 100755
--- a/sql/table.sql
+++ b/sql/table.sql
@@ -310,6 +310,9 @@ INSERT INTO meta (species_id, meta_key, meta_value) VALUES
INSERT INTO meta (species_id, meta_key, meta_value)
VALUES (NULL, 'patch', 'patch_92_93_a.sql|schema_version');
+INSERT INTO meta (species_id, meta_key, meta_value)
+ VALUES (NULL, 'patch', 'patch_92_93_b.sql|biotype_table');
+
/**
@table meta_coord
@desc Describes which co-ordinate systems the different feature tables use.
@@ -2110,6 +2113,39 @@ CREATE TABLE external_db (
) COLLATE=latin1_swedish_ci ENGINE=MyISAM;
+/**
+@table biotype
+@desc Stores data about the biotypes and mappings to Sequence Ontology.
+
+@column biotype_id Primary key, internal identifier.
+@column name Ensembl biotype name.
+@column object_type Ensembl object type: 'gene' or 'transcript'.
+@column db_type Type, e.g. 'cdna', 'core', 'coreexpressionatlas', 'coreexpressionest', 'coreexpressiongnf', 'funcgen', 'otherfeatures', 'rnaseq', 'variation', 'vega', 'presite', 'sangervega'
+@column attrib_type_id Foreign key references to the @link attrib_type table.
+@column description Description.
+@column biotype_group Group, e.g. 'coding', 'pseudogene', 'snoncoding', 'lnoncoding', 'mnoncoding', 'LRG', 'undefined', 'no_group'
+@column so_acc Sequence Ontology accession of the biotype.
+
+
+@see attrib_type
+
+*/
+
+
+CREATE TABLE biotype (
+ biotype_id INTEGER UNSIGNED NOT NULL AUTO_INCREMENT,
+ name VARCHAR(64) NOT NULL,
+ object_type ENUM('gene','transcript') NOT NULL DEFAULT 'gene',
+ db_type set('cdna','core','coreexpressionatlas','coreexpressionest','coreexpressiongnf','funcgen','otherfeatures','rnaseq','variation','vega','presite','sangervega') NOT NULL DEFAULT 'core',
+ attrib_type_id INTEGER DEFAULT NULL,
+ description TEXT,
+ biotype_group ENUM('coding','pseudogene','snoncoding','lnoncoding','mnoncoding','LRG','undefined','no_group') DEFAULT NULL,
+ so_acc VARCHAR(64),
+ PRIMARY KEY (biotype_id),
+ UNIQUE KEY name_type_idx (name, object_type)
+) ENGINE=MyISAM DEFAULT CHARSET=latin1;
+
+
/**
@table external_synonym
@desc Some xref objects can be referred to by more than one name. This table relates names to xref IDs.