diff --git a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
index 91fe5819086bc0ae8924bee8752331b549bb52bd..ea80ad1d1c5856f75356754a241dc0f805dadb92 100755
--- a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
@@ -51,11 +51,9 @@ use Bio::EnsEMBL::DBSQL::DBConnection;
=head2 new
- Arg [1] : string SOURCE
- The source name of the database. This may be removed soon.
- Arg [2] : Bio::EnsEMBL::DBSQL::DBAdaptor DNADB
- The dna database to be attached to this database. This may also
- be changed.
+ Arg [-DNADB]: (optional) Bio::EnsEMBL::DBSQL::DBAdaptor DNADB
+ All sequence, assembly, contig information etc, will be
+ retrieved from this database instead.
Arg [..] : Other args are passed to superclass
Bio::EnsEMBL::DBSQL::DBConnection
Example : $db = new Bio::EnsEMBL::DBSQL::DBAdaptor(
@@ -76,11 +74,7 @@ sub new {
#call superclass constructor
my $self = $class->SUPER::new(@args);
- my ( $source, $dnadb ) = $self->_rearrange([qw(SOURCE DNADB)],@args);
-
- if(defined $source) {
- $self->source($source);
- }
+ my ( $dnadb ) = $self->_rearrange([qw(DNADB)],@args);
if(defined $dnadb) {
$self->dnadb($dnadb);
@@ -90,31 +84,6 @@ sub new {
}
-=head2 source
-
- Arg [1] : (optional) string $source
- The source of info in the database connected to (e.g. 'embl')
- Example : $db_adaptor->source('sanger');
- Description: Sets/Gets the source or human readable name of the genes in
- the connected database. For example for the sanger db the source
- would be 'sanger'.
- Returntype : string
- Exceptions : none
- Caller : Bio::EnsEMBL::GeneAdaptor Bio::EnsEMBL::LiteGeneAdaptor EnsWeb
-
-=cut
-
-sub source {
- my ($self, $source) = @_;
-
- if(defined $source) {
- $self->{'_source'} = $source;
- }
-
- return $self->{'_source'};
-}
-
-
=head2 get_MetaContainer
Args : none
@@ -951,4 +920,20 @@ sub add_ExternalFeatureFactory{
}
+
+
+
+#
+# sub DEPRECATED METHODS
+#
+#
+
+sub source {
+ my $self = shift;
+
+ $self->warn("DBAdaptor::source method is deprecated - do not use" .
+ $self->stack_trace_dump);
+
+}
+
1;
diff --git a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
index b88ad1e00d9309e7aa3c0007291b06731216a708..072579cc66bd973f792ff85b5f990324556c6509 100644
--- a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
@@ -194,7 +194,6 @@ sub fetch_by_dbID {
$ana = $self->db->get_AnalysisAdaptor->fetch_by_dbID($arr[4]);
$gene->analysis($ana);
$gene->type($arr[5]);
- $gene->source($self->db->source());
$first = 0;
}
@@ -435,6 +434,7 @@ sub fetch_all_by_contig_list{
Arg [1] : Bio::EnsEMBL::Slice $slice
the slice to fetch genes from
+ Arg [2]
Example : $genes = $gene_adaptor->fetch_all_by_Slice($slice);
Description: Retrieves all genes which are present on a slice
Returntype : listref of Bio::EnsEMBL::Genes in slice coordinates
@@ -444,22 +444,22 @@ sub fetch_all_by_contig_list{
=cut
sub fetch_all_by_Slice {
- my ( $self, $slice, $type ) = @_;
+ my ( $self, $slice, $logic_name ) = @_;
my @out = ();
+ $logic_name ||= '';
+
+ my $key = $slice->name .":" . $logic_name;
+
#check the cache which uses the slice name as it key
- if($self->{'_slice_gene_cache'}{$slice->name()}) {
- return $self->{'_slice_gene_cache'}{$slice->name()};
+ if($self->{'_slice_gene_cache'}{$key}) {
+ return $self->{'_slice_gene_cache'}{$key};
}
my $mapper = $self->db->get_AssemblyMapperAdaptor->fetch_by_type
( $slice->assembly_type() );
- $mapper->register_region( $slice->chr_name(),
- $slice->chr_start(),
- $slice->chr_end());
-
my @cids = $mapper->list_contig_ids( $slice->chr_name(),
$slice->chr_start(),
$slice->chr_end());
@@ -468,15 +468,31 @@ sub fetch_all_by_Slice {
if ( scalar (@cids) == 0 ) {
return [];
}
-
+
my $str = "(".join( ",",@cids ).")";
-
+
+ my $where = "WHERE e.contig_id in $str
+ AND et.exon_id = e.exon_id
+ AND et.transcript_id = t.transcript_id
+ AND g.gene_id = t.gene_id";
+
+ if($logic_name) {
+ #determine analysis id via logic_name
+ my $analysis =
+ $self->db->get_AnalysisAdaptor()->fetch_by_logic_name($logic_name);
+ unless(defined($analysis) && $analysis->dbID()) {
+ $self->warn("No analysis for logic name $logic_name exists");
+ return [];
+ }
+
+ my $analysis_id = $analysis->dbID;
+ $where .= " AND g.analysis_id = $analysis_id";
+ }
+
my $sql = "
SELECT distinct(t.gene_id)
- FROM transcript t,exon_transcript et,exon e
- WHERE e.contig_id in $str
- AND et.exon_id = e.exon_id
- AND et.transcript_id = t.transcript_id";
+ FROM transcript t,exon_transcript et,exon e, gene g
+ $where";
my $sth = $self->db->prepare($sql);
$sth->execute;
@@ -493,7 +509,7 @@ sub fetch_all_by_Slice {
}
#place the results in an LRU cache
- $self->{'_slice_gene_cache'}{$slice->name} = \@out;
+ $self->{'_slice_gene_cache'}{$key} = \@out;
return \@out;
}
@@ -1071,7 +1087,7 @@ sub update {
$sth->execute($gene->type,
$gene->analysis->dbID,
$xref_id,
- $tcout,
+ $tcount,
$gene->dbID);
}
diff --git a/modules/Bio/EnsEMBL/Gene.pm b/modules/Bio/EnsEMBL/Gene.pm
index 1c1adbc7c1ccea2853f942f407d8bf511f00f9c7..87ed3f4336cefba8fa7520e231cc07a97f4bd004 100755
--- a/modules/Bio/EnsEMBL/Gene.pm
+++ b/modules/Bio/EnsEMBL/Gene.pm
@@ -1,9 +1,6 @@
-
#
# BioPerl module for Gene
#
-# Cared for by Ewan Birney <birney@sanger.ac.uk>
-#
# Copyright Ewan Birney
#
# You may distribute this module under the same terms as perl itself
@@ -20,48 +17,45 @@ Confirmed genes. Basically has a set of transcripts
=head1 DESCRIPTION
-Needs more description.
+A representation of a Gene within the ensembl system. A gene is basically a
+set of one or more alternative transcripts.
=head1 CONTACT
-Describe contact details here
-
-=head1 APPENDIX
-
-The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
+Contact the EnsEMBL development mailing list for info <ensembl-dev@ebi.ac.uk>
=cut
-
-# Let the code begin...
-
-
package Bio::EnsEMBL::Gene;
use vars qw(@ISA);
use strict;
-# Object preamble - inheriets from Bio::SeqFeature::Generic
-
use Bio::EnsEMBL::Root;
use Bio::EnsEMBL::TranscriptI;
use Bio::Annotation::DBLink;
use Bio::EnsEMBL::DBEntry;
-
@ISA = qw(Bio::EnsEMBL::Root);
-# new() is inherited from Bio::Root::Object
-# _initialize is where the heavy stuff will happen when new is called
+
+=head2 new
+
+ Arg [1] : none
+ Example : $gene = Bio::EnsEMBL::Gene->new();
+ Description: Creates a new gene object
+ Returntype : Bio::EnsEMBL::Gene
+ Exceptions : none
+ Caller : general
+
+=cut
sub new {
my($class,@args) = @_;
my $self = bless {}, $class;
-
$self->{'_transcript_array'} = [];
-# $self->{'_db_link'} = [];
-# set stuff in self from @args
- return $self; # success - we hope!
+
+ return $self;
}
@@ -248,29 +242,6 @@ sub chr_name {
}
-=head2 source
-
- Arg [1] : string $source
- Example : none
- Description: get/set for attribute source
- Returntype : string
- Exceptions : none
- Caller : general
-
-=cut
-
-
-sub source {
- my ($self, $source) = @_;
-
- if(defined $source) {
- $self->{'_source'} = $source;
- }
-
- return $self->{'_source'};
-}
-
-
=head2 is_known
diff --git a/modules/Bio/EnsEMBL/Lite/GeneAdaptor.pm b/modules/Bio/EnsEMBL/Lite/GeneAdaptor.pm
index ba0c8bb7fa70acf3beab10cb437348b41e87b138..d9c53cb4a17a615ba2ae888df50d803abd0f95b9 100644
--- a/modules/Bio/EnsEMBL/Lite/GeneAdaptor.pm
+++ b/modules/Bio/EnsEMBL/Lite/GeneAdaptor.pm
@@ -30,6 +30,7 @@ package Bio::EnsEMBL::Lite::GeneAdaptor;
use Bio::EnsEMBL::DBSQL::BaseAdaptor;
use Bio::EnsEMBL::DBSQL::DBAdaptor;
use Bio::EnsEMBL::Transcript;
+use Bio::EnsEMBL::Analysis;
use Bio::EnsEMBL::Gene;
use Bio::EnsEMBL::Utils::Cache; #CPAN LRU Cache
@@ -166,12 +167,14 @@ sub fetch_by_gene_id_list {
=cut
sub fetch_all_by_Slice {
- my ( $self, $slice, $empty_flag ) = @_;
+ my ( $self, $slice, $logic_name, $empty_flag ) = @_;
+
+ my $key = $slice->name . ":$logic_name";
if($empty_flag) {
# return from cache or the _get_empty_Genes fn while caching results....
- return $self->{'_slice_empty_gene_cache'}{$slice->name()} ||=
- $self->_get_empty_Genes($slice);
+ return $self->{'_slice_empty_gene_cache'}{$key} ||=
+ $self->_get_empty_Genes($slice, $logic_name);
}
#check the cache which uses the slice name as it key
@@ -179,52 +182,42 @@ sub fetch_all_by_Slice {
return $self->{'_slice_gene_cache'}{$slice->name()};
}
- my $sth = $self->prepare( "SELECT t.id, t.transcript_id, t.chr_name, t.chr_start, t.chr_end,
+ my $where = 'WHERE t.chr_name = ? and t.chr_start <= ? and
+ t.chr_start >= ? and t.chr_end >= ?
+ AND g.gene_id = t.gene_id
+ AND g.db = t.db';
+
+ my @bind_vals = ( $slice->chr_name,
+ $slice->chr_end,
+ $slice->chr_start - $MAX_TRANSCRIPT_LENGTH,
+ $slice->chr_start);
+
+ if($logic_name) {
+ $where .= " and g.analysis = ?";
+ push @bind_vals, $logic_name;
+ }
+
+ my $sth = $self->prepare(
+ "SELECT t.id, t.transcript_id, t.chr_name, t.chr_start, t.chr_end,
t.chr_strand, t.transcript_name, t.translation_id,
t.translation_name, t.gene_id, t.type, t.gene_name, t.db,
- t.exon_structure, t.external_name, t.external_status, t.exon_ids, t.external_db,
- t.coding_start, t.coding_end,
+ t.exon_structure, t.external_name, t.external_status,
+ t.exon_ids, t.external_db, t.coding_start, t.coding_end,
g.external_name as gene_external_name,
g.external_db as gene_external_db,
g.external_status as gene_external_status,
- g.type as gene_type
- FROM transcript t
- LEFT JOIN gene g
- ON g.gene_id = t.gene_id
- AND g.db = t.db
- WHERE t.chr_name = ? and t.chr_start <= ? and t.chr_start >= ? and
- t.chr_end >= ?"
- );
+ g.type as gene_type,
+ g.analysis as analysis
+ FROM transcript t, gene g
+ $where");
- $sth->execute( $slice->chr_name, $slice->chr_end,
- $slice->chr_start - $MAX_TRANSCRIPT_LENGTH,
- $slice->chr_start );
+ $sth->execute( @bind_vals );
- return $self->{'_slice_gene_cache'}{$slice->name} =
+ return $self->{'_slice_gene_cache'}{$key} =
$self->_objects_from_sth( $sth, $slice );
-
}
-=head2 fetch_by_Slice
-
- Arg [1] : none
- Example : none
- Description: DEPRECATED use fetch_all_by_Slice instead
- Returntype : none
- Exceptions : none
- Caller : none
-
-=cut
-
-sub fetch_by_Slice {
- my ($self, @args) = @_;
-
- $self->warn("fetch_by_Slice has been renamed fetch_all_by_Slice\n" . caller);
-
- return $self->fetch_all_by_Slice(@args);
-}
-
sub fetch_by_DBEntry {
my ($self, $db, $dbentry, $chr_coords ) = @_;
@@ -262,7 +255,8 @@ sub fetch_by_stable_id {
t.external_db, t.coding_start, t.coding_end,
g.external_name as gene_external_name,
g.external_status as gene_external_status,
- g.external_db as gene_external_db, g.type as gene_type
+ g.external_db as gene_external_db, g.type as gene_type
+ g.analysis as analysis
FROM transcript t
LEFT JOIN gene g
ON g.gene_id = t.gene_id
@@ -298,7 +292,8 @@ sub fetch_by_transcript_stable_id {
t.external_db, t.coding_start, t.coding_end,
g.external_name as gene_external_name,
g.external_status as gene_external_status,
- g.external_db as gene_external_db, g.type as gene_type
+ g.external_db as gene_external_db, g.type as gene_type
+ g.analysis as analysis
FROM transcript t
LEFT JOIN gene g
ON g.gene_id = t.gene_id
@@ -328,8 +323,10 @@ sub _objects_from_sth {
my %exon_cache;
my %gene_cache;
+ my %analysis_cache;
my $core_db_adaptor = $self->db->get_db_adaptor('core');
+
my ( $gene, $transcript, $translation );
my ( $exon_id );
@@ -347,9 +344,14 @@ sub _objects_from_sth {
$gene->stable_id( $hr->{'gene_name'} );
$gene->dbID( $hr->{'gene_id'} );
$gene->adaptor( $core_db_adaptor->get_GeneAdaptor() );
- $gene->source( $hr->{'db'} );
+ #$gene->source( $hr->{'db'} );
$gene->strand( $hr->{'chr_strand'} );
+ #set the gene's analysis
+ $analysis_cache{$hr->{'analysis'}} ||=
+ Bio::EnsEMBL::Analysis->new(-logic_name => $hr->{'analysis'});
+ $gene->analysis($analysis_cache{$hr->{'analysis'}});
+
if( defined $hr->{'gene_type' } ) {
$gene->external_name( $hr->{'gene_external_status'} );
$gene->external_name( $hr->{'gene_external_name'} );
@@ -549,22 +551,37 @@ sub _objects_from_sth {
=cut
sub _get_empty_Genes {
- my ($self, $slice) = @_;
+ my ($self, $slice, $logic_name) = @_;
my $chr_start = $slice->chr_start();
my $chr_end = $slice->chr_end();
my $chr_name = $slice->chr_name();
+
+
+ my $where = "WHERE g.chr_name = ? AND g.chr_start <= ? AND
+ g.chr_start >= ? AND g.chr_end >= ?";
+
+ my @bind_vals = ( $chr_name,
+ $chr_end,
+ $chr_start - $MAX_TRANSCRIPT_LENGTH,
+ $chr_start );
+
+
+ if($logic_name) {
+ $where .= " and g.analysis_id = ?";
+ push @bind_vals, $logic_name;
+ }
+
my $sth = $self->prepare
( "SELECT g.db, g.gene_id, g.gene_name, g.chr_name, g.chr_start,
- g.chr_end, g.chr_strand, g.type, g.external_name, g.external_db, g.external_status
+ g.chr_end, g.chr_strand, g.type, g.external_name, g.external_db,
+ g.external_status, g.analysis
FROM gene g
- WHERE g.chr_name = ? AND g.chr_start <= ? AND
- g.chr_start >= ? AND g.chr_end >= ?" );
+ $where"
+ );
- $sth->execute( $chr_name, $chr_end,
- $chr_start - $MAX_TRANSCRIPT_LENGTH,
- $chr_start );
+ $sth->execute(@bind_vals);
my @out = ();
@@ -572,6 +589,8 @@ sub _get_empty_Genes {
my $hashref;
+ my %analysis_cache;
+
while($hashref = $sth->fetchrow_hashref()) {
my $gene = new Bio::EnsEMBL::Gene();
$gene->start($hashref->{'chr_start'} - $chr_start);
@@ -579,9 +598,14 @@ sub _get_empty_Genes {
$gene->stable_id( $hashref->{'gene_name'} );
$gene->dbID( $hashref->{'gene_id'} );
$gene->adaptor( $core_gene_adaptor );
- $gene->source( $hashref->{'db'} );
+ #$gene->source( $hashref->{'db'} );
$gene->strand( $hashref->{'chr_strand'} );
+ my $analysis = $analysis_cache{$hashref->{'analysis'}} ||=
+ Bio::EnsEMBL::Analysis->new(-logic_name => $hashref->{'analysis'});
+
+ $gene->analysis($analysis);
+
if( defined $hashref->{'type' } ) {
$gene->external_status( $hashref->{'external_status'} );
$gene->external_name( $hashref->{'external_name'} );
@@ -641,7 +665,8 @@ sub fetch_all_by_external_name {
t.coding_start, t.coding_end,
g.external_name as gene_external_name,
g.external_db as gene_external_db, g.external_status as gene_external_status,
- g.type as gene_type
+ g.type as gene_type,
+ g.analysis as analysis
FROM transcript t, gene_xref as gx, gene as g
where g.gene_id = t.gene_id AND g.db = t.db and t.db = ? and gx.external_name = ? and gx.gene_id = g.gene_id
order by g.gene_name, t.gene_name"
@@ -683,7 +708,7 @@ sub _get_empty_Genes_by_external_name {
$gene->stable_id( $hashref->{'gene_name'} );
$gene->dbID( $hashref->{'gene_id'} );
$gene->adaptor( $core_gene_adaptor );
- $gene->source( $hashref->{'db'} );
+ #$gene->source( $hashref->{'db'} );
$gene->strand( $hashref->{'chr_strand'} );
if( defined $hashref->{'type' } ) {
diff --git a/modules/Bio/EnsEMBL/Slice.pm b/modules/Bio/EnsEMBL/Slice.pm
index 0d2b52499418f70e65ead3000f9f5490fa0bcf32..9e5894ef9eb717dee85a8f503e68758ce8c949d9 100644
--- a/modules/Bio/EnsEMBL/Slice.pm
+++ b/modules/Bio/EnsEMBL/Slice.pm
@@ -34,10 +34,6 @@ This modules is part of the Ensembl project http://www.ensembl.org
Questions can be posted to the ensembl-dev mailing list:
ensembl-dev@ebi.ac.uk
-=head1 APPENDIX
-
-The rest of the documentation details each of the object methods. Internal methods are usually preceded with a _
-
=cut
@@ -58,7 +54,6 @@ use Bio::EnsEMBL::Tile;
@ISA = qw(Bio::EnsEMBL::Root Bio::PrimarySeqI);
-
=head2 new
Arg [...] : List of optional named arguments
@@ -593,7 +588,9 @@ sub get_all_SNPs {
=head2 get_all_Genes
- Arg [1] : (optional) boolean $empty_flag
+ Arg [1] : (optional) string $logic_name
+ The name of the analysis used to generate the genes to retrieve
+ Arg [2] : (optional) boolean $empty_flag
Example : @genes = $slice->get_all_Genes;
Description: Retrieves all genes that overlap this slice. The empty flag is
used by the web code and is used to retrieve light weight genes
@@ -608,40 +605,18 @@ sub get_all_SNPs {
=cut
sub get_all_Genes{
- my ($self, $empty_flag) = @_;
+ my ($self, $logic_name, $empty_flag) = @_;
#caching is performed on a per slice basis in the GeneAdaptor
- return $self->adaptor->db->get_GeneAdaptor->fetch_all_by_Slice($self,
+ return $self->adaptor->db->get_GeneAdaptor->fetch_all_by_Slice($self,
+ $logic_name,
$empty_flag);
}
-=head2 get_all_Genes_by_source
- Arg [1] : string $source
- Arg [2] : (optional) boolean $empty_flag
- Example : @genes = @{$slice->get_all_Genes_by_souce('core')};
- Description: Retrieves genes that overlap this slice from database $source.
- This is primarily used by web code to retrieve subsets of genes
- from the lite database (which contains an sets of genes from
- several databases). The empty flag indicates light weight
- genes that only have a start, end and strand should be used
- (only works if lite db is available). If the lite database has
- been attached to the core database this method will use the
- lite database (and genes will not be as full featured).
- Returntype : listref of Bio::EnsEMBL::Genes
- Exceptions : none
- Caller : contigview
-=cut
-
-sub get_all_Genes_by_source{
- my ($self, $source, $empty_flag) = @_;
- my @out =
- grep { $_->source eq $source } @{$self->get_all_Genes($empty_flag)};
- return \@out;
-}
@@ -1353,4 +1328,25 @@ sub accession_number {
# sub DEPRECATED METHODS #
###############################################################################
+
+=head2 get_all_Genes_by_source
+
+ Arg [1] : none
+ Example : none
+ Description: DEPRECATED use get_all_Genes instead
+ Returntype : none
+ Exceptions : none
+ Caller : none
+
+=cut
+
+sub get_all_Genes_by_source {
+ my ($self, @args) = @_;
+
+ $self->warn("call to deprecated method get_all_Genes_by_source. " .
+ "Use get_all_Genes instead\n " . join(':', caller));
+
+ return $self->get_all_Genes;
+}
+
1;