From ac52bc8e147f4f8b9c98ebf7fffaeed4ead981e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andreas=20Kusalananda=20K=C3=A4h=C3=A4ri?=
<ak4@sanger.ac.uk>
Date: Thu, 21 Jun 2007 14:42:21 +0000
Subject: [PATCH] Added new optional argument $external_db_name to
fetch_all_by_external_name() in GeneAdaptor.pm, TranscriptAdaptor.pm, and in
TranslationAdaptor.pm.
This will limit the returned genes, transcripts, or translations, to
those that originates from the named external database.
This also means adding the optional argument to
list_gene_ids_by_extids(), list_transcript_ids_by_extids(),
list_translation_ids_by_extids(), and to _type_by_external_id() in
DBEntryAdaptor.pm.
The matching is done on 'db_name' in the 'external_db' table with LIKE
and an appended '%' to the given $external_db_name.
---
modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm | 172 +++++++++++-------
modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm | 30 +--
.../Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm | 43 +++--
.../Bio/EnsEMBL/DBSQL/TranslationAdaptor.pm | 32 ++--
4 files changed, 170 insertions(+), 107 deletions(-)
diff --git a/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
index 25f476acd7..67ef7f0a85 100644
--- a/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
@@ -837,9 +837,10 @@ sub list_gene_ids_by_external_db_id{
return keys %T;
}
-=head2 list_gene_ids_by_external_db_id
+=head2 list_gene_ids_by_extids
- Arg [1] : string $external_id
+ Arg [1] : string $external_name
+ Arg [2] : (optional) string $external_db_name
Example : @gene_ids = $dbea->list_gene_ids_by_extids('ARSE');
Description: Retrieve a list of geneid by an external identifier that is
linked to any of the genes transcripts, translations or the
@@ -851,20 +852,25 @@ sub list_gene_ids_by_external_db_id{
=cut
-sub list_gene_ids_by_extids{
- my ($self,$name) = @_;
+sub list_gene_ids_by_extids {
+ my ( $self, $external_name, $external_db_name ) = @_;
- my %T = map { ($_, 1) }
- $self->_type_by_external_id( $name, 'Translation', 'gene' ),
- $self->_type_by_external_id( $name, 'Transcript', 'gene' ),
- $self->_type_by_external_id( $name, 'Gene' );
- return keys %T;
+ my %T = map { ( $_, 1 ) }
+ $self->_type_by_external_id( $external_name, 'Translation', 'gene',
+ $external_db_name ),
+ $self->_type_by_external_id( $external_name, 'Transcript', 'gene',
+ $external_db_name ),
+ $self->_type_by_external_id( $external_name, 'Gene', undef,
+ $external_db_name );
+
+ return keys %T;
}
=head2 list_transcript_ids_by_extids
- Arg [1] : string $external_id
+ Arg [1] : string $external_name
+ Arg [2] : (optional) string $external_db_name
Example : @tr_ids = $dbea->list_gene_ids_by_extids('BCRA2');
Description: Retrieve a list transcript ids by an external identifier that
is linked to any of the genes transcripts, translations or the
@@ -876,32 +882,39 @@ sub list_gene_ids_by_extids{
=cut
-sub list_transcript_ids_by_extids{
- my ($self,$name) = @_;
- my @transcripts;
+sub list_transcript_ids_by_extids {
+ my ( $self, $external_name, $external_db_name ) = @_;
- my %T = map { ($_, 1) }
- $self->_type_by_external_id( $name, 'Translation', 'transcript' ),
- $self->_type_by_external_id( $name, 'Transcript' );
- return keys %T;
+ my %T = map { ( $_, 1 ) }
+ $self->_type_by_external_id( $external_name, 'Translation',
+ 'transcript', $external_db_name
+ ),
+ $self->_type_by_external_id( $external_name, 'Transcript', undef,
+ $external_db_name );
+
+ return keys %T;
}
=head2 list_translation_ids_by_extids
- Arg [1] : string $name
- Example : @tr_ids = $dbea->list_gene_ids_by_extids('GO:0004835');
- Description: Gets a list of translation IDs by external display IDs
- Returntype : list of Ints
- Exceptions : none
- Caller : unknown
+ Arg [1] : string $external_name
+ Arg [2] : (optional) string $external_db_name
+ Example : @tr_ids = $dbea->list_gene_ids_by_extids('GO:0004835');
+ Description: Gets a list of translation IDs by external display IDs
+ Returntype : list of Ints
+ Exceptions : none
+ Caller : unknown
Status : Stable
=cut
-sub list_translation_ids_by_extids{
- my ($self,$name) = @_;
- return $self->_type_by_external_id($name, 'Translation');
+sub list_translation_ids_by_extids {
+ my ( $self, $external_name, $external_db_name ) = @_;
+
+ return
+ $self->_type_by_external_id( $external_name, 'Translation', undef,
+ $external_db_name );
}
=head2 _type_by_external_id
@@ -909,6 +922,7 @@ sub list_translation_ids_by_extids{
Arg [1] : string $name - dbprimary_acc
Arg [2] : string $ensType - ensembl_object_type
Arg [3] : (optional) string $extraType
+ Arg [4] : (optional) string $external_db_name
other object type to be returned
Example : $self->_type_by_external_id($name, 'Translation');
Description: Gets
@@ -921,42 +935,45 @@ sub list_translation_ids_by_extids{
=cut
-sub _type_by_external_id{
- my ($self, $name, $ensType, $extraType) = @_;
+sub _type_by_external_id {
+ my ( $self, $name, $ensType, $extraType, $external_db_name ) = @_;
- my $from_sql = '';
+ my $from_sql = '';
my $where_sql = '';
- my $ID_sql = "oxr.ensembl_id";
+ my $ID_sql = "oxr.ensembl_id";
- if (defined $extraType) {
- if (lc($extraType) eq 'translation') {
+ if ( defined $extraType ) {
+ if ( lc($extraType) eq 'translation' ) {
$ID_sql = "tl.translation_id";
} else {
$ID_sql = "t.${extraType}_id";
}
- if (lc($ensType) eq 'translation') {
- $from_sql = 'transcript t, translation tl, ';
+ if ( lc($ensType) eq 'translation' ) {
+ $from_sql = 'transcript t, translation tl, ';
$where_sql = qq(
t.transcript_id = tl.transcript_id AND
tl.translation_id = oxr.ensembl_id AND
t.is_current = 1 AND
);
} else {
- $from_sql = 'transcript t, ';
- $where_sql = 't.'.lc($ensType).'_id = oxr.ensembl_id AND '.
- 't.is_current = 1 AND ';
+ $from_sql = 'transcript t, ';
+ $where_sql = 't.'
+ . lc($ensType)
+ . '_id = oxr.ensembl_id AND '
+ . 't.is_current = 1 AND ';
}
}
- if (lc($ensType) eq 'gene') {
- $from_sql = 'gene g, ';
+ if ( lc($ensType) eq 'gene' ) {
+ $from_sql = 'gene g, ';
$where_sql = 'g.gene_id = oxr.ensembl_id AND g.is_current = 1 AND ';
- } elsif (lc($ensType) eq 'transcript') {
+ } elsif ( lc($ensType) eq 'transcript' ) {
$from_sql = 'transcript t, ';
- $where_sql = 't.transcript_id = oxr.ensembl_id AND t.is_current = 1 AND ';
- } elsif (lc($ensType) eq 'translation') {
- $from_sql = 'transcript t, translation tl, ';
+ $where_sql =
+ 't.transcript_id = oxr.ensembl_id AND t.is_current = 1 AND ';
+ } elsif ( lc($ensType) eq 'translation' ) {
+ $from_sql = 'transcript t, translation tl, ';
$where_sql = qq(
t.transcript_id = tl.transcript_id AND
tl.translation_id = oxr.ensembl_id AND
@@ -964,43 +981,74 @@ sub _type_by_external_id{
);
}
+ if ( defined($external_db_name) ) {
+ # Involve the 'external_db' table to limit the hits to a particular
+ # external database.
+
+ $from_sql .= 'external_db xdb, ';
+ $where_sql .=
+ 'xdb.db_name LIKE '
+ . $self->dbc()->db_handle()->quote( $external_db_name . '%' )
+ . ' AND xdb.external_db_id = x.external_db_id AND';
+ }
+
my @queries = (
"SELECT $ID_sql
FROM $from_sql xref x, object_xref oxr
WHERE $where_sql x.dbprimary_acc = ? AND
- x.xref_id = oxr.xref_id AND oxr.ensembl_object_type= ?",
+ x.xref_id = oxr.xref_id AND
+ oxr.ensembl_object_type= ?",
"SELECT $ID_sql
FROM $from_sql xref x, object_xref oxr
WHERE $where_sql x.display_label = ? AND
- x.xref_id = oxr.xref_id AND oxr.ensembl_object_type= ?",
- "SELECT $ID_sql
+ x.xref_id = oxr.xref_id AND
+ oxr.ensembl_object_type= ?"
+ );
+
+ if ( defined $external_db_name ) {
+ # If we are given the name of an external database, we need to join
+ # between the 'xref' and the 'object_xref' tables on 'xref_id'.
+
+ push @queries, "SELECT $ID_sql
+ FROM $from_sql xref x, object_xref oxr, external_synonym syn
+ WHERE $where_sql syn.synonym = ? AND
+ x.xref_id = oxr.xref_id AND
+ oxr.ensembl_object_type= ? AND
+ syn.xref_id = oxr.xref_id";
+ } else {
+ # If we weren't given an external database name, we can get away
+ # with less joins here.
+
+ push @queries, "SELECT $ID_sql
FROM $from_sql object_xref oxr, external_synonym syn
WHERE $where_sql syn.synonym = ? AND
- syn.xref_id = oxr.xref_id AND oxr.ensembl_object_type= ?",
- );
+ oxr.ensembl_object_type= ? AND
+ syn.xref_id = oxr.xref_id";
+ }
-# Increase speed of query by splitting the OR in query into three separate
-# queries. This is because the 'or' statments render the index useless
-# because MySQL can't use any fields in the index.
+ # Increase speed of query by splitting the OR in query into three
+ # separate queries. This is because the 'or' statments render the
+ # index useless because MySQL can't use any fields in it.
- my %hash = ();
+ my %hash = ();
my @result = ();
- foreach( @queries ) {
-
- my $sth = $self->prepare( $_ );
- $sth->bind_param(1, "$name", SQL_VARCHAR);
- $sth->bind_param(2, $ensType, SQL_VARCHAR);
+ foreach (@queries) {
+ my $sth = $self->prepare($_);
+ $sth->bind_param( 1, "$name", SQL_VARCHAR );
+ $sth->bind_param( 2, $ensType, SQL_VARCHAR );
$sth->execute();
- while( my $r = $sth->fetchrow_array() ) {
- if( !exists $hash{$r} ) {
- $hash{$r} = 1;
- push( @result, $r );
+
+ while ( my $r = $sth->fetchrow_array() ) {
+ if ( !exists $hash{$r} ) {
+ $hash{$r} = 1;
+ push( @result, $r );
}
}
}
+
return @result;
-}
+} ## end sub _type_by_external_id
=head2 _type_by_external_type
diff --git a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
index 6e04517203..74d97cb2bf 100644
--- a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
@@ -670,15 +670,18 @@ sub fetch_by_translation_stable_id {
=head2 fetch_all_by_external_name
- Arg [1] : String $external_id
+ Arg [1] : String $external_name
The external identifier for the gene to be obtained
+ Arg [2] : (optional) String $external_db_name
+ The name of the external database from which the
+ identifier originates.
Example : @genes = @{$gene_adaptor->fetch_all_by_external_name('BRCA2')}
- Description: Retrieves a list of genes with an external database
- idenitifier $external_id. The genes returned are in their
- native coordinate system. I.e. in the coordinate system they
- are stored in the database in. If another coordinate system
- is required then the Gene::transfer or Gene::transform method
- can be used.
+ Description: Retrieves a list of genes with an external database
+ identifier $external_name. The genes returned are in
+ their native coordinate system, i.e. in the coordinate
+ system they are stored in the database in. If another
+ coordinate system is required then the Gene::transfer or
+ Gene::transform method can be used.
Returntype : listref of Bio::EnsEMBL::Genes
Exceptions : none
Caller : goview, general
@@ -687,17 +690,18 @@ sub fetch_by_translation_stable_id {
=cut
sub fetch_all_by_external_name {
- my ($self, $external_id) = @_;
+ my ( $self, $external_name, $external_db_name ) = @_;
my $entryAdaptor = $self->db->get_DBEntryAdaptor();
- my (@ids, @result);
- @ids = $entryAdaptor->list_gene_ids_by_extids($external_id);
+ my @ids =
+ $entryAdaptor->list_gene_ids_by_extids( $external_name,
+ $external_db_name );
- my $genes = $self->fetch_all_by_dbID_list(\@ids);
+ my %genes_by_dbIDs =
+ map { $_->dbID(), $_ } @{ $self->fetch_all_by_dbID_list( \@ids ) };
- my %genes_by_dbIDs = map { $_->dbID(),$_ } @$genes;
- @result = map { $genes_by_dbIDs{ $_ } } @ids;
+ my @result = map { $genes_by_dbIDs{$_} } @ids;
return \@result;
}
diff --git a/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
index 4423eba79b..cd5320d551 100644
--- a/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
@@ -415,20 +415,24 @@ sub fetch_all_by_Slice {
=head2 fetch_all_by_external_name
- Arg [1] : String $external_id
+ Arg [1] : String $external_name
An external identifier of the transcript to be obtained
- Example : my @transcripts = @{ $tr_adaptor->fetch_all_by_external_name
- ('NP_065811.1') };
- Description: Retrieves all transcripts which are associated with an
- external identifier such as a GO term, Swissprot
- identifer, etc. Usually there will only be a single transcript
- returned in the listref, but not always. Transcripts are
- returned in their native coordinate system. That is, the
- coordinate system in which they are stored in the database. If
- they are required in another coordinate system the
- Transcript::transfer or Transcript::transform method can be
- used to convert them. If no transcripts with the external
- identifier are found, a reference to an empty list is returned.
+ Arg [2] : (optional) String $external_db_name
+ The name of the external database from which the
+ identifier originates.
+ Example : my @transcripts =
+ @{ $tr_adaptor->fetch_all_by_external_name( 'NP_065811.1') };
+ Description: Retrieves all transcripts which are associated with
+ an external identifier such as a GO term, Swissprot
+ identifer, etc. Usually there will only be a single
+ transcript returned in the list reference, but not
+ always. Transcripts are returned in their native
+ coordinate system, i.e. the coordinate system in which
+ they are stored in the database. If they are required
+ in another coordinate system the Transcript::transfer or
+ Transcript::transform method can be used to convert them.
+ If no transcripts with the external identifier are found,
+ a reference to an empty list is returned.
Returntype : Listref of Bio::EnsEMBL::Transcript objects
Exceptions : none
Caller : general
@@ -437,17 +441,16 @@ sub fetch_all_by_Slice {
=cut
sub fetch_all_by_external_name {
- my $self = shift;
- my $external_id = shift;
-
- my @trans = ();
+ my ( $self, $external_name, $external_db_name ) = @_;
my $entryAdaptor = $self->db->get_DBEntryAdaptor();
- my @ids = $entryAdaptor->list_transcript_ids_by_extids($external_id);
- return $self->fetch_all_by_dbID_list(\@ids);
-}
+ my @ids =
+ $entryAdaptor->list_transcript_ids_by_extids( $external_name,
+ $external_db_name );
+ return $self->fetch_all_by_dbID_list( \@ids );
+}
=head2 fetch_by_display_label
diff --git a/modules/Bio/EnsEMBL/DBSQL/TranslationAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/TranslationAdaptor.pm
index bb63fa15e0..8d05dc7ce1 100644
--- a/modules/Bio/EnsEMBL/DBSQL/TranslationAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/TranslationAdaptor.pm
@@ -144,13 +144,19 @@ sub fetch_by_Transcript {
=head2 fetch_all_by_external_name
- Arg [1] : string $external_id
- The external identifier for the tranlsation(s) to be obtained.
- Example : @tls = @{$trl_adaptor->fetch_all_by_external_name('BRCA2')};
- Description: Retrieves a list of translations fetched via an external
- identifier. Note that this may not be a particularly useful
- method, because translations do not make much sense out of the
- context of their transcript. It may be better to use the
+ Arg [1] : string $external_name
+ The external identifier for the translation(s) to be
+ obtained.
+ Arg [2] : (optional) string $external_db_name
+ The name of the external database from which the
+ identifier originates.
+ Example : my @translations =
+ @{ $trl_adaptor->fetch_all_by_external_name('BRCA2') };
+ Description: Retrieves a list of translations fetched via an
+ external identifier. Note that this may not be a
+ particularly useful method, because translations
+ do not make much sense out of the context of
+ their transcript. It may be better to use the
TranscriptAdaptor::fetch_all_by_external_name instead.
Returntype : reference to a list of Translations
Exceptions : none
@@ -162,19 +168,21 @@ sub fetch_by_Transcript {
=cut
sub fetch_all_by_external_name {
- my $self = shift;
- my $external_id = shift;
+ my ( $self, $external_name, $external_db_name ) = @_;
my $entry_adaptor = $self->db->get_DBEntryAdaptor();
- my @ids = $entry_adaptor->list_translation_ids_by_extids($external_id);
+
+ my @ids =
+ $entry_adaptor->list_translation_ids_by_extids( $external_name,
+ $external_db_name );
my $transcript_adaptor = $self->db()->get_TranscriptAdaptor();
my @out;
-
foreach my $id (@ids) {
my $transcript = $transcript_adaptor->fetch_by_translation_id($id);
- if($transcript) {
+
+ if ( defined($transcript) ) {
push @out, $self->fetch_by_Transcript($transcript);
}
}
--
GitLab