diff --git a/modules/Bio/EnsEMBL/DBSQL/AffyArrayAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/AffyArrayAdaptor.pm
index d8c4dfea02dbc57761918edeab2449773fff4de2..f26b324207a768db339c5e33558fdbdd8130321d 100644
--- a/modules/Bio/EnsEMBL/DBSQL/AffyArrayAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/AffyArrayAdaptor.pm
@@ -110,8 +110,11 @@ sub _objs_from_sth {
Args : None
Example : my @array_ids = @{$aaa->list_dbIDs()};
- Description: Gets an array of internal IDs for all AffyArray objects in the
- current database.
+ Description: Gets an array of internal IDs for all AffyArray objects
+ in the current database. NOTE: In a multi-species
+ database, this method will return the dbIDs of all
+ AffyArray objects, not just the ones associated with the
+ current species.
Returntype : List of ints
Exceptions : None
Caller : ?
@@ -126,7 +129,12 @@ sub list_dbIDs {
# Can't use _list_dbIDs because only want OligoArray objects of type AFFY
my @out;
+
+ # FIXME: This SQL will not work as expected on multi-species
+ # databases. It needs to be anchored in a coord_system entry
+ # coord_system.species_id = $self->species_id(). /ak4@2008-07-15
my $sql = "SELECT oligo_array_id FROM oligo_array WHERE type='AFFY'";
+
my $sth = $self->prepare($sql);
$sth->execute;
diff --git a/modules/Bio/EnsEMBL/DBSQL/AffyFeatureAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/AffyFeatureAdaptor.pm
index a1a16ffa20b258fc7bf91d3c235b01dbbf889051..d361d6dfd0516f4f440e5838d3dc22bfcf651112 100644
--- a/modules/Bio/EnsEMBL/DBSQL/AffyFeatureAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/AffyFeatureAdaptor.pm
@@ -112,8 +112,11 @@ sub _new_fast {
Args : None
Example : my @feature_ids = @{$afa->list_dbIDs()};
- Description: Gets an array of internal IDs for all AffyFeature objects in
- the current database.
+ Description: Gets an array of internal IDs for all AffyFeature objects
+ in the current database. NOTE: In a multi-species
+ database, this method will return the dbIDs of all
+ AffyFeature objects, not just the ones associated with
+ the current species.
Returntype : List of ints
Exceptions : None
Caller : ?
@@ -128,6 +131,10 @@ sub list_dbIDs {
# Can't use _list_dbIDs because only want OligoProbe objects on arrays of type AFFY
my @out;
+
+ # FIXME: This SQL will not work as expected on multi-species
+ # databases. It needs to be anchored in a coord_system entry
+ # coord_system.species_id = $self->species_id(). /ak4@2008-07-15
my $sql = "
SELECT DISTINCT of.oligo_feature_id
FROM oligo_feature of, oligo_probe op, oligo_array oa
diff --git a/modules/Bio/EnsEMBL/DBSQL/AffyProbeAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/AffyProbeAdaptor.pm
index 7880bbf4ba5330c947eb2e078f15ab1758a1dd9c..54a0dc7fc85eb20946b0131707c75c5e1b2d37b9 100644
--- a/modules/Bio/EnsEMBL/DBSQL/AffyProbeAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/AffyProbeAdaptor.pm
@@ -158,8 +158,11 @@ sub _objs_from_sth {
Arg [1] : none
Example : my @probe_ids = @{$apa->list_dbIDs()};
- Description: Gets an array of internal IDs for all AffyProbe objects in the
- current database.
+ Description: Gets an array of internal IDs for all AffyProbe objects
+ in the current database. NOTE: In a multi-species
+ database, this method will return the dbIDs of all
+ AffyProbe objects, not just the ones associated with
+ the current species.
Returntype : List of ints
Exceptions : None
Caller : ?
@@ -174,6 +177,10 @@ sub list_dbIDs {
# Can't use _list_dbIDs because only want OligoProbe objects on arrays of type AFFY
my @out;
+
+ # FIXME: This SQL will not work as expected on multi-species
+ # databases. It needs to be anchored in a coord_system entry
+ # coord_system.species_id = $self->species_id(). /ak4@2008-07-15
my $sql = "
SELECT DISTINCT op.oligo_probe_id
FROM oligo_probe op, oligo_array oa
diff --git a/modules/Bio/EnsEMBL/DBSQL/AssemblyExceptionFeatureAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/AssemblyExceptionFeatureAdaptor.pm
index dfaae4157126916db1479de8987dfe3a00178968..42b6e9a636f65055f05976758245da1dd2fd1b41 100644
--- a/modules/Bio/EnsEMBL/DBSQL/AssemblyExceptionFeatureAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/AssemblyExceptionFeatureAdaptor.pm
@@ -97,11 +97,26 @@ sub fetch_all {
return $self->{'_aexc_cache'};
}
- my $sth = $self->prepare
- ("SELECT assembly_exception_id, seq_region_id, seq_region_start,
- seq_region_end, exc_type, exc_seq_region_id, exc_seq_region_start,
- exc_seq_region_end, ori
- FROM assembly_exception");
+ my $statement = qq(
+ SELECT ae.assembly_exception_id,
+ ae.seq_region_id,
+ ae.seq_region_start,
+ ae.seq_region_end,
+ ae.exc_type,
+ ae.exc_seq_region_id,
+ ae.exc_seq_region_start,
+ ae.exc_seq_region_end,
+ ae.ori
+ FROM assembly_exception ae,
+ coord_system cs,
+ seq_region sr
+ WHERE cs.species_id = ?
+ AND sr.coord_system_id = cs.coord_system_id
+ AND sr.seq_region_id = ae.seq_region_id);
+
+ my $sth = $self->prepare($statement);
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
diff --git a/modules/Bio/EnsEMBL/DBSQL/AssemblyMapperAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/AssemblyMapperAdaptor.pm
index 09f03dcbcb6bb891cbfb0939d4b06d75283de6d5..07bc9f2adf1ecfd9b21151b3175734649a3b8582 100644
--- a/modules/Bio/EnsEMBL/DBSQL/AssemblyMapperAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/AssemblyMapperAdaptor.pm
@@ -134,14 +134,22 @@ sub cache_seq_ids_with_mult_assemblys{
$self->{'multi_seq_ids'} = {};
- my $sql=(<<SQL);
- SELECT seq_region_id
- FROM seq_region_attrib sra, attrib_type at
- WHERE sra.attrib_type_id = at.attrib_type_id and code = "MultAssem"
-SQL
+ my $sql = qq(
+ SELECT sra.seq_region_id
+ FROM seq_region_attrib sra,
+ attrib_type at,
+ seq_region sr,
+ coord_system cs
+ WHERE sra.attrib_type_id = at.attrib_type_id
+ AND code = "MultAssem"
+ AND sra.seq_region_id = sr.seq_region_id
+ AND sr.coord_system_id = cs.coord_system_id
+ AND cs.species_id = ?);
my $sth = $self->prepare($sql);
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
+
$sth->execute();
my ($seq_region_id);
diff --git a/modules/Bio/EnsEMBL/DBSQL/BaseAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/BaseAdaptor.pm
index 06cbc45c144ef7944ed5ce30626134d1a5f62d50..970eb744bb0d7fe561b24728be4b68bc6b1fa923 100755
--- a/modules/Bio/EnsEMBL/DBSQL/BaseAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/BaseAdaptor.pm
@@ -114,29 +114,27 @@ use DBI qw(:sql_types);
=cut
sub new {
- my ($class,$dbobj) = @_;
-
- my $self = {};
- bless $self,$class;
-
- if( !defined $dbobj || !ref $dbobj ) {
+ my ( $class, $dbobj ) = @_;
+
+ my $self = bless {}, $class;
+
+ if ( !defined $dbobj || !ref $dbobj ) {
throw("Don't have a db [$dbobj] for new adaptor");
}
- if($dbobj->isa('Bio::EnsEMBL::DBSQL::DBAdaptor')){
+
+ if ( $dbobj->isa('Bio::EnsEMBL::DBSQL::DBAdaptor') ) {
$self->db($dbobj);
- $self->dbc($dbobj->dbc);
- }
- elsif( ref($dbobj) =~ /DBAdaptor$/){
+ $self->dbc( $dbobj->dbc );
+ $self->species_id( $dbobj->species_id() );
+ } elsif ( ref($dbobj) =~ /DBAdaptor$/ ) {
$self->db($dbobj);
- $self->dbc($dbobj->dbc);
- }
- elsif( ref($dbobj) =~ /DBConnection$/){
- $self->dbc($dbobj);
- }
- else{
+ $self->dbc( $dbobj->dbc );
+ } elsif ( ref($dbobj) =~ /DBConnection$/ ) {
+ $self->dbc($dbobj);
+ } else {
throw("Don't have a DBAdaptor [$dbobj] for new adaptor");
}
-
+
return $self;
}
@@ -175,17 +173,19 @@ sub prepare{
using.
Returntype : Bio::EnsEMBL::DBSQL::DBAdaptor
Exceptions : none
- Caller : Adaptors inherited fro BaseAdaptor
+ Caller : Adaptors inherited from BaseAdaptor
Status : Stable
=cut
-sub db{
- my $self = shift;
- $self->{'db'} = shift if(@_);
+sub db {
+ my ( $self, $value ) = @_;
- return $self->{'db'};
+ if ( defined($value) ) {
+ $self->{'db'} = $value;
+ }
+ return $self->{'db'};
}
=head2 dbc
@@ -197,18 +197,45 @@ sub db{
using.
Returntype : Bio::EnsEMBL::DBSQL::DBConnection
Exceptions : none
- Caller : Adaptors inherited fro BaseAdaptor
+ Caller : Adaptors inherited from BaseAdaptor
Status : Stable
=cut
-sub dbc{
- my $self = shift;
- $self->{'dbc'} = shift if(@_);
+sub dbc {
+ my ( $self, $value ) = @_;
+
+ if ( defined($value) ) {
+ $self->{'dbc'} = $value;
+ }
return $self->{'dbc'};
}
+=head2 species_id
+
+ Arg [1] : (optional) int $species_id
+ The internal ID of the species in a multi-species database.
+ Example : $db = $adaptor->db();
+ Description: Getter/Setter for the internal ID of the species in a
+ multi-species database. The default species ID is 1.
+ Returntype : Integer
+ Exceptions : none
+ Caller : Adaptors inherited from BaseAdaptor
+ Status : Stable
+
+=cut
+
+sub species_id {
+ my ( $self, $value ) = @_;
+
+ if ( defined($value) ) {
+ $self->{'species_id'} = $value;
+ }
+
+ return $self->{'species_id'} || 1;
+}
+
# list primary keys for a particular table
# args are table name and primary key field
diff --git a/modules/Bio/EnsEMBL/DBSQL/BaseFeatureAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/BaseFeatureAdaptor.pm
index 828a2e772ac0ab5ed692e75b765c41bca9cbb277..4cc56046e6c404117c4d2b88df9078743544a1c2 100644
--- a/modules/Bio/EnsEMBL/DBSQL/BaseFeatureAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/BaseFeatureAdaptor.pm
@@ -919,12 +919,20 @@ sub _list_seq_region_ids {
my @out;
my $sql = qq(
- SELECT distinct(sr.seq_region_id)
- FROM seq_region sr, $table a
- WHERE sr.seq_region_id = a.seq_region_id
- );
+ SELECT DISTINCT
+ sr.seq_region_id
+ FROM seq_region sr,
+ $table a,
+ coord_system cs
+ WHERE sr.seq_region_id = a.seq_region_id
+ AND sr.coord_system_id = cs.coord_system_id
+ AND cs.species_id = ?);
+
my $sth = $self->prepare($sql);
- $sth->execute;
+
+ $sth->bin_param( 1, $self->species_id(), SQL_INTEGER );
+
+ $sth->execute();
while (my ($id) = $sth->fetchrow) {
push(@out, $id);
diff --git a/modules/Bio/EnsEMBL/DBSQL/BaseMetaContainer.pm b/modules/Bio/EnsEMBL/DBSQL/BaseMetaContainer.pm
index b0180d11d758a8ae85d71f8160ee84630d8bc27a..80e3ceb020e3b1c11173cddc338c741d14d07f70 100644
--- a/modules/Bio/EnsEMBL/DBSQL/BaseMetaContainer.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/BaseMetaContainer.pm
@@ -88,27 +88,48 @@ sub get_schema_version {
=cut
sub list_value_by_key {
- my ($self,$key) = @_;
- my @result;
+ my ( $self, $key ) = @_;
$self->{'cache'} ||= {};
- if( exists $self->{'cache'}->{$key} ) {
+
+ if ( exists $self->{'cache'}->{$key} ) {
return $self->{'cache'}->{$key};
}
- my $sth = $self->prepare( "SELECT meta_value
- FROM meta
- WHERE meta_key = ? ORDER BY meta_id" );
- $sth->execute( $key );
- while( my $arrRef = $sth->fetchrow_arrayref() ) {
+ my $sth;
+ if ( !$self->_species_specific_key($key) ) {
+ $sth =
+ $self->prepare( "SELECT meta_value "
+ . "FROM meta "
+ . "WHERE meta_key = ? "
+ . "AND species_id IS NULL "
+ . "ORDER BY meta_id" );
+
+ $sth->bind_param( 1, $key, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ $sth =
+ $self->prepare( "SELECT meta_value "
+ . "FROM meta "
+ . "WHERE meta_key = ? "
+ . "AND species_id = ? "
+ . "ORDER BY meta_id" );
+
+ $sth->bind_param( 1, $key, SQL_VARCHAR );
+ $sth->bind_param( 2, $self->species_id(), SQL_INTEGER );
+ $sth->execute();
+ }
+
+ my @result;
+ while ( my $arrRef = $sth->fetchrow_arrayref() ) {
push( @result, $arrRef->[0] );
}
+
$sth->finish();
$self->{'cache'}->{$key} = \@result;
return \@result;
-}
-
+} ## end sub list_value_by_key
=head2 store_key_value
@@ -128,22 +149,36 @@ sub list_value_by_key {
sub store_key_value {
my ( $self, $key, $value ) = @_;
- if ($self->key_value_exists($key, $value)) {
- warn("Key/value pair $key/$value already exists in the meta table; not storing duplicate");
+ if ( $self->key_value_exists( $key, $value ) ) {
+ warn( "Key-value pair '$key'-'$value' "
+ . "already exists in the meta table; "
+ . "not storing duplicate" );
return;
}
- my $sth = $self->prepare( "INSERT INTO meta( meta_key, meta_value)
- VALUES( ?, ? )" );
+ if ( !$self->_species_specific_key($key) ) {
+ my $sth = $self->prepare(
+ 'INSERT INTO meta (species_id, meta_key, meta_value) '
+ . 'VALUES(\N, ?, ?)' );
- my $res = $sth->execute( $key, $value );
+ $sth->bind_param( 1, $key, SQL_VARCHAR );
+ $sth->bind_param( 2, $value, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ my $sth = $self->prepare(
+ 'INSERT INTO meta (species_id, meta_key, meta_value) '
+ . 'VALUES (?, ?, ?)' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
+ $sth->bind_param( 2, $key, SQL_VARCHAR );
+ $sth->bind_param( 3, $value, SQL_VARCHAR );
+ $sth->execute();
+ }
$self->{'cache'} ||= {};
delete $self->{'cache'}->{$key};
-
- return;
-}
+} ## end sub store_key_value
=head2 update_key_value
@@ -163,11 +198,28 @@ sub store_key_value {
sub update_key_value {
my ( $self, $key, $value ) = @_;
- my $sth = $self->prepare( "UPDATE meta SET meta_value = ? WHERE meta_key = ?" );
+ if ( !$self->_species_specific_key($key) ) {
+ my $sth =
+ $self->prepare( 'UPDATE meta SET meta_value = ? '
+ . 'WHERE meta_key = ?'
+ . 'AND species_id IS NULL' );
- my $res = $sth->execute( $value, $key );
- return;
-}
+ $sth->bind_param( 1, $value, SQL_VARCHAR );
+ $sth->bind_param( 2, $key, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ my $sth =
+ $self->prepare( 'UPDATE meta '
+ . 'SET meta_value = ? '
+ . 'WHERE meta_key = ? '
+ . 'AND species_id = ?' );
+
+ $sth->bind_param( 1, $value, SQL_VARCHAR );
+ $sth->bind_param( 2, $key, SQL_VARCHAR );
+ $sth->bind_param( 3, $self->species_id(), SQL_INTEGER );
+ $sth->execute();
+ }
+} ## end sub update_key_value
=head2 delete_key
@@ -185,15 +237,28 @@ sub update_key_value {
=cut
sub delete_key {
- my ($self, $key) = @_;
+ my ( $self, $key ) = @_;
- my $sth = $self->prepare("DELETE FROM meta WHERE meta_key = ?");
- $sth->execute($key);
- $sth->finish();
+ if ( !$self->_species_specific_key($key) ) {
+ my $sth =
+ $self->prepare( 'DELETE FROM meta '
+ . 'WHERE meta_key = ?'
+ . 'AND species_id IS NULL' );
- delete $self->{'cache'}->{$key};
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ my $sth =
+ $self->prepare( 'DELETE FROM meta '
+ . 'WHERE meta_key = ? '
+ . 'AND species_id = ?' );
+
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->bin_param( 2, $self->species_id(), SQL_INTEGER );
+ $sth->execute();
+ }
- return;
+ delete $self->{'cache'}->{$key};
}
=head2 delete_key_value
@@ -213,16 +278,33 @@ sub delete_key {
=cut
sub delete_key_value {
- my ($self, $key, $value) = @_;
+ my ( $self, $key, $value ) = @_;
- my $sth = $self->prepare("DELETE FROM meta WHERE meta_key = ? AND meta_value = ?");
- $sth->execute($key, $value);
- $sth->finish();
+ if ( !$self->_species_specific_key($key) ) {
+ my $sth =
+ $self->prepare( 'DELETE FROM meta '
+ . 'WHERE meta_key = ? '
+ . 'AND meta_value = ?'
+ . 'AND species_id IS NULL' );
- delete $self->{'cache'}->{$key};
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->bin_param( 2, $value, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ my $sth =
+ $self->prepare( 'DELETE FROM meta '
+ . 'WHERE meta_key = ? '
+ . 'AND meta_value = ? '
+ . 'AND species_id = ?' );
+
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->bin_param( 2, $value, SQL_VARCHAR );
+ $sth->bin_param( 3, $self->species_id(), SQL_INTEGER );
+ $sth->execute();
+ }
- return;
-}
+ delete $self->{'cache'}->{$key};
+} ## end sub delete_key_value
=head2 key_value_exists
@@ -231,7 +313,8 @@ sub delete_key_value {
Arg [2] : string $value
the value to check
Example : if ($meta_container->key_value_exists($key, $value)) ...
- Description: Return true if a particular key/value pair exists, undef otherwise
+ Description: Return true (1) if a particular key/value pair exists,
+ false (0) otherwise.
Returntype : boolean
Exceptions : none
Caller : ?
@@ -240,20 +323,51 @@ sub delete_key_value {
=cut
sub key_value_exists {
+ my ( $self, $key, $value ) = @_;
- my ($self, $key, $value) = @_;
-
- my $sth = $self->prepare( "SELECT meta_value FROM meta WHERE meta_key = ? AND meta_value = ?" );
- $sth->execute($key, $value);
+ my $sth;
+ if ( !$self->_species_specific_key($key) ) {
+ $sth =
+ $self->prepare( 'SELECT meta_value '
+ . 'FROM meta '
+ . 'WHERE meta_key = ? '
+ . 'AND meta_value = ?'
+ . 'AND species_id IS NULL' );
+
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->bin_param( 2, $value, SQL_VARCHAR );
+ $sth->execute();
+ } else {
+ $sth =
+ $self->prepare( 'SELECT meta_value '
+ . 'FROM meta '
+ . 'WHERE meta_key = ? '
+ . 'AND meta_value = ? '
+ . 'AND species_id = ?' );
+
+ $sth->bin_param( 1, $key, SQL_VARCHAR );
+ $sth->bin_param( 2, $value, SQL_VARCHAR );
+ $sth->bin_param( 3, $self->species_id(), SQL_INTEGER );
+ $sth->execute();
+ }
- while( my $arrRef = $sth->fetchrow_arrayref() ) {
- if ($arrRef->[0] eq $value) {
+ while ( my $arrRef = $sth->fetchrow_arrayref() ) {
+ if ( $arrRef->[0] eq $value ) {
$sth->finish();
return 1;
}
}
- return undef;
+ return 0;
+} ## end sub key_value_exists
+
+# This utility method determines whether the key is a species-specific
+# meta key or not. If the key is either 'patch' or 'schema_version',
+# then it is not species-specific.
+
+sub _species_specific_key {
+ my ( $self, $key ) = @_;
+ return ( $key ne 'patch' && $key ne 'schema_version' );
}
1;
diff --git a/modules/Bio/EnsEMBL/DBSQL/CoordSystemAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/CoordSystemAdaptor.pm
index eb6791e34218594f0a2e56e6fbe85ef92ee90158..925bc13a63e6d8ae43e09c3ab1f843fad0361b36 100644
--- a/modules/Bio/EnsEMBL/DBSQL/CoordSystemAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/CoordSystemAdaptor.pm
@@ -126,28 +126,27 @@ use vars qw(@ISA);
=cut
sub new {
- my $caller = shift;
+ my ( $proto, @args ) = @_;
- my $class = ref($caller) || $caller;
-
- my $self = $class->SUPER::new(@_);
+ my $class = ref($proto) || $proto;
+ my $self = $class->SUPER::new(@args);
#
# Cache the entire contents of the coord_system table cross-referenced
- # by dbID and name
+ # by dbID and name.
#
- #keyed on name, list of coord_system value
+ # keyed on name, list of coord_system value
$self->{'_name_cache'} = {};
- #keyed on id, coord_system value
+ # keyed on id, coord_system value
$self->{'_dbID_cache'} = {};
- #keyed on rank
+ # keyed on rank
$self->{'_rank_cache'} = {};
- #keyed on id, 1/undef values
- $self->{'_is_sequence_level'} = {};
+ # keyed on id, 1/undef values
+ $self->{'_is_sequence_level'} = {};
$self->{'_is_default_version'} = {};
#cache to store the seq_region_mapping information
@@ -157,143 +156,184 @@ sub new {
$self->{'_external_seq_region_mapping'} = {};
my $sth = $self->prepare(
- 'SELECT coord_system_id, name, rank, version, attrib ' .
- 'FROM coord_system');
+ 'SELECT coord_system_id, name, rank, version, attrib '
+ . 'FROM coord_system '
+ . 'WHERE species_id = ?' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
- my ($dbID, $name, $rank, $version, $attrib);
- $sth->bind_columns(\$dbID, \$name, \$rank, \$version, \$attrib);
+ my ( $dbID, $name, $rank, $version, $attrib );
+ $sth->bind_columns( \( $dbID, $name, $rank, $version, $attrib ) );
- while($sth->fetch()) {
+ while ( $sth->fetch() ) {
my $seq_lvl = 0;
my $default = 0;
- if($attrib) {
- foreach my $attrib (split(',', $attrib)) {
+
+ if ( defined($attrib) ) {
+ foreach my $attrib ( split( ',', $attrib ) ) {
$self->{"_is_$attrib"}->{$dbID} = 1;
- if($attrib eq 'sequence_level') {
+ if ( $attrib eq 'sequence_level' ) {
$seq_lvl = 1;
- } elsif($attrib eq 'default_version') {
+ } elsif ( $attrib eq 'default_version' ) {
$default = 1;
}
}
}
- my $cs = Bio::EnsEMBL::CoordSystem->new
- (-DBID => $dbID,
- -ADAPTOR => $self,
- -NAME => $name,
- -VERSION => $version,
- -RANK => $rank,
- -SEQUENCE_LEVEL => $seq_lvl,
- -DEFAULT => $default);
+ my $cs =
+ Bio::EnsEMBL::CoordSystem->new( -DBID => $dbID,
+ -ADAPTOR => $self,
+ -NAME => $name,
+ -VERSION => $version,
+ -RANK => $rank,
+ -SEQUENCE_LEVEL => $seq_lvl,
+ -DEFAULT => $default );
$self->{'_dbID_cache'}->{$dbID} = $cs;
- $self->{'_name_cache'}->{lc($name)} ||= [];
+ $self->{'_name_cache'}->{ lc($name) } ||= [];
$self->{'_rank_cache'}->{$rank} = $cs;
- push @{$self->{'_name_cache'}->{lc($name)}}, $cs;
- }
+
+ push @{ $self->{'_name_cache'}->{ lc($name) } }, $cs;
+
+ } ## end while ( $sth->fetch() )
$sth->finish();
- $self->_cache_mapping_paths;
+ $self->_cache_mapping_paths();
- $self->_cache_seq_region_mapping;
+ $self->_cache_seq_region_mapping();
return $self;
-}
+} ## end sub new
-#this cache will load the information from the seq_region_table, if any, to allow mapping
-#between internal and external seq_region_id
-sub _cache_seq_region_mapping{
- my $self = shift;
-
- #for a given core database, will return the schema_build information
- my $schema_build = $self->db->_get_schema_build();
- #prepare the query to get relation for the current database being used
- my $sql = 'SELECT s.internal_seq_region_id, s.external_seq_region_id from seq_region_mapping s, mapping_set ms where ms.mapping_set_id = s.mapping_set_id and ms.schema_build="'.$schema_build.'"';
- #load the cache:
- foreach my $row (@{$self->db->dbc->db_handle->selectall_arrayref($sql)}){
- #the internal->external
- $self->{'_internal_seq_region_mapping'}->{$row->[0]} = $row->[1];
- #the external->internal
- $self->{'_external_seq_region_mapping'}->{$row->[1]} = $row->[0];
- }
- #and return
- return;
-}
+sub _cache_seq_region_mapping {
+ #
+ # This cache will load the information from the seq_region_table, if
+ # any, to allow mapping between internal and external seq_region_id.
+ #
+
+ my ($self) = @_;
+
+ # For a given core database, will return the schema_build information.
+ my $schema_build = $self->db->_get_schema_build();
+
+ # Prepare the query to get relation for the current database being
+ # used.
+ my $sql = qq(
+ SELECT s.internal_seq_region_id,
+ s.external_seq_region_id
+ FROM seq_region_mapping s,
+ mapping_set ms,
+ seq_region sr,
+ coord_system cs
+ WHERE ms.mapping_set_id = s.mapping_set_id
+ AND ms.schema_build = ?
+ AND s.internal_seq_region_id = sr.seq_region_id
+ AND sr.coord_system_id = cs.coord_system_id
+ AND cs.species_id = ?);
+
+ my $sth = $self->prepare($sql);
+
+ $sth->bind_param( 1, $schema_build, SQL_VARCHAR );
+ $sth->bind_param( 2, $self->species_id(), SQL_INTEGER );
+
+ $sth->execute();
-sub _cache_mapping_paths{
+ # Load the cache:
+ foreach my $row ( @{ $sth->fetchall_arrayref() } ) {
+ # internal->external
+ $self->{'_internal_seq_region_mapping'}->{ $row->[0] } = $row->[1];
+ # external->internal
+ $self->{'_external_seq_region_mapping'}->{ $row->[1] } = $row->[0];
+ }
+
+ $sth->finish();
+
+} ## end sub _cache_seq_region_mapping
+
+
+sub _cache_mapping_paths {
#
- # Retrieve a list of available mappings from the meta table.
- # this may eventually be moved a table of its own if this proves too
- # cumbersome
+ # Retrieve a list of available mappings from the meta table. This
+ # may eventually be moved a table of its own if this proves too
+ # cumbersome.
#
- my $self = shift;
+
+ my ($self) = @_;
my %mapping_paths;
my $mc = $self->db()->get_MetaContainer();
- MAP_PATH:
- foreach my $map_path (@{$mc->list_value_by_key('assembly.mapping')}) {
- my @cs_strings = split(/[|#]/, $map_path);
+MAP_PATH:
+ foreach
+ my $map_path ( @{ $mc->list_value_by_key('assembly.mapping') } )
+ {
+ my @cs_strings = split( /[|#]/, $map_path );
- if(@cs_strings < 2) {
- warning("Incorrectly formatted assembly.mapping value in meta " .
- "table: $map_path");
+ if ( @cs_strings < 2 ) {
+ warning( "Incorrectly formatted assembly.mapping value in meta "
+ . "table: $map_path" );
next MAP_PATH;
}
my @coord_systems;
foreach my $cs_string (@cs_strings) {
- my($name, $version) = split(/:/, $cs_string);
- my $cs = $self->fetch_by_name($name, $version);
- if(!$cs) {
- warning("Unknown coordinate system specified in meta table " .
- " assembly.mapping:\n $name:$version");
+ my ( $name, $version ) = split( /:/, $cs_string );
+
+ my $cs = $self->fetch_by_name( $name, $version );
+
+ if ( !$cs ) {
+ warning( "Unknown coordinate system specified in meta table "
+ . " assembly.mapping:\n $name:$version" );
next MAP_PATH;
}
+
push @coord_systems, $cs;
}
- # if the delimiter is a # we want a special case, multiple parts of the same
- # componente map to same assembly part. As this looks like the "long" mapping
- # we just make the path a bit longer :-)
+ # If the delimiter is a # we want a special case, multiple parts of
+ # the same componente map to same assembly part. As this looks like
+ # the "long" mapping we just make the path a bit longer :-)
- if( $map_path =~ /\#/ && scalar( @coord_systems ) == 2 ) {
- splice( @coord_systems, 1, 0, ( undef ));
+ if ( $map_path =~ /#/ && scalar(@coord_systems) == 2 ) {
+ splice( @coord_systems, 1, 0, (undef) );
}
my $cs1 = $coord_systems[0];
- my $cs2 = $coord_systems[$#coord_systems];
+ my $cs2 = $coord_systems[$#coord_systems];
- my $key1 = $cs1->name().':'.$cs1->version();
- my $key2 = $cs2->name().':'.$cs2->version();
+ my $key1 = $cs1->name() . ':' . $cs1->version();
+ my $key2 = $cs2->name() . ':' . $cs2->version();
- if(exists($mapping_paths{"$key1|$key2"})) {
- warning("Meta table specifies multiple mapping paths between " .
- "coord systems $key1 and $key2.\n" .
- "Choosing shorter path arbitrarily.");
+ if ( exists( $mapping_paths{"$key1|$key2"} ) ) {
+ warning( "Meta table specifies multiple mapping paths between "
+ . "coord systems $key1 and $key2.\n"
+ . "Choosing shorter path arbitrarily." );
- next MAP_PATH if(@{$mapping_paths{"$key1|$key2"}} < @coord_systems);
+ if ( @{ $mapping_paths{"$key1|$key2"} } < @coord_systems ) {
+ next MAP_PATH;
+ }
}
$mapping_paths{"$key1|$key2"} = \@coord_systems;
- }
+ } ## end foreach my $map_path ( @{ $mc...
#
- # Create the pseudo coord system 'toplevel' and cache it so that
- # only one of these is created for each db...
+ # Create the pseudo coord system 'toplevel' and cache it so that only
+ # one of these is created for each db...
#
- my $toplevel = Bio::EnsEMBL::CoordSystem->new(-TOP_LEVEL => 1,
- -NAME => 'toplevel',
- -ADAPTOR => $self);
+
+ my $toplevel =
+ Bio::EnsEMBL::CoordSystem->new( -TOP_LEVEL => 1,
+ -NAME => 'toplevel',
+ -ADAPTOR => $self );
$self->{'_top_level'} = $toplevel;
$self->{'_mapping_paths'} = \%mapping_paths;
- return 1;
-}
-
+ return 1;
+} ## end sub _cache_mapping_paths
=head2 fetch_all
@@ -934,16 +974,20 @@ sub store {
# store the coordinate system in the database
#
- my $sth = $db->dbc->prepare('INSERT INTO coord_system ' .
- 'SET name = ?, ' .
- 'version = ?, ' .
- 'attrib = ?,' .
- 'rank = ?');
+ my $sth =
+ $db->dbc->prepare( 'INSERT INTO coord_system '
+ . 'SET name = ?, '
+ . 'version = ?, '
+ . 'attrib = ?,'
+ . 'rank = ?,'
+ . 'species_id = ?' );
+
+ $sth->bind_param( 1, $name, SQL_VARCHAR );
+ $sth->bind_param( 2, $version, SQL_VARCHAR );
+ $sth->bind_param( 3, $attrib_str, SQL_VARCHAR );
+ $sth->bind_param( 4, $rank, SQL_INTEGER );
+ $sth->bind_param( 5, $self->species_id(), SQL_INTEGER );
- $sth->bind_param(1,$name,SQL_VARCHAR);
- $sth->bind_param(2,$version,SQL_VARCHAR);
- $sth->bind_param(3,$attrib_str,SQL_VARCHAR);
- $sth->bind_param(4,$rank,SQL_INTEGER);
$sth->execute();
my $dbID = $sth->{'mysql_insertid'};
$sth->finish();
diff --git a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
index 2852e19aa46c3d045ab68504027245273e2f8a5a..dc0bcf63fa5ef2e299d5e5679ae793a876b3b7a9 100755
--- a/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DBAdaptor.pm
@@ -81,36 +81,28 @@ my $reg = "Bio::EnsEMBL::Registry";
=cut
sub new {
- my($class, @args) = @_;
+ my ( $class, @args ) = @_;
- my $self ={};
- bless $self,$class;
+ my $self = bless {}, $class;
-
- my ($species, $group, $con, $dnadb) =
- rearrange([qw(SPECIES GROUP DBCONN DNADB)], @args);
+ my ( $species, $species_id, $group, $con, $dnadb ) =
+ rearrange( [qw(SPECIES SPECIES_ID GROUP DBCONN DNADB)], @args );
- if(defined($con)){
- $self->dbc($con);
- }
- else{
- $self->dbc(new Bio::EnsEMBL::DBSQL::DBConnection(@args));
- }
-
- if(defined($species)){
- $self->species($species);
+ if ( defined($con) ) { $self->dbc($con) }
+ else {
+ $self->dbc( new Bio::EnsEMBL::DBSQL::DBConnection(@args) );
}
- if(defined($group)){
- $self->group($group);
- }
+ if ( defined($species) ) { $self->species($species) }
+ if ( defined($group) ) { $self->group($group) }
+
+ $species_id ||= 1;
+ $self->species_id($species_id);
$self = Bio::EnsEMBL::Utils::ConfigRegistry::gen_load($self);
- if(defined $dnadb) {
- $self->dnadb($dnadb);
- }
-
+ if ( defined $dnadb ) { $self->dnadb($dnadb) }
+
return $self;
}
@@ -587,8 +579,7 @@ sub add_GenericFeatureAdaptor {
$self->{'generic_feature_adaptors'}->{$name} = $adaptor_obj;
}
-=head2 species
-
+=head2 species
Arg [1] : (optional) string $arg
The new value of the species used by this DBAdaptor.
Example : $species = $dba->species()
@@ -604,12 +595,42 @@ sub add_GenericFeatureAdaptor {
=cut
sub species {
- my ($self, $arg ) = @_;
- ( defined $arg ) &&
- ( $self->{_species} = $arg );
+ my ( $self, $arg ) = @_;
+
+ if ( defined($arg) ) {
+ $self->{_species} = $arg;
+ }
+
$self->{_species};
}
+=head2 species_id
+
+ Arg [1] : (optional) string $arg
+ The new value of the species_id used by this DBAdaptor
+ when dealing with multi-species databases.
+ Example : $species_id = $dba->species_id()
+ Description: Getter/Setter for the species_id of to use for this
+ connection. There is currently no point in setting
+ this value after the connection has already been
+ established by the constructor.
+ Returntype : string
+ Exceptions : none
+ Caller : new
+ Status : Stable
+
+=cut
+
+sub species_id {
+ my ( $self, $arg ) = @_;
+
+ if ( defined($arg) ) {
+ $self->{_species_id} = $arg;
+ }
+
+ $self->{_species_id};
+}
+
=head2 group
diff --git a/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
index fe5167b784938106bf9a959a28f7e29b86b0e481..f061bd396078fb2f42d93bacd9c1e12a91ce4928 100644
--- a/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DBEntryAdaptor.pm
@@ -54,7 +54,8 @@ use strict;
Arg [1] : int $dbID
the unique database identifier for the DBEntry to retrieve
Example : my $db_entry = $db_entry_adaptor->fetch_by_dbID($dbID);
- Description: retrieves a dbEntry from the database via its unique identifier
+ Description: Retrieves a dbEntry from the database via its unique
+ identifier.
Returntype : Bio::EnsEMBL::DBEntry
Exceptions : none
Caller : general
@@ -153,9 +154,13 @@ sub fetch_by_dbID {
retrieve.
Example : my $xref = $dbea->fetch_by_db_accession('Interpro','IPR003439');
print $xref->description(), "\n" if($xref);
- Description: Retrieves a DBEntry (xref) via the name of the database it is
- from and its primary accession in that database. Undef is
- returned if the xref cannot be found in the database.
+ Description: Retrieves a DBEntry (xref) via the name of the database
+ it is from and its primary accession in that database.
+ Undef is returned if the xref cannot be found in the
+ database.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : Bio::EnsEMBL::DBSQL::DBEntry
Exceptions : thrown if arguments are incorrect
Caller : general, domainview
@@ -788,6 +793,9 @@ sub remove_from_object {
Arf [4] : optional $exdb_type (external database type)
Example : $self->_fetch_by_object_type( $translation_id, 'Translation' )
Description: Fetches DBEntry by Object type
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : arrayref of DBEntry objects; may be of type IdentityXref if
there is mapping data, or GoXref if there is linkage data.
Exceptions : none
@@ -968,10 +976,15 @@ SSQL
Arg [1] : string $external_id
Example : @gene_ids = $dbea->list_gene_ids_by_external_db_id(1020);
- Description: Retrieve a list of geneid by an external identifier that is
- linked to any of the genes transcripts, translations or the
- gene itself. NOTE: if more than one external identifier has the
- same primary accession then genes for each of these is returned.
+ Description: Retrieve a list of geneid by an external identifier that
+ is linked to any of the genes transcripts, translations
+ or the gene itself.
+ NOTE: If more than one external identifier has the
+ same primary accession then genes for each of these is
+ returned.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : list of ints
Exceptions : none
Caller : unknown
@@ -1077,6 +1090,9 @@ sub list_translation_ids_by_extids {
Arg [4] : (optional) string $external_db_name
other object type to be returned
Example : $self->_type_by_external_id($name, 'Translation');
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Description: Gets
Returntype : list of dbIDs (gene_id, transcript_id, etc.)
Exceptions : none
@@ -1219,6 +1235,9 @@ sub _type_by_external_id {
other object type to be returned
Example : $self->_type_by_external_db_id(1030, 'Translation');
Description: Gets
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : list of dbIDs (gene_id, transcript_id, etc.)
Exceptions : none
Caller : list_translation_ids_by_extids
@@ -1298,8 +1317,11 @@ sub _type_by_external_db_id{
Example : @canc_refs = @{$db_entry_adaptor->fetch_all_by_description("%cancer%")};
@db_entries = @{$db_entry_adaptor->fetch_all_by_description("%cancer%","MIM_MORBID")};
- Description: Retrieves DBEntrys that match the description. Optionally you can search on
- external databases tpye
+ Description: Retrieves DBEntries that match the description.
+ Optionally you can search on external databases type.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : ref to array of Bio::EnsEMBL::DBSQL::DBEntry
Exceptions : None.
Caller : General
diff --git a/modules/Bio/EnsEMBL/DBSQL/DensityTypeAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/DensityTypeAdaptor.pm
index 736c27e55c51cae085168ff861735badb0837e15..de23d96fca1ec88f5052e4379f4a621a56a31afb 100644
--- a/modules/Bio/EnsEMBL/DBSQL/DensityTypeAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/DensityTypeAdaptor.pm
@@ -70,7 +70,10 @@ sub new {
Arg [1] : none
Example : my @density_types = @{$density_type_adaptor->fetch_all};
- Description: Retrieves every density type in the database
+ Description: Retrieves every density type in the database.
+ NOTE: In a multi-species database, this method will
+ return all the entries, not just the ones associated with
+ the current species.
Returntype : reference to list of Bio::EnsEMBL::DensityType objects
Exceptions : none
Caller : general, new
@@ -150,7 +153,10 @@ sub fetch_by_dbID {
Arg [1] : string $logic_name
Example : my @dts = @{$dtype_adaptor->fetch_all('repeat_coverage')};
- Description: Retrieves all density types with a given logic name
+ Description: Retrieves all density types with a given logic name.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : reference to list of Bio::EnsEMBL::DensityTypes
Exceptions : thrown if logic_name argument is not provided
Caller : general
diff --git a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
index f9031a88f82f270e7921dbf454311d8b36ec5d0e..54da59ceab42b77ff0b0c7c894e6cb4b5b19b508 100644
--- a/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/GeneAdaptor.pm
@@ -337,20 +337,26 @@ sub fetch_all_by_domain {
throw("domain argument is required") unless ($domain);
my $sth = $self->prepare(qq(
- SELECT tr.gene_id
- FROM interpro i,
- protein_feature pf,
- transcript tr,
- translation tl
- WHERE i.interpro_ac = ?
- AND i.id = pf.hit_name
- AND pf.translation_id = tl.translation_id
- AND tr.transcript_id = tl.transcript_id
- AND tr.is_current = 1
- GROUP BY tr.gene_id
- ));
+ SELECT tr.gene_id
+ FROM interpro i,
+ protein_feature pf,
+ transcript tr,
+ translation tl,
+ seq_region sr,
+ coord_system cs
+ WHERE cs.species_id = ?
+ AND cs.coord_system_id = sr.coord_system_id
+ AND sr.seq_region_id = tr.seq_region_id
+ AND tr.is_current = 1
+ AND tr.transcript_id = tl.transcript_id
+ AND tl.translation_id = pf.translation_id
+ AND pf.hit_name = i.id
+ AND i.interpro_ac = ?
+ GROUP BY tr.gene_id));
+
+ $sth->bind_param( 1, $self->species_id(), SQL_VARCHAR );
+ $sth->bind_param( 2, $domain, SQL_VARCHAR );
- $sth->bind_param(1, $domain, SQL_VARCHAR);
$sth->execute();
my @array = @{$sth->fetchall_arrayref()};
@@ -965,17 +971,17 @@ sub store {
# column status is used from schema version 34 onwards (before it was
# confidence)
- my $sth = $self->prepare( $store_gene_sql );
- $sth->bind_param(1, $type, SQL_VARCHAR);
- $sth->bind_param(2, $analysis_id, SQL_INTEGER);
- $sth->bind_param(3, $seq_region_id, SQL_INTEGER);
- $sth->bind_param(4, $gene->start, SQL_INTEGER);
- $sth->bind_param(5, $gene->end, SQL_INTEGER);
- $sth->bind_param(6, $gene->strand, SQL_TINYINT);
- $sth->bind_param(7, $gene->description, SQL_LONGVARCHAR);
- $sth->bind_param(8, $gene->source, SQL_VARCHAR);
- $sth->bind_param(9, $gene->status, SQL_VARCHAR);
- $sth->bind_param(10, $is_current, SQL_TINYINT);
+ my $sth = $self->prepare($store_gene_sql);
+ $sth->bind_param( 1, $type, SQL_VARCHAR );
+ $sth->bind_param( 2, $analysis_id, SQL_INTEGER );
+ $sth->bind_param( 3, $seq_region_id, SQL_INTEGER );
+ $sth->bind_param( 4, $gene->start, SQL_INTEGER );
+ $sth->bind_param( 5, $gene->end, SQL_INTEGER );
+ $sth->bind_param( 6, $gene->strand, SQL_TINYINT );
+ $sth->bind_param( 7, $gene->description, SQL_LONGVARCHAR );
+ $sth->bind_param( 8, $gene->source, SQL_VARCHAR );
+ $sth->bind_param( 9, $gene->status, SQL_VARCHAR );
+ $sth->bind_param( 10, $is_current, SQL_TINYINT );
$sth->execute();
$sth->finish();
@@ -1132,8 +1138,8 @@ sub remove {
}
# remove all alternative allele entries associated with this gene
- my $sth = $self->prepare("delete from alt_allele where gene_id = ?");
- $sth->bind_param(1, $gene->dbID, SQL_INTEGER);
+ my $sth = $self->prepare("DELETE FROM alt_allele WHERE gene_id = ?");
+ $sth->bind_param( 1, $gene->dbID, SQL_INTEGER );
$sth->execute();
$sth->finish();
@@ -1149,22 +1155,25 @@ sub remove {
# remove the gene stable identifier
- $sth = $self->prepare( "delete from gene_stable_id where gene_id = ? " );
- $sth->bind_param(1, $gene->dbID, SQL_INTEGER);
+ $sth =
+ $self->prepare("DELETE FROM gene_stable_id WHERE gene_id = ? ");
+ $sth->bind_param( 1, $gene->dbID, SQL_INTEGER );
$sth->execute();
$sth->finish();
# remove any unconventional transcript associations involving this gene
- $sth = $self->prepare( "delete from unconventional_transcript_association where gene_id = ? " );
- $sth->bind_param(1, $gene->dbID, SQL_INTEGER);
+ $sth =
+ $self->prepare( "DELETE FROM unconventional_transcript_association "
+ . "WHERE gene_id = ? " );
+ $sth->bind_param( 1, $gene->dbID, SQL_INTEGER );
$sth->execute();
$sth->finish();
# remove this gene from the database
- $sth = $self->prepare( "delete from gene where gene_id = ? " );
- $sth->bind_param(1, $gene->dbID, SQL_INTEGER);
+ $sth = $self->prepare("DELETE FROM gene WHERE gene_id = ? ");
+ $sth->bind_param( 1, $gene->dbID, SQL_INTEGER );
$sth->execute();
$sth->finish();
@@ -1193,26 +1202,28 @@ sub remove {
sub get_Interpro_by_geneid {
my ($self, $gene_stable_id) = @_;
-
+
my $sql = qq(
- SELECT i.interpro_ac,
- x.description
- FROM transcript t,
- translation tl,
- protein_feature pf,
- interpro i,
- xref x,
- gene_stable_id gsi
- WHERE gsi.stable_id = '$gene_stable_id'
- AND t.gene_id = gsi.gene_id
- AND t.is_current = 1
- AND tl.transcript_id = t.transcript_id
- AND tl.translation_id = pf.translation_id
- AND i.id = pf.hit_name
- AND i.interpro_ac = x.dbprimary_acc
- );
-
+ SELECT i.interpro_ac,
+ x.description
+ FROM transcript t,
+ translation tl,
+ protein_feature pf,
+ interpro i,
+ xref x,
+ gene_stable_id gsi
+ WHERE gsi.stable_id = ?
+ AND t.gene_id = gsi.gene_id
+ AND t.is_current = 1
+ AND tl.transcript_id = t.transcript_id
+ AND tl.translation_id = pf.translation_id
+ AND i.id = pf.hit_name
+ AND i.interpro_ac = x.dbprimary_acc);
+
my $sth = $self->prepare($sql);
+
+ $sth->bind_param( 1, $gene_stable_id, SQL_VARCHAR );
+
$sth->execute;
my @out;
@@ -1511,22 +1522,23 @@ sub _objs_from_sth {
=cut
-sub cache_gene_seq_mappings{
+sub cache_gene_seq_mappings {
my ($self) = @_;
# get the sequence level to map too
- my $sql = qq(
- SELECT name
- FROM coord_system
- WHERE attrib like "%sequence_level%"
- );
+ my $sql =
+ 'SELECT name '
+ . 'FROM coord_system '
+ . 'WHERE attrib like "%%sequence_level%%"'
+ . 'AND species_id = ?';
my $sth = $self->prepare($sql);
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
-
+
my $sequence_level = $sth->fetchrow_array();
-
+
$sth->finish();
my $csa = $self->db->get_CoordSystemAdaptor();
@@ -1536,14 +1548,15 @@ sub cache_gene_seq_mappings{
# get level to map to two
- my $mcc = $self->db->get_MetaCoordContainerAdaptor();
+ my $mcc = $self->db->get_MetaCoordContainerAdaptor();
my $csnew = $mcc->fetch_all_CoordSystems_by_feature_type('gene');
foreach my $cs2 (@$csnew) {
- my $am = $ama->fetch_by_CoordSystems($cs1, $cs2);
- $am->register_all();
+ my $am = $ama->fetch_by_CoordSystems( $cs1, $cs2 );
+ $am->register_all();
}
-}
+
+} ## end sub cache_gene_seq_mappings
=head2 fetch_all_by_exon_supporting_evidence
diff --git a/modules/Bio/EnsEMBL/DBSQL/MetaCoordContainer.pm b/modules/Bio/EnsEMBL/DBSQL/MetaCoordContainer.pm
index d121a19f3ee66a294b2b173ca4150ff87254ef0c..d7d2fad9dd61572cc3f6b2b4c6a223a77c2d825e 100644
--- a/modules/Bio/EnsEMBL/DBSQL/MetaCoordContainer.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/MetaCoordContainer.pm
@@ -20,22 +20,31 @@ sub new {
my $self = $class->SUPER::new(@_);
#
- # Retrieve the list of the coordinate systems that features are stored in
- # and cache them
+ # Retrieve the list of the coordinate systems that features are stored
+ # in and cache them.
#
- my $sth = $self->prepare
- ('SELECT table_name, coord_system_id, max_length FROM meta_coord');
+
+ my $sth = $self->prepare(
+ 'SELECT mc.table_name, mc.coord_system_id, mc.max_length '
+ . 'FROM meta_coord mc, coord_system cs '
+ . 'WHERE mc.coord_system_id = cs.coord_system_id '
+ . 'AND cs.species_id = ?' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
- while(my ($table_name, $cs_id, $max_length) = $sth->fetchrow_array()) {
- $self->{'_feature_cache'}->{lc($table_name)} ||= [];
- push @{$self->{'_feature_cache'}->{lc($table_name)}}, $cs_id;
- $self->{'_max_len_cache'}->{$cs_id}->{lc($table_name)} = $max_length;
+ while ( my ( $table_name, $cs_id, $max_length ) =
+ $sth->fetchrow_array() )
+ {
+ $self->{'_feature_cache'}->{ lc($table_name) } ||= [];
+ push @{ $self->{'_feature_cache'}->{ lc($table_name) } }, $cs_id;
+ $self->{'_max_len_cache'}->{$cs_id}->{ lc($table_name) } =
+ $max_length;
}
$sth->finish();
return $self;
-}
+} ## end sub new
diff --git a/modules/Bio/EnsEMBL/DBSQL/MiscFeatureAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/MiscFeatureAdaptor.pm
index 360bc71cc0a27f07c168ed803fdd9a7e2cdab0ab..b1f50a088981fe2026efed3b710c382fd550f894 100644
--- a/modules/Bio/EnsEMBL/DBSQL/MiscFeatureAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/MiscFeatureAdaptor.pm
@@ -130,10 +130,11 @@ sub fetch_all_by_Slice_and_set_code {
#get the misc feature with synonym 'AL014121'
($feat)=@{$mfa->fetch_all_by_attrib_type_value('synonym','AL014121');
Description: Retrieves MiscFeatures which have a particular attribute.
- If the attribute value argument is also provided only features
- which have the attribute AND a particular value are returned.
- The features are returned in their native coordinate system
- (i.e. the coordinate system that they are stored in).
+ If the attribute value argument is also provided only
+ features which have the attribute AND a particular value
+ are returned. The features are returned in their native
+ coordinate system (i.e. the coordinate system that they
+ are stored in).
Returntype : listref of Bio::EnsEMBL::MiscFeatures
Exceptions : throw if attrib_type code arg is not provided
Caller : general
@@ -142,59 +143,71 @@ sub fetch_all_by_Slice_and_set_code {
=cut
sub fetch_all_by_attribute_type_value {
- my $self = shift;
+ my $self = shift;
my $attrib_type_code = shift;
- my $attrib_value = shift;
-
- throw("Attrib type code argument is required.") if(!$attrib_type_code);
-
- #
- # Need to do 2 queries so that all of the ids come back with the features.
- # The problem with adding attrib constraints to filter the misc_features
- # which come back is that not all of the attributes will come back
- #
-
- my $sql = "SELECT DISTINCT ma.misc_feature_id " .
- "FROM misc_attrib ma, attrib_type at " .
- "WHERE ma.attrib_type_id = at.attrib_type_id " .
- "AND at.code = ?";
-
- my @bind_vals = ($attrib_type_code);
-
- if($attrib_value) {
- push @bind_vals, $attrib_value;
+ my $attrib_value = shift;
+
+ throw("Attrib type code argument is required.")
+ if ( !$attrib_type_code );
+
+ # Need to do 2 queries so that all of the ids come back with the
+ # features. The problem with adding attrib constraints to filter the
+ # misc_features which come back is that not all of the attributes will
+ # come back
+
+ my $sql = qq(
+ SELECT DISTINCT
+ ma.misc_feature_id
+ FROM misc_attrib ma,
+ attrib_type at,
+ misc_feature mf,
+ seq_region sr,
+ coord_system cs
+ WHERE ma.attrib_type_id = at.attrib_type_id
+ AND at.code = ?
+ AND ma.misc_feature_id = mf.misc_feature_id
+ AND mf.seq_region_id = sr.seq_region_id
+ AND sr.coord_system_id = cs.coord_system_id
+ AND cs.species_id = ?);
+
+ if ($attrib_value) {
$sql .= " AND ma.value = ?";
}
my $sth = $self->prepare($sql);
- $sth->bind_param(1,$attrib_type_code,SQL_VARCHAR);
- $sth->bind_param(2,$attrib_value,SQL_VARCHAR) if ($attrib_value);
+
+ $sth->bind_param( 1, $attrib_type_code, SQL_VARCHAR );
+ $sth->bind_param( 2, $self->species_id(), SQL_INTEGER );
+ if ($attrib_value) {
+ $sth->bind_param( 3, $attrib_value, SQL_VARCHAR );
+ }
+
$sth->execute();
- my @ids = map {$_->[0]} @{$sth->fetchall_arrayref()};
+ my @ids = map { $_->[0] } @{ $sth->fetchall_arrayref() };
$sth->finish();
- #construct constraints from the list of ids. Split ids into
- #groups of 1000 to ensure that the query is not too big
+ # Construct constraints from the list of ids. Split ids into groups
+ # of 1000 to ensure that the query is not too big.
my @constraints;
- while(@ids) {
- my @subset = splice(@ids, 0, 1000);
- if(@subset == 1) {
+ while (@ids) {
+ my @subset = splice( @ids, 0, 1000 );
+ if ( @subset == 1 ) {
push @constraints, "mf.misc_feature_id = $subset[0]";
} else {
- my $id_str = join(',',@subset);
+ my $id_str = join( ',', @subset );
push @constraints, "mf.misc_feature_id in ($id_str)";
}
}
my @results;
foreach my $constraint (@constraints) {
- push @results, @{$self->generic_fetch($constraint)};
+ push @results, @{ $self->generic_fetch($constraint) };
}
return \@results;
-}
+} ## end sub fetch_all_by_attribute_type_value
#_tables
diff --git a/modules/Bio/EnsEMBL/DBSQL/MiscSetAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/MiscSetAdaptor.pm
index 551330b3da8577945631b6109080b06e2153957b..f2ea0b67d7e8032e922ace3e347c860daf495e48 100644
--- a/modules/Bio/EnsEMBL/DBSQL/MiscSetAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/MiscSetAdaptor.pm
@@ -89,7 +89,10 @@ sub new {
Example : foreach my $ms (@{$msa->fetch_all()}) {
print $ms->code(), ' ', $ms->name(), "\n";
}
- Description: Retrieves every MiscSet defined in the DB
+ Description: Retrieves every MiscSet defined in the DB.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : listref of Bio::EnsEMBL::MiscSets
Exceptions : none
Caller : general
diff --git a/modules/Bio/EnsEMBL/DBSQL/OligoProbeAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/OligoProbeAdaptor.pm
index 6245dcbd67ba3f965ec695f15ca7083c3a283880..c6e76f93f6f255ce82116b893ceb6cc87f344eec 100644
--- a/modules/Bio/EnsEMBL/DBSQL/OligoProbeAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/OligoProbeAdaptor.pm
@@ -53,9 +53,12 @@ use vars qw(@ISA);
Arg [2] : (optional) string - name of probeset
Arg [3] : string - name of probe
Example : my $probe = $opa->fetch_by_array_probeset_probe('Array-1', 'Probeset-1', 'Probe-1');
- Description: Returns a probe given a combination of array name, probeset and
- probe name. This will uniquely define an Affy probe. Only one
- probe is ever returned.
+ Description: Returns a probe given a combination of array name,
+ probeset and probe name. This will uniquely define an
+ Affy probe. Only one probe is ever returned.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : Bio::EnsEMBL::OligoProbe
Exceptions : None
Caller : General
diff --git a/modules/Bio/EnsEMBL/DBSQL/PredictionExonAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/PredictionExonAdaptor.pm
index d01803c2401ad71610524a3ed6d7a3fa4339a9eb..5186a2cd983892a08b233844245b7bebf7d90c0d 100644
--- a/modules/Bio/EnsEMBL/DBSQL/PredictionExonAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/PredictionExonAdaptor.pm
@@ -247,8 +247,9 @@ sub remove {
return undef;
}
- my $sth = $self->prepare( "delete from prediction_exon where prediction_exon_id = ?" );
- $sth->bind_param(1,$pexon->dbID,SQL_INTEGER);
+ my $sth = $self->prepare(
+ "DELETE FROM prediction_exon WHERE prediction_exon_id = ?");
+ $sth->bind_param( 1, $pexon->dbID, SQL_INTEGER );
$sth->execute();
$pexon->dbID(undef);
diff --git a/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
index 5db6a8c4abe3d3dfd47cdbfa0dc49ad17907c08b..5cae0f3fb4a9b2227c64f2eb304c502e135580b8 100644
--- a/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm
@@ -235,18 +235,18 @@ sub _fetch_seq {
} else {
# retrieve uncached portions of the sequence
- my $sth = $self->prepare
- ("SELECT SUBSTRING( d.sequence, ?, ?)
- FROM dna d
- WHERE d.seq_region_id = ?");
+ my $sth =
+ $self->prepare( "SELECT SUBSTRING(d.sequence, ?, ?) "
+ . "FROM dna d "
+ . "WHERE d.seq_region_id = ?" );
my $tmp_seq;
my $min = ($i << $SEQ_CHUNK_PWR) + 1;
- $sth->bind_param(1,$min,SQL_INTEGER);
- $sth->bind_param(2,1 << $SEQ_CHUNK_PWR,SQL_INTEGER);
- $sth->bind_param(3,$seq_region_id,SQL_INTEGER);
+ $sth->bind_param( 1, $min, SQL_INTEGER );
+ $sth->bind_param( 2, 1 << $SEQ_CHUNK_PWR, SQL_INTEGER );
+ $sth->bind_param( 3, $seq_region_id, SQL_INTEGER );
$sth->execute();
$sth->bind_columns(\$tmp_seq);
@@ -260,24 +260,24 @@ sub _fetch_seq {
}
# return only the requested portion of the entire sequence
- my $min = ($chunk_min << $SEQ_CHUNK_PWR) + 1;
- my $max = ($chunk_max+1) << $SEQ_CHUNK_PWR;
- my $seq = substr($entire_seq, $start-$min, $length);
+ my $min = ( $chunk_min << $SEQ_CHUNK_PWR ) + 1;
+ my $max = ( $chunk_max + 1 ) << $SEQ_CHUNK_PWR;
+ my $seq = substr( $entire_seq, $start - $min, $length );
return \$seq;
} else {
# do not do any caching for requests of very large sequences
- my $sth = $self->prepare
- ("SELECT SUBSTRING( d.sequence, ?, ?)
- FROM dna d
- WHERE d.seq_region_id = ?");
+ my $sth =
+ $self->prepare( "SELECT SUBSTRING(d.sequence, ?, ?) "
+ . "FROM dna d "
+ . "WHERE d.seq_region_id = ?" );
my $tmp_seq;
- $sth->bind_param(1,$start,SQL_INTEGER);
- $sth->bind_param(2,$length,SQL_INTEGER);
- $sth->bind_param(3,$seq_region_id,SQL_INTEGER);
+ $sth->bind_param( 1, $start, SQL_INTEGER );
+ $sth->bind_param( 2, $length, SQL_INTEGER );
+ $sth->bind_param( 3, $seq_region_id, SQL_INTEGER );
$sth->execute();
$sth->bind_columns(\$tmp_seq);
diff --git a/modules/Bio/EnsEMBL/DBSQL/SliceAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/SliceAdaptor.pm
index f8444521e9b2c426fc621fc2d536d027e2f1352a..dac3fc5ea6f92610b88b6b494587d8f9857da3e9 100644
--- a/modules/Bio/EnsEMBL/DBSQL/SliceAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/SliceAdaptor.pm
@@ -187,16 +187,18 @@ sub fetch_by_region {
$strand, $version, $no_fuzz )
= @_;
- $start = 1 if (!defined($start));
- $strand = 1 if (!defined($strand));
+ if ( !defined($start) ) { $start = 1 }
+ if ( !defined($strand) ) { $strand = 1 }
- throw('seq_region_name argument is required') if (!defined($seq_region_name));
+ if ( !defined($seq_region_name) ) {
+ throw('seq_region_name argument is required');
+ }
my $cs;
my $csa = $self->db->get_CoordSystemAdaptor();
- if ($coord_system_name) {
- $cs = $csa->fetch_by_name($coord_system_name,$version);
+ if ( defined($coord_system_name) ) {
+ $cs = $csa->fetch_by_name( $coord_system_name, $version );
## REMOVE THESE THREE LINES WHEN STICKLEBACK DB IS FIXED!
## Anne/ap5 (2007-10-09):
@@ -206,167 +208,194 @@ sub fetch_by_region {
# 'groups' in the stickleback community, even though they really are
# chromosomes!
- if( !$cs && $coord_system_name eq 'chromosome' ) {
- $cs = $csa->fetch_by_name('group',$version);
+ if ( !defined($cs) && $coord_system_name eq 'chromosome' ) {
+ $cs = $csa->fetch_by_name( 'group', $version );
}
- if (!$cs) {
- throw("Unknown coordinate system:\n name='$coord_system_name' " .
- "version='$version'\n");
+ if ( !defined($cs) ) {
+ throw(
+ sprintf( "Unknown coordinate system:\n"
+ . "name='%s' version='%s'\n",
+ $coord_system_name, $version
+ ) );
}
+
# fetching by toplevel is same as fetching w/o name or version
- if ($cs->is_top_level()) {
- $cs = undef;
+ if ( $cs->is_top_level() ) {
+ $cs = undef;
$version = undef;
}
- }
+ } ## end if ( defined($coord_system_name...
my $constraint;
my $sql;
- my @bind_vals;
+ my @bind_params;
my $key;
- if ($cs) {
-
- push @bind_vals, $cs->dbID();
- $sql = "SELECT sr.name, sr.seq_region_id, sr.length, " .
- $cs->dbID() ." FROM seq_region sr ";
+ if ( defined($cs) ) {
+ $sql = sprintf( "SELECT sr.name, sr.seq_region_id, sr.length, %d "
+ . "FROM seq_region sr ",
+ $cs->dbID() );
- $constraint = "sr.coord_system_id = ?";
+ $constraint = "AND sr.coord_system_id = ?";
+ push( @bind_params, [ $cs->dbID(), SQL_INTEGER ] );
- $key = "$seq_region_name:".$cs->dbID();
+ $key = "$seq_region_name:" . $cs->dbID();
} else {
- $sql = "SELECT sr.name, sr.seq_region_id, sr.length, " .
- " cs.coord_system_id " .
- "FROM seq_region sr, coord_system cs ";
+ $sql =
+ "SELECT sr.name, sr.seq_region_id, sr.length, cs.coord_system_id "
+ . "FROM seq_region sr, coord_system cs ";
- $constraint = "sr.coord_system_id = cs.coord_system_id ";
- if($version) {
+ $constraint = "AND sr.coord_system_id = cs.coord_system_id "
+ . "AND cs.species_id = ? ";
+ push( @bind_params, [ $self->species_id(), SQL_INTEGER ] );
+
+ if ( defined($version) ) {
$constraint .= "AND cs.version = ? ";
- push @bind_vals, $version;
+ push( @bind_params, [ $version, SQL_VARCHAR ] );
}
+
$constraint .= "ORDER BY cs.rank ASC";
}
# check the cache so we only go to the db if necessary
my $length;
my $arr;
- if ($key) {
- $arr = $self->{'sr_name_cache'}->{$key};
- }
- if ($arr) {
+ if ( defined($key) ) { $arr = $self->{'sr_name_cache'}->{$key} }
+
+ if ( defined($arr) ) {
$length = $arr->[3];
} else {
- my $sth = $self->prepare($sql . " WHERE sr.name = ? AND " . $constraint);
- $sth->bind_param(1, $seq_region_name, SQL_VARCHAR);
- if ($cs){
- $sth->bind_param(2, $cs->dbID, SQL_INTEGER);
- }
- else{
- $sth->bind_param(2, $version, SQL_VARCHAR) if ($version);
+ my $sth =
+ $self->prepare( $sql . "WHERE sr.name = ? " . $constraint );
+
+ unshift( @bind_params, [ $seq_region_name, SQL_VARCHAR ] );
+
+ my $pos = 0;
+ foreach my $param (@bind_params) {
+ $sth->bind_param( ++$pos, $param->[0], $param->[1] );
}
$sth->execute();
- if ($sth->rows() == 0) {
+ if ( $sth->rows() == 0 ) {
$sth->finish();
if ($no_fuzz) { return undef }
- # do fuzzy matching, assuming that we are just missing a version on
- # the end of the seq_region name
-
- $sth = $self->prepare($sql . " WHERE sr.name LIKE ? AND " . $constraint);
+ # Do fuzzy matching, assuming that we are just missing a version
+ # on the end of the seq_region name.
- $sth->bind_param(1, "$seq_region_name.%", SQL_VARCHAR);
+ $sth =
+ $self->prepare( $sql . " WHERE sr.name LIKE ? " . $constraint );
- if ($cs){
- $sth->bind_param(2, $cs->dbID, SQL_INTEGER);
- }
- else{
- $sth->bind_param(2, $version, SQL_VARCHAR) if ($version);
+ $bind_params[0] =
+ [ sprintf( '%s.%%', $seq_region_name ), SQL_VARCHAR ];
+
+ $pos = 0;
+ foreach my $param (@bind_params) {
+ $sth->bind_param( ++$pos, $param->[0], $param->[1] );
}
+
$sth->execute();
my $prefix_len = length($seq_region_name) + 1;
- my $high_ver = undef;
- my $high_cs = $cs;
+ my $high_ver = undef;
+ my $high_cs = $cs;
- # find the fuzzy-matched seq_region with the highest postfix (which ought
- # to be a version)
+ # Find the fuzzy-matched seq_region with the highest postfix
+ # (which ought to be a version).
- my ($tmp_name, $id, $tmp_length, $cs_id);
- $sth->bind_columns(\$tmp_name, \$id, \$tmp_length, \$cs_id);
+ my ( $tmp_name, $id, $tmp_length, $cs_id );
+ $sth->bind_columns( \( $tmp_name, $id, $tmp_length, $cs_id ) );
my $i = 0;
- while ($sth->fetch) {
- my $tmp_cs = ($cs) ? $cs : $csa->fetch_by_dbID($cs_id);
+ while ( $sth->fetch ) {
+ my $tmp_cs =
+ ( defined($cs) ? $cs : $csa->fetch_by_dbID($cs_id) );
# cache values for future reference
my $arr = [ $id, $tmp_name, $cs_id, $tmp_length ];
$self->{'sr_name_cache'}->{"$tmp_name:$cs_id"} = $arr;
- $self->{'sr_id_cache'}->{"$id"} = $arr;
-
- my $tmp_ver = substr($tmp_name, $prefix_len);
-
- # skip versions which are non-numeric and apparently not versions
- next if($tmp_ver !~ /^\d+$/);
-
- # take version with highest num, if two versions match take one with
- # highest ranked coord system (lowest num)
- if(!defined($high_ver) || $tmp_ver > $high_ver ||
- ($tmp_ver == $high_ver && $tmp_cs->rank < $high_cs->rank)) {
- $seq_region_name = $tmp_name;
- $length = $tmp_length;
- $high_ver = $tmp_ver;
- $high_cs = $tmp_cs;
+ $self->{'sr_id_cache'}->{"$id"} = $arr;
+
+ my $tmp_ver = substr( $tmp_name, $prefix_len );
+
+ # skip versions which are non-numeric and apparently not
+ # versions
+ if ( $tmp_ver !~ /^\d+$/ ) { next }
+
+ # take version with highest num, if two versions match take one
+ # with highest ranked coord system (lowest num)
+ if ( !defined($high_ver)
+ || $tmp_ver > $high_ver
+ || ( $tmp_ver == $high_ver && $tmp_cs->rank < $high_cs->rank )
+ )
+ {
+ $seq_region_name = $tmp_name;
+ $length = $tmp_length;
+ $high_ver = $tmp_ver;
+ $high_cs = $tmp_cs;
}
$i++;
- }
+ } ## end while ( $sth->fetch )
$sth->finish();
# warn if fuzzy matching found more than one result
- if ($i > 1) {
- warning("Fuzzy matching of seq_region_name returned more than one result.\nYou might want to check whether the returned seq_region\n(".$high_cs->name.":$seq_region_name) is the one you intended to fetch.\n");
+ if ( $i > 1 ) {
+ warning(
+ sprintf(
+ "Fuzzy matching of seq_region_name "
+ . "returned more than one result.\n"
+ . "You might want to check whether the returned seq_region\n"
+ . "(%s:%s) is the one you intended to fetch.\n",
+ $high_cs->name(), $seq_region_name
+ ) );
}
$cs = $high_cs;
- #return if we did not find any appropriate match:
- return undef if (!defined($high_ver));
+ # return if we did not find any appropriate match:
+ if ( !defined($high_ver) ) { return undef }
} else {
- my ($id, $cs_id);
- ($seq_region_name, $id, $length, $cs_id) = $sth->fetchrow_array();
+ my ( $id, $cs_id );
+ ( $seq_region_name, $id, $length, $cs_id ) =
+ $sth->fetchrow_array();
$sth->finish();
- # cahce to speed up for future queries
+ # cache to speed up for future queries
my $arr = [ $id, $seq_region_name, $cs_id, $length ];
$self->{'sr_name_cache'}->{"$seq_region_name:$cs_id"} = $arr;
- $self->{'sr_id_cache'}->{"$id"} = $arr;
- $cs = $csa->fetch_by_dbID( $cs_id );
+ $self->{'sr_id_cache'}->{"$id"} = $arr;
+ $cs = $csa->fetch_by_dbID($cs_id);
}
- }
+ } ## end else [ if ( defined($arr) )
- $end = $length if(!defined($end));
+ if ( !defined($end) ) { $end = $length }
- if($end+1 < $start) {
- throw("start [$start] must be less than or equal to end+1 [$end+1]");
+ if ( $end + 1 < $start ) {
+ throw(
+ sprintf(
+ "start [%d] must be less than or equal to end+1 [%d]",
+ $start, $end + 1
+ ) );
}
- return Bio::EnsEMBL::Slice->new(-COORD_SYSTEM => $cs,
- -SEQ_REGION_NAME => $seq_region_name,
- -SEQ_REGION_LENGTH => $length,
- -START => $start,
- -END => $end,
- -STRAND => $strand,
- -ADAPTOR => $self);
-}
+ return
+ Bio::EnsEMBL::Slice->new( -COORD_SYSTEM => $cs,
+ -SEQ_REGION_NAME => $seq_region_name,
+ -SEQ_REGION_LENGTH => $length,
+ -START => $start,
+ -END => $end,
+ -STRAND => $strand,
+ -ADAPTOR => $self );
+} ## end sub fetch_by_region
@@ -444,27 +473,26 @@ sub fetch_by_name {
=cut
sub fetch_by_seq_region_id {
- my ($self, $seq_region_id,$start,$end,$strand) = @_;
+ my ( $self, $seq_region_id, $start, $end, $strand ) = @_;
- my $arr = $self->{'sr_id_cache'}->{ $seq_region_id };
- my ($name, $length, $cs);
+ my $arr = $self->{'sr_id_cache'}->{$seq_region_id};
+ my ( $name, $length, $cs, $cs_id );
- if( $arr && defined($arr->[2])) {
- my $cs_id;
- ($name, $cs_id, $length ) = ( $arr->[1], $arr->[2], $arr->[3] );
+ if ( $arr && defined( $arr->[2] ) ) {
+ ( $name, $cs_id, $length ) = ( $arr->[1], $arr->[2], $arr->[3] );
$cs = $self->db->get_CoordSystemAdaptor->fetch_by_dbID($cs_id);
} else {
- my $sth = $self->prepare("SELECT name, length, coord_system_id " .
- "FROM seq_region " .
- "WHERE seq_region_id = ?");
+ my $sth =
+ $self->prepare( "SELECT sr.name, sr.coord_system_id, sr.length "
+ . "FROM seq_region sr"
+ . "WHERE sr.seq_region_id = ? " );
- $sth->bind_param(1,$seq_region_id,SQL_INTEGER);
+ $sth->bind_param( 1, $seq_region_id, SQL_INTEGER );
$sth->execute();
- return undef if($sth->rows() == 0);
+ if ( $sth->rows() == 0 ) { return undef }
- my $cs_id;
- ($name, $length, $cs_id) = $sth->fetchrow_array();
+ ( $name, $cs_id, $length ) = $sth->fetchrow_array();
$sth->finish();
$cs = $self->db->get_CoordSystemAdaptor->fetch_by_dbID($cs_id);
@@ -476,14 +504,15 @@ sub fetch_by_seq_region_id {
$self->{'sr_id_cache'}->{"$seq_region_id"} = $arr;
}
- return Bio::EnsEMBL::Slice->new(-COORD_SYSTEM => $cs,
- -SEQ_REGION_NAME => $name,
- -SEQ_REGION_LENGTH => $length,
- -START => $start || 1,
- -END => $end || $length,
- -STRAND => $strand || 1,
- -ADAPTOR => $self);
-}
+ return
+ Bio::EnsEMBL::Slice->new( -COORD_SYSTEM => $cs,
+ -SEQ_REGION_NAME => $name,
+ -SEQ_REGION_LENGTH => $length,
+ -START => $start || 1,
+ -END => $end || $length,
+ -STRAND => $strand || 1,
+ -ADAPTOR => $self );
+} ## end sub fetch_by_seq_region_id
@@ -621,48 +650,64 @@ sub fetch_all {
my $sth;
my %bad_vals=();
+
#
# Get a hash of non reference seq regions
#
- if(!$include_non_reference){
- my $sth2 = $self->prepare(
- "SELECT sr.seq_region_id ".
- "FROM seq_region sr, seq_region_attrib sra, attrib_type at ".
- " WHERE at.code='non_ref'".
- " AND sra.seq_region_id=sr.seq_region_id ".
- " AND at.attrib_type_id=sra.attrib_type_id " );
+ if ( !$include_non_reference ) {
+ my $sth2 =
+ $self->prepare( 'SELECT sr.seq_region_id '
+ . 'FROM seq_region sr, seq_region_attrib sra, '
+ . 'attrib_type at, coord_system cs '
+ . 'WHERE at.code = "non_ref" '
+ . 'AND sra.seq_region_id = sr.seq_region_id '
+ . 'AND at.attrib_type_id = sra.attrib_type_id '
+ . 'AND sr.coord_system_id = cs.coord_system_id '
+ . 'AND cs.species_id = ?' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth2->execute();
+
my ($seq_region_id);
- $sth2->bind_columns(\$seq_region_id);
- while($sth2->fetch()) {
+ $sth2->bind_columns( \$seq_region_id );
+
+ while ( $sth2->fetch() ) {
$bad_vals{$seq_region_id} = 1;
}
+
$sth2->finish();
}
+
#
# Retrieve the seq_regions from the database
#
- if($orig_cs->is_top_level()) {
- $sth =
- $self->prepare("SELECT sr.seq_region_id, sr.name, sr.length, " .
- " sr.coord_system_id " .
- "FROM seq_region sr, " .
- " seq_region_attrib sra, attrib_type at " .
- "WHERE at.code='toplevel' " .
- "AND at.attrib_type_id=sra.attrib_type_id " .
- "AND sra.seq_region_id=sr.seq_region_id");
+ if ( $orig_cs->is_top_level() ) {
+ $sth =
+ $self->prepare( 'SELECT sr.seq_region_id, sr.name, '
+ . 'sr.length, sr.coord_system_id '
+ . 'FROM seq_region sr, seq_region_attrib sra, '
+ . 'attrib_type at, coord_system cs '
+ . 'WHERE at.code = "toplevel" '
+ . 'AND at.attrib_type_id = sra.attrib_type_id '
+ . 'AND sra.seq_region_id = sr.seq_region_id '
+ . 'AND sr.coord_system_id = cs.coord_system_id '
+ . 'AND cs.species_id = ?' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
} else {
- $sth =
- $self->prepare('SELECT seq_region_id, name, length, coord_system_id ' .
- 'FROM seq_region ' .
- 'WHERE coord_system_id =?');
- $sth->bind_param(1,$orig_cs->dbID,SQL_INTEGER);
- $sth->execute();
+ $sth =
+ $self->prepare( 'SELECT seq_region_id, name, '
+ . 'length, coord_system_id '
+ . 'FROM seq_region sr, coord_system cs '
+ . 'WHERE coord_system_id = ?' );
+
+ $sth->bind_param( 1, $orig_cs->dbID, SQL_INTEGER );
+ $sth->execute();
}
- my ($seq_region_id, $name, $length, $cs_id);
- $sth->bind_columns(\$seq_region_id, \$name, \$length, \$cs_id);
+ my ( $seq_region_id, $name, $length, $cs_id );
+ $sth->bind_columns( \( $seq_region_id, $name, $length, $cs_id ) );
my $cache_count = 0;
@@ -734,20 +779,27 @@ sub fetch_all {
=cut
-sub is_toplevel{
+sub is_toplevel {
my $self = shift;
- my $id = shift;
+ my $id = shift;
- my $sth = $self->prepare("SELECT at.code from seq_region_attrib sra, attrib_type at WHERE sra.seq_region_id = $id AND at.attrib_type_id = sra.attrib_type_id AND at.code = 'toplevel'");
-
+ my $sth = $self->prepare(
+ "SELECT at.code from seq_region_attrib sra, attrib_type at "
+ . "WHERE sra.seq_region_id = ? "
+ . "AND at.attrib_type_id = sra.attrib_type_id "
+ . "AND at.code = 'toplevel'" );
+
+ $sth->bind_param( 1, $id, SQL_INTEGER );
$sth->execute();
-
- my $code = undef;
- $sth->bind_columns(\$code);
- while($sth->fetch){
+
+ my $code;
+ $sth->bind_columns( \$code );
+
+ while ( $sth->fetch ) {
$sth->finish;
return 1;
}
+
$sth->finish;
return 0;
}
@@ -797,27 +849,32 @@ sub fetch_by_band {
=cut
sub fetch_by_chr_band {
- my ($self,$chr,$band) = @_;
+ my ( $self, $chr, $band ) = @_;
- my $chr_slice = $self->fetch_by_region('toplevel', $chr);
+ my $chr_slice = $self->fetch_by_region( 'toplevel', $chr );
my $seq_region_id = $self->get_seq_region_id($chr_slice);
- my $sth = $self->dbc->prepare
- ("select min(k.seq_region_start), max(k.seq_region_end) " .
- "from karyotype as k " .
- "where k.seq_region_id = ? and k.band like ?");
+ my $sth =
+ $self->prepare( 'SELECT MIN(k.seq_region_start), '
+ . 'MAX(k.seq_region_end) '
+ . 'FROM karyotype k '
+ . 'WHERE k.seq_region_id = ? '
+ . 'AND k.band LIKE ?' );
- $sth->bind_param(1,$seq_region_id,SQL_INTEGER);
- $sth->bind_param(2,"$band%",SQL_VARCHAR);
+ $sth->bind_param( 1, $seq_region_id, SQL_INTEGER );
+ $sth->bind_param( 2, "$band%", SQL_VARCHAR );
$sth->execute();
- my ( $slice_start, $slice_end) = $sth->fetchrow_array;
- if(defined $slice_start) {
- return $self->fetch_by_region('toplevel',$chr,$slice_start,$slice_end);
+ my ( $slice_start, $slice_end ) = $sth->fetchrow_array;
+
+ if ( defined $slice_start ) {
+ return
+ $self->fetch_by_region( 'toplevel', $chr,
+ $slice_start, $slice_end );
}
throw("Band not recognised in database");
-}
+} ## end sub fetch_by_chr_band
@@ -1486,13 +1543,9 @@ sub store_assembly{
=cut
-
-
sub prepare {
- my $self = shift;
- my $sql = shift;
-
- return $self->db()->dnadb()->dbc->prepare( $sql );
+ my ( $self, $sql ) = @_;
+ return $self->db()->dnadb()->dbc->prepare($sql);
}
sub _build_exception_cache {
@@ -1500,27 +1553,30 @@ sub _build_exception_cache {
# build up a cache of the entire assembly exception table
# it should be small anyway
- my $sth = $self->prepare
- ("SELECT seq_region_id, seq_region_start, seq_region_end,
- exc_type, exc_seq_region_id, exc_seq_region_start,
- exc_seq_region_end
- FROM assembly_exception");
-
+ my $sth =
+ $self->prepare( 'SELECT ae.seq_region_id, ae.seq_region_start, '
+ . 'ae.seq_region_end, ae.exc_type, ae.exc_seq_region_id, '
+ . 'ae.exc_seq_region_start, ae.exc_seq_region_end'
+ . 'FROM assembly_exception ae, '
+ . 'seq_region sr, coord_system cs '
+ . 'WHERE sr.seq_region_id = ar.seq_region_id '
+ . 'AND sr.coord_system_id = cs.coord_system_id '
+ . 'AND cs.species_id = ?' );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
my %hash;
$self->{'asm_exc_cache'} = \%hash;
my $row;
- while($row = $sth->fetchrow_arrayref()) {
+ while ( $row = $sth->fetchrow_arrayref() ) {
my @result = @$row;
- $hash{$result[0]} ||= [];
- push(@{$hash{$result[0]}}, \@result);
+ $hash{ $result[0] } ||= [];
+ push( @{ $hash{ $result[0] } }, \@result );
}
$sth->finish();
-
- return;
-}
+} ## end sub _build_exception_cache
=head2 cache_toplevel_seq_mappings
@@ -1544,9 +1600,11 @@ sub cache_toplevel_seq_mappings {
SELECT name
FROM coord_system
WHERE attrib like "%sequence_level%"
+ AND species_id = ?
SSQL
my $sth = $self->prepare($sql);
+ $sth->bin_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
my $sequence_level = $sth->fetchrow_array();
@@ -1570,9 +1628,11 @@ SSQL
AND sra.attrib_type_id = at.attrib_type_id
AND at.code = "toplevel"
AND cs.coord_system_id = sr.coord_system_id;
+ AND cs.species_id = ?
LSQL
$sth = $self->prepare($sql);
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
while ( my $csn = $sth->fetchrow_array() ) {
@@ -1681,12 +1741,17 @@ sub fetch_by_clone_accession{
#this unfortunately needs a version on the end to work
if(! ($name =~ /\./)) {
- my $sth = $self->prepare("SELECT sr.name " .
- "FROM seq_region sr, coord_system cs " .
- "WHERE cs.name = 'clone' " .
- "AND cs.coord_system_id = sr.coord_system_id ".
- "AND sr.name LIKE '$name.%'");
+ my $sth =
+ $self->prepare( "SELECT sr.name "
+ . "FROM seq_region sr, coord_system cs "
+ . "WHERE cs.name = 'clone' "
+ . "AND cs.coord_system_id = sr.coord_system_id "
+ . "AND sr.name LIKE '$name.%'"
+ . "AND cs.species_id = ?" );
+
+ $sth->bind_param( 1, $self->species_id(), SQL_INTEGER );
$sth->execute();
+
if(!$sth->rows()) {
$sth->finish();
throw("Clone $name not found in database");
diff --git a/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
index 22d7fbc52001bf52a56af5b16c2b5f0ac4620cb1..6339dd341b811ef7772d20a92642cf153da36281 100644
--- a/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/TranscriptAdaptor.pm
@@ -718,8 +718,10 @@ sub store {
}
if(defined($dxref_id)) {
- my $sth = $self->prepare( "update transcript set display_xref_id = ?".
- " where transcript_id = ?");
+ my $sth =
+ $self->prepare( "UPDATE transcript "
+ . "SET display_xref_id = ? "
+ . "WHERE transcript_id = ?" );
$sth->bind_param(1, $dxref_id, SQL_INTEGER);
$sth->bind_param(2, $transc_dbID, SQL_INTEGER);
$sth->execute();
@@ -738,9 +740,9 @@ sub store {
#
# Link transcript to exons in exon_transcript table
#
- my $etst =
- $self->prepare("insert into exon_transcript (exon_id,transcript_id,rank)"
- ." values (?,?,?)");
+ my $etst = $self->prepare(
+ "INSERT INTO exon_transcript (exon_id,transcript_id,rank) "
+ . "VALUES (?,?,?)" );
my $rank = 1;
foreach my $exon ( @{$transcript->get_all_Exons} ) {
$etst->bind_param(1, $exon->dbID, SQL_INTEGER);
diff --git a/modules/Bio/EnsEMBL/DBSQL/UnconventionalTranscriptAssociationAdaptor.pm b/modules/Bio/EnsEMBL/DBSQL/UnconventionalTranscriptAssociationAdaptor.pm
index ad7b6608f04078e139ab81f962a7156851f2521b..f2ed230b8775ee44d80b03cfaf2251fcb0d0a835 100644
--- a/modules/Bio/EnsEMBL/DBSQL/UnconventionalTranscriptAssociationAdaptor.pm
+++ b/modules/Bio/EnsEMBL/DBSQL/UnconventionalTranscriptAssociationAdaptor.pm
@@ -51,8 +51,11 @@ use vars qw(@ISA);
Arg [1] : String type
the type of associations to obtain
Example : $utas = $utaa->fetch_all_by_type('antisense');
- Description: Obtains all unconventional transcript associations that have
- a particular interaction type.
+ Description: Obtains all unconventional transcript associations that
+ have a particular interaction type.
+ NOTE: In a multi-species database, this method will
+ return all the entries matching the search criteria, not
+ just the ones associated with the current species.
Returntype : listREF of Bio::EnsEMBL::UnconventionalTranscriptAssociations
Exceptions : none
Caller : general
diff --git a/modules/Bio/EnsEMBL/Registry.pm b/modules/Bio/EnsEMBL/Registry.pm
index fbe7e27b294d5ced89a46f098f20c0c289de45ef..6b39dab70affe59f6600fab6eb1014b8ade9f997 100644
--- a/modules/Bio/EnsEMBL/Registry.pm
+++ b/modules/Bio/EnsEMBL/Registry.pm
@@ -601,9 +601,9 @@ sub remove_DBAdaptor{
delete $registry_register{$species}{$group};
- #This will remove the DBAdaptor and all the other adaptors
+ # This will remove the DBAdaptor and all the other adaptors
- #Now remove if from the _DBA array
+ # Now remove if from the _DBA array
my $index;
@@ -618,7 +618,7 @@ sub remove_DBAdaptor{
}
}
- #Now remove from _DBA cache
+ # Now remove from _DBA cache
splice(@{$registry_register{'_DBA'}}, $index, 1);
return;
@@ -644,17 +644,17 @@ sub remove_DBAdaptor{
sub reset_DBAdaptor{
my ($self, $species, $group, $dbname, $host, $port, $user, $pass) = @_;
- #Check mandatory params
+ # Check mandatory params
if(! (defined $species && defined $group && defined $dbname)){
throw('Must provide at least a species, group and dbname parmeter to redefine a DB in the registry');
}
- #validate species here
+ # Validate species here
my $alias = $self->get_alias($species);
throw("Could not find registry alias for species:\t$species") if(! defined $alias);
- #Get all current defaults if not defined
+ # Get all current defaults if not defined
my $current_db = $self->get_DBAdaptor($alias, $group);
if(! defined $current_db){
@@ -673,7 +673,7 @@ sub reset_DBAdaptor{
my @adaptors = @{$self->get_all_adaptors};
- #ConfigRegistry should automatically add this to the Registry
+ # ConfigRegistry should automatically add this to the Registry
my $db = $class->new(
-user => $user,
-host => $host,
@@ -763,51 +763,45 @@ sub get_DNAAdaptor{
=cut
-sub add_adaptor{
- my ($class,$species,$group,$type,$adap, $reset)= @_;
+sub add_adaptor {
+ my ( $class, $species, $group, $type, $adap, $reset ) = @_;
$species = $class->get_alias($species);
-#
-# Becouse the adaptors are not stored initially only there class paths when
-# the adaptors are obtained we need to store these instead.
-# It is not necessarily an error if the registry is overwritten without
-# the reset set but it is an indication that we are overwriting a database
-# which should be a warning for now
-#
+ # Since the adaptors are not stored initially, only their class paths
+ # when the adaptors are obtained, we need to store these instead. It
+ # is not necessarily an error if the registry is overwritten without
+ # the reset set but it is an indication that we are overwriting a
+ # database which should be a warning for now
- if(defined($reset)){ # JUST REST THE HASH VALUE NO MORE PROCESSING NEEDED
- $registry_register{$species}{lc($group)}{lc($type)} = $adap;
+ if ( defined($reset) )
+ { # JUST REST THE HASH VALUE NO MORE PROCESSING NEEDED
+ $registry_register{$species}{ lc($group) }{ lc($type) } = $adap;
return;
}
- if(defined($registry_register{$species}{lc($group)}{lc($type)})){
- #print STDERR ("Overwriting Adaptor in Registry for $species $group $type\n");
- $registry_register{$species}{lc($group)}{lc($type)} = $adap;
- return;
+ if (
+ defined( $registry_register{$species}{ lc($group) }{ lc($type) } ) )
+ {
+ # print STDERR (
+ # "Overwriting Adaptor in Registry for $species $group $type\n");
+ $registry_register{$species}{ lc($group) }{ lc($type) } = $adap;
+ return;
}
- $registry_register{$species}{lc($group)}{lc($type)} = $adap;
+ $registry_register{$species}{ lc($group) }{ lc($type) } = $adap;
- if(!defined ($registry_register{$species}{'list'})){
- my @list =();
- push(@list,$type);
- $registry_register{$species}{'list'}= \@list;
- }
- else{
- push(@{$registry_register{$species}{'list'}},$type);
+ if ( !defined( $registry_register{$species}{'list'} ) ) {
+ $registry_register{$species}{'list'} = [$type];
+ } else {
+ push( @{ $registry_register{$species}{'list'} }, $type );
}
-
-
- if(!defined ($registry_register{lc($type)}{$species})){
- my @list =();
- push(@list,$adap);
- $registry_register{lc($type)}{$species}= \@list;
- }
- else{
- push(@{$registry_register{lc($type)}{$species}},$adap);
+ if ( !defined( $registry_register{ lc($type) }{$species} ) ) {
+ $registry_register{ lc($type) }{$species} = [$type];
+ } else {
+ push( @{ $registry_register{ lc($type) }{$species} }, $adap );
}
-}
+} ## end sub add_adaptor
=head2 get_adaptor
@@ -835,11 +829,9 @@ sub get_adaptor{
$group = $dnadb_group;
}
- my $ret = $registry_register{$species}{lc($group)}{lc($type)};
- if(!defined($ret)){
-
- return undef;
- }
+ my $ret = $registry_register{$species}{ lc($group) }{ lc($type) };
+ if ( !defined($ret) ) { return undef; }
+
if(!ref($ret)){ # not instantiated yet
my $dba = $registry_register{$species}{lc($group)}{'_DB'};
my $module = $ret;
@@ -883,7 +875,7 @@ sub get_all_adaptors{
my (%species_hash, %group_hash, %type_hash);
- if(@args == 1){ #old species only one parameter
+ if(@args == 1){ # Old species only one parameter
warn("-SPECIES argument should now be used to get species adaptors");
$species = $args[0];
}
@@ -1008,7 +1000,7 @@ sub alias_exists{
sub set_disconnect_when_inactive{
foreach my $dba ( @{get_all_DBAdaptors()}){
my $dbc = $dba->dbc;
- #disconnect if connected
+ # Disconnect if connected
$dbc->disconnect_if_idle() if $dbc->connected();
$dbc->disconnect_when_inactive(1);
}
@@ -1029,7 +1021,7 @@ sub disconnect_all {
foreach my $dba ( @{get_all_DBAdaptors()||[]} ){
my $dbc = $dba->dbc;
next unless $dbc;
- #disconnect if connected
+ # Disconnect if connected
$dbc->disconnect_if_idle() if $dbc->connected();
}
}
@@ -1159,148 +1151,211 @@ sub load_registry_from_url {
=cut
sub load_registry_from_db {
- my($self, @args) = @_;
- my ($host, $port, $user, $pass, $verbose, $db_version, $wait_timeout) =
- rearrange([qw(HOST PORT USER PASS VERBOSE DB_VERSION WAIT_TIMEOUT )], @args);
+ my ( $self, @args ) = @_;
+
+ my ( $host, $port, $user, $pass, $verbose, $db_version,
+ $wait_timeout ) =
+ rearrange(
+ [qw(HOST PORT USER PASS VERBOSE DB_VERSION WAIT_TIMEOUT )],
+ @args );
my $go_version = 0;
my $compara_version =0;
my $ancestral_version =0;
$user ||= "ensro";
- if(!defined($port)){
- $port = 3306;
- if($host eq "ensembldb.ensembl.org"){
- if( !defined($db_version) or $db_version >= 48){
- $port = 5306;
+ if ( !defined($port) ) {
+ $port = 3306;
+ if ( $host eq "ensembldb.ensembl.org" ) {
+ if ( !defined($db_version) or $db_version >= 48 ) {
+ $port = 5306;
}
}
}
-
$wait_timeout ||= 0;
- my $db = DBI->connect( "DBI:mysql:host=$host;port=$port" , $user, $pass );
- my $res = $db->selectall_arrayref( "show databases" );
- my @dbnames = map {$_->[0] } @$res;
+ my $dbh =
+ DBI->connect( "DBI:mysql:host=$host;port=$port", $user, $pass );
+
+ my $res = $dbh->selectall_arrayref("show databases");
+ my @dbnames = map { $_->[0] } @$res;
my %temp;
my $software_version = $self->software_version();
- if (defined($db_version)) {
+
+ if ( defined($db_version) ) {
$software_version = $db_version;
}
- print "Will only load release $software_version databases\n" if ($verbose);
- for my $db (@dbnames){
- if($db =~ /^([a-z]+_[a-z]+_[a-z]+)_(\d+)_(\d+[a-z]*)/){
- if($2 eq $software_version){
- $temp{$1} = $2."_".$3;
+
+ if ($verbose) {
+ printf( "Will only load v%d databases\n", $software_version );
+ }
+
+ for my $db (@dbnames) {
+ if ( $db =~ /^(\w+)_collection_core_(\d+)/ ) {
+ if ( $2 eq $software_version ) {
+ $temp{$1} = 'collection_core_' . $2;
}
- }
- elsif($db =~ /^(.+)_(userdata)$/){
- $temp{$1} = $2;
- }
- elsif($db =~ /^ensembl_compara_(\d+)/){
- if($1 eq $software_version){
- $compara_version = $1;
+ } elsif ( $db =~ /^([a-z]+_[a-z]+_[a-z]+)_(\d+)_(\d+[a-z]*)/ ) {
+ if ( $2 eq $software_version ) {
+ $temp{$1} = $2 . "_" . $3;
}
- }
- elsif($db =~ /^ensembl_ancestral_(\d+)/){
- if($1 eq $software_version){
- $ancestral_version = $1;
+ } elsif ( $db =~ /^(.+)_(userdata)$/ ) {
+ $temp{$1} = $2;
+ } elsif ( $db =~ /^ensembl_compara_(\d+)/ ) {
+ if ( $1 eq $software_version ) {
+ $compara_version = $1;
}
- }
- elsif($db =~ /^ensembl_go_(\d+)/){
- if($1 eq $software_version){
- $go_version = $1;
+ } elsif ( $db =~ /^ensembl_ancestral_(\d+)/ ) {
+ if ( $1 eq $software_version ) {
+ $ancestral_version = $1;
+ }
+ } elsif ( $db =~ /^ensembl_go_(\d+)/ ) {
+ if ( $1 eq $software_version ) {
+ $go_version = $1;
}
}
+ } ## end for my $db (@dbnames)
+
+ @dbnames = ();
+
+ foreach my $key ( keys %temp ) {
+ push @dbnames, $key . "_" . $temp{$key};
}
-
- @dbnames =();
-
- foreach my $key ( keys %temp){
- push @dbnames, $key."_".$temp{$key};
- }
- # register core databases
-
+
+ # Register Core databases
+
my @core_dbs = grep { /^[a-z]+_[a-z]+_core_\d+_/ } @dbnames;
-
- for my $coredb ( @core_dbs ) {
- my ($species, $num ) = ( $coredb =~ /(^[a-z]+_[a-z]+)_core_(\d+)/ );
- my $dba = Bio::EnsEMBL::DBSQL::DBAdaptor->new
- ( -group => "core",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -dbname => $coredb,
- -wait_timeout => $wait_timeout
+
+ foreach my $coredb (@core_dbs) {
+ my ( $species, $num ) =
+ ( $coredb =~ /(^[a-z]+_[a-z]+)_core_(\d+)/ );
+
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(-group => "core",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -dbname => $coredb,
+ -wait_timeout => $wait_timeout
);
- (my $sp = $species ) =~ s/_/ /g;
+
+ ( my $sp = $species ) =~ s/_/ /g;
$self->add_alias( $species, $sp );
- print $coredb." loaded\n" if ($verbose);
+
+ if ($verbose) {
+ printf( "Species '%s' loaded from database '%s'\n",
+ $species, $coredb );
+ }
}
+ # Register multi-species databases
+ my @multi_dbs = grep { /_collection_core_\d+$/ } @dbnames;
+
+ foreach my $multidb (@multi_dbs) {
+ my $sth =
+ $dbh->prepare(
+ sprintf( 'SELECT species_id, meta_value FROM %s.species_meta ',
+ $dbh->quote_identifier($multidb) )
+ . "WHERE meta_key = 'species.db_name'" );
+ $sth->execute();
+
+ my ( $species_id, $species );
+ $sth->bind_columns( \( $species_id, $species ) );
+
+ while ( $sth->fetch() ) {
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(
+ -group => "core",
+ -species => $species,
+ -species_id => $species_id,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -dbname => $multidb,
+ -wait_timeout => $wait_timeout
+ );
+
+ ( my $sp = $species ) =~ s/_/ /g;
+ $self->add_alias( $species, $sp );
+
+ if ($verbose) {
+ printf( "Species '%s' (id:%d) loaded from database '%s'\n",
+ $species, $species_id, $multidb );
+ }
+ }
+ } ## end foreach my $multidb (@multi_dbs)
+
# register cdna databases
-
+
my @cdna_dbs = grep { /^[a-z]+_[a-z]+_cdna_\d+_/ } @dbnames;
-
- for my $cdnadb ( @cdna_dbs ) {
- my ($species, $num ) = ( $cdnadb =~ /(^[a-z]+_[a-z]+)_cdna_(\d+)/ );
- my $dba = Bio::EnsEMBL::DBSQL::DBAdaptor->new
- ( -group => "cdna",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -dbname => $cdnadb,
- -wait_timeout => $wait_timeout
+
+ for my $cdnadb (@cdna_dbs) {
+ my ( $species, $num ) =
+ ( $cdnadb =~ /(^[a-z]+_[a-z]+)_cdna_(\d+)/ );
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(-group => "cdna",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -dbname => $cdnadb,
+ -wait_timeout => $wait_timeout
);
- (my $sp = $species ) =~ s/_/ /g;
+ ( my $sp = $species ) =~ s/_/ /g;
$self->add_alias( $species, $sp );
- print $cdnadb." loaded\n" if ($verbose);
+ print $cdnadb. " loaded\n" if ($verbose);
}
my @vega_dbs = grep { /^[a-z]+_[a-z]+_vega_\d+_/ } @dbnames;
-
- for my $vegadb ( @vega_dbs ) {
- my ($species, $num ) = ( $vegadb =~ /(^[a-z]+_[a-z]+)_vega_(\d+)/ );
- my $dba = Bio::EnsEMBL::DBSQL::DBAdaptor->new
- ( -group => "vega",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $vegadb
- );
- (my $sp = $species ) =~ s/_/ /g;
+
+ for my $vegadb (@vega_dbs) {
+ my ( $species, $num ) =
+ ( $vegadb =~ /(^[a-z]+_[a-z]+)_vega_(\d+)/ );
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(
+ -group => "vega",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $vegadb );
+ ( my $sp = $species ) =~ s/_/ /g;
$self->add_alias( $species, $sp );
- print $vegadb." loaded\n" if ($verbose);
+ print $vegadb. " loaded\n" if ($verbose);
}
-
+
+ # Otherfeatures
+
my @other_dbs = grep { /^[a-z]+_[a-z]+_otherfeatures_\d+_/ } @dbnames;
-
- for my $other_db ( @other_dbs ) {
- my ($species, $num) = ( $other_db =~ /(^[a-z]+_[a-z]+)_otherfeatures_(\d+)/ );
- my $dba = Bio::EnsEMBL::DBSQL::DBAdaptor->new
- ( -group => "otherfeatures",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $other_db
- );
- (my $sp = $species ) =~ s/_/ /g;
- $self->add_alias( $species, $sp );
- print $other_db." loaded\n" if ($verbose);
+
+ for my $other_db (@other_dbs) {
+ my ( $species, $num ) =
+ ( $other_db =~ /(^[a-z]+_[a-z]+)_otherfeatures_(\d+)/ );
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(
+ -group => "otherfeatures",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $other_db );
+ ( my $sp = $species ) =~ s/_/ /g;
+ $self->add_alias( $species, $sp );
+ print $other_db. " loaded\n" if ($verbose);
}
-
+
+ # User upload DBs
+
my @userupload_dbs = grep { /_userdata$/ } @dbnames;
for my $userupload_db ( @userupload_dbs ) {
my ($species) = ( $userupload_db =~ /(^.+)_userdata$/ );
@@ -1319,282 +1374,385 @@ sub load_registry_from_db {
print $userupload_db." loaded\n" if ($verbose);
}
-
+ # Variation
+
eval "require Bio::EnsEMBL::Variation::DBSQL::DBAdaptor";
- if($@) {
- #ignore variations as code required not there for this
- print "Bio::EnsEMBL::Variation::DBSQL::DBAdaptor module not found so variation databases will be ignored if found\n" if ($verbose);
- }
- else{
- my @variation_dbs = grep { /^[a-z]+_[a-z]+_variation_\d+_/ } @dbnames;
-
- for my $variation_db ( @variation_dbs ) {
- my ($species, $num ) = ( $variation_db =~ /(^[a-z]+_[a-z]+)_variation_(\d+)/ );
- my $dba = Bio::EnsEMBL::Variation::DBSQL::DBAdaptor->new
- ( -group => "variation",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $variation_db
- );
- print $variation_db." loaded\n" if ($verbose);
+ if ($@) {
+ # Ignore variations as code required not there for this
+ print
+"Bio::EnsEMBL::Variation::DBSQL::DBAdaptor module not found so variation databases will be ignored if found\n"
+ if ($verbose);
+ } else {
+ my @variation_dbs =
+ grep { /^[a-z]+_[a-z]+_variation_\d+_/ } @dbnames;
+
+ for my $variation_db (@variation_dbs) {
+ my ( $species, $num ) =
+ ( $variation_db =~ /(^[a-z]+_[a-z]+)_variation_(\d+)/ );
+ my $dba =
+ Bio::EnsEMBL::Variation::DBSQL::DBAdaptor->new(
+ -group => "variation",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $variation_db
+ );
+ print $variation_db. " loaded\n" if ($verbose);
}
}
eval "require Bio::EnsEMBL::Funcgen::DBSQL::DBAdaptor";
- if($@) {
+ if ($@) {
#ignore funcgen DBs as code required not there for this
- print "Bio::EnsEMBL::Funcgen::DBSQL::DBAdaptor module not found so functional genomics databases will be ignored if found\n" if ($verbose);
- }
- else{
+ print
+"Bio::EnsEMBL::Funcgen::DBSQL::DBAdaptor module not found so functional genomics databases will be ignored if found\n"
+ if ($verbose);
+ } else {
my @funcgen_dbs = grep { /^[a-z]+_[a-z]+_funcgen_\d+_/ } @dbnames;
-
- for my $funcgen_db ( @funcgen_dbs ) {
- my ($species, $num ) = ( $funcgen_db =~ /(^[a-z]+_[a-z]+)_funcgen_(\d+)/ );
- my $dba = Bio::EnsEMBL::Funcgen::DBSQL::DBAdaptor->new
- ( -group => "funcgen",
- -species => $species,
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $funcgen_db
- );
- print $funcgen_db." loaded\n" if ($verbose);
- }
- }
-
- #Compara
- if($compara_version){
- eval "require Bio::EnsEMBL::Compara::DBSQL::DBAdaptor";
- if($@) {
- #ignore compara as code required not there for this
- print "Bio::EnsEMBL::Compara::DBSQL::DBAdaptor not found so compara database ensembl_compara_$compara_version will be ignored\n" if ($verbose);
+ for my $funcgen_db (@funcgen_dbs) {
+ my ( $species, $num ) =
+ ( $funcgen_db =~ /(^[a-z]+_[a-z]+)_funcgen_(\d+)/ );
+ my $dba =
+ Bio::EnsEMBL::Funcgen::DBSQL::DBAdaptor->new(
+ -group => "funcgen",
+ -species => $species,
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $funcgen_db );
+ print $funcgen_db. " loaded\n" if ($verbose);
}
- else{
- my $compara_db = "ensembl_compara_".$compara_version;
-
- my $dba = Bio::EnsEMBL::Compara::DBSQL::DBAdaptor->new
- ( -group => "compara",
- -species => "multi",
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $compara_db
- );
- print $compara_db." loaded\n" if ($verbose);
- }
- }
- else{
- print "No Compara database found" if ($verbose);
}
+ # Compara
- #Ancestral sequences
- if($ancestral_version){
- my $ancestral_db = "ensembl_ancestral_".$ancestral_version;
- my $dba = Bio::EnsEMBL::DBSQL::DBAdaptor->new
- ( -group => "core",
- -species => "Ancestral sequences",
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -wait_timeout => $wait_timeout,
- -dbname => $ancestral_db
- );
- print $ancestral_db." loaded\n" if ($verbose);
- }
- else{
+ if ($compara_version) {
+ eval "require Bio::EnsEMBL::Compara::DBSQL::DBAdaptor";
+ if ($@) {
+ # Ignore Compara as code required not there for this
+ if ($verbose) {
+ printf( "Bio::EnsEMBL::Compara::DBSQL::DBAdaptor "
+ . "not found so compara database "
+ . "ensembl_compara_%d will be ignored\n",
+ $compara_version );
+ }
+ } else {
+ my $compara_db = "ensembl_compara_" . $compara_version;
+
+ my $dba =
+ Bio::EnsEMBL::Compara::DBSQL::DBAdaptor->new(
+ -group => "compara",
+ -species => "multi",
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $compara_db );
+ if ($verbose) {
+ printf( "%s loaded\n", $compara_db );
+ }
+ }
+ } elsif ($verbose) {
+ print("No Compara database found\n");
+ }
+
+ # Ancestral sequences
+
+ if ($ancestral_version) {
+ my $ancestral_db = "ensembl_ancestral_" . $ancestral_version;
+ my $dba =
+ Bio::EnsEMBL::DBSQL::DBAdaptor->new(
+ -group => "core",
+ -species => "Ancestral sequences",
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -wait_timeout => $wait_timeout,
+ -dbname => $ancestral_db );
+ print $ancestral_db. " loaded\n" if ($verbose);
+ } else {
print "No Ancestral database found" if ($verbose);
}
+ # GO
- #GO
- if($go_version){
+ if ($go_version) {
eval "require Bio::EnsEMBL::ExternalData::GO::GOAdaptor";
- if($@) {
+ if ($@) {
#ignore go as code required not there for this
-# print $@;
- print "GO software not installed so go database ensemb_go_$go_version will be ignored\n" if ($verbose);
- }
- else{
- my $go_db = "ensembl_go_".$go_version;
- my $dba = Bio::EnsEMBL::ExternalData::GO::GOAdaptor->new
- ( -group => "go",
- -species => "multi",
- -host => $host,
- -user => $user,
- -pass => $pass,
- -port => $port,
- -dbname => $go_db
- );
- print $go_db." loaded\n" if ($verbose);
+ # print $@;
+ if ($verbose) {
+ print "GO software not installed "
+ . "so GO database ensemb_go_$go_version will be ignored\n";
+ }
+ } else {
+ my $go_db = "ensembl_go_" . $go_version;
+ my $dba =
+ Bio::EnsEMBL::ExternalData::GO::GOAdaptor->new(
+ -group => "go",
+ -species => "multi",
+ -host => $host,
+ -user => $user,
+ -pass => $pass,
+ -port => $port,
+ -dbname => $go_db
+ );
+ print $go_db. " loaded\n" if ($verbose);
}
- }
- else{
- print "No go database found" if ($verbose);
+ } elsif ($verbose) {
+ print("No GO database found\n");
}
- #hard coded aliases for the different species
+ # Hard coded aliases for the different species
- my @aliases = ('chimp','PanTro1', 'Pan', 'P_troglodytes');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Pan_troglodytes",
- -alias => \@aliases);
-
- @aliases = ('elegans','worm');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Caenorhabditis_elegans",
- -alias => \@aliases);
-
- @aliases = ('tetraodon');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Tetraodon_nigroviridis",
- -alias => \@aliases);
-
- @aliases = ('H_Sapiens', 'homo sapiens', 'Homo_Sapiens', 'Homo', 'human', 'Hg17','ensHS', '9606');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Homo_sapiens",
- -alias => \@aliases);
-
- @aliases = ('M_Musculus', 'mus musculus', 'Mus_Musculus', 'Mus', 'mouse','Mm5','ensMM','10090');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Mus_musculus",
- -alias => \@aliases);
-
- @aliases = ('R_Norvegicus', 'rattus norvegicus', 'Rattus_Norvegicus', 'Rattus', 'rat', 'Rn3', '10116');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Rattus_norvegicus",
- -alias => \@aliases);
-
- @aliases = ('T_Rubripes', 'Fugu', 'takifugu');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Takifugu_rubripes",
- -alias => \@aliases);
-
- @aliases = ('G_Gallus', 'gallus gallus', 'Chicken', 'GalGal2');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Gallus_Gallus",
- -alias => \@aliases);
-
- @aliases = ('D_Rerio', 'danio rerio', 'Danio_Rerio', 'Danio', 'zebrafish', 'zfish');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Danio_rerio",
- -alias => \@aliases);
-
- @aliases = ('X_Tropicalis', 'xenopus tropicalis','Xenopus_tropicalis', 'Xenopus');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Xenopus_tropicalis",
- -alias => \@aliases);
-
- @aliases = ('A_Gambiae', 'Anopheles Gambiae','Anopheles_gambiae', 'Anopheles','mosquito');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Anopheles_gambiae",
- -alias => \@aliases);
-
-
- @aliases = ('D_Melanogaster', 'drosophila melanogaster', 'Drosophila_melanogaster', 'drosophila', 'fly');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Drosophila_melanogaster",
- -alias => \@aliases);
-
- @aliases = ('S_Cerevisiae', 'Saccharomyces Cerevisiae',
- 'Saccharomyces_cerevisiae', 'Saccharomyces', 'yeast');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Saccharomyces_cerevisiae",
- -alias => \@aliases);
-
- @aliases = ('C_Familiaris', 'Canis Familiaris',
- 'Canis_familiaris', 'Canis', 'dog');
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Canis_familiaris",
- -alias => \@aliases);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Ciona_intestinalis",
- -alias => ['ciona','Ciona intestinalis']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Bos_taurus",
- -alias => ['cow','bos_taurus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Macaca_mulatta",
- -alias => ['rhesus','rhesus_monkey','macaque','macaca mulatta']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Otolemur_garnettii",
- -alias => ['bushbaby','galago','Otolemur garnettii']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Oryctolagus_cuniculus",
- -alias => ['rabbit','Oryctolagus cuniculus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Felis_catus",
- -alias => ['cat','felis catus']);
+ my @aliases = ( 'chimp', 'PanTro1', 'Pan', 'P_troglodytes' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Pan_troglodytes",
+ -alias => \@aliases );
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Sus_scrofa",
- -alias => ['pig','sus scrofa']);
+ @aliases = ( 'elegans', 'worm' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Caenorhabditis_elegans",
+ -alias => \@aliases );
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Sorex_araneus",
- -alias => ['shrew','ground_shrew','european_shrew','Sorex araneus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Erinaceus_europaeus",
- -alias => ['western_european_hedgehog','Erinaceus europaeus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Myotis_lucifugus",
- -alias => ['microbat','little_brown_bat']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Dasypus_novemcinctus",
- -alias => ['armadillo','arma','Dasypus novemcinctu']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Loxodonta_africana",
- -alias => ['african_elephant','elephant','Loxodonta africana']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Echinops_telfairi",
- -alias => ['tenrec','madagascar_hedgehog','lesser_hedgehog','Echinops telfairi']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Monodelphis_domestica",
- -alias => ['opossum','Monodelphis domestica']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Ornithorhynchus_anatinus",
- -alias => ['platypus','Ornithorhynchus anatinus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Gasterosteus_aculeatus",
- -alias => ['stickleback','Gasterosteus aculeatus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Oryzias_latipes",
- -alias => ['medaka','Oryzias latipes']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Cavia_porcellus",
- -alias => ['guinea_pig','"Cavia porcellus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Aedes_aegypti",
- -alias => ['aedes','Aedes aegypti']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Spermophilus_tridecemlineatus",
- -alias => ['squirrel','Spermophilus tridecemlineatus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Tupaia_belangeri",
- -alias => ['tree_shrew','Tupaia belangeri']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Culex_pipiens",
- -alias => ['culex','Culex Pipiens']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Ochotona_princeps",
- -alias => ['pika','Ochotona princeps']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Anolis_carolinensis",
- -alias => ['anolis','anolis_lizard','Anolis carolinensis']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Microcebus_murinus",
- -alias => ['mouse_lemur','Microcebus murinus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Pongo_pygmaeus",
- -alias => ['orang','orang_utan','orangutan','Pongo pygmaeus']);
-
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "Equus_caballus",
- -alias => ['horse', 'Equuscaballus']);
+ @aliases = ('tetraodon');
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Tetraodon_nigroviridis",
+ -alias => \@aliases );
+
+ @aliases = ( 'H_Sapiens', 'homo sapiens',
+ 'Homo_Sapiens', 'Homo',
+ 'human', 'Hg17',
+ 'ensHS', '9606' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Homo_sapiens",
+ -alias => \@aliases );
+
+ @aliases = ( 'M_Musculus', 'mus musculus',
+ 'Mus_Musculus', 'Mus',
+ 'mouse', 'Mm5',
+ 'ensMM', '10090' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Mus_musculus",
+ -alias => \@aliases );
+
+ @aliases = ( 'R_Norvegicus', 'rattus norvegicus',
+ 'Rattus_Norvegicus', 'Rattus',
+ 'rat', 'Rn3',
+ '10116' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Rattus_norvegicus",
+ -alias => \@aliases );
+
+ @aliases = ( 'T_Rubripes', 'Fugu', 'takifugu' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Takifugu_rubripes",
+ -alias => \@aliases );
+
+ @aliases = ( 'G_Gallus', 'gallus gallus', 'Chicken', 'GalGal2' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Gallus_Gallus",
+ -alias => \@aliases );
+
+ @aliases = ( 'D_Rerio', 'danio rerio',
+ 'Danio_Rerio', 'Danio',
+ 'zebrafish', 'zfish' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Danio_rerio",
+ -alias => \@aliases );
+
+ @aliases = ( 'X_Tropicalis', 'xenopus tropicalis',
+ 'Xenopus_tropicalis', 'Xenopus' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Xenopus_tropicalis",
+ -alias => \@aliases );
+
+ @aliases = ( 'A_Gambiae', 'Anopheles Gambiae',
+ 'Anopheles_gambiae', 'Anopheles',
+ 'mosquito' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Anopheles_gambiae",
+ -alias => \@aliases );
+
+ @aliases = ( 'D_Melanogaster', 'drosophila melanogaster',
+ 'Drosophila_melanogaster', 'drosophila',
+ 'fly' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Drosophila_melanogaster",
+ -alias => \@aliases );
+
+ @aliases = ( 'S_Cerevisiae', 'Saccharomyces Cerevisiae',
+ 'Saccharomyces_cerevisiae', 'Saccharomyces',
+ 'yeast' );
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Saccharomyces_cerevisiae",
+ -alias => \@aliases );
+
+ @aliases = ( 'C_Familiaris', 'Canis Familiaris',
+ 'Canis_familiaris', 'Canis',
+ 'dog' );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Canis_familiaris",
+ -alias => \@aliases );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Ciona_intestinalis",
+ -alias => [ 'ciona', 'Ciona intestinalis' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Bos_taurus",
+ -alias => [ 'cow', 'bos_taurus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Macaca_mulatta",
+ -alias => [ 'rhesus', 'rhesus_monkey', 'macaque', 'macaca mulatta' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Otolemur_garnettii",
+ -alias => [ 'bushbaby', 'galago', 'Otolemur garnettii' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Oryctolagus_cuniculus",
+ -alias => [ 'rabbit', 'Oryctolagus cuniculus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Felis_catus",
+ -alias => [ 'cat', 'felis catus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Sus_scrofa",
+ -alias => [ 'pig', 'sus scrofa' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Sorex_araneus",
+ -alias =>
+ [ 'shrew', 'ground_shrew', 'european_shrew', 'Sorex araneus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Erinaceus_europaeus",
+ -alias => [ 'western_european_hedgehog', 'Erinaceus europaeus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Myotis_lucifugus",
+ -alias => [ 'microbat', 'little_brown_bat' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Dasypus_novemcinctus",
+ -alias => [ 'armadillo', 'arma', 'Dasypus novemcinctu' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Loxodonta_africana",
+ -alias => [ 'african_elephant', 'elephant', 'Loxodonta africana' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Echinops_telfairi",
+ -alias => [
+ 'tenrec', 'madagascar_hedgehog',
+ 'lesser_hedgehog', 'Echinops telfairi'
+ ] );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Monodelphis_domestica",
+ -alias => [ 'opossum', 'Monodelphis domestica' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Ornithorhynchus_anatinus",
+ -alias => [ 'platypus', 'Ornithorhynchus anatinus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Gasterosteus_aculeatus",
+ -alias => [ 'stickleback', 'Gasterosteus aculeatus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Oryzias_latipes",
+ -alias => [ 'medaka', 'Oryzias latipes' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Cavia_porcellus",
+ -alias => [ 'guinea_pig', '"Cavia porcellus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Aedes_aegypti",
+ -alias => [ 'aedes', 'Aedes aegypti' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Spermophilus_tridecemlineatus",
+ -alias => [ 'squirrel', 'Spermophilus tridecemlineatus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Tupaia_belangeri",
+ -alias => [ 'tree_shrew', 'Tupaia belangeri' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Culex_pipiens",
+ -alias => [ 'culex', 'Culex Pipiens' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Ochotona_princeps",
+ -alias => [ 'pika', 'Ochotona princeps' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Anolis_carolinensis",
+ -alias => [ 'anolis', 'anolis_lizard', 'Anolis carolinensis' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Microcebus_murinus",
+ -alias => [ 'mouse_lemur', 'Microcebus murinus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Pongo_pygmaeus",
+ -alias => [ 'orang', 'orang_utan', 'orangutan', 'Pongo pygmaeus' ]
+ );
+
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(
+ -species => "Equus_caballus",
+ -alias => [ 'horse', 'Equuscaballus' ]
+ );
@aliases = ('compara');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "multi",
- -alias => \@aliases);
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias( -species => "multi",
+ -alias => \@aliases
+ );
@aliases = ('go');
- Bio::EnsEMBL::Utils::ConfigRegistry->add_alias(-species => "multi",
- -alias => \@aliases);
-}
+ Bio::EnsEMBL::Utils::ConfigRegistry->add_alias( -species => "multi",
+ -alias => \@aliases
+ );
+} ## end sub load_registry_from_db
#
@@ -1772,7 +1930,7 @@ sub version_check{
$database_version = $mca->get_schema_version();
}
if($database_version == 0){
- #try to work out the version
+ # Try to work out the version
if($dba->dbc->dbname() =~ /^_test_db_/){
return 1;
}
@@ -1826,7 +1984,7 @@ sub get_species_and_object_type{
$type{G} = "gene";
$type{P} = "translation";
- #Do each in turn in order of the usual suspects. This should increase speed on average.
+ # Do each in turn in order of the usual suspects. This should increase speed on average.
if($stable_id =~ /^ENS([GTP])000/){ # HUMAN NOTE 000 needed else other species will match
return "Homo_sapiens", $type{$1};
@@ -1853,7 +2011,7 @@ sub get_species_and_object_type{
return "Pan_troglodytes", $type{$1};
}
- #rest done alphabetically
+ # Rest done alphabetically
elsif($stable_id =~ /^AAEL/){ #
if($stable_id =~ /-R\w$/){
return "aedes_aegypti", "Transcript";