Inheritance diagram for Bio::EnsEMBL::DBSQL::GeneAdaptor:

Class Summary

Synopsis

  use Bio::EnsEMBL::Registry;

  Bio::EnsEMBL::Registry-\>load_registry_from_db(
    -host =\> 'ensembldb.ensembl.org',
    -user =\> 'anonymous',
  );

  $gene_adaptor =
    Bio::EnsEMBL::Registry-\>get_adaptor( "human", "core", "gene" );

  $gene = $gene_adaptor-\>fetch_by_dbID(1234);

  $gene = $gene_adaptor-\>fetch_by_stable_id('ENSG00000184129');

  @genes = @{ $gene_adaptor-\>fetch_all_by_external_name('BRCA2') };

  $slice_adaptor =
    Bio::EnsEMBL::Registry-\>get_adaptor( "human", "core", "slice" );

  $slice =
    $slice_adaptor-\>fetch_by_region( 'chromosome', '1', 1, 1000000 );

  @genes = @{ $gene_adaptor-\>fetch_all_by_Slice($slice) };

Description

This is a database aware adaptor for the retrieval and storage of gene
objects.

Definition at line 44 of file GeneAdaptor.pm.

Available Methods
protected	_check_start_end_strand ()
protected	_columns ()
protected	_create_feature ()
protected	_create_feature_fast ()
protected	_default_where_clause ()
protected	_final_clause ()
protected	_left_join ()
protected	_list_dbIDs ()
protected	_list_seq_region_ids ()
protected	_logic_name_to_constraint ()
protected	_max_feature_length ()
protected	_objs_from_sth ()
protected	_pre_store ()
protected	_pre_store_userdata ()
protected	_remap ()
protected Bio::EnsEMBL::Utils::Cache	_slice_feature_cache ()
protected	_slice_fetch ()
protected	_straight_join ()
protected	_tables ()
public Listref	bind_param_generic_fetch ()
public void	cache_gene_seq_mappings ()
public void	clear_cache ()
public Bio::EnsEMBL::DBSQL::DBAdaptor	db ()
public Bio::EnsEMBL::DBSQL::DBConnection	dbc ()
public	dump_data ()
public	fetch_all ()
public Listref	fetch_all_alt_alleles ()
public Listref	fetch_all_by_biotype ()
public	fetch_all_by_DBEntry ()
public Listref	fetch_all_by_dbID_list ()
public List	fetch_all_by_domain ()
public Listref	fetch_all_by_exon_supporting_evidence ()
public Listref	fetch_all_by_external_name ()
public Listref	fetch_all_by_GOTerm ()
public Listref	fetch_all_by_GOTerm_accession ()
public Listref	fetch_all_by_logic_name ()
public	fetch_all_by_RawContig ()
public	fetch_all_by_RawContig_and_score ()
public	fetch_all_by_RawContig_constraint ()
public Reference	fetch_all_by_Slice ()
public Reference	fetch_all_by_Slice_and_external_dbname_link ()
public Listref	fetch_all_by_Slice_and_score ()
public Listref	fetch_all_by_Slice_constraint ()
public Listref	fetch_all_by_transcript_supporting_evidence ()
public Listref	fetch_all_versions_by_stable_id ()
public Bio::EnsEMBL::Feature	fetch_by_dbID ()
public Bio::EnsEMBL::Gene	fetch_by_display_label ()
public Bio::EnsEMBL::Gene	fetch_by_exon_stable_id ()
public	fetch_by_maximum_DBLink ()
public	fetch_by_Peptide_id ()
public Bio::EnsEMBL::Gene	fetch_by_stable_id ()
public Bio::EnsEMBL::Gene	fetch_by_transcript_id ()
public Bio::EnsEMBL::Gene	fetch_by_transcript_stable_id ()
public Bio::EnsEMBL::Gene	fetch_by_translation_stable_id ()
public Bio::EnsEMBL::Utils::Iterator	fetch_Iterator_by_Slice ()
public Bio::EnsEMBL::Utils::Iterator	fetch_Iterator_by_Slice_method ()
public Listref	fetch_nearest_Gene_by_Feature ()
public Listref	generic_fetch ()
public	get_description ()
public	get_display_xref ()
public	get_dumped_data ()
public Listref	get_Interpro_by_geneid ()
public	get_seq_region_id_external ()
public	get_seq_region_id_internal ()
public	get_stable_entry_info ()
public Boolean	is_multispecies ()
public	is_ref ()
public Scalar	last_insert_id ()
public Listref	list_dbIDs ()
public	list_seq_region_ids ()
public Reference	list_stable_ids ()
public Bio::EnsEMBL::BaseFeatureAdaptor	new ()
public DBI::StatementHandle	prepare ()
public void	remove ()
public	remove_by_analysis_id ()
public	remove_by_feature_id ()
public	remove_by_RawContig ()
public void	remove_by_Slice ()
public Int	species_id ()
public Boolean	start_equals_end ()
public The	store ()
public void	store_alt_alleles ()
public void	update ()

Method Documentation

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_check_start_end_strand ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::GeneAdaptor::_columns ( )

Undocumented method

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_create_feature ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_create_feature_fast ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseAdaptor::_default_where_clause ( ) [inherited]

Undocumented method

Code:

click to view

Reimplemented in Bio::EnsEMBL::DBSQL::MiscFeatureAdaptor, Bio::EnsEMBL::DBSQL::RepeatFeatureAdaptor, Bio::EnsEMBL::Map::DBSQL::MarkerFeatureAdaptor, and Bio::EnsEMBL::Map::DBSQL::QtlFeatureAdaptor.

protected Bio::EnsEMBL::DBSQL::BaseAdaptor::_final_clause ( ) [inherited]

Undocumented method

Code:

click to view

Reimplemented in Bio::EnsEMBL::DBSQL::ExonAdaptor, Bio::EnsEMBL::DBSQL::MiscFeatureAdaptor, and Bio::EnsEMBL::DBSQL::PredictionExonAdaptor.

protected Bio::EnsEMBL::DBSQL::GeneAdaptor::_left_join ( )

Undocumented method

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

protected Bio::EnsEMBL::DBSQL::BaseAdaptor::_list_dbIDs ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_list_seq_region_ids ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_logic_name_to_constraint ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_max_feature_length ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::GeneAdaptor::_objs_from_sth ( )

Undocumented method

Code:

click to view

sub _objs_from_sth {
  my ($self, $sth, $mapper, $dest_slice) = @_;

  #
  # This code is ugly because an attempt has been made to remove as many
  # function calls as possible for speed purposes.  Thus many caches and
  # a fair bit of gymnastics is used.
  #

  my $sa             = $self->db()->get_SliceAdaptor();
  my $aa             = $self->db()->get_AnalysisAdaptor();
  my $dbEntryAdaptor = $self->db()->get_DBEntryAdaptor();

  my @genes;
  my %analysis_hash;
  my %slice_hash;
  my %sr_name_hash;
  my %sr_cs_hash;

  my (
    $gene_id,                 $seq_region_id,
    $seq_region_start,        $seq_region_end,
    $seq_region_strand,       $analysis_id,
    $biotype,                 $display_xref_id,
    $gene_description,        $status,
    $source,                  $is_current,
    $canonical_transcript_id, $canonical_annotation,
    $stable_id,               $version,
    $created_date,            $modified_date,
    $xref_display_id,         $xref_primary_acc,
    $xref_desc,               $xref_version,
    $external_db,             $external_status,
    $external_release,        $external_db_name,
    $info_type,               $info_text
  );

  $sth->bind_columns(
    \(
      $gene_id,                 $seq_region_id,
      $seq_region_start,        $seq_region_end,
      $seq_region_strand,       $analysis_id,
      $biotype,                 $display_xref_id,
      $gene_description,        $status,
      $source,                  $is_current,
      $canonical_transcript_id, $canonical_annotation,
      $stable_id,               $version,
      $created_date,            $modified_date,
      $xref_display_id,         $xref_primary_acc,
      $xref_desc,               $xref_version,
      $external_db,             $external_status,
      $external_release,        $external_db_name,
      $info_type,               $info_text
    ) );

  my $asm_cs;
  my $cmp_cs;
  my $asm_cs_vers;
  my $asm_cs_name;
  my $cmp_cs_vers;
  my $cmp_cs_name;

  if($mapper) {
    $asm_cs = $mapper->assembled_CoordSystem();
    $cmp_cs = $mapper->component_CoordSystem();
    $asm_cs_name = $asm_cs->name();
    $asm_cs_vers = $asm_cs->version();
    $cmp_cs_name = $cmp_cs->name();
    $cmp_cs_vers = $cmp_cs->version();
  }

  my $dest_slice_start;
  my $dest_slice_end;
  my $dest_slice_strand;
  my $dest_slice_length;
  my $dest_slice_sr_name;
  my $dest_slice_sr_id;

  if($dest_slice) {
    $dest_slice_start  = $dest_slice->start();
    $dest_slice_end    = $dest_slice->end();
    $dest_slice_strand = $dest_slice->strand();
    $dest_slice_length = $dest_slice->length();
    $dest_slice_sr_name = $dest_slice->seq_region_name();
    $dest_slice_sr_id = $dest_slice->get_seq_region_id();
  }

  FEATURE: while($sth->fetch()) {
    #get the analysis object
    my $analysis = $analysis_hash{$analysis_id} ||=
      $aa->fetch_by_dbID($analysis_id);

    #need to get the internal_seq_region, if present
    $seq_region_id = $self->get_seq_region_id_internal($seq_region_id);
    my $slice = $slice_hash{"ID:".$seq_region_id};

    if(!$slice) {
      $slice = $sa->fetch_by_seq_region_id($seq_region_id);
      $slice_hash{"ID:".$seq_region_id} = $slice;
      $sr_name_hash{$seq_region_id} = $slice->seq_region_name();
      $sr_cs_hash{$seq_region_id} = $slice->coord_system();
    }

    my $sr_name = $sr_name_hash{$seq_region_id};
    my $sr_cs   = $sr_cs_hash{$seq_region_id};

    #
    # remap the feature coordinates to another coord system 
    # if a mapper was provided
    #
    if($mapper) {

      ($seq_region_id,$seq_region_start,$seq_region_end,$seq_region_strand) =
        $mapper->fastmap($sr_name, $seq_region_start, $seq_region_end,
             $seq_region_strand, $sr_cs);

      #skip features that map to gaps or coord system boundaries
      next FEATURE if(!defined($seq_region_id));

      #get a slice in the coord system we just mapped to
#      if($asm_cs == $sr_cs || ($cmp_cs != $sr_cs && $asm_cs->equals($sr_cs))) {
        $slice = $slice_hash{"ID:".$seq_region_id} ||=
          $sa->fetch_by_seq_region_id($seq_region_id);
#      } else {
#        $slice = $slice_hash{"NAME:$sr_name:$asm_cs_name:$asm_cs_vers"} ||=
#          $sa->fetch_by_region($asm_cs_name, $sr_name, undef, undef, undef,
#                               $asm_cs_vers);
#      }
    }

    #
    # If a destination slice was provided convert the coords.
    #
    if ( defined($dest_slice) ) {
      if ( $dest_slice_strand == 1 ) {
        # Positive strand.

        $seq_region_start = $seq_region_start - $dest_slice_start + 1;
        $seq_region_end   = $seq_region_end - $dest_slice_start + 1;

        if ( $dest_slice->is_circular() ) {
          # Handle cicular chromosomes.

          if ( $seq_region_start > $seq_region_end ) {
            # Looking at a feature overlapping the chromsome origin.

            if ( $seq_region_end > $dest_slice_start ) {
              # Looking at the region in the beginning of the
              # chromosome.
              $seq_region_start -= $dest_slice->seq_region_length();
            }

            if ( $seq_region_end < 0 ) {
              $seq_region_end += $dest_slice->seq_region_length();
            }

          } else {

            if (    $dest_slice_start > $dest_slice_end
                 && $seq_region_end < 0 )
            {
              # Looking at the region overlapping the chromosome
              # origin and a feature which is at the beginning of the
              # chromosome.
              $seq_region_start += $dest_slice->seq_region_length();
              $seq_region_end   += $dest_slice->seq_region_length();
            }
          }

        } ## end if ( $dest_slice->is_circular...)

      } else {
        # Negative strand.

        if (    $dest_slice->is_circular()
             && $seq_region_start > $seq_region_end )
        {
          # Handle cicular chromosomes.

          if ( $seq_region_end > $dest_slice_start ) {
            # Looking at the region in the beginning of the
            # chromosome.
            $seq_region_start = $dest_slice_end - $seq_region_end + 1;
            $seq_region_end =
              $seq_region_end -
              $dest_slice->seq_region_length -
              $dest_slice_start + 1;
          } else {
            my $tmp_seq_region_start = $seq_region_start;
            $seq_region_start =
              $dest_slice_end -
              $seq_region_end -
              $dest_slice->seq_region_length + 1;
            $seq_region_end =
              $dest_slice_end - $tmp_seq_region_start + 1;
          }

        } else {
          # Non-circular chromosome.

          my $tmp_seq_region_start = $seq_region_start;
          $seq_region_start = $dest_slice_end - $seq_region_end + 1;
          $seq_region_end = $dest_slice_end - $tmp_seq_region_start + 1;
        }

        $seq_region_strand = -$seq_region_strand;

      } ## end else [ if ( $dest_slice_strand...)]

      # Throw away features off the end of the requested slice or on
      # different seq_region.

      if (    $seq_region_end < 1
           || $seq_region_start > $dest_slice_length
           || ( $dest_slice_sr_id ne $seq_region_id ) )
      {
        next FEATURE;
      }

      $slice = $dest_slice;
    } ## end if ( defined($dest_slice...))

    my $display_xref;

    if ($display_xref_id) {
      $display_xref = Bio::EnsEMBL::DBEntry->new_fast( {
          'dbID'            => $display_xref_id,
          'adaptor'         => $dbEntryAdaptor,
          'display_id'      => $xref_display_id,
          'primary_id'      => $xref_primary_acc,
          'version'         => $xref_version,
          'description'     => $xref_desc,
          'release'         => $external_release,
          'dbname'          => $external_db,
          'db_display_name' => $external_db_name,
          'info_type'       => $info_type,
          'info_text'       => $info_text
      } );
      $display_xref->status($external_status);
    }

    # Finally, create the new Gene.
    push(
      @genes,
      $self->_create_feature_fast(
        'Bio::EnsEMBL::Gene',
        {
          'analysis'      => $analysis,
          'biotype'       => $biotype,
          'start'         => $seq_region_start,
          'end'           => $seq_region_end,
          'strand'        => $seq_region_strand,
          'adaptor'       => $self,
          'slice'         => $slice,
          'dbID'          => $gene_id,
          'stable_id'     => $stable_id,
          'version'       => $version,
          'created_date'  => $created_date || undef,
          'modified_date' => $modified_date || undef,
          'description'   => $gene_description,
          'external_name'   => undef,              # will use display_id
                                                   # from display_xref
          'external_db'     => $external_db,
          'external_status' => $external_status,
          'display_xref'    => $display_xref,
          'status'          => $status,
          'source'          => $source,
          'is_current'      => $is_current,
          'canonical_transcript_id' => $canonical_transcript_id,
          'canonical_annotation'    => $canonical_annotation
        } ) );

  }

  return \@genes;
}

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_pre_store ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_pre_store_userdata ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_remap ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::Utils::Cache Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_slice_feature_cache ( ) [inherited]

 
  Description	: Returns the feature cache if we are allowed to cache and
                will build it if we need to. We will never return a reference
                to the hash to avoid unintentional auto-vivfying caching
  Returntype 	: Bio::EnsEMBL::Utils::Cache
  Exceptions 	: None
  Caller     	: Internal

Code:

click to view

protected Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::_slice_fetch ( ) [inherited]

Undocumented method

Code:

click to view

sub _slice_fetch {
  my ( $self, $slice, $orig_constraint ) = @_;

  my $slice_start         = $slice->start();
  my $slice_end           = $slice->end();
  my $slice_strand        = $slice->strand();
  my $slice_cs            = $slice->coord_system();
  my $slice_seq_region    = $slice->seq_region_name();
  my $slice_seq_region_id = $slice->get_seq_region_id();

  #get the synonym and name of the primary_table
  my @tabs = $self->_tables;
  my ( $tab_name, $tab_syn ) = @{ $tabs[0] };

  #find out what coordinate systems the features are in
  my $mcc      = $self->db->get_MetaCoordContainer();
  my @feat_css = ();

  my $mca        = $self->db->get_MetaContainer();
  my $value_list = $mca->list_value_by_key( $tab_name . "build.level" );
  if ( @$value_list and $slice->is_toplevel() ) {
    push @feat_css, $slice_cs;
  } else {
    @feat_css =
      @{ $mcc->fetch_all_CoordSystems_by_feature_type($tab_name) };
  }

  my $asma = $self->db->get_AssemblyMapperAdaptor();
  my @features;

  # fetch the features from each coordinate system they are stored in
COORD_SYSTEM: foreach my $feat_cs (@feat_css) {
    my $mapper;
    my @coords;
    my @ids;

    if ( $feat_cs->equals($slice_cs) ) {
      # no mapping is required if this is the same coord system

      my $max_len = $self->_max_feature_length()
        || $mcc->fetch_max_length_by_CoordSystem_feature_type( $feat_cs,
                                                            $tab_name );

      my $constraint = $orig_constraint;

      my $sr_id;
      if ( $slice->adaptor() ) {
        $sr_id = $slice->adaptor()->get_seq_region_id($slice);
      } else {
        $sr_id =
          $self->db()->get_SliceAdaptor()->get_seq_region_id($slice);
      }

      # If there is mapping information, use the external_seq_region_id
      # to get features.

      my @sr_ids = ($sr_id);

      while (1) {
        my $ext_sr_id = $self->get_seq_region_id_external($sr_id);

        if ( $ext_sr_id == $sr_id ) { last }

        push( @sr_ids, $ext_sr_id );
        $sr_id = $ext_sr_id;
      }

      $constraint .= " AND " if ($constraint);

      
      $constraint .= "${tab_syn}.seq_region_id IN ("
          . join( ',', @sr_ids ) . ") AND";

      #faster query for 1bp slices where SNP data is not compressed
      if ( $self->start_equals_end && $slice_start == $slice_end ) {
      $constraint .=
          " AND ${tab_syn}.seq_region_start = $slice_end" .
          " AND ${tab_syn}.seq_region_end = $slice_start";

      } else {

      if ( !$slice->is_circular() ) {
          # Deal with the default case of a non-circular chromosome.
          $constraint .= " ${tab_syn}.seq_region_start <= $slice_end AND "
          . "${tab_syn}.seq_region_end >= $slice_start";

          if ( $max_len ) {
          my $min_start = $slice_start - $max_len;
          $constraint .= " AND ${tab_syn}.seq_region_start >= $min_start";
          }

      } else {
          # Deal with the case of a circular chromosome.
          if ( $slice_start > $slice_end ) {
          $constraint .= " ( ${tab_syn}.seq_region_start >= $slice_start "
              . "OR ${tab_syn}.seq_region_start <= $slice_end "
              . "OR ${tab_syn}.seq_region_end >= $slice_start "
              . "OR ${tab_syn}.seq_region_end <= $slice_end "
              . "OR ${tab_syn}.seq_region_start > ${tab_syn}.seq_region_end)";

          } else {
          $constraint .= " ((${tab_syn}.seq_region_start <= $slice_end "
              . "AND ${tab_syn}.seq_region_end >= $slice_start) "
              . "OR (${tab_syn}.seq_region_start > ${tab_syn}.seq_region_end "
              . "AND (${tab_syn}.seq_region_start <= $slice_end "
              . "OR ${tab_syn}.seq_region_end >= $slice_start)))";
          }
      }

      }

      my $fs = $self->generic_fetch( $constraint, undef, $slice );

    # features may still have to have coordinates made relative to slice
    # start
      $fs = $self->_remap( $fs, $mapper, $slice );

      push @features, @$fs;
    } else {
      $mapper = $asma->fetch_by_CoordSystems( $slice_cs, $feat_cs );

      next unless defined $mapper;

      # Get list of coordinates and corresponding internal ids for
      # regions the slice spans
      @coords =
        $mapper->map( $slice_seq_region, $slice_start, $slice_end,
                      $slice_strand, $slice_cs );

      @coords = grep { !$_->isa('Bio::EnsEMBL::Mapper::Gap') } @coords;

      next COORD_SYSTEM if ( !@coords );

      @ids = map { $_->id() } @coords;
      #coords are now id rather than name
      #      @ids = @{$asma->seq_regions_to_ids($feat_cs, \@ids)};

      # When regions are large and only partially spanned
      # by slice it is faster to to limit the query with
      # start and end constraints.  Take simple approach:
      # use regional constraints if there are less than a
      # specific number of regions covered.

      if ( @coords > $MAX_SPLIT_QUERY_SEQ_REGIONS ) {
        my $constraint = $orig_constraint;
        my $id_str = join( ',', @ids );
        $constraint .= " AND " if ($constraint);
        $constraint .= "${tab_syn}.seq_region_id IN ($id_str)";
        my $fs = $self->generic_fetch( $constraint, $mapper, $slice );

        $fs = $self->_remap( $fs, $mapper, $slice );

        push @features, @$fs;

      } else {
        # do multiple split queries using start / end constraints

        my $max_len = (
                $self->_max_feature_length()
                  || $mcc->fetch_max_length_by_CoordSystem_feature_type(
                                                     $feat_cs, $tab_name
                  ) );

        my $len = @coords;
        for ( my $i = 0; $i < $len; $i++ ) {
          my $constraint = $orig_constraint;
          $constraint .= " AND " if ($constraint);
          $constraint .=
              "${tab_syn}.seq_region_id = "
            . $ids[$i] . " AND "
            . "${tab_syn}.seq_region_start <= "
            . $coords[$i]->end() . " AND "
            . "${tab_syn}.seq_region_end >= "
            . $coords[$i]->start();

          if ($max_len) {
            my $min_start = $coords[$i]->start() - $max_len;
            $constraint .=
              " AND ${tab_syn}.seq_region_start >= $min_start";
          }
          my $fs = $self->generic_fetch( $constraint, $mapper, $slice );

          $fs = $self->_remap( $fs, $mapper, $slice );

          push @features, @$fs;
        }
      } ## end else [ if ( @coords > $MAX_SPLIT_QUERY_SEQ_REGIONS)]
    } ## end else [ if ( $feat_cs->equals(...))]
  } ## end foreach my $feat_cs (@feat_css)

  return \@features;
} ## end sub _slice_fetch

protected Bio::EnsEMBL::DBSQL::BaseAdaptor::_straight_join ( ) [inherited]

Undocumented method

Code:

click to view

protected Bio::EnsEMBL::DBSQL::GeneAdaptor::_tables ( )

Undocumented method

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

public Listref Bio::EnsEMBL::DBSQL::BaseAdaptor::bind_param_generic_fetch ( ) [inherited]

 Arg [1]   : (optional)  scalar $param
              This is the parameter to bind
 Arg [2]   : (optional) int $sql_type
              Type of the parameter (from DBI (:sql_types))
 Example   :  $adaptor->bind_param_generic_fetch($stable_id,SQL_VARCHAR);
              $adaptor->generic_fetch();
 Description:  When using parameters for the query, will call the bind_param to avoid
               some security issues. If there are no arguments, will return the bind_parameters
 ReturnType : listref
 Exceptions:  if called with one argument

Code:

click to view

public void Bio::EnsEMBL::DBSQL::GeneAdaptor::cache_gene_seq_mappings ( )

  Example    : $gene_adaptor->cache_gene_seq_mappings();
  Description: caches all the assembly mappings needed for genes
  Returntype : None
  Exceptions : None
  Caller     : general
  Status     : At Risk
             : New experimental code

Code:

click to view

public void Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::clear_cache ( ) [inherited]

  Args      : None
  Example   : my $sa =
                $registry->get_adaptor( 'Mus musculus', 'Core',
                                        'Slice' );
              my $ga =
                $registry->get_adaptor( 'Mus musculus', 'Core',
                                        'Gene' );

              my $slice =
                $sa->fetch_by_region( 'Chromosome', '1', 1e8,
                                      1.05e8 );

              my $genes = $ga->fetch_all_by_Slice($slice);

              $ga->clear_cache();

  Description   : Empties the feature cache associated with this
                  feature adaptor.
  Return type   : None
  Exceptions    : None
  Caller        : General
  Status        : At risk (under development)

Code:

click to view

public Bio::EnsEMBL::DBSQL::DBAdaptor Bio::EnsEMBL::DBSQL::BaseAdaptor::db ( ) [inherited]

  Arg [1]    : (optional) Bio::EnsEMBL::DBSQL::DBAdaptor $obj 
               the database this adaptor is using.
  Example    : $db = $adaptor->db();
  Description: Getter/Setter for the DatabaseConnection that this adaptor is 
               using.
  Returntype : Bio::EnsEMBL::DBSQL::DBAdaptor
  Exceptions : none
  Caller     : Adaptors inherited from BaseAdaptor
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::DBConnection Bio::EnsEMBL::DBSQL::BaseAdaptor::dbc ( ) [inherited]

  Arg [1]    : (optional) Bio::EnsEMBL::DBSQL::DBConnection $obj 
               the database this adaptor is using.
  Example    : $db = $adaptor->db();
  Description: Getter/Setter for the DatabaseConnection that this adaptor is 
               using.
  Returntype : Bio::EnsEMBL::DBSQL::DBConnection
  Exceptions : none
  Caller     : Adaptors inherited from BaseAdaptor
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseAdaptor::dump_data ( ) [inherited]

Undocumented method

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all ( )

Undocumented method

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_alt_alleles ( )

  Arg [1]    : Bio::EnsEMBL::Gene $gene
               The gene to fetch alternative alleles for
  Example    : my @alt_genes = @{ $gene_adaptor->fetch_all_alt_alleles($gene) };
               foreach my $alt_gene (@alt_genes) {
                 print "Alternate allele: " . $alt_gene->stable_id() . "\\n";
               }
  Description: Retrieves genes which are alternate alleles to a provided gene.
               Alternate alleles in Ensembl are genes which are similar and are
               on an alternative haplotype of the same region. There are not 
               currently very many of these. This method will return a 
               reference to an empty list if no alternative alleles are found.
  Returntype : listref of Bio::EnsEMBL::Genes
  Exceptions : throw if incorrect arg provided
               warning if gene arg does not have dbID
  Caller     : Gene::get_all_alt_alleles
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_biotype ( )

  Arg [1]    : String $biotype 
               listref of $biotypes
               The biotype of the gene to retrieve. You can have as an argument a reference
               to a list of biotypes
  Example    : $gene = $gene_adaptor->fetch_all_by_biotype('protein_coding'); 
               $gene = $gene_adaptor->fetch_all_by_biotypes(['protein_coding', 'sRNA', 'miRNA']);
  Description: Retrieves an array reference of gene objects from the database via its biotype or biotypes.
               The genes will be retrieved in its native coordinate system (i.e.
               in the coordinate system it is stored in the database). It may
               be converted to a different coordinate system through a call to
               transform() or transfer(). If the gene or exon is not found
               undef is returned instead.
  Returntype  : listref of Bio::EnsEMBL::Gene
  Exceptions : if we cant get the gene in given coord system
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_DBEntry ( )

Description:

Deprecated:

Use fetch_all_by_external_name instead

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::BaseAdaptor::fetch_all_by_dbID_list ( ) [inherited]

  Arg [1]    : listref of integers $id_list
               The unique database identifiers for the features to
               be obtained.
  Arg [2]    : optional - Bio::EnsEMBL::Slice to map features onto.
  Example    : @feats = @{$adaptor->fetch_all_by_dbID_list([1234, 2131, 982]))};
  Description: Returns the features created from the database
               defined by the the IDs in contained in the provided
               ID list $id_list.  The features will be returned
               in their native coordinate system.  That is, the
               coordinate system in which they are stored in the
               database.  In order to convert the features to a
               particular coordinate system use the transfer() or
               transform() method.  If none of the features are
               found in the database a reference to an empty list is
               returned.
  Returntype : listref of Bio::EnsEMBL::Features
  Exceptions : thrown if $id arg is not provided
               does not exist
  Caller     : general
  Status     : Stable

Code:

click to view

Reimplemented in Bio::EnsEMBL::DBSQL::OntologyTermAdaptor.

public List Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_domain ( )

  Arg [1]    : String $domain
               The domain to fetch genes from
  Example    : my @genes = @{ $gene_adaptor->fetch_all_by_domain($domain) };
  Description: Retrieves a listref of genes whose translation contain interpro
               domain $domain. The genes are returned in their native coord
               system (i.e. the coord_system they are stored in). If the coord
               system needs to be changed, then tranform or transfer should be
               called on the individual objects returned.
  Returntype : list of Bio::EnsEMBL::Genes
  Exceptions : none
  Caller     : domainview
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_exon_supporting_evidence ( )

  Arg [1]    : String $hit_name
               Name of supporting feature
  Arg [2]    : String $feature_type 
               one of "dna_align_feature" or "protein_align_feature"
  Arg [3]    : (optional) Bio::Ensembl::Analysis
  Example    : $genes = $gene_adaptor->fetch_all_by_exon_supporting_evidence(
                  'XYZ', 'dna_align_feature');
  Description: Gets all the genes with transcripts with exons which have a
               specified hit on a particular type of feature. Optionally filter
               by analysis.
  Returntype : Listref of Bio::EnsEMBL::Gene
  Exceptions : If feature_type is not of correct type.
  Caller     : general
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_external_name ( )

  Arg [1]    : String $external_name
               The external identifier for the gene to be obtained
  Arg [2]    : (optional) String $external_db_name
               The name of the external database from which the
               identifier originates.
  Example    : @genes = @{$gene_adaptor->fetch_all_by_external_name('BRCA2')}
               @many_genes = @{$gene_adaptor->fetch_all_by_external_name('BRCA%')}
  Description: Retrieves a list of genes with an external database
               identifier $external_name. The genes returned are in
               their native coordinate system, i.e. in the coordinate
               system they are stored in the database in.  If another
               coordinate system is required then the Gene::transfer or
               Gene::transform method can be used.
               SQL wildcards % and _ are supported in the $external_name
  Returntype : listref of Bio::EnsEMBL::Gene
  Exceptions : none
  Caller     : goview, general
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_GOTerm ( )

  Arg [1]   : Bio::EnsEMBL::OntologyTerm
              The GO term for which genes should be fetched.

  Example:  @genes = @{
              $gene_adaptor->fetch_all_by_GOTerm(
                $go_adaptor->fetch_by_accession('GO:0030326') ) };

  Description   : Retrieves a list of genes that are associated with
                  the given GO term, or with any of its descendent
                  GO terms.  The genes returned are in their native
                  coordinate system, i.e. in the coordinate system
                  in which they are stored in the database.  If
                  another coordinate system is required then the
                  Gene::transfer or Gene::transform method can be
                  used.

  Return type   : listref of Bio::EnsEMBL::Gene
  Exceptions    : Throws of argument is not a GO term
  Caller        : general
  Status        : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_GOTerm_accession ( )

  Arg [1]   : String
              The GO term accession for which genes should be
              fetched.

  Example   :

    @genes =
      @{ $gene_adaptor->fetch_all_by_GOTerm_accession(
        'GO:0030326') };

  Description   : Retrieves a list of genes that are associated with
                  the given GO term, or with any of its descendent
                  GO terms.  The genes returned are in their native
                  coordinate system, i.e. in the coordinate system
                  in which they are stored in the database.  If
                  another coordinate system is required then the
                  Gene::transfer or Gene::transform method can be
                  used.

  Return type   : listref of Bio::EnsEMBL::Gene
  Exceptions    : Throws of argument is not a GO term accession
  Caller        : general
  Status        : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_logic_name ( ) [inherited]

  Arg [3]    : string $logic_name
               the logic name of the type of features to obtain
  Example    : $fs = $a->fetch_all_by_logic_name('foobar');
  Description: Returns a listref of features created from the database.
               only features with an analysis of type $logic_name will
               be returned.  If the logic name is invalid (not in the
               analysis table), a reference to an empty list will be
               returned.
  Returntype : listref of Bio::EnsEMBL::SeqFeatures
  Exceptions : thrown if no $logic_name
  Caller     : General
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_RawContig ( ) [inherited]

Description:

Deprecated:: use fetch_all_by_Slice instead

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_RawContig_and_score ( ) [inherited]

Description:

Deprecated:: use fetch_all_by_Slice_and_score instead

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_RawContig_constraint ( ) [inherited]

Description:

Deprecated:: use fetch_all_by_RawContig_constraint instead

Code:

click to view

public Reference Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_Slice ( )

  Arg [1]    : Bio::EnsEMBL::Slice $slice
               The slice to fetch genes on.
  Arg [2]    : (optional) string $logic_name
               the logic name of the type of features to obtain
  Arg [3]    : (optional) boolean $load_transcripts
               if true, transcripts will be loaded immediately rather than
               lazy loaded later.
  Arg [4]    : (optional) string $source
               the source name of the features to obtain.
  Arg [5]    : (optional) string biotype
                the biotype of the features to obtain.
  Example    : @genes = @{$gene_adaptor->fetch_all_by_Slice()};
  Description: Overrides superclass method to optionally load transcripts
               immediately rather than lazy-loading them later.  This
               is more efficient when there are a lot of genes whose
               transcripts are going to be used.
  Returntype : reference to list of genes 
  Exceptions : thrown if exon cannot be placed on transcript slice
  Caller     : Slice::get_all_Genes
  Status     : Stable

Code:

click to view

sub fetch_all_by_Slice {
  my ( $self, $slice, $logic_name, $load_transcripts, $source,
    $biotype ) = @_;

  my $constraint = 'g.is_current = 1';

  if ( defined($source) ) {
    $constraint .= " and g.source = '$source'";
  }
  if ( defined($biotype) ) {
    $constraint .= " and g.biotype = '$biotype'";
  }

  my $genes =
    $self->SUPER::fetch_all_by_Slice_constraint( $slice, $constraint,
    $logic_name );

  # If there are less than two genes, still do lazy-loading.
  if ( !$load_transcripts || @$genes < 2 ) {
    return $genes;
  }

  # Preload all of the transcripts now, instead of lazy loading later,
  # faster than one query per transcript.

  # First check if transcripts are already preloaded.
  # FIXME: Should check all transcripts.
  if ( exists( $genes->[0]->{'_transcript_array'} ) ) {
    return $genes;
  }

  # Get extent of region spanned by transcripts.
  my ( $min_start, $max_end );
  foreach my $g (@$genes) {
    if ( !defined($min_start) || $g->seq_region_start() < $min_start ) {
      $min_start = $g->seq_region_start();
    }
    if ( !defined($max_end) || $g->seq_region_end() > $max_end ) {
      $max_end = $g->seq_region_end();
    }
  }

  my $ext_slice;

  if ( $min_start >= $slice->start() && $max_end <= $slice->end() ) {
    $ext_slice = $slice;
  } else {
    my $sa = $self->db()->get_SliceAdaptor();
    $ext_slice = $sa->fetch_by_region(
      $slice->coord_system->name(), $slice->seq_region_name(),
      $min_start,                   $max_end,
      $slice->strand(),             $slice->coord_system->version() );
  }

  # Associate transcript identifiers with genes.

  my %g_hash = map { $_->dbID => $_ } @{$genes};

  my $g_id_str = join( ',', keys(%g_hash) );

  my $sth =
    $self->prepare( "SELECT gene_id, transcript_id "
      . "FROM   transcript "
      . "WHERE  gene_id IN ($g_id_str)" );

  $sth->execute();

  my ( $g_id, $tr_id );
  $sth->bind_columns( \( $g_id, $tr_id ) );

  my %tr_g_hash;

  while ( $sth->fetch() ) {
    $tr_g_hash{$tr_id} = $g_hash{$g_id};
  }

  my $ta          = $self->db()->get_TranscriptAdaptor();
  my $transcripts = $ta->fetch_all_by_Slice(
    $ext_slice,
    1, undef,
    sprintf( "t.transcript_id IN (%s)",
      join( ',', sort { $a <=> $b } keys(%tr_g_hash) ) ) );

  # Move transcripts onto gene slice, and add them to genes.
  foreach my $tr ( @{$transcripts} ) {
    if ( !exists( $tr_g_hash{ $tr->dbID() } ) ) { next }

    my $new_tr;
    if ( $slice != $ext_slice ) {
      $new_tr = $tr->transfer($slice);
      if ( !defined($new_tr) ) {
        throw("Unexpected. "
            . "Transcript could not be transfered onto Gene slice." );
      }
    } else {
      $new_tr = $tr;
    }

    $tr_g_hash{ $tr->dbID() }->add_Transcript($new_tr);
  }

  return $genes;
} ## end sub fetch_all_by_Slice

Reimplemented from Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor.

public Reference Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_Slice_and_external_dbname_link ( )

  Arg [1]    : Bio::EnsEMBL::Slice $slice
               The slice to fetch genes on.
  Arg [2]    : (optional) string $logic_name
               the logic name of the type of features to obtain
  Arg [3]    : (optional) boolean $load_transcripts
               if true, transcripts will be loaded immediately
               rather than lazy loaded later.
  Arg [4]    : Name of the external database
  Example    : @genes = @{
                 $ga->fetch_all_by_Slice_and_external_dbname_link(
                                          $slice, undef, undef, "HUGO" ) };
  Description: Overrides superclass method to optionally load
               transcripts immediately rather than lazy-loading them
               later.  This is more efficient when there are a lot
               of genes whose transcripts are going to be used. The
               genes are then filtered to return only those with
               external database links of the type specified
  Returntype : reference to list of genes
  Exceptions : thrown if exon cannot be placed on transcript slice
  Caller     : 
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_Slice_and_score ( ) [inherited]

  Arg [1]    : Bio::EnsEMBL::Slice $slice
               the slice from which to obtain features
  Arg [2]    : (optional) float $score
               lower bound of the the score of the features retrieved
  Arg [3]    : (optional) string $logic_name
               the logic name of the type of features to obtain
  Example    : $fts = $a->fetch_all_by_Slice_and_score($slice,90,'Swall');
  Description: Returns a list of features created from the database which are 
               are on the Slice defined by $slice and which have a score 
               greater than $score. If $logic_name is defined, 
               only features with an analysis of type $logic_name will be 
               returned. 
  Returntype : listref of Bio::EnsEMBL::SeqFeatures in Slice coordinates
  Exceptions : none
  Caller     : Bio::EnsEMBL::Slice
  Status     : Stable

Code:

click to view

Reimplemented in Bio::EnsEMBL::Map::DBSQL::MarkerFeatureAdaptor.

public Listref Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_all_by_Slice_constraint ( ) [inherited]

  Arg [1]    : Bio::EnsEMBL::Slice $slice
               the slice from which to obtain features
  Arg [2]    : (optional) string $constraint
               An SQL query constraint (i.e. part of the WHERE clause)
  Arg [3]    : (optional) string $logic_name
               the logic name of the type of features to obtain
  Example    : $fs = $a->fetch_all_by_Slice_constraint($slc, 'perc_ident > 5');
  Description: Returns a listref of features created from the database which 
               are on the Slice defined by $slice and fulfill the SQL 
               constraint defined by $constraint. If logic name is defined, 
               only features with an analysis of type $logic_name will be 
               returned. 
  Returntype : listref of Bio::EnsEMBL::SeqFeatures in Slice coordinates
  Exceptions : thrown if $slice is not defined
  Caller     : Bio::EnsEMBL::Slice
  Status     : Stable

Code:

click to view

sub fetch_all_by_Slice_constraint {
  my ( $self, $slice, $constraint, $logic_name ) = @_;


  my @result = ();

  if ( !ref($slice)
       || !(    $slice->isa('Bio::EnsEMBL::Slice')
             or $slice->isa('Bio::EnsEMBL::LRGSlice') ) )
  {
    throw("Bio::EnsEMBL::Slice argument expected.");
  }

  $constraint ||= '';
  $constraint =
    $self->_logic_name_to_constraint( $constraint, $logic_name );

  # If the logic name was invalid, undef was returned
  if ( !defined($constraint) ) { return [] }

  my $key;
  my $cache;

  # Will only use feature_cache if hasn't been no_cache attribute set
  if (
    !( defined( $self->db()->no_cache() ) && $self->db()->no_cache() ) )
  {

    #strain test and add to constraint if so to stop caching.
    if ( $slice->isa('Bio::EnsEMBL::StrainSlice') ) {
      my $string =
        $self->dbc()->db_handle()->quote( $slice->strain_name() );

      if ( $constraint ne "" ) {
        $constraint .= " AND $string = $string ";
      } else {
        $constraint .= " $string = $string ";
      }
    }

    # Check the cache and return the cached results if we have already
    # done this query.  The cache key is the made up from the slice
    # name, the constraint, and the bound parameters (if there are any).
    $key = uc( join( ':', $slice->name(), $constraint ) );

    my $bind_params = $self->bind_param_generic_fetch();

    if ( defined($bind_params) ) {
      $key .= ':'
        . join( ':', map { $_->[0] . '/' . $_->[1] } @{$bind_params} );
    }

    $cache = $self->_slice_feature_cache();
    if ( exists( $cache->{$key} ) ) {
      # Clear the bound parameters and return the cached data.
      $self->{'_bind_param_generic_fetch'} = ();
      return $cache->{$key};
    }
  } ## end if ( !( defined( $self...)))

  my $sa = $slice->adaptor();

  # Hap/PAR support: retrieve normalized 'non-symlinked' slices.
  my @proj = @{ $sa->fetch_normalized_slice_projection($slice) };


 
  if ( !@proj ) {
    throw( 'Could not retrieve normalized Slices. '
         . 'Database contains incorrect assembly_exception information.'
    );
  }

  # Want to get features on the FULL original slice as well as any
  # symlinked slices.

  # Filter out partial slices from projection that are on same
  # seq_region as original slice.

  my $sr_id = $slice->get_seq_region_id();

  @proj = grep { $_->to_Slice->get_seq_region_id() != $sr_id } @proj;

  my $segment = bless( [ 1, $slice->length(), $slice ],
                       'Bio::EnsEMBL::ProjectionSegment' );
  push( @proj, $segment );

  # construct list of Hap/PAR boundaries for entire seq region
  my @bounds;

  my $ent_slice = $sa->fetch_by_seq_region_id($sr_id);
  if ( $slice->strand() == -1 ) {
    $ent_slice = $ent_slice->invert();
  }

  my @ent_proj =
    @{ $sa->fetch_normalized_slice_projection($ent_slice) };
  shift(@ent_proj);    # skip first

  @bounds = map { $_->from_start() - $slice->start() + 1 } @ent_proj;


  # fetch features for the primary slice AND all symlinked slices
  foreach my $seg (@proj) {


    my $offset    = $seg->from_start();
    my $seg_slice = $seg->to_Slice();
    my $features =
      $self->_slice_fetch( $seg_slice, $constraint );

    # If this was a symlinked slice offset the feature coordinates as
    # needed.
    if ( $seg_slice->name() ne $slice->name() ) {

    FEATURE:
      foreach my $f ( @{$features} ) {
        if ( $offset != 1 ) {
          $f->{'start'} += $offset - 1;
          $f->{'end'}   += $offset - 1;
        }

        # discard boundary crossing features from symlinked regions
        foreach my $bound (@bounds) {
          if ( $f->{'start'} < $bound && $f->{'end'} >= $bound ) {
            next FEATURE;
          }
        }

        $f->{'slice'} = $slice;
        push( @result, $f );
      }
    } else {
      push( @result, @{$features} );
    }
  } ## end foreach my $seg (@proj)

  # Will only use feature_cache when set attribute no_cache in DBAdaptor
  if ( defined($key) ) {
    $cache->{$key} = \@result;
  }

  return \@result;
} ## end sub fetch_all_by_Slice_constraint

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_by_transcript_supporting_evidence ( )

  Arg [1]    : String $hit_name
               Name of supporting feature
  Arg [2]    : String $feature_type 
               one of "dna_align_feature" or "protein_align_feature"
  Arg [3]    : (optional) Bio::Ensembl::Analysis
  Example    : $genes = $gene_adaptor->fetch_all_by_transcript_supporting_evidence('XYZ', 'dna_align_feature');
  Description: Gets all the genes with transcripts with evidence for a
               specified hit on a particular type of feature. Optionally filter
               by analysis.
  Returntype : Listref of Bio::EnsEMBL::Gene.
  Exceptions : If feature_type is not of correct type.
  Caller     : general
  Status     : Stable

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_all_versions_by_stable_id ( )

  Arg [1]     : String $stable_id 
                The stable ID of the gene to retrieve
  Example     : $gene = $gene_adaptor->fetch_all_versions_by_stable_id
                  ('ENSG00000148944');
  Description : Similar to fetch_by_stable_id, but retrieves all versions of a
                gene stored in the database.
  Returntype  : listref of Bio::EnsEMBL::Gene
  Exceptions  : if we cant get the gene in given coord system
  Caller      : general
  Status      : At Risk

Code:

click to view

public Bio::EnsEMBL::Feature Bio::EnsEMBL::DBSQL::BaseAdaptor::fetch_by_dbID ( ) [inherited]

  Arg [1]    : int $id
               The unique database identifier for the feature to be obtained
  Example    : $feat = $adaptor->fetch_by_dbID(1234));
               $feat = $feat->transform('contig');
  Description: Returns the feature created from the database defined by the
               the id $id.  The feature will be returned in its native
               coordinate system.  That is, the coordinate system in which it
               is stored in the database.  In order to convert it to a
               particular coordinate system use the transfer() or transform()
               method.  If the feature is not found in the database then
               undef is returned instead
  Returntype : Bio::EnsEMBL::Feature or undef
  Exceptions : thrown if $id arg is not provided
               does not exist
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_display_label ( )

  Arg [1]    : String $label - display label of gene to fetch
  Example    : my $gene = $geneAdaptor->fetch_by_display_label("BRCA2");
  Description: Returns the gene which has the given display label or undef if
               there is none. If there are more than 1, only the first is
               reported.
  Returntype : Bio::EnsEMBL::Gene
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_exon_stable_id ( )

  Arg [1]    : String $id
               The stable id of an exon of the gene to retrieve
  Example    : $gene = $gene_adptr->fetch_by_exon_stable_id('ENSE00000148944');
  Description: Retrieves a gene object from the database via an exon stable id.
               The gene will be retrieved in its native coordinate system (i.e.
               in the coordinate system it is stored in the database). It may
               be converted to a different coordinate system through a call to
               transform() or transfer(). If the gene or exon is not found
               undef is returned instead.
  Returntype : Bio::EnsEMBL::Gene or undef
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_maximum_DBLink ( )

Description:

Deprecated:

use fetch_all_by_external_name instead

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_Peptide_id ( )

  Description:
Deprecated:
, use fetch_by_translation_stable_id()

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_stable_id ( )

  Arg [1]    : String $id 
               The stable ID of the gene to retrieve
  Example    : $gene = $gene_adaptor->fetch_by_stable_id('ENSG00000148944');
  Description: Retrieves a gene object from the database via its stable id.
               The gene will be retrieved in its native coordinate system (i.e.
               in the coordinate system it is stored in the database). It may
               be converted to a different coordinate system through a call to
               transform() or transfer(). If the gene or exon is not found
               undef is returned instead.
  Returntype : Bio::EnsEMBL::Gene or undef
  Exceptions : if we cant get the gene in given coord system
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_transcript_id ( )

  Arg [1]    : Int $trans_id
               Unique database identifier for the transcript whose gene should
               be retrieved. The gene is returned in its native coord
               system (i.e. the coord_system it is stored in). If the coord
               system needs to be changed, then tranform or transfer should
               be called on the returned object. undef is returned if the
               gene or transcript is not found in the database.
  Example    : $gene = $gene_adaptor->fetch_by_transcript_id(1241);
  Description: Retrieves a gene from the database via the database identifier
               of one of its transcripts.
  Returntype : Bio::EnsEMBL::Gene
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_transcript_stable_id ( )

  Arg [1]    : string $trans_stable_id
               transcript stable ID whose gene should be retrieved
  Example    : my $gene = $gene_adaptor->fetch_by_transcript_stable_id
                 ('ENST0000234');
  Description: Retrieves a gene from the database via the stable ID of one of
               its transcripts
  Returntype : Bio::EnsEMBL::Gene
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Gene Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_by_translation_stable_id ( )

  Arg [1]    : String $translation_stable_id
               The stable id of a translation of the gene to be obtained
  Example    : my $gene = $gene_adaptor->fetch_by_translation_stable_id
                 ('ENSP00000278194');
  Description: Retrieves a gene via the stable id of one of its translations.
  Returntype : Bio::EnsEMBL::Gene
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::Utils::Iterator Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_Iterator_by_Slice ( ) [inherited]

  Arg [1]    : Bio::EnsEMBL::Slice
  Arg [2]    : Optional string: logic name of analysis
  Arg [3]    : Optional int: Chunk size to iterate over. Default is 500000
  Example    : my $slice_iter = $feature_adaptor->fetch_Iterator_by_Slice($slice);

               while(my $feature = $slice_iter->next && defined $feature){
                 #Do something here
               }

  Description: Creates an Iterator which chunks the query Slice to facilitate
               large Slice queries which would have previously run out of memory
  Returntype : Bio::EnsEMBL::Utils::Iterator
  Exceptions : None
  Caller     : general
  Status     : at risk

Code:

click to view

public Bio::EnsEMBL::Utils::Iterator Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::fetch_Iterator_by_Slice_method ( ) [inherited]

  Arg [1]    : CODE ref of Slice fetch method
  Arg [2]    : ARRAY ref of parameters for Slice fetch method
  Arg [3]    : Optional int: Slice index in parameters array
  Arg [4]    : Optional int: Slice chunk size. Default=500000
  Example    : my $slice_iter = $feature_adaptor->fetch_Iterator_by_Slice_method
                               	      ($feature_adaptor->can('fetch_all_by_Slice_Arrays'),
	                                   \@fetch_method_params,
	                                   0,#Slice idx
	                                  );

               while(my $feature = $slice_iter->next && defined $feature){
                 #Do something here
               }

  Description: Creates an Iterator which chunks the query Slice to facilitate
               large Slice queries which would have previously run out of memory
  Returntype : Bio::EnsEMBL::Utils::Iterator
  Exceptions : Throws if mandatory params not valid
  Caller     : general
  Status     : at risk

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::fetch_nearest_Gene_by_Feature ( )

  Arg [1]    : Feature object
  Example    : $genes = $gene_adaptor->fetch_nearest_Gene_by_Feature($feat);
  Description: Gets the nearest gene to the feature 
  Returntype : Listref of Bio::EnsEMBL::Gene, EMPTY list if no nearest
  Caller     : general
  Status     : UnStable

Code:

click to view

sub fetch_nearest_Gene_by_Feature{
  my $self = shift;
  my $feat = shift;

  my $stranded = shift; 
  my $stream = shift;  # 1 up stream -1 downstream
  my @genes;


  my $strand = $feat->strand;
  if(defined($stream) and !$strand){
    warn("stream specified but feature has no strand so +ve strand will be used");
    $strand = 1;
  }
  my $min_dist = 999;
  my $gene_id = 0;

  my $overlapping = $feat->get_overlapping_Genes();

  return $overlapping if(defined(@{$overlapping}[0]));

  my $seq_region_id = $feat->slice->adaptor->get_seq_region_id($feat->slice);
  my $start = ($feat->start + $feat->slice->start) -1;
  my $end   = ($feat->end   + $feat->slice->start) -1;


  my @gene_ids;
  if(!defined($stream) or $stream == 0){

    my $sql1 = "select g.gene_id, (? - g.seq_region_end)  as 'dist' from gene g where ";
    if($stranded){
      $sql1 .= "g.seq_region_strand = ".$strand." and ";
    }
    $sql1 .= "seq_region_id = ? and g.seq_region_end < ? order by dist limit 10";
    
    #
    # MAYBE set the result of prepare to be static in case lots of calls.
    #
    my $sql1_sth = $self->prepare($sql1) || die "Could not prepare $sql1";
    $sql1_sth->execute($start, $seq_region_id, $start) || die "Could not execute sql";
    $sql1_sth->bind_columns(\$gene_id, \$min_dist)     || die "Could mot bin columns";
 
    my $last_dist = 99999999999999999;
    while($sql1_sth->fetch()){
      if($min_dist <= $last_dist){
    push @gene_ids, $gene_id;
    $last_dist = $min_dist;
      }
    }   
    $sql1_sth->finish();
    


    my $sql2 = "select g.gene_id, (g.seq_region_start - ?)  as 'dist' from gene g  where ";
    if($stranded){
      $sql2 .= "g.seq_region_strand = ".$feat->strand." and ";
    }
    $sql2 .= "seq_region_id = ? and g.seq_region_start > ? order by dist limit 10";

    my $sql2_sth = $self->prepare($sql2) || die "could not prepare $sql2";
    
    my ($tmp_min_dist, $tmp_gene_id);
    $sql2_sth->execute($end, $seq_region_id, $end)             || die "Could not execute sql";
    $sql2_sth->bind_columns(\$tmp_gene_id, \$tmp_min_dist)     || die "Could mot bin columns";
    my $first =1;
    while($sql2_sth->fetch()){
      if( $tmp_min_dist <= $last_dist){
    if($first){
      $first = 0;
      if($tmp_min_dist < $last_dist){
        @gene_ids = (); #reset
      }
    }   
    push @gene_ids, $tmp_gene_id;
    $last_dist = $tmp_min_dist;
      }
    }
    $sql2_sth->finish();


  } 
  elsif(($stream*$strand) == 1){
    my $sql1 = "select g.gene_id, (? - g.seq_region_end)  as 'dist' from gene g where ";
    if($stranded){
      $sql1 .= "g.seq_region_strand = ".$strand." and ";
    }
    $sql1 .= "seq_region_id = ? and g.seq_region_end < ? order by dist limit 10";
    
    #
    # MAYBE set the result of prepare to be static in case lots of calls.
    #
    my $sql1_sth = $self->prepare($sql1) || die "Could not prepare $sql1";
    $sql1_sth->execute($start, $seq_region_id, $start) || die "Could not execute sql";
    $sql1_sth->bind_columns(\$gene_id, \$min_dist)     || die "Could mot bin columns";
    
    my $last_dist;
    my $first = 1;
    while($sql1_sth->fetch()){
      if($first){
    $first = 0;
      }
      else{
    next if ($min_dist > $last_dist);
      } 
      push @gene_ids, $gene_id;
      $last_dist = $min_dist;
    }   
    $sql1_sth->finish();
  } 
  elsif(($stream * $strand) == -1){

    my $sql2 = "select g.gene_id, (g.seq_region_start - ?)  as 'dist' from gene g  where ";
    if($stranded){
      $sql2 .= "g.seq_region_strand = ".$feat->strand." and ";
    }
    $sql2 .= "seq_region_id = ? and g.seq_region_start > ? order by dist limit 10";
    
    my $sql2_sth = $self->prepare($sql2) || die "could not prepare $sql2";
    
    my ($tmp_min_dist, $tmp_gene_id);
    $sql2_sth->execute($end, $seq_region_id, $end)             || die "Could not execute sql";
    $sql2_sth->bind_columns(\$tmp_gene_id, \$tmp_min_dist)     || die "Could mot bin columns";
    my $first =1;
    my $last_dist;
    while($sql2_sth->fetch()){
      if($first){
    $first = 0; 
      } 
      else{
    next if ($tmp_min_dist > $last_dist);
      }
      push @gene_ids, $tmp_gene_id;
      $last_dist = $tmp_min_dist;
    }
    $sql2_sth->finish();
  }
  else{
    die "Invalid stream or strand must be -1, 0 or 1\n";
  }



  foreach my $gene_id (@gene_ids){
    push @genes, $self->fetch_by_dbID($gene_id);
  }
  return \@genes;

}

public Listref Bio::EnsEMBL::DBSQL::BaseAdaptor::generic_fetch ( ) [inherited]

  Arg [1]    : (optional) string $constraint
               An SQL query constraint (i.e. part of the WHERE clause)
  Arg [2]    : (optional) Bio::EnsEMBL::AssemblyMapper $mapper
               A mapper object used to remap features
               as they are retrieved from the database
  Arg [3]    : (optional) Bio::EnsEMBL::Slice $slice
               A slice that features should be remapped to
  Example    : $fts = $a->generic_fetch('contig_id in (1234, 1235)', 'Swall');
  Description: Performs a database fetch and returns feature objects in
               contig coordinates.
  Returntype : listref of Bio::EnsEMBL::SeqFeature in contig coordinates
  Exceptions : none
  Caller     : BaseFeatureAdaptor, ProxyDnaAlignFeatureAdaptor::generic_fetch
  Status     : Stable

Code:

click to view

sub generic_fetch {
  my ($self, $constraint, $mapper, $slice) = @_;

  my @tabs = $self->_tables();

  my $extra_default_where;

  # Hack for feature types that needs to be restricted to species_id (in
  # coord_system).
  if (    $self->is_multispecies()
       && $self->isa('Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor')
       && !$self->isa('Bio::EnsEMBL::DBSQL::UnmappedObjectAdaptor') )
  {
    # We do a check to see if there is already seq_region
    # and coord_system defined to ensure we get the right
    # alias.  We then do the extra query irrespectively of
    # what has already been specified by the user.
    my %thash = map { $_->[0] => $_->[1] } @tabs;

    my $sr_alias =
      ( exists( $thash{seq_region} ) ? $thash{seq_region} : 'sr' );
    my $cs_alias =
      ( exists( $thash{coord_system} ) ? $thash{coord_system} : 'cs' );

    if ( !exists( $thash{seq_region} ) ) {
      push( @tabs, [ 'seq_region', $sr_alias ] );
    }
    if ( !exists( $thash{coord_system} ) ) {
      push( @tabs, [ 'coord_system', $cs_alias ] );
    }

    $extra_default_where = sprintf(
                      '%s.seq_region_id = %s.seq_region_id '
                        . 'AND %s.coord_system_id = %s.coord_system_id '
                        . 'AND %s.species_id = ?',
                      $tabs[0]->[1], $sr_alias, $sr_alias,
                      $cs_alias,     $cs_alias );

    $self->bind_param_generic_fetch( $self->species_id(), SQL_INTEGER );
  } ## end if ( $self->is_multispecies...)

  my $columns = join(', ', $self->_columns());

  my $db = $self->db();

  #
  # Construct a left join statement if one was defined, and remove the
  # left-joined table from the table list
  #
  my @left_join_list = $self->_left_join();
  my $left_join_prefix = '';
  my $left_join = '';
  my @tables;
  if(@left_join_list) {
    my %left_join_hash = map { $_->[0] => $_->[1] } @left_join_list;
    while(my $t = shift @tabs) {
        my $t_alias = $t->[0] . " " . $t->[1];
      if( exists $left_join_hash{ $t->[0] } || exists $left_join_hash{$t_alias}) {
        my $condition = $left_join_hash{ $t->[0] };
        $condition ||= $left_join_hash{$t_alias};
        my $syn = $t->[1];
        $left_join .=
          "\n  LEFT JOIN " . $t->[0] . " $syn ON $condition ) ";
        $left_join_prefix .= '(';
      } else {
        push @tables, $t;
      }
    }
  } else {
    @tables = @tabs;
  }

  my $straight_join = '';

  if($self->_straight_join()) {
    $straight_join = "STRAIGHT_JOIN";
  }

  #construct a nice table string like 'table1 t1, table2 t2'
  my $tablenames = join(', ', map({ join(' ', @$_) } @tables));

  my $sql =
      "SELECT $straight_join $columns\n"
    . "FROM $left_join_prefix ($tablenames) $left_join";

  my $default_where = $self->_default_where_clause();
  my $final_clause = $self->_final_clause;

  if ($extra_default_where) {
    if ($default_where) {
      $default_where .= "\n AND $extra_default_where";
    } else {
      $default_where = $extra_default_where;
    }
  }

  #append a where clause if it was defined
  if ($constraint) {
    $sql .= "\n WHERE $constraint ";
    if ($default_where) {
      $sql .= " AND\n       $default_where ";
    }
  } elsif ($default_where) {
    $sql .= "\n WHERE $default_where ";
  }

  #append additional clauses which may have been defined
  $sql .= "\n$final_clause";


  # FOR DEBUG:
  #printf(STDERR "SQL:\n%s\n", $sql);
  
  
  my $sth = $db->dbc->prepare($sql);
  my $bind_parameters = $self->bind_param_generic_fetch();
  if (defined $bind_parameters){
      #if we have bind the parameters, call the DBI to bind them
      my $i = 1;
      foreach my $param (@{$bind_parameters}){
        $sth->bind_param($i,$param->[0],$param->[1]);
        $i++;
      }
      #after binding parameters, undef for future queries
      $self->{'_bind_param_generic_fetch'} = ();
  }
  eval { $sth->execute() };
  if ($@) {
    throw("Detected an error whilst executing SQL '${sql}': $@");
  }

  my $res = $self->_objs_from_sth($sth, $mapper, $slice);
  $sth->finish();
  return $res;
}

Reimplemented in Bio::EnsEMBL::DBSQL::DataFileAdaptor.

public Bio::EnsEMBL::DBSQL::GeneAdaptor::get_description ( )

Description:

Deprecated:: , use gene->get_description

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::get_display_xref ( )

Description:

Deprecated:: use $gene->display_xref

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseAdaptor::get_dumped_data ( ) [inherited]

Undocumented method

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::get_Interpro_by_geneid ( )

  Arg [1]    : String $gene_stable_id
               The stable ID of the gene to obtain
  Example    : @i = @{
                  $gene_adaptor->get_Interpro_by_geneid(
                    $gene->stable_id() ) };
  Description: Gets interpro accession numbers by gene stable id. A hack really

we should have a much more structured system than this.
  Returntype : listref of strings (Interpro_acc:description)
  Exceptions : none 
  Caller     : domainview
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::get_seq_region_id_external ( ) [inherited]

Undocumented method

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::get_seq_region_id_internal ( ) [inherited]

Undocumented method

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::get_stable_entry_info ( )

Description:

Deprecated:: use $gene->stable_id instead

Code:

click to view

public Boolean Bio::EnsEMBL::DBSQL::BaseAdaptor::is_multispecies ( ) [inherited]

  Arg [1]    : (optional) boolean $arg
  Example    : if ($adaptor->is_multispecies()) { }
  Description: Getter/Setter for the is_multispecies boolean of
               to use for this adaptor.
  Returntype : boolean
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::is_ref ( )

Undocumented method

Code:

click to view

public Scalar Bio::EnsEMBL::DBSQL::BaseAdaptor::last_insert_id ( ) [inherited]

  Arg [1]     : (optional) $field the name of the field the inserted ID was pushed 
                into
  Arg [2]     : (optional) HashRef used to pass extra attributes through to the 
                DBD driver
  Description : Delegating method which uses DBI to extract the last inserted 
                identifier. If using MySQL we just call the DBI method 
                DBI::last_insert_id() since MySQL ignores any extra
                arguments. See DBI for more information about this 
                delegated method. 
  Example     : my $id = $self->last_insert_id('my_id'); my $other_id = $self->last_insert_id();
  Returntype  : Scalar or undef

Code:

click to view

public Listref Bio::EnsEMBL::DBSQL::GeneAdaptor::list_dbIDs ( )

  Example    : @gene_ids = @{$gene_adaptor->list_dbIDs()};
  Description: Gets an array of internal ids for all genes in the current db
  Arg[1]     : <optional> int. not 0 for the ids to be sorted by the seq_region.
  Returntype : Listref of Ints
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::DBSQL::GeneAdaptor::list_seq_region_ids ( )

Undocumented method

Code:

click to view

public Reference Bio::EnsEMBL::DBSQL::GeneAdaptor::list_stable_ids ( )

  Example    : @stable_gene_ids = @{$gene_adaptor->list_stable_ids()};
  Description: Gets an listref of stable ids for all genes in the current db
  Returntype : reference to a list of strings
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

public Bio::EnsEMBL::BaseFeatureAdaptor Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::new ( ) [inherited]

  Arg [1]    : list of args @args
               Superclass constructor arguments
  Example    : none
  Description: Constructor which warns if caching has been switched off
  Returntype : Bio::EnsEMBL::BaseFeatureAdaptor
  Exceptions : none
  Caller     : implementing subclass constructors
  Status     : Stable

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseAdaptor.

Reimplemented in Bio::EnsEMBL::DBSQL::DensityFeatureAdaptor, and Bio::EnsEMBL::DBSQL::UnmappedObjectAdaptor.

public DBI::StatementHandle Bio::EnsEMBL::DBSQL::BaseAdaptor::prepare ( ) [inherited]

  Arg [1]    : string $string
               a SQL query to be prepared by this adaptors database
  Example    : $sth = $adaptor->prepare("select yadda from blabla")
  Description: provides a DBI statement handle from the adaptor. A convenience
               function so you dont have to write $adaptor->db->prepare all the
               time
  Returntype : DBI::StatementHandle
  Exceptions : none
  Caller     : Adaptors inherited from BaseAdaptor
  Status     : Stable

Code:

click to view

Reimplemented in Bio::EnsEMBL::DBSQL::SliceAdaptor, and Bio::EnsEMBL::External::BlastAdaptor.

public void Bio::EnsEMBL::DBSQL::GeneAdaptor::remove ( )

  Arg [1]    : Bio::EnsEMBL::Gene $gene
               the gene to remove from the database
  Example    : $gene_adaptor->remove($gene);
  Description: Removes a gene completely from the database. All associated
               transcripts, exons, stable_identifiers, descriptions, etc.
               are removed as well. Use with caution!
  Returntype : none
  Exceptions : throw on incorrect arguments 
               warning if gene is not stored in this database
  Caller     : general
  Status     : Stable

Code:

click to view

Reimplemented from Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor.

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::remove_by_analysis_id ( ) [inherited]

Undocumented method

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::remove_by_feature_id ( ) [inherited]

Undocumented method

Code:

click to view

public Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::remove_by_RawContig ( ) [inherited]

Description:

Deprecated:: use remove_by_Slice instead

Code:

click to view

public void Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::remove_by_Slice ( ) [inherited]

  Arg [1]    : Bio::Ensembl::Slice $slice
  Example    : $feature_adaptor->remove_by_Slice($slice);
  Description: This removes features from the database which lie on a region
               represented by the passed in slice.  Only features which are
               fully contained by the slice are deleted; features which overlap
               the edge of the slice are not removed.
               The table the features are removed from is defined by
               the abstract method_tablename.
  Returntype : none
  Exceptions : thrown if no slice is supplied
  Caller     : general
  Status     : Stable

Code:

click to view

public Int Bio::EnsEMBL::DBSQL::BaseAdaptor::species_id ( ) [inherited]

  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

Code:

click to view

public Boolean Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor::start_equals_end ( ) [inherited]

  Arg [1]    : (optional) boolean $newval
  Example    : $bfa->start_equals_end(1);
  Description: Getter/Setter for the start_equals_end flag.  If set
               to true sub _slice_fetch will use a simplified sql to retrieve 1bp slices.
  Returntype : boolean
  Exceptions : none
  Caller     : EnsemblGenomes variation DB build
  Status     : Stable

Code:

click to view

public The Bio::EnsEMBL::DBSQL::GeneAdaptor::store ( )

  Arg [1]    : Bio::EnsEMBL::Gene $gene
               The gene to store in the database
  Arg [2]    : ignore_release in xrefs [default 1] set to 0 to use release info 
               in external database references
  Example    : $gene_adaptor->store($gene);
  Description: Stores a gene in the database.
  Returntype : the database identifier (dbID) of the newly stored gene
  Exceptions : thrown if the $gene is not a Bio::EnsEMBL::Gene or if 
               $gene does not have an analysis object
  Caller     : general
  Status     : Stable

Code:

click to view

sub store {
  my ($self, $gene, $ignore_release) = @_;

  if (!ref $gene || !$gene->isa('Bio::EnsEMBL::Gene') ) {
    throw("Must store a gene object, not a $gene");
  }
  if(!defined($ignore_release)){
    $ignore_release = 1;
  }
  my $db = $self->db();

  if ($gene->is_stored($db)) {
    return $gene->dbID();
  }

  # ensure coords are correct before storing
  $gene->recalculate_coordinates();

  my $analysis = $gene->analysis();
  throw("Genes must have an analysis object.") if(!defined($analysis));

  my $analysis_id;
  if ($analysis->is_stored($db)) {
    $analysis_id = $analysis->dbID();
  } else {
    $analysis_id = $db->get_AnalysisAdaptor->store($analysis);
  }

  my $type = $gene->biotype || "";

  # default to is_current = 1 if this attribute is not set
  my $is_current = $gene->is_current;
  $is_current = 1 unless (defined($is_current));

  my $original             = $gene;
  my $original_transcripts = $gene->get_all_Transcripts();

  my $seq_region_id;

  ( $gene, $seq_region_id ) = $self->_pre_store($gene);

  my $store_gene_sql = qq(
        INSERT INTO gene
           SET biotype = ?,
               analysis_id = ?,
               seq_region_id = ?,
               seq_region_start = ?,
               seq_region_end = ?,
               seq_region_strand = ?,
               description = ?,
               source = ?,
               status = ?,
               is_current = ?,
               canonical_transcript_id = ?,
               canonical_annotation = ?
  );

  if (defined($gene->stable_id)) {
      my $created = $self->db->dbc->from_seconds_to_date($gene->created_date());
      my $modified = $self->db->dbc->from_seconds_to_date($gene->modified_date());
      $store_gene_sql .= ", stable_id = ?, version = ?, created_date = " . $created . " , modified_date = " . $modified;

  }

  # 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 );

  # Canonical transcript ID will be updated later.
  # Set it to zero for now.
  $sth->bind_param( 11, 0, SQL_TINYINT );

  $sth->bind_param( 12, $gene->canonical_annotation(), SQL_VARCHAR );

  if ( defined($gene->stable_id) ) {

     $sth->bind_param( 13, $gene->stable_id, SQL_VARCHAR );
     my $version = ($gene->version()) ? $gene->version() : 1;
     $sth->bind_param( 14, $version, SQL_INTEGER );
  }

  $sth->execute();
  $sth->finish();

  my $gene_dbID = $sth->{'mysql_insertid'};

  # store the dbentries associated with this gene
  my $dbEntryAdaptor = $db->get_DBEntryAdaptor();

  foreach my $dbe ( @{ $gene->get_all_DBEntries } ) {
    $dbEntryAdaptor->store( $dbe, $gene_dbID, "Gene", $ignore_release );
  }

  # We allow transcripts not to share equal exons and instead have
  # copies.  For the database we still want sharing though, to have
  # easier time with stable ids. So we need to have a step to merge
  # exons together before store.
  my %exons;

  foreach my $trans ( @{$gene->get_all_Transcripts} ) {
    foreach my $e ( @{$trans->get_all_Exons} ) {
      my $key = $e->hashkey();
      if( exists $exons{ $key } ) {
        $trans->swap_exons( $e, $exons{$key} );
      } else {
        $exons{$key} = $e;
      }
    }
  }

  my $transcript_adaptor = $db->get_TranscriptAdaptor();

  my $transcripts = $gene->get_all_Transcripts();

  my $new_canonical_transcript_id;
  for ( my $i = 0; $i < @$transcripts; $i++ ) {
    my $new = $transcripts->[$i];
    my $old = $original_transcripts->[$i];

    $transcript_adaptor->store( $new, $gene_dbID, $analysis_id );

    if ( !defined($new_canonical_transcript_id)
         && $new->is_canonical() )
    {
      $new_canonical_transcript_id = $new->dbID();
    }

    # update the original transcripts since we may have made copies of
    # them by transforming the gene
    $old->dbID( $new->dbID() );
    $old->adaptor( $new->adaptor() );

    if ( $new->translation ) {
      $old->translation->dbID( $new->translation()->dbID );
      $old->translation->adaptor( $new->translation()->adaptor );
    }
  }

  if ( defined($new_canonical_transcript_id) ) {
    # Now the canonical transcript has been stored, so update the
    # canonical_transcript_id of this gene with the new dbID.
    my $sth = $self->prepare(
      q(
      UPDATE gene
      SET canonical_transcript_id = ?
      WHERE gene_id = ?)
    );

    $sth->bind_param( 1, $new_canonical_transcript_id, SQL_INTEGER );
    $sth->bind_param( 2, $gene_dbID, SQL_INTEGER );

    $sth->execute();
    $sth->finish();
  }

  # update gene to point to display xref if it is set
  if(my $display_xref = $gene->display_xref) {
    my $dxref_id;
    if($display_xref->is_stored($db)) {
      $dxref_id = $display_xref->dbID();
    } else {
      $dxref_id = $dbEntryAdaptor->exists($display_xref);
    }

    if(defined($dxref_id)) {
      my $sth = $self->prepare
        ("UPDATE gene SET display_xref_id = ? WHERE gene_id = ?");
      $sth->bind_param(1, $dxref_id, SQL_INTEGER);
      $sth->bind_param(2, $gene_dbID, SQL_INTEGER);
      $sth->execute();
      $sth->finish();
      $display_xref->dbID($dxref_id);
      $display_xref->adaptor($dbEntryAdaptor);
      $display_xref->dbID($dxref_id);
      $display_xref->adaptor($dbEntryAdaptor);
    } else {
      warning("Display_xref ".$display_xref->dbname().":".
              $display_xref->display_id() . " is not stored in database.\n".
              "Not storing relationship to this gene.");
      $display_xref->dbID(undef);
      $display_xref->adaptor(undef);
    }
  }

  # store gene attributes if there are any
  my $attr_adaptor = $db->get_AttributeAdaptor();
  $attr_adaptor->store_on_Gene($gene_dbID, $gene->get_all_Attributes);

  # store unconventional transcript associations if there are any
  my $utaa = $db->get_UnconventionalTranscriptAssociationAdaptor();
  foreach my $uta (@{$gene->get_all_unconventional_transcript_associations()}) {
    $utaa->store($uta);
  }

  # set the adaptor and dbID on the original passed in gene not the
  # transfered copy
  $original->adaptor($self);
  $original->dbID($gene_dbID);

  return $gene_dbID;
}

Reimplemented from Bio::EnsEMBL::DBSQL::BaseFeatureAdaptor.

public void Bio::EnsEMBL::DBSQL::GeneAdaptor::store_alt_alleles ( )

  Arg [1]    : reference to list of Bio::EnsEMBL::Genes $genes
  Example    : $gene_adaptor->store_alt_alleles([$gene1, $gene2, $gene3]);
  Description: This method creates a group of alternative alleles (i.e. locus)
               from a set of genes. The genes should be genes from alternate
               haplotypes which are similar. The genes must already be stored
               in this database. At least 2 genes must be in the list reference
               provided.
  Returntype : none
  Exceptions : throw on incorrect arguments
               throw on sql error (e.g. duplicate unique id)
  Caller     : general
  Status     : Stable

Code:

click to view

sub store_alt_alleles {
  my $self = shift;
  my $genes = shift;

  if(!ref($genes) eq 'ARRAY') {
    throw('List reference of Bio::EnsEMBL::Gene argument expected.');
  }

  my $num_genes = scalar(@$genes);

  if($num_genes < 2) {
    throw("At least 2 genes must be provided to construct alternate alleles.");
  }

  return if(!@$genes);
  
  #
  #insert the first gene seperately in order to get a unique identifier for
  #the set of alleles
  #
  my $gene = $genes->[0];

  if(!ref($gene) || !$gene->isa('Bio::EnsEMBL::Gene')) {
    throw('List reference of Bio::EnsEMBL::Gene argument expected.');
  }

  my $gene_id = $gene->dbID();

  if (!$gene_id) {
    throw("Genes must have dbIDs in order to construct alternate alleles.");
  }

  my $sth = $self->prepare("INSERT INTO alt_allele (gene_id) VALUES (?)");
  $sth->bind_param(1, $gene->dbID, SQL_INTEGER);
  $sth->execute();
  
  my $alt_allele_id = $sth->{'mysql_insertid'};
  $sth->finish();

  #
  # Insert all subsequent alt alleles using the alt_allele identifier
  # from the first insert
  #

  $sth = $self->prepare("INSERT INTO alt_allele (alt_allele_id, gene_id) " .
                        "VALUES (?,?)");
  
  for (my $i = 1; $i < $num_genes; $i++) {
    my $gene = $genes->[$i];

    if (!ref($gene) || !$gene->isa('Bio::EnsEMBL::Gene')) {
      throw("List reference of Bio::EnsEMBL::Gene argument expected"); 
    }
    
    $gene_id = $gene->dbID();
    
    if (!$gene_id) {
      # This is an error but we have already inserted into the database
      # delete the already inserted entries to restore the state of the
      # database
      $sth->finish();
      $sth->prepare("DELETE FROM alt_allele WHERE alt_allele_id = ?");
      $sth->bind_param(1, $alt_allele_id, SQL_INTEGER);
      $sth->execute();
      $sth->finish();
      throw('Genes must have dbIDs in order to construct alternate alleles.');
    }

    $sth->bind_param(1, $alt_allele_id, SQL_INTEGER);
    $sth->bind_param(2, $gene_id, SQL_INTEGER);
    eval {
    $sth->execute();
    };

    if ($@) {
      # an error occured, revert the db to the previous state
      $sth = $self->prepare("DELETE FROM alt_allele WHERE alt_allele_id = ?");
      $sth->bind_param(1, $alt_allele_id, SQL_INTEGER);
      $sth->execute();
      $sth->finish();
      throw("An SQL error occured inserting alternate alleles:\n$@");
    }
  }
  
  $sth->finish();

  return;
}

public void Bio::EnsEMBL::DBSQL::GeneAdaptor::update ( )

  Arg [1]    : Bio::EnsEMBL::Gene $gene
               The gene to update
  Example    : $gene_adaptor->update($gene);
  Description: Updates the type, analysis, display_xref, status, is_current and
               description of a gene in the database.
  Returntype : None
  Exceptions : thrown if the $gene is not a Bio::EnsEMBL::Gene
  Caller     : general
  Status     : Stable

Code:

click to view

The documentation for this class was generated from the following file:

Bio/EnsEMBL/DBSQL/GeneAdaptor.pm

Class Summary

Synopsis

Description

Available Methods

Method Documentation