Inheritance diagram for Bio::EnsEMBL::DBSQL::SequenceAdaptor:

Public Member Functions
public Bio::EnsEMBL::DBSQL::SequenceAdaptor	new ()

public String	fetch_by_Slice_start_end_strand ()

public	can_access_Slice ()

protected	_fetch_by_Slice_start_end_strand_circular ()

protected	_rna_edit ()

protected	_fetch_raw_seq ()

public void	store ()

public void	remove ()

protected	_populate_seq_region_edits ()

Public Member Functions inherited from Bio::EnsEMBL::DBSQL::BaseAdaptor
public Bio::EnsEMBL::DBSQL::BaseAdaptor	new ()

public DBI::StatementHandle	prepare ()

public Bio::EnsEMBL::DBSQL::DBAdaptor	db ()

public Bio::EnsEMBL::DBSQL::DBConnection	dbc ()

public Boolean	is_multispecies ()

public Int	species_id ()

protected	_list_dbIDs ()

protected	_straight_join ()

protected	_can_straight_join ()

public Listref	bind_param_generic_fetch ()

protected	_bind_param_generic_fetch ()

public String	generate_in_constraint ()

public Listref	generic_fetch ()

public Int	generic_count ()

protected	_generate_sql ()

public Bio::EnsEMBL::Feature	fetch_by_dbID ()

protected	_uncached_fetch_by_dbID ()

public Listref	fetch_all_by_dbID_list ()

protected	_uncached_fetch_all_by_dbID_list ()

protected ArrayRef	_uncached_fetch_all_by_id_list ()

public	fetch_all ()

public Scalar	last_insert_id ()

public	insert_ignore_clause ()

protected Bio::EnsEMBL::DBSQL::Support::BaseCache	_id_cache ()

protected Boolean	_no_id_cache ()

public Boolean	ignore_cache_override ()

public Int	schema_version ()

protected	_tables ()

protected	_columns ()

protected	_default_where_clause ()

protected	_left_join ()

protected	_final_clause ()

protected	_objs_from_sth ()

protected	_build_id_cache ()

protected	_logic_name_to_constraint ()

Public Member Functions inherited from Bio::EnsEMBL::DBSQL::BaseSequenceAdaptor
public StringRef	fetch_by_Slice_start_end_strand ()

public Boolean	can_access_Slice ()

public Bio::EnsEMBL::Slice	expand_Slice ()

public Bio::EnsEMBL::DBSQL::SequenceAdaptor	new ()

protected	_init_seq_instance ()

public void	clear_cache ()

public	chunk_power ()

public	cache_size ()

public	seq_cache_max ()

protected ScalarRef	_fetch_raw_seq ()

protected ScalarRef	_fetch_seq ()

Detailed Description

Synopsis

my $sa = $registry->get_adaptor( 'Human', 'Core', 'Sequence' );
 
my $dna =
  ${ $sa->fetch_by_Slice_start_end_strand( $slice, 1, 1000, -1 ) };

Description

An adaptor for the retrieval of DNA sequence from the EnsEMBL database

Definition at line 22 of file SequenceAdaptor.pm.

Member Function Documentation

◆ _fetch_by_Slice_start_end_strand_circular()

protected Bio::EnsEMBL::DBSQL::SequenceAdaptor::_fetch_by_Slice_start_end_strand_circular ( )

Undocumented method

Code:

click to view

sub _fetch_by_Slice_start_end_strand_circular {
  my ( $self, $slice, $start, $end, $strand ) = @_;
 
  assert_ref( $slice, 'Bio::EnsEMBL::Slice' );
  
  $strand ||= 1;
  if ( !defined($start) ) {
    $start ||= 1;
  }
 
  if ( !defined($end) ) {
      $end = $slice->end() - $slice->start() + 1;
  }
 
  if ( $start > $end && $slice->is_circular() ) {
    my ($seq, $seq1, $seq2);
 
    my $midpoint = $slice->seq_region_length - $slice->start + 1;
    $seq1 = ${ $self->_fetch_by_Slice_start_end_strand_circular( $slice, 1,  $midpoint, 1 )};
    $seq2 = ${ $self->_fetch_by_Slice_start_end_strand_circular( $slice, $midpoint + 1, $slice->length(), 1 )};
 
    $seq = $slice->strand > 0 ? "$seq1$seq2" : "$seq2$seq1";
 
    reverse_comp( \$seq ) if ( $strand == -1 );
 
    return \$seq;
  }
 
  # Get a new slice that spans the exact region to retrieve dna from
  my $right_expand = $end - $slice->length();    #negative is fine
  my $left_expand  = 1 - $start;                 #negative is fine
 
  if ( $right_expand || $left_expand ) {
    $slice =
        $slice->strand > 0
      ? $slice->expand( $left_expand,  $right_expand )
      : $slice->expand( $right_expand, $left_expand );
  }
 
  # Retrieve normalized 'non-symlinked' slices.  This allows us to
  # support haplotypes and PARs.
  my $slice_adaptor = $slice->adaptor();
  my @symproj =
    @{ $slice_adaptor->fetch_normalized_slice_projection($slice) };
 
  if ( @symproj == 0 ) {
    throw(   'Could not retrieve normalized Slices. Database contains '
           . 'incorrect assembly_exception information.' );
  }
 
  # Call this method again with any slices that were 'symlinked' to by
  # this slice.
  if ( @symproj != 1 || $symproj[0]->[2] != $slice ) {
    my $seq;
    foreach my $segment (@symproj) {
      my $symlink_slice = $segment->[2];
 
      # Get sequence from each symlinked area.
      $seq .= ${
        $self->fetch_by_Slice_start_end_strand( $symlink_slice, 1,
                                                undef, 1 ) };
    }
    if ( $strand == -1 ) {
      reverse_comp( \$seq );
    }
 
    return \$seq;
  }
 
  # We need to project this slice onto the sequence coordinate system
  # even if the slice is in the same coord system, we want to trim out
  # flanking gaps (if the slice is past the edges of the seqregion).
  my $csa      = $self->db->get_CoordSystemAdaptor();
  my $seqlevel = $csa->fetch_sequence_level();
 
  my @projection =
    @{ $slice->project( $seqlevel->name(), $seqlevel->version() ) };
 
  my $seq   = '';
  my $total = 0;
  my $tmp_seq;
 
  # Fetch sequence from each of the sequence regions projected onto.
  foreach my $segment (@projection) {
    my ( $start, $end, $seq_slice ) = @{$segment};
 
    # Check for gaps between segments and pad them with Ns
    my $gap = $start - $total - 1;
    if ($gap) {
      $seq .= 'N' x $gap;
    }
 
    my $seq_region_id = $slice_adaptor->get_seq_region_id($seq_slice);
 
    $tmp_seq = ${
      $self->_fetch_seq( $seq_region_id, $seq_slice->start(),
                         $seq_slice->length() ) };
 
    # Reverse compliment on negatively oriented slices.
    if ( $seq_slice->strand == -1 ) {
      reverse_comp( \$tmp_seq );
    }
 
    $seq .= $tmp_seq;
 
    $total = $end;
  }
 
  # Check for any remaining gaps at the end.
  my $gap = $slice->length() - $total;
 
  if ($gap) {
    $seq .= 'N' x $gap;
  }
 
  # If the sequence is too short it is because we came in with a
  # seqlevel slice that was partially off of the seq_region.  Pad the
  # end with Ns to make long enough
  if ( length($seq) != $slice->length() ) {
    $seq .= 'N' x ( $slice->length() - length($seq) );
  }
 
  if ( defined( $self->{_rna_edits_cache} )
       && defined(
            $self->{_rna_edits_cache}->{ $slice->get_seq_region_id } ) )
  {
    $self->_rna_edit( $slice, \$seq );
  }
 
  return \$seq;
} ## end sub _fetch_by_Slice_start_end_strand_circular

◆ _fetch_raw_seq()

protected Bio::EnsEMBL::DBSQL::SequenceAdaptor::_fetch_raw_seq ( )

  Description : Communicates with the database to fetch back sequence

Code:

click to view

◆ _populate_seq_region_edits()

protected Bio::EnsEMBL::DBSQL::SequenceAdaptor::_populate_seq_region_edits ( )

  Description:  Query the database for any _rna_edit attributes attached to a seq region

Code:

click to view

◆ _rna_edit()

protected Bio::EnsEMBL::DBSQL::SequenceAdaptor::_rna_edit ( )

  Description : Performs within sequence region editting when 
                the underlying sequence is incorrect. Used by LRGs.

Code:

click to view

◆ can_access_Slice()

public Bio::EnsEMBL::DBSQL::SequenceAdaptor::can_access_Slice ( )

  Description : Returns 1 since we can access any Slice's data

Code:

click to view

◆ fetch_by_Slice_start_end_strand()

public String Bio::EnsEMBL::DBSQL::SequenceAdaptor::fetch_by_Slice_start_end_strand ( )

  Arg  [1]   : Bio::EnsEMBL::Slice slice
               The slice from which you want the sequence
  Arg  [2]   : (optional) int startBasePair 
               The start base pair relative to the start of the slice. Negative
               values or values greater than the length of the slice are fine.
               default = 1
  Arg  [3]   : (optional) int endBasePair
               The end base pair relative to the start of the slice. Negative
               values or values greater than the length of the slice are fine,
               but the end must be greater than or equal to the start
               count from 1
               default = the length of the slice
  Arg  [4]   : (optional) int strand 
               1, -1
               default = 1
  Example    :

$dna = $seq_adptr->fetch_by_Slice_start_end_strand($slice, 1,

1000, -1);

  Description: Retrieves from db the sequence for this slice
               uses AssemblyMapper to find the assembly
  Returntype : string 
  Exceptions : endBasePair should be less or equal to length of slice 
  Caller     : Bio::EnsEMBL::Slice::seq(), Slice::subseq() 
  Status     : Stable

Code:

click to view

sub fetch_by_Slice_start_end_strand {
   my ( $self, $slice, $start, $end, $strand ) = @_;
 
   if(!ref($slice) || !($slice->isa("Bio::EnsEMBL::Slice") or $slice->isa('Bio::EnsEMBL::LRGSlice')) ) {
     throw("Slice argument is required.");
   }
 
   $start = 1 if(!defined($start));
 
 
   if ( ( !defined($end) || $start > $end || $start < 0 || $end < 0 || $slice->start> $slice->end ) && $slice->is_circular ) {
         
       if ( !defined($end) || ($start > $end ) ) {
     return $self->_fetch_by_Slice_start_end_strand_circular( $slice, $start, $end, $strand );
       }
 
       if ( defined($end) && ($end < 0) ) {
     $end += $slice->seq_region_length;
       }
       
       if ($start < 0) {
           $start += $slice->seq_region_length;
       }
 
       if($slice->start> $slice->end) {
           return $self->_fetch_by_Slice_start_end_strand_circular( $slice, $slice->start, $slice->end, $strand );
       }
  }
        
  if ( ( !defined($end) ) && (not $slice->is_circular) ) {
           $end = $slice->end() - $slice->start() + 1;
  }
 
  if ( $start > $end ) {
      throw("Start must be less than or equal to end.");
  }
 
   $strand ||= 1;
   #get a new slice that spans the exact region to retrieve dna from
   my $right_expand  = $end - $slice->length(); #negative is fine
   my $left_expand   = 1 - $start; #negative is fine
 
   if($right_expand || $left_expand) {
     $slice = $slice->expand($left_expand, $right_expand);
   }
   
   #retrieve normalized 'non-symlinked' slices
   #this allows us to support haplotypes and PARs
   my $slice_adaptor = $slice->adaptor();
   my @symproj=@{$slice_adaptor->fetch_normalized_slice_projection($slice)};
 
   if(@symproj == 0) {
     throw('Could not retrieve normalized Slices. Database contains ' .
           'incorrect assembly_exception information.');
   }
 
   #call this method again with any slices that were 'symlinked' to by this
   #slice
   if(@symproj != 1 || $symproj[0]->[2] != $slice) {
     my $seq;
     foreach my $segment (@symproj) {
       my $symlink_slice = $segment->[2];
       #get sequence from each symlinked area
       $seq .= ${$self->fetch_by_Slice_start_end_strand($symlink_slice,
                                                        1,undef,1)};
     }
     if($strand == -1) {
       reverse_comp(\$seq);
     }
     return \$seq;
   }
 
   # we need to project this slice onto the sequence coordinate system
   # even if the slice is in the same coord system, we want to trim out
   # flanking gaps (if the slice is past the edges of the seqregion)
   my $csa = $self->db->get_CoordSystemAdaptor();
   my $seqlevel = $csa->fetch_sequence_level();
 
   my @projection=@{$slice->project($seqlevel->name(), $seqlevel->version())};
 
   my $seq = '';
   my $total = 0;
   my $tmp_seq;
 
   #fetch sequence from each of the sequence regions projected onto
   foreach my $segment (@projection) {
     my ($start, $end, $seq_slice) = @$segment;
 
     #check for gaps between segments and pad them with Ns
     my $gap = $start - $total - 1;
     if($gap) {
       $seq .= 'N' x $gap;
     }
 
     my $seq_region_id = $slice_adaptor->get_seq_region_id($seq_slice);
 
     $tmp_seq = ${$self->_fetch_seq($seq_region_id,
                                    $seq_slice->start, $seq_slice->length())};
 
     if(!defined $tmp_seq) {
         throw('No sequence found for seq_region '.$seq_region_id.':'.$seq_slice->start);
     }
 
     #reverse compliment on negatively oriented slices
     if($seq_slice->strand == -1) {
       reverse_comp(\$tmp_seq);
     }
 
     $seq .= $tmp_seq;
 
     $total = $end;
   }
 
   #check for any remaining gaps at the end
   my $gap = $slice->length - $total;
   if($gap) {
     $seq .= 'N' x $gap;
   }
 
   #if the sequence is too short it is because we came in with a seqlevel
   #slice that was partially off of the seq_region.  Pad the end with Ns
   #to make long enough
   if(length($seq) != $slice->length()) {
     $seq .= 'N' x ($slice->length() - length($seq));
   }
 
   if(defined($self->{_rna_edits_cache}) and defined($self->{_rna_edits_cache}->{$slice->get_seq_region_id})){
     $self->_rna_edit($slice,\$seq);
   }
 
   #if they asked for the negative slice strand revcomp the whole thing
   reverse_comp(\$seq) if($strand == -1);
 
   return \$seq;
}

◆ new()

public Bio::EnsEMBL::DBSQL::SequenceAdaptor Bio::EnsEMBL::DBSQL::SequenceAdaptor::new ( )

  Arg [1]    : none
  Example    :

my $sa = $db_adaptor->get_SequenceAdaptor();

  Description: Constructor. Calls superclass constructor and initialises
               internal cache structure.
  Returntype : Bio::EnsEMBL::DBSQL::SequenceAdaptor
  Exceptions : none
  Caller     : DBAdaptor::get_SequenceAdaptor
  Status     : Stable

Code:

click to view

◆ remove()

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

   
  Arg [1]    : int $seq_region_id the id of the sequence region this dna   
               is associated with.   
  Example    :

@co
de $seq_adaptor->remove(11);

  Description: removes a dna sequence for a given seq_region_id    
  Returntype : none    
  Exceptions : throw if the database delete fails    
  Caller     : Internal    
  Status     : Stable

Code:

click to view

◆ store()

public void Bio::EnsEMBL::DBSQL::SequenceAdaptor::store ( )

  Arg [1]    : int $seq_region_id the id of the sequence region this dna
               will be associated with.
  Arg [2]    : string $sequence the dna sequence to be stored 
               in the database.  Note that the sequence passed in will be
               converted to uppercase.
  Example    :

$seq_adaptor->store(11, 'ACTGGGTACCAAACAAACACAACA');

  Description: stores a dna sequence in the databases dna table and returns the
               database identifier for the new record.
  Returntype : none
  Exceptions : throw if the database insert fails
  Caller     : sequence loading scripts
  Status     : Stable

Code:

click to view

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

ensembl/modules/Bio/EnsEMBL/DBSQL/SequenceAdaptor.pm

Public Member Functions

Detailed Description

Synopsis

Description

Member Function Documentation

◆ _fetch_by_Slice_start_end_strand_circular()

◆ _fetch_raw_seq()

◆ _populate_seq_region_edits()

◆ _rna_edit()

◆ can_access_Slice()

◆ fetch_by_Slice_start_end_strand()

◆ new()

◆ remove()

◆ store()