Inheritance diagram for Bio::EnsEMBL::Upstream:

Public Member Functions
public Bio::EnsEMBL::Upstream	new ()

public Bio::EnsEMBL::Transcript	transcript ()

public Int	length ()

protected void	_flush_cache ()

public Int	upstart ()

public Int	upend ()

public Int	downstart ()

public Int	downend ()

public	transform ()

public Arrayref	derive_upstream_coords ()

public Arrayref	derive_downstream_coords ()

protected void	_derive_coords ()

protected In	_bases_to_trim ()

protected Bio::EnsEMBL::Exon	_first_coding_Exon ()

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

public Int	start ()

public Int	end ()

public Int	strand ()

public void	move ()

public Int	length ()

public Bio::EnsEMBL::Analysis	analysis ()

public Bio::EnsEMBL::Slice	slice ()

public Boolean Or Undef	equals ()

public Bio::EnsEMBL::Feature	transform ()

public Bio::EnsEMBL::Feature	transfer ()

public Listref	project_to_slice ()

public Listref	project ()

public String	seqname ()

public String	display_id ()

public String	version ()

public Bio::EnsEMBL::Slice	feature_Slice ()

public String	seq_region_name ()

public Int	seq_region_length ()

public Boolean	seq_region_strand ()

public Int	seq_region_start ()

public Int	seq_region_end ()

public String	coord_system_name ()

public String	seq ()

public Listref	get_all_alt_locations ()

public Boolean	overlaps ()

public Boolean	overlaps_local ()

public List	get_overlapping_Genes ()

public Bio::EnsEMBL::Gene	get_nearest_Gene ()

public String	feature_so_acc ()

public String	feature_so_term ()

public Hashref	summary_as_hash ()

public String	species ()

public	sub_SeqFeature ()

public	add_sub_SeqFeature ()

public	flush_sub_SeqFeature ()

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

public Instance	new_fast ()

public Int	dbID ()

public Bio::EnsEMBL::DBSQL::BaseAdaptor	adaptor ()

public Boolean	is_stored ()

public	get_all_DAS_Features ()

Detailed Description

Synopsis

use Bio::EnsEMBL::Upstream;
 
my $upstream = Bio::EnsEMBL::Upstream->new(
  -transcript => $transcript,
  -length     => 2000           # bp
);
 
# Retrieve coordinates of upstream region
my $upstream_region_start = $upstream->upstart;
my $upstream_region_end   = $upstream->upend;
 
# Retrieve coordinates in 'downstream' first intron
my $intron_region_start = $upstream->downstart;
my $intron_region_end   = $upstream->downend;
 
# Coordinates are returned in the same scheme as the input transcript.
# However, the coordinates of an upstream region can be transformed to
# any other scheme using a slice
 
$upstream->transform($slice);
 
# Coordinates can be retrieved in scheme in the same manner as the
# above.

Description

An object that determines the upstream region of a transcript.  Such a
region is non-coding and ensures that other genes or transcripts are
not present.  Ultimately, these objects can be used to looking for
promoter elements.  To this end, it is also possible to derive a region
downstream of the first exon, within the first intron and where promoter
elements sometimes are found.

Definition at line 45 of file Upstream.pm.

Member Function Documentation

◆ _bases_to_trim()

protected In Bio::EnsEMBL::Upstream::_bases_to_trim ( )

  Arg        : string $end_to_trim (either 'right_end' or 
               'left_end').
  Arg        : Bio::EnsEMBL::Slice
  Example    :

$self->_derive_coords('right_end', $slice);

  Description: Finds exons from other genes/transcripts that
               invade our upstream/downstream slice and 
               returns the number of bases that should be 
               truncated from the appropriate end of the 
               upstream/downstream region.
  Returntype : in
  Exceptions : Throws if argument is not either 'right_end' 
               or 'left_end'
  Caller     : $self->_derive_coords
  Status     : Stable

Code:

click to view

◆ _derive_coords()

protected void Bio::EnsEMBL::Upstream::_derive_coords ( )

  Arg        : string $direction (either 'up' or 'down').
  Example    :

$self->_derive_coords('up');

  Description: Determines the coordinates of either upstream 
               or downstream region.
  Returntype : none
  Exceptions : Throws if argument is not either 'up' or 'down'
  Caller     : $self->upstart, $self->upend, $self->downstart, 
               $self->downend
  Status     : Stable

Code:

click to view

sub _derive_coords {
  my ($self, $direction) = @_;
 
  # Check direction
  throw("Must specify either \'up\' of \'down\'-stream direction to derive coords.")
    unless (($direction eq 'up')||($direction eq 'down'));
 
  # Put things in easily accessible places.
  my $core_db_slice_adaptor = $self->transcript->slice->adaptor;
  my $region_length = $self->length;
 
  # Whatever coord system the gene is currently is, transform to the toplevel.
  my $transcript = $self->transcript->transform('toplevel');
 
  # Use our transformed transcript to determine the upstream region coords.
  # End should always be just before the coding start (like ATG), including 3' UTR.
  # Start is the outer limit of the region upstream (furthest from ATG).
 
  my $region_start;
  my $region_end;
 
  if ($transcript->strand == 1){
    if ($direction eq 'up'){
      $region_end = $transcript->coding_region_start - 1;
      $region_start = $region_end - $region_length;
    } elsif ($direction eq 'down'){
      $region_end = $self->_first_coding_Exon->end + 1;
      $region_start = $region_end + $region_length;
    }
  } elsif ($transcript->strand == -1) {
    if ($direction eq 'up'){
      $region_end = $transcript->coding_region_end + 1;
      $region_start = $region_end + $region_length;
 
    } elsif ($direction eq 'down'){
      $region_end = $self->_first_coding_Exon->start - 1;
      $region_start = $region_end - $region_length;
    }
  }
 
  # Trim the upstream/downstream region to remove extraneous coding sequences 
  # from other genes and/or transcripts.
    
  my ($slice_low_coord, $slice_high_coord) = sort {$a <=> $b} ($region_start, $region_end);
 
  my $region_slice 
      = $core_db_slice_adaptor->fetch_by_region($transcript->slice->coord_system->name,
                        $transcript->slice->seq_region_name, 
                        $slice_low_coord, 
                        $slice_high_coord);
 
  if ($transcript->strand == 1) {
    if ($direction eq 'up') {
      $region_start += $self->_bases_to_trim('left_end', $region_slice);
    } elsif ($direction eq 'down') {
      $region_start -= $self->_bases_to_trim('right_end', $region_slice);
    }
  } elsif ($transcript->strand == -1) {
    if ($direction eq 'up') {
      $region_start -= $self->_bases_to_trim('right_end', $region_slice);
    } elsif ($direction eq 'down') {
      $region_start += $self->_bases_to_trim('left_end', $region_slice);
    }
  }
 
  # Always return start < end
 
  ($region_start, $region_end) = sort {$a <=> $b} ($region_start, $region_end);
 
  if ($direction eq 'up') {
    $self->upstart($region_start);
    $self->upend($region_end);
  } elsif ($direction eq 'down') {
    $self->downstart($region_start);
    $self->downend($region_end);
  }
}

◆ _first_coding_Exon()

protected Bio::EnsEMBL::Exon Bio::EnsEMBL::Upstream::_first_coding_Exon ( )

  Arg        : none
  Example    :

$self->_first_coding_Exon;

  Description: Finds the first exon of our transcript that 
               contains coding bases.
  Returntype : Bio::EnsEMBL::Exon
  Exceptions : none
  Caller     : $self->_derive_coords, $self->_bases_to_trim
  Status     : Stable

Code:

click to view

◆ _flush_cache()

protected void Bio::EnsEMBL::Upstream::_flush_cache ( )

  Arg        : none
  Example    :

$self->_flush_cache;

  Description: Empties cached coordinates (called when 
           coordinate scheme or region length has changed).
  Returntype : none
  Exceptions : none
  Caller     : $self->length, $self->transform
  Status     : Stable

Code:

click to view

◆ derive_downstream_coords()

public Arrayref Bio::EnsEMBL::Upstream::derive_downstream_coords ( )

  Arg        : none
  Example    :

my ($downstart, $downend)

= $self->derive_downstream_coords;

  Description: Derives downstream coordinates (for 
               compatability with older scripts).
  Returntype : arrayref
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

◆ derive_upstream_coords()

public Arrayref Bio::EnsEMBL::Upstream::derive_upstream_coords ( )

  Arg        : none
  Example    :

my ($upstart, $upend)

= $self->derive_upstream_coords;

  Description: Derives upstream coordinates (for 
               compatability with older scripts).
  Returntype : arrayref
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

◆ downend()

public Int Bio::EnsEMBL::Upstream::downend ( )

  Arg        : none
  Example    :

$self->downend;

  Description: Returns the end coordinate of the region 
               in the first intron of the transcript.  This 
               coordinate is always furthest from the first 
               exon (irregardless of strand).
  Returntype : int
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

◆ downstart()

public Int Bio::EnsEMBL::Upstream::downstart ( )

  Arg        : none
  Example    :

$self->downstart;

  Description: Returns the start coordinate of the region 
               in the first intron of the transcript.  This 
               coordinate is always closest to the first 
               exon (irregardless of strand).
  Returntype : int
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

◆ length()

public Int Bio::EnsEMBL::Upstream::length ( )

  Arg        : (optional) int $length
  Example    :

$self->length(2000); # bp

  Description: Getter/setter for upstream region length.
  Returntype : int
  Exceptions : Throws if length is requested before it has been set.
  Caller     : $self->new, $self->_derive_coords
  Status     : Stable

Code:

click to view

◆ new()

public Bio::EnsEMBL::Upstream Bio::EnsEMBL::Upstream::new ( )

  Arg [transcript] : (optional) Bio::EnsEMBL::Transcript
  Arg [length]     : (optional) int $length
  Example    :

$upstream = Bio::EnsEMBL::Upstream->new(-transcript => $transcript,

-length => 2000);

  Description: Creates a new upstream object
  Returntype : Bio::EnsEMBL::Upstream
  Exceptions : none
  Caller     : Bio::EnsEMBL::Transcript, general
  Status     : Stable

Code:

click to view

◆ transcript()

public Bio::EnsEMBL::Transcript Bio::EnsEMBL::Upstream::transcript ( )

  Arg        : (optional) Bio::EnsEMBL::Transcript
  Example    :

$self->transcript($transcript);

  Description: Getter/setter for transcript object
  Returntype : Bio::EnsEMBL::Transcript
  Exceptions : Throws if argument is not undefined 
               or a Bio::EnsEMBL::Transcript
  Caller     : $self->new, $self->_derive_coords, 
               $self->_first_coding_Exon
  Status     : Stable

Code:

click to view

◆ transform()

public Bio::EnsEMBL::Upstream::transform ( )

  Arg        : 
  Example    :

  Description: Not yet implemented
  Returntype : 
  Exceptions : 
  Caller     : 
  Status     : At Risk

Code:

click to view

◆ upend()

public Int Bio::EnsEMBL::Upstream::upend ( )

  Arg        : none
  Example    :

$self->upend;

  Description: Returns the end coordinate of the region 
               upstream of the transcript.  This coordinate 
               always always abutts the translation 
               initiation codon, whereas upstart always 
               returns the coorindate furthest from the 
               translation initiation codon.
  Returntype : int
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

◆ upstart()

public Int Bio::EnsEMBL::Upstream::upstart ( )

  Arg        : none
  Example    :

$self->upstart;

  Description: Returns the start coordinate of the region 
               upstream of the transcript.  This coordinate 
               is always the furthest from the translation 
               initiation codon, whereas upend always abutts 
               the translation initiation codon.
  Returntype : int
  Exceptions : none
  Caller     : general
  Status     : Stable

Code:

click to view

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

ensembl/modules/Bio/EnsEMBL/Upstream.pm

Public Member Functions

Detailed Description

Synopsis

Description

Member Function Documentation

◆ _bases_to_trim()

◆ _derive_coords()

◆ _first_coding_Exon()

◆ _flush_cache()

◆ derive_downstream_coords()

◆ derive_upstream_coords()

◆ downend()

◆ downstart()

◆ length()

◆ new()

◆ transcript()

◆ transform()

◆ upend()

◆ upstart()