Public Member Functions
public Bio::EnsEMBL::IdMapping::Cache	new ()

public List	build_cache_by_slice ()

public List	build_cache_all ()

public Int	build_cache_from_genes ()

public Listref	filter_biotypes ()

public Bio::EnsEMBL::IdMapping::TinyFeature	add ()

public Listref	add_list ()

public	get_by_key ()

public	get_by_name ()

public	get_count_by_name ()

public	find_common_coord_systems ()

public	seq_regions_compatible ()

public	check_db_connection ()

public	check_db_read_permissions ()

public	check_db_write_permissions ()

public	do_upload ()

public	get_db_privs ()

public	check_empty_tables ()

public	check_sequence ()

public	check_meta_entries ()

public	fetch_value_from_db ()

public	get_DBAdaptor ()

public	get_production_DBAdaptor ()

public	cache_file_exists ()

public	cache_file ()

public	instance_file ()

public	dump_path ()

public	write_all_to_file ()

public	write_to_file ()

public	write_instance_to_file ()

public	read_from_file ()

public	read_and_merge ()

public	merge ()

public	read_instance_from_file ()

public	slice_names ()

public	logger ()

public	conf ()

public	cache_method ()

public	highest_common_cs ()

public	highest_common_cs_version ()

public	add_common_cs ()

public	is_common_cs ()

Detailed Description

Description

Definition at line 18 of file Cache.pm.

Member Function Documentation

◆ add()

public Bio::EnsEMBL::IdMapping::TinyFeature Bio::EnsEMBL::IdMapping::Cache::add ( )

  Arg[1]      : String $name - a cache name (e.g. 'genes_by_id')
  Arg[2]      : String type - a cache type (e.g. "source.$slice_name")
  Arg[3]      : String $key - key of this entry (e.g. a gene dbID)
  Arg[4]      : Bio::EnsEMBL::IdMappping::TinyFeature $val - value to cache
  Example     :

$cache->add('genes_by_id',

                  'source.chromosome:NCBI36:X:1:1000000:1', '1234', $tiny_gene);
  Description : Adds a TinyFeature object to a named cache.
  Return type : Bio::EnsEMBL::IdMapping::TinyFeature
  Exceptions  : thrown on wrong or missing arguments
  Caller      : internal
  Status      : At Risk
              : under development

Code:

click to view

◆ add_common_cs()

public Bio::EnsEMBL::IdMapping::Cache::add_common_cs ( )

Undocumented method

Code:

click to view

◆ add_list()

public Listref Bio::EnsEMBL::IdMapping::Cache::add_list ( )

  Arg[1]      : String $name - a cache name (e.g. 'genes_by_id')
  Arg[2]      : String type - a cache type (e.g. "source.$slice_name")
  Arg[3]      : String $key - key of this entry (e.g. a gene dbID)
  Arg[4]      : List of Bio::EnsEMBL::IdMappping::TinyFeature @val - values
                to cache
  Example     :

$cache->add_list('transcripts_by_exon_id',

                  'source.chromosome:NCBI36:X:1:1000000:1', '1234',
                  $tiny_transcript1, $tiny_transcript2);
  Description : Adds a list of TinyFeature objects to a named cache.
  Return type : Listref of Bio::EnsEMBL::IdMapping::TinyFeature objects
  Exceptions  : thrown on wrong or missing arguments
  Caller      : internal
  Status      : At Risk
              : under development

Code:

click to view

◆ build_cache_all()

public List Bio::EnsEMBL::IdMapping::Cache::build_cache_all ( )

  Arg[1]      : String $dbtype - db type (source|target)
  Example     :

my ($num_genes, $filesize) = $cache->build_cache_all('source');

  Description : Builds a cache of genes, transcripts, translations and exons
                needed by the IdMapping application and serialises the
                resulting cache object to a file. All genes across the genome
                are processed in one go. This method should be used when
                build_cache_by_seq_region can't be used due to a large number
                of toplevel seq_regions (e.g. 2x genomes).
  Return type : list of the number of genes processed and the size of the
                serialised cache file
  Exceptions  : thrown on invalid slice name
  Caller      : general
  Status      : At Risk
              : under development

Code:

click to view

◆ build_cache_by_slice()

public List Bio::EnsEMBL::IdMapping::Cache::build_cache_by_slice ( )

  Arg[1]      : String $dbtype - db type (source|target)
  Arg[2]      : String $slice_name - the name of a slice (format as returned by
                Bio::EnsEMBL::Slice->name)
  Example     :

my ($num_genes, $filesize) = $cache->build_cache_by_slice(

                  'source', 'chromosome:NCBI36:X:1:1000000:-1');
  Description : Builds a cache of genes, transcripts, translations and exons
                needed by the IdMapping application and serialises the resulting
                cache object to a file, one slice at a time.
  Return type : list of the number of genes processed and the size of the
                serialised cache file
  Exceptions  : thrown on invalid slice name
  Caller      : general
  Status      : At Risk
              : under development

Code:

click to view

◆ build_cache_from_genes()

public Int Bio::EnsEMBL::IdMapping::Cache::build_cache_from_genes ( )

  Arg[1]      : String $type - cache type
  Arg[2]      : Listref of Bio::EnsEMBL::Genes $genes - genes to build cache
                from
  Arg[3]      : Boolean $need_project - indicate if we need to project exons to
                common coordinate system
  Example     :

$cache->build_cache_from_genes(

                  'source.chromosome:NCBI36:X:1:100000:1', @genes);
  Description : Builds the cache by fetching transcripts, translations and exons
                for a list of genes from the database, and creating lightweight
                Bio::EnsEMBL::IdMapping::TinyFeature objects containing only the
                data needed by the IdMapping application. These objects are
                attached to a name cache in this cache object. Exons only need
                to be projected to a commond coordinate system if their native
                coordinate system isn't common to source and target assembly
                itself.
  Return type : int - number of genes after filtering
  Exceptions  : thrown on wrong or missing arguments
  Caller      : internal
  Status      : At Risk
              : under development

Code:

click to view

sub build_cache_from_genes {
  my $self         = shift;
  my $type         = shift;
  my $genes        = shift;
  my $need_project = shift;
 
  throw("You must provide a type.") unless $type;
  throw("You must provide a listref of genes.")
    unless ( ref($genes) eq 'ARRAY' );
 
  # biotype filter
  if ( $self->conf()->param('biotypes') ||
       $self->conf()->param('biotypes_include') ||
       $self->conf()->param('biotypes_exclude') )
  {
    $genes = $self->filter_biotypes($genes);
  }
  my $num_genes = scalar(@$genes);
 
  # initialise cache for the given type.
  $self->{'cache'}->{$type} = {};
 
  #my $i = 0;
  #my $num_genes = scalar(@$genes);
  #my $progress_id = $self->logger->init_progress($num_genes);
 
 # loop over genes sorted by gene location.
 # the sort will hopefully improve assembly mapper cache performance and
 # therefore speed up exon sequence retrieval
  foreach my $gene ( sort { $a->start <=> $b->start } @$genes ) {
    #$self->logger->log_progressbar($progress_id, ++$i, 2);
    #$self->logger->log_progress($num_genes, ++$i, 20, 3, 1);
 
    if ( $need_project eq 'CHECK' ) {
      # find out whether native coord_system is a common coord_system.
      # if so, you don't need to project.
      # also don't project if no common coord_system present
      if ( $self->highest_common_cs ) {
        my $csid = join( ':',
                         $gene->slice->coord_system_name,
                         $gene->slice->coord_system->version );
        if ( $self->is_common_cs($csid) ) {
          $need_project = 0;
        }
      }
      else {
        $need_project = 0;
      }
    }
 
    # create lightweigt gene
    my $lgene =
      Bio::EnsEMBL::IdMapping::TinyGene->new_fast( [
                          $gene->dbID,          $gene->stable_id,
                          $gene->version,       $gene->created_date,
                          $gene->modified_date, $gene->start,
                          $gene->end,           $gene->strand,
                          $gene->slice->seq_region_name, $gene->biotype,
                          $gene->analysis->logic_name,
                          ] );
 
    # build gene caches
    $self->add( 'genes_by_id', $type, $gene->dbID, $lgene );
 
    # transcripts
    foreach my $tr ( @{ $gene->get_all_Transcripts } ) {
      my $ltr =
        Bio::EnsEMBL::IdMapping::TinyTranscript->new_fast( [
                               $tr->dbID,          $tr->stable_id,
                               $tr->version,       $tr->created_date,
                               $tr->modified_date, $tr->start,
                               $tr->end,           $tr->strand,
                               $tr->length, md5_hex( $tr->spliced_seq ),
                                ] );
 
      $ltr->biotype( $tr->biotype() );
      $ltr->seq_region_name( $tr->slice->seq_region_name() );
      $lgene->add_Transcript($ltr);
 
      # build transcript caches
      $self->add( 'transcripts_by_id',      $type, $tr->dbID, $ltr );
      $self->add( 'genes_by_transcript_id', $type, $tr->dbID, $lgene );
 
      # translation (if there is one)
      if ( my $tl = $tr->translation ) {
        my $ltl =
          Bio::EnsEMBL::IdMapping::TinyTranslation->new_fast( [
                         $tl->dbID,          $tl->stable_id,
                         $tl->version,       $tl->created_date,
                         $tl->modified_date, $tr->dbID,
                         $tr->translate->seq,
                       ] );
 
        $ltr->add_Translation($ltl);
 
        $self->add( 'translations_by_id', $type, $tl->dbID, $ltl );
 
        undef $tl;
      }
 
      # exons
      foreach my $exon ( @{ $tr->get_all_Exons } ) {
        my $lexon =
          Bio::EnsEMBL::IdMapping::TinyExon->new_fast( [
                         $exon->dbID,
                         $exon->stable_id,
                         $exon->version,
                         $exon->created_date,
                         $exon->modified_date,
                         $exon->start,
                         $exon->end,
                         $exon->strand,
                         $exon->slice->seq_region_name,
                         $exon->slice->coord_system_name,
                         $exon->slice->coord_system->version,
                         $exon->slice->subseq( $exon->start, $exon->end,
                                               $exon->strand ),
                         $exon->phase,
                         $need_project, ] );
 
        # get coordinates in common coordinate system if needed
        if ($need_project) {
          my @seg = @{
            $exon->project( $self->highest_common_cs,
                            $self->highest_common_cs_version ) };
 
          if ( scalar(@seg) == 1 ) {
            my $sl = $seg[0]->to_Slice;
            $lexon->common_start( $sl->start );
            $lexon->common_end( $sl->end );
            $lexon->common_strand( $sl->strand );
            $lexon->common_sr_name( $sl->seq_region_name );
          }
        }
 
        $ltr->add_Exon($lexon);
 
        $self->add( 'exons_by_id', $type, $exon->dbID, $lexon );
        $self->add_list( 'transcripts_by_exon_id',
                         $type, $exon->dbID, $ltr );
 
        undef $exon;
      } ## end foreach my $exon ( @{ $tr->get_all_Exons...})
 
      undef $tr;
    } ## end foreach my $tr ( @{ $gene->get_all_Transcripts...})
 
    undef $gene;
  } ## end foreach my $gene ( sort { $a...})
 
  return $num_genes;
} ## end sub build_cache_from_genes

◆ cache_file()

public Bio::EnsEMBL::IdMapping::Cache::cache_file ( )

Undocumented method

Code:

click to view

◆ cache_file_exists()

public Bio::EnsEMBL::IdMapping::Cache::cache_file_exists ( )

Undocumented method

Code:

click to view

◆ cache_method()

public Bio::EnsEMBL::IdMapping::Cache::cache_method ( )

Undocumented method

Code:

click to view

◆ check_db_connection()

public Bio::EnsEMBL::IdMapping::Cache::check_db_connection ( )

Undocumented method

Code:

click to view

◆ check_db_read_permissions()

public Bio::EnsEMBL::IdMapping::Cache::check_db_read_permissions ( )

Undocumented method

Code:

click to view

◆ check_db_write_permissions()

public Bio::EnsEMBL::IdMapping::Cache::check_db_write_permissions ( )

Undocumented method

Code:

click to view

◆ check_empty_tables()

public Bio::EnsEMBL::IdMapping::Cache::check_empty_tables ( )

Undocumented method

Code:

click to view

◆ check_meta_entries()

public Bio::EnsEMBL::IdMapping::Cache::check_meta_entries ( )

Undocumented method

Code:

click to view

◆ check_sequence()

public Bio::EnsEMBL::IdMapping::Cache::check_sequence ( )

Undocumented method

Code:

click to view

◆ conf()

public Bio::EnsEMBL::IdMapping::Cache::conf ( )

Undocumented method

Code:

click to view

◆ do_upload()

public Bio::EnsEMBL::IdMapping::Cache::do_upload ( )

Undocumented method

Code:

click to view

◆ dump_path()

public Bio::EnsEMBL::IdMapping::Cache::dump_path ( )

Undocumented method

Code:

click to view

◆ fetch_value_from_db()

public Bio::EnsEMBL::IdMapping::Cache::fetch_value_from_db ( )

Undocumented method

Code:

click to view

◆ filter_biotypes()

public Listref Bio::EnsEMBL::IdMapping::Cache::filter_biotypes ( )

  Arg[1]      : Listref of Bio::EnsEMBL::Genes $genes - the genes to filter
  Example     :

my @filtered = @{ $cache->filter_biotypes(\@genes) };

  Description : Filters a list of genes by biotype.  Biotypes are
                taken from the IdMapping configuration parameter
                'biotypes_include' or 'biotypes_exclude'.

                If the configuration parameter 'biotypes_exclude' is
                defined, then rather than returning the genes whose
                biotype is listed in the configuration parameter
                'biotypes_include' the method will return the genes
                whose biotype is *not* listed in the 'biotypes_exclude'
                configuration parameter.

                It is an error to define both these configuration
                parameters.

                The old parameter 'biotypes' is equivalent to
                'biotypes_include'.

  Return type : Listref of Bio::EnsEMBL::Genes (or empty list)
  Exceptions  : none
  Caller      : internal
  Status      : At Risk
              : under development

Code:

click to view

◆ find_common_coord_systems()

public Bio::EnsEMBL::IdMapping::Cache::find_common_coord_systems ( )

Undocumented method

Code:

click to view

◆ get_by_key()

public Bio::EnsEMBL::IdMapping::Cache::get_by_key ( )

Undocumented method

Code:

click to view

◆ get_by_name()

public Bio::EnsEMBL::IdMapping::Cache::get_by_name ( )

Undocumented method

Code:

click to view

◆ get_count_by_name()

public Bio::EnsEMBL::IdMapping::Cache::get_count_by_name ( )

Undocumented method

Code:

click to view

◆ get_db_privs()

public Bio::EnsEMBL::IdMapping::Cache::get_db_privs ( )

Undocumented method

Code:

click to view

◆ get_DBAdaptor()

public Bio::EnsEMBL::IdMapping::Cache::get_DBAdaptor ( )

Undocumented method

Code:

click to view

◆ get_production_DBAdaptor()

public Bio::EnsEMBL::IdMapping::Cache::get_production_DBAdaptor ( )

Undocumented method

Code:

click to view

◆ highest_common_cs()

public Bio::EnsEMBL::IdMapping::Cache::highest_common_cs ( )

Undocumented method

Code:

click to view

◆ highest_common_cs_version()

public Bio::EnsEMBL::IdMapping::Cache::highest_common_cs_version ( )

Undocumented method

Code:

click to view

◆ instance_file()

public Bio::EnsEMBL::IdMapping::Cache::instance_file ( )

Undocumented method

Code:

click to view

◆ is_common_cs()

public Bio::EnsEMBL::IdMapping::Cache::is_common_cs ( )

Undocumented method

Code:

click to view

◆ logger()

public Bio::EnsEMBL::IdMapping::Cache::logger ( )

Undocumented method

Code:

click to view

◆ merge()

public Bio::EnsEMBL::IdMapping::Cache::merge ( )

Undocumented method

Code:

click to view

◆ new()

public Bio::EnsEMBL::IdMapping::Cache Bio::EnsEMBL::IdMapping::Cache::new ( )

  Arg [LOGGER]: Bio::EnsEMBL::Utils::Logger $logger - a logger object
  Arg [CONF]  : Bio::EnsEMBL::Utils::ConfParser $conf - a configuration object
  Example     :

my $cache = Bio::EnsEMBL::IdMapping::Cache->new(
                 -LOGGER => $logger,
                 -CONF   => $conf,
               );

  Description : constructor
  Return type : Bio::EnsEMBL::IdMapping::Cache object
  Exceptions  : thrown on wrong or missing arguments
  Caller      : general
  Status      : At Risk
              : under development

Code:

click to view

◆ read_and_merge()

public Bio::EnsEMBL::IdMapping::Cache::read_and_merge ( )

Undocumented method

Code:

click to view

◆ read_from_file()

public Bio::EnsEMBL::IdMapping::Cache::read_from_file ( )

Undocumented method

Code:

click to view

◆ read_instance_from_file()

public Bio::EnsEMBL::IdMapping::Cache::read_instance_from_file ( )

Undocumented method

Code:

click to view

◆ seq_regions_compatible()

public Bio::EnsEMBL::IdMapping::Cache::seq_regions_compatible ( )

Undocumented method

Code:

click to view

◆ slice_names()

public Bio::EnsEMBL::IdMapping::Cache::slice_names ( )

Undocumented method

Code:

click to view

◆ write_all_to_file()

public Bio::EnsEMBL::IdMapping::Cache::write_all_to_file ( )

Undocumented method

Code:

click to view

◆ write_instance_to_file()

public Bio::EnsEMBL::IdMapping::Cache::write_instance_to_file ( )

Undocumented method

Code:

click to view

◆ write_to_file()

public Bio::EnsEMBL::IdMapping::Cache::write_to_file ( )

Undocumented method

Code:

click to view

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

ensembl/modules/Bio/EnsEMBL/IdMapping/Cache.pm

Public Member Functions

Detailed Description

Description

Member Function Documentation

◆ add()

◆ add_common_cs()

◆ add_list()

◆ build_cache_all()

◆ build_cache_by_slice()

◆ build_cache_from_genes()

◆ cache_file()

◆ cache_file_exists()

◆ cache_method()

◆ check_db_connection()

◆ check_db_read_permissions()

◆ check_db_write_permissions()

◆ check_empty_tables()

◆ check_meta_entries()

◆ check_sequence()

◆ conf()

◆ do_upload()

◆ dump_path()

◆ fetch_value_from_db()

◆ filter_biotypes()

◆ find_common_coord_systems()

◆ get_by_key()

◆ get_by_name()

◆ get_count_by_name()

◆ get_db_privs()

◆ get_DBAdaptor()

◆ get_production_DBAdaptor()

◆ highest_common_cs()

◆ highest_common_cs_version()

◆ instance_file()

◆ is_common_cs()

◆ logger()

◆ merge()

◆ new()

◆ read_and_merge()

◆ read_from_file()

◆ read_instance_from_file()

◆ seq_regions_compatible()

◆ slice_names()

◆ write_all_to_file()

◆ write_instance_to_file()

◆ write_to_file()