Inheritance diagram for Bio::EnsEMBL::Utils::VegaCuration::Transcript:

Public Member Functions
public Array	find_non_overlaps ()

public Boolean	check_remarks_and_update_names ()

public void	check_names_and_overlap ()

public Hashref	get_havana_fragmented_loci_comments ()

Public Member Functions inherited from Bio::EnsEMBL::Utils::VegaCuration::Gene
public Int	find_gaps ()

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

public Boolean	parse_common_options ()

public Boolean	parse_extra_options ()

public Array	allowed_params ()

public Array	get_common_params ()

public Array	get_loutre_params ()

public Array	get_annotrack_params ()

public void	remove_vega_params ()

public Boolean	confirm_params ()

public String	list_all_params ()

public String	create_commandline_options ()

public Boolean	check_required_params ()

public Boolean	user_proceed ()

public String	read_user_input ()

public Boolean	comma_to_list ()

public Boolean	list_or_file ()

public Scalar	param ()

public String	error ()

public Int	warnings ()

public String	serverroot ()

public DBAdaptor	get_database ()

public DBI	get_dbconnection ()

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

public Boolean	dynamic_use ()

public Hashref	get_chrlength ()

public Hashref	get_ensembl_chr_mapping ()

public Int	get_taxonomy_id ()

public String	get_species_scientific_name ()

public String	species ()

public List	sort_chromosomes ()

protected Values	_by_chr_num ()

public Hashref	split_chromosomes_by_size ()

public Boolean	is_patch ()

public Boolean	log ()

public	lock_log ()

public	unlock_log ()

public Boolean	log_warning ()

public void	log_error ()

public Boolean	log_verbose ()

public Boolean	log_stamped ()

public Filehandle	log_filehandle ()

public Filehandle	filehandle ()

public Filehandle	init_log_date ()

public Filehandle	init_log ()

public Boolean	finish_log ()

public String	date_and_mem ()

public String	date ()

public String	date_and_time ()

public	date_format ()

public String	mem ()

public A	commify ()

public Arrayref	fetch_non_hidden_slices ()

public Arrayref	get_non_hidden_slice_names ()

public Arrayref	get_wanted_chromosomes ()

public Boolean	is_haplotype ()

public Arrayref	get_unique_genes ()

public	get_attrib_values ()

public Arrayref	fix_attrib_value ()

protected Attrib_type	_get_attrib_id ()

public Array_ref	store_new_attribute ()

public Array_ref	update_attribute ()

public void	remove_duplicate_attribs ()

public	save_seq ()

public String	get_alignment ()

public	allowed_duplicate_regions ()

Detailed Description

Synopsis

Description

Definition at line 14 of file Transcript.pm.

Member Function Documentation

◆ check_names_and_overlap()

public void Bio::EnsEMBL::Utils::VegaCuration::Transcript::check_names_and_overlap ( )

   Arg[1]     : arayref of arrayrefs of duplicated names
   Arg[2]     : B::E::Gene (with potentially duplicated transcript names)
   Arg[3]     : FH (to log new duplicates)
   Example    :

$support->check_names_and_overlap($transcripts,$gene,$fh)

   Description: checks pairs of transcripts identified as having duplicate Vega names:
to see if they have identical names in loutre (shouldn't have)
distinguish between overlapping and non overlapping transcripts
   Returntype : none

Code:

click to view

◆ check_remarks_and_update_names()

public Boolean Bio::EnsEMBL::Utils::VegaCuration::Transcript::check_remarks_and_update_names ( )

   Arg[1]     : B::E::Gene (with potentially duplicated transcript names)
   Arg[2]     : counter 1 (no. of patched genes)
   Arg[3]     : counter 2 (no. of patched transcripts)
   Example    :

$support->update_names($gene,\$c1,\$c2)

   Description: - checks remarks and patches transcripts with identical names according to
                CDS and length
   Returntype : true | false (depending on whether patched or not), counter1, counter2

Code:

click to view

sub check_remarks_and_update_names {
  my $self = shift;
  my ($gene,$gene_c,$trans_c) = @_;
  my $action = ($self->param('dry_run')) ? 'Would add' : 'Added';
  my $aa  = $gene->adaptor->db->get_AttributeAdaptor;
  my $dbh = $gene->adaptor->db->dbc->db_handle;
 
  #get list of IDs that have previously been sent to annotators
  my $seen_genes = $self->get_havana_fragmented_loci_comments;
 
  my $gsi    = $gene->stable_id;
  my $gid    = $gene->dbID;
  my $g_name;
  my $study_more = 1;
  eval {
    $g_name = $gene->display_xref->display_id;
  };    
  if ($@) {
    $g_name = $gene->get_all_Attributes('name')->[0]->value;
  }
 
  #get existing gene remarks
  my $remarks = [ map {$_->value} @{$gene->get_all_Attributes('remark')} ];
 
  #shout if there is no remark to identify this as being fragmented
  if ( grep {$_ eq 'fragmented locus' } @$remarks) {
    $study_more = 0;
  }
  else {
    $self->log_warning("Gene $gsi should have a fragmented locus remark\n");
  }
 
  ##patch transcript names according to length and CDS
  $gene_c++;
 
  #separate coding and non_coding transcripts
  my $coding_trans = [];
  my $noncoding_trans = [];
  foreach my $trans ( @{$gene->get_all_Transcripts()} ) {
    if ($trans->translate) {
      push @$coding_trans, $trans;
    }
    else {
      push @$noncoding_trans, $trans;
    }
  }
 
  #sort transcripts coding > non-coding, then on length
  my $c = 0;
  $self->log("\nPatching names according to CDS and length:\n",1);
  foreach my $array_ref ($coding_trans,$noncoding_trans) {
    foreach my $trans ( sort { $b->length <=> $a->length } @$array_ref ) {
      $trans_c++;
      my $tsi = $trans->stable_id;
      my $t_name;
      eval {
    $t_name = $trans->display_xref->display_id;
      };    
      if ($@) {
    $t_name = $trans->get_all_Attributes('name')->[0]->value;
      }
      $c++;
      my $ext = sprintf("%03d", $c);
      my $new_name = $g_name.'-'.$ext;
      $self->log(sprintf("%-20s%-3s%-20s", "$t_name ", "-->", "$new_name")."\n",1);
      if (! $self->param('dry_run')) {
    
    # update transcript display xref
    $dbh->do(qq(UPDATE xref x, external_db edb
                       SET x.display_label  = "$new_name"
                     WHERE x.external_db_id = edb.external_db_id
                       AND x.dbprimary_acc  = "$tsi"
                       AND edb.db_name      = "Vega_transcript"));
      }
    }
  }
  return ($study_more,$gene_c,$trans_c);
}

◆ find_non_overlaps()

public Array Bio::EnsEMBL::Utils::VegaCuration::Transcript::find_non_overlaps ( )

   Args       : arrayref of B::E::Transcripts
   Example    :

find_non_overlaps($all_transcripts)

   Description: identifies any non-overlapping transcripts
   Returntype : array refs of stable IDs
   Exceptions : none

Code:

click to view

◆ get_havana_fragmented_loci_comments()

public Hashref Bio::EnsEMBL::Utils::VegaCuration::Transcript::get_havana_fragmented_loci_comments ( )

   Args       : none
   Example    :

my $results = $support->get_havana_fragmented_loci_comments

   Description: parses the HEREDOC containing Havana comments in this module
   Returntype : hashref

Code:

click to view

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

ensembl/modules/Bio/EnsEMBL/Utils/VegaCuration/Transcript.pm

Public Member Functions

Detailed Description

Synopsis

Description

Member Function Documentation

◆ check_names_and_overlap()

◆ check_remarks_and_update_names()

◆ find_non_overlaps()

◆ get_havana_fragmented_loci_comments()