ensembl-hive 2.8.1

Public Member Functions
public	run ()

public Boolean	is_file_header_valid ()

Detailed Description

Description

A parser class to parse the MGI (descriptions) source. Creates 'MISC' xref using MGI accession with description and
also creates the synonyms extracted from the pipe seperated synonym_field

-species = mus_musculus
-species_id = 10090
-data_uri = http://www.informatics.jax.org/downloads/reports/MRK_List2.rpt
-file_format = TSV
-columns = [accession chromosome position start end strand label status marker marker_type feature_type synonym_field]

Synopsis

my $parser = XrefParser::MGI_Desc_Parser->new($db->dbh);
$parser->run({
  source_id  => 58,
  species_id => 10090,
  files      => ["MRK_List2.rpt"],
});

Definition at line 27 of file MGI_Desc_Parser.pm.

Member Function Documentation

◆ is_file_header_valid()

public Boolean XrefParser::MGI_Desc_Parser::is_file_header_valid ( )

  Arg [1..N] : list of column names provided by Text::CSV::header()
  Example    :

if ( ! is_file_header_valid( $csv->header( $fh ) ) {
                confess 'Bad header';
              }

  Description: Verifies if the header of a MGI_Desc file follows
               expected syntax.
  Return type: boolean
  Exceptions : none
  Caller     : internal
  Status     : Stable

Code:

click to view

◆ run()

public XrefParser::MGI_Desc_Parser::run ( )

Undocumented method

Code:

click to view

sub run {
 
  my ($self, $ref_arg) = @_;
  my $source_id  = $ref_arg->{source_id};
  my $species_id = $ref_arg->{species_id};
  my $files      = $ref_arg->{files};
  my $verbose    = $ref_arg->{verbose} // 0;
  my $dbi        = $ref_arg->{dbi} // $self->dbi;
 
  if ( ( !defined $source_id ) or
       ( !defined $species_id ) or
       ( !defined $files ) ) {
    confess 'Need to pass source_id, species_id and files as pairs';
  }
 
  my $file = @{$files}[0];
 
  my $mgi_io = $self->get_filehandle($file);
  if ( !defined $mgi_io ) {
    confess "Could not open $file\n";
  }
 
  my $input_file = Text::CSV->new({
    sep_char           => "\t",
    quote_char         => undef,
    escape_char        => undef,
    strict             => 1,
    binary             => 1
  }) or confess "Cannot use file $file: " . Text::CSV->error_diag();
 
  my $xref_count = 0;
  my $syn_count  = 0;
  my %acc_to_xref;
 
  # read and validate header
  if ( ! is_file_header_valid( $input_file->header( $mgi_io ) ) ) {
    confess "Malformed or unexpected header in MGI_Desc file '${file}'";
  }
 
  while ( my $data = $input_file->getline($mgi_io) ) {
    my $accession = $data->[0];
    my $marker = $data->[8];
 
    $acc_to_xref{$accession} = $self->add_xref({
      acc        => $accession,
      label      => $data->[6],
      desc       => $marker,
      source_id  => $source_id,
      species_id => $species_id,
      dbi        => $dbi,
      info_type  => 'MISC',
    });
    if ( $verbose && !$marker ) {
      print "$accession has no description\n";
    }
    $xref_count += 1;
 
    if ( defined $acc_to_xref{$accession} ) {
      my @synonyms;
      my $synonym_field = $data->[11];
      if ( $synonym_field ) {
        @synonyms = split qr{ [|] }msx, $synonym_field;
      }
      foreach my $syn (@synonyms) {
        $self->add_synonym( $acc_to_xref{$accession}, $syn, $dbi );
        $syn_count += 1;
      }
    }
 
  } ## end while ( my $data = $input_file...)
 
  $mgi_io->eof
    || confess "Error parsing file $file: " . $input_file->error_diag();
  $mgi_io->close();
 
  if ($verbose) {
    print "$xref_count MGI Description Xrefs added\n";
    print "$syn_count synonyms added\n";
  }
 
  return 0;    #successful
} ## end sub run

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

ensembl/misc-scripts/xref_mapping/XrefParser/MGI_Desc_Parser.pm

XrefParser::MGI_Desc_Parser::is_file_header_valid

public Boolean is_file_header_valid()

XrefParser::MGI_Desc_Parser::run

public run()

XrefParser::MGI_Desc_Parser

Definition: MGI_Desc_Parser.pm:27

XrefParser
MGI_Desc_Parser
Generated on Tue Jan 6 2026 13:32:14 for ensembl-hive by 1.8.17