Xref parser mgiparser

Created by: premanand17

Requirements

• Filling out the template is required. Any pull request that does not include enough information to be reviewed in a timely manner may be closed at the maintainers' discretion;
• Review the contributing guidelines for this repository; remember in particular:
  • do not modify code without testing for regression
  • provide simple unit tests to test the changes
  • if you change the schema you must patch the test databases as well, see Updating the schema
  • the PR must not fail unit testing

Description

Updates:

Used Text:CSV for parsing the file Removed loading for mgi description from xref table Updated to get the description from the same file being read (MRK_ENSEMBL.rpt)

Use case

XrefParser for source MGI (MGI_official) for mouse (mus musculus)

Benefits

Code quality improvements, removed dependency on previous loaded mgi description from xref table

Possible Drawbacks

None

Testing

No until test. However, have tested it by running the xref_parser script and checked the _xref database for row counts.

misc-scripts/xref_mapping/XrefParser/MGIParser.pm

+
 =head1 LICENSE
 
 Copyright [1999-2015] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
@@ -23,101 +24,86 @@ use strict;
 use warnings;
 use Carp;
 use DBI;
+use Text::CSV;
 
-use base qw(XrefParser::BaseParser);
+use parent qw(XrefParser::BaseParser);
 
 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};
-  my $dbi          = $ref_arg->{dbi};
-  $dbi = $self->dbi unless defined $dbi;
-
-  if((!defined $source_id) or (!defined $species_id) or (!defined $files) ){
+  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 ) )
+  {
     croak "Need to pass source_id, species_id and files as pairs";
   }
-  $verbose |=0;
 
-  my $file = @{$files}[0];
+  my $file = shift @{$files};
 
   my $file_io = $self->get_filehandle($file);
   if ( !defined $file_io ) {
-    print STDERR "ERROR: Could not open $file\n";
-    return 1;    # 1 is an error
-  }
-  my %label;
-  my %version;
-  my %description;
-  my %accession;
-
-  my $sql = 'select source_id from source where name like "MGI" and priority_description like "descriptions"';
-  my $sth = $dbi->prepare($sql);
-  
-  $sth->execute();
-  my ($mgi_source_id);
-  $sth->bind_columns(\$mgi_source_id);
-  my @arr;
-  while($sth->fetch()){
-    push @arr, $mgi_source_id;
+    croak "Could not open $file\n";
   }
-  $sth->finish;
-  
-  $sql = "select accession, label, version,  description from xref where source_id in (".join(", ",@arr).")";
-
-  $sth = $dbi->prepare($sql);
-  $sth->execute();
-  my ($acc, $lab, $ver, $desc);
-  $sth->bind_columns(\$acc, \$lab, \$ver, \$desc);
-  while (my @row = $sth->fetchrow_array()) {
-    if(defined($desc)){
-      $accession{$lab} = $acc;
-      $label{$acc} = $lab;
-      $version{$acc} = $ver;
-      $description{$acc} = $desc;
-    }
-  }
-  $sth->finish;
 
   #synonyms
-  $sql = "insert ignore into synonym (xref_id, synonym) values (?, ?)";
-  my $add_syn_sth = $dbi->prepare($sql);    
-
-  my $syn_hash = $self->get_ext_synonyms("MGI", $dbi);
+  my $syn_hash = $self->get_ext_synonyms( "MGI", $dbi );
+
+  #Init input file
+  my $input_file = Text::CSV->new(
+    {
+      sep_char           => "\t",
+      empty_is_undef     => 1,
+      strict             => 1,
+      allow_loose_quotes => 1,
+    }
+  ) or croak "Cannot use file $file: " . Text::CSV->error_diag();
 
-  my $count = 0;
+# init headers
+# MGI:1915941	1110028C15Rik	RIKEN cDNA 1110028C15 gene	33.61	1	ENSMUSG00000026004	ENSMUST00000042389 ENSMUST00000068168 ENSMUST00000113987 ENSMUST00000129190 ENSMUST00000132960	ENSMUSP00000036975 ENSMUSP00000063843 ENSMUSP00000109620 ENSMUSP00000118603
+  $input_file->column_names( [qw(accession symbol name position chrom ens_gene_stableid)] );    #ignore last two columns EnsemblTranscriptIDs and EnsemblProteinIDs
+  my $count     = 0;
   my $syn_count = 0;
-  while ( my $line = $file_io->getline() ) {
-#MGI:1915941	1110028C15Rik	RIKEN cDNA 1110028C15 gene	33.61	1	ENSMUSG00000026004	ENSMUST00000042389 ENSMUST00000068168 ENSMUST00000113987 ENSMUST00000129190 ENSMUST00000132960	ENSMUSP00000036975 ENSMUSP00000063843 ENSMUSP00000109620 ENSMUSP00000118603
-
-    if($line =~ /(MGI:\d+).*(ENSMUSG\d+)/){
-      my $acc = $1;
-      my $ensid = $2;
-      my $xref_id = $self->add_xref({ acc        => $acc,
-				      version    => $version{$acc},
-				      label      => $label{$acc},
-				      desc       => $description{$acc},
-				      source_id  => $source_id,
-                                      dbi        => $dbi,
-				      species_id => $species_id,
-				      info_type  => "DIRECT"} );
-
-      $self->add_direct_xref( $xref_id, $ensid, "Gene", '', $dbi);
-      if(defined($syn_hash->{$acc})){
-	foreach my $syn (@{$syn_hash->{$acc}}){
-	  $add_syn_sth->execute($xref_id, $syn);
-	}
+  while ( my $data = $input_file->getline_hr($file_io) ) {
+
+    my $acc     = $data->{'accession'};
+    my $ensid   = $data->{'ens_gene_stableid'};
+    my $xref_id = $self->add_xref(
+      {
+        acc        => $acc,
+        version    => 0,
+        label      => $data->{'symbol'},
+        desc       => $data->{'name'},
+        source_id  => $source_id,
+        dbi        => $dbi,
+        species_id => $species_id,
+        info_type  => "DIRECT"
+      }
+    );
+
+    $self->add_direct_xref( $xref_id, $ensid, "Gene", undef, $dbi );
+    if ( defined( $syn_hash->{$acc} ) ) {
+      foreach my $syn ( @{ $syn_hash->{$acc} } ) {
+        $self->add_to_syn( $acc, $source_id, $syn, $species_id, $dbi );
+        $syn_count++;
       }
-      $count++;
-    }
-    else{
-      print STDERR "PROBLEM: $line";
     }
+    $count++;
+
+  }
+  $input_file->eof
+    or croak "Error parsing file $file: " . $input_file->error_diag();
+  $file_io->close();
 
+  if ($verbose) {
+    print "$count direct MGI xrefs added\n";
+    print $syn_count. " synonyms added\n";
   }
-  print "$count direct MGI xrefs added\n";
   return 0;
 
 }