view release on metacpan or  search on metacpan

lib/Bio/DB/GFF/Adaptor/dbi/mysqlcmap.pm  view on Meta::CPAN

       max(fstop),
       fstrand,
       feature_name as gname
  FROM fdata,cmap_feature,fattribute,fattribute_to_feature
  WHERE fattribute_to_feature.fattribute_value LIKE ?
    AND cmap_feature.gclass=?
    AND cmap_feature.feature_id=fdata.feature_id
    AND fattribute.fattribute_name='Alias'
    AND fattribute_to_feature.fattribute_id=fattribute.fattribute_id
    AND fattribute_to_feature.fid=fdata.fid
    GROUP BY fref,fstrand,feature_name
END
;

use constant GETFORCEDSEQCOORDS =><<END;
SELECT fref,
       IF(ISNULL(gclass),'Sequence',gclass),
       min(fstart),
       max(fstop),
       fstrand
  FROM fdata,cmap_feature
  WHERE cmap_feature.feature_name=?
    AND cmap_feature.gclass=?
    AND fdata.fref=?
    AND cmap_feature.feature_id=fdata.feature_id
    GROUP BY fref,fstrand
END
;

use constant FULLTEXTSEARCH => <<END;
SELECT distinct gclass,feature_name,fattribute_value,MATCH(fattribute_value) AGAINST (?) as score
  FROM cmap_feature,fattribute_to_feature,fdata
  WHERE cmap_feature.feature_id=fdata.feature_id
    AND fdata.fid=fattribute_to_feature.fid
    AND MATCH(fattribute_value) AGAINST (?)
END
;

=head1 DESCRIPTION

This adaptor implements a specific mysql database schema that is
compatible with Bio::DB::GFF.  It inherits from
Bio::DB::GFF::Adaptor::dbi, which itself inherits from Bio::DB::GFF.

The schema uses several tables:

=over 4

=item fdata

This is the feature data table.  Its columns are:
-
    fid	           feature ID (integer)
    fref           reference sequence name (string)
    fstart         start position relative to reference (integer)
    fstop          stop position relative to reference (integer)
    ftypeid        feature type ID (integer)
    fscore         feature score (float); may be null
    fstrand        strand; one of "+" or "-"; may be null
    fphase         phase; one of 0, 1 or 2; may be null
    feature_id     group ID used to be 'gid' (integer)
    ftarget_start  for similarity features, the target start position (integer)
    ftarget_stop   for similarity features, the target stop position (integer)

Note that it would be desirable to normalize the reference sequence
name, since there are usually many features that share the same
reference feature.  However, in the current schema, query performance
suffers dramatically when this additional join is added.

=item cmap_feature (replaces fgroup)

This is the group table. There is one row for each group.  This is the 
shared table between CMap and GBrowse.  There are many CMap related 
columns but only a few that GBrowse uses.  

GBrowse Columns:

    feature_id     the group ID (integer)
    gclass         the class of the group (string)
    feature_name   the name of the group (string)

The group table serves multiple purposes.  As you might expect, it is
used to cluster features that logically belong together, such as the
multiple exons of the same transcript.  It is also used to assign a
name and class to a singleton feature.  Finally, the group table is
used to identify the target of a similarity hit.  This is consistent
with the way in which the group field is used in the GFF version 2
format.

The cmap_feature.feature_id field joins with the fdata.feature_id field. 

Examples:

  mysql> select * from cmap_feature where feature_name='sjj_2L52.1';
  +--------------+-------------+--------------+
  | feature_id   | gclass      | feature_name |
  +--------------+-------------+--------------+
  | 69736        | PCR_product | sjj_2L52.1   |
  +--------------+-------------+--------------+
  1 row in set (0.70 sec)

  mysql> select fref,fstart,fstop from fdata,cmap_feature 
            where gclass='PCR_product' and feature_name = 'sjj_2L52.1' 
                  and fdata.feature_id=cmap_feature.feature_id;
  +---------------+--------+-------+
  | fref          | fstart | fstop |
  +---------------+--------+-------+
  | CHROMOSOME_II |   1586 |  2355 |
  +---------------+--------+-------+
  1 row in set (0.03 sec)

=item ftype

This table contains the feature types, one per row.  Columns are:

    ftypeid      the feature type ID (integer)
    fmethod      the feature type method name (string)
    fsource      the feature type source name (string)

The ftype.ftypeid field joins with the fdata.ftypeid field.  Example:

lib/Bio/DB/GFF/Adaptor/dbi/mysqlcmap.pm  view on Meta::CPAN

  FROM cmap_feature,fattribute_to_feature,fdata
  WHERE cmap_feature.feature_id=fdata.feature_id
     AND fdata.fid=fattribute_to_feature.fid
END
;
  $query .= " AND ($search) " if ($search);

  my $sth = $self->dbh->do_query($query);
  my @results;
  while (my ($class,$name,$note) = $sth->fetchrow_array) {
     next unless $class && $name;    # sorry, ignore NULL objects
     my @matches = $note =~ /($regex)/g;
     my $relevance = 10*@matches;
     my $featname = Bio::DB::GFF::Featname->new($class=>$name);
     push @results,[$featname,$note,$relevance];
     last if $limit && @results >= $limit;
  }
  @results;
}

# sub search_notes {
#   my $self = shift;
#   my ($search_string,$limit) = @_;
#   my $query = FULLTEXTSEARCH;
#   $query .= " limit $limit" if defined $limit;
#   my $sth = $self->dbh->do_query($query,$search_string,$search_string);
#   my @results;
#   while (my ($class,$name,$note,$relevance) = $sth->fetchrow_array) {
#      next unless $class && $name;    # sorry, ignore NULL objects
#      $relevance = sprintf("%.2f",$relevance);  # trim long floats
#      my $featname = Bio::DB::GFF::Featname->new($class=>$name);
#      push @results,[$featname,$note,$relevance];
#   }
#   @results;
# }

=head2 make_features_order_by_part

 Title   : make_features_order_by_part
 Usage   : ($query,@args) = $db->make_features_order_by_part()
 Function: make the ORDER BY part of the features() query
 Returns : a SQL fragment and bind arguments, if any
 Args    : none
 Status  : protected

This method creates the part of the features query that immediately
follows the ORDER BY part of the query issued by features() and
related methods.

=cut

sub make_features_order_by_part {
  my $self = shift;
  my $options = shift || {};
  return "cmap_feature.feature_name";
}

=head2 create_cmap_viewer_link

 Title   : create_cmap_viewer_link
 Usage   : $link_str = $db->create_cmap_viewer_link(data_source=>$ds,group_id=>$gid)
 Function: 
 Returns : 
 Args    : 
 Status  : 


=cut

sub create_cmap_viewer_link {
  my $self = shift;
  my %args = @_;
  my $data_source = $args{'data_source'};
  my $gid         = $args{'group_id'};
  my $link_str    = undef;

  my $db = $self->features_db;
  my $sql_str = qq[
    select f.feature_name, 
        f.feature_type_accession feature_type_aid,
        m.accession_id as map_aid,
        ms.accession_id as map_set_aid 
    from cmap_feature f, 
        cmap_map m, 
        cmap_map_set ms 
    where f.map_id=m.map_id 
        and ms.map_set_id=m.map_set_id 
        and f.feature_id=$gid
    ];

  my $result_ref = $db->selectrow_hashref($sql_str,{ Columns => {} });
  
  if ( $result_ref ) {
    $link_str='/cgi-bin/cmap/viewer?ref_map_set_aid='
      . $result_ref->{'map_set_aid'}
      . '&ref_map_aids='
      . $result_ref->{'map_aid'}
      . '&data_source='
      . $data_source
      . '&highlight='
      .$result_ref->{'feature_name'}
      . '&feature_type_'
      .$result_ref->{'feature_type_aid'}
      . '=2';
  }

  return $link_str;
}

1;


__END__

=head1 BUGS

none ;-)

=head1 SEE ALSO

L<Bio::DB::GFF>, L<bioperl>

=head1 AUTHOR

Ben Faga E<lt>faga@cshl.orgE<gt>.

Modified from mysql.pm by:

Lincoln Stein E<lt>lstein@cshl.orgE<gt>.

Copyright (c) 2002 Cold Spring Harbor Laboratory.

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.

=cut