Bio-DB-GFF

 view release on metacpan or  search on metacpan

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

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:

  mysql> select fref,fstart,fstop,fmethod,fsource from fdata,cmap_feature,ftype 
         where gclass='PCR_product' 
               and feature_name = 'sjj_2L52.1'
               and fdata.feature_id=cmap_feature.feature_id
               and fdata.ftypeid=ftype.ftypeid;
  +---------------+--------+-------+-------------+-----------+
  | fref          | fstart | fstop | fmethod     | fsource   |
  +---------------+--------+-------+-------------+-----------+
  | CHROMOSOME_II |   1586 |  2355 | PCR_product | GenePairs |
  +---------------+--------+-------+-------------+-----------+
  1 row in set (0.08 sec)

=item fdna

This table holds the raw DNA of the reference sequences.  It has three
columns:

    fref          reference sequence name (string)
    foffset       offset of this sequence
    fdna          the DNA sequence (longblob)

To overcome problems loading large blobs, DNA is automatically
fragmented into multiple segments when loading, and the position of
each segment is stored in foffset.  The fragment size is controlled by
the -clump_size argument during initialization.

=item fattribute_to_feature

This table holds "attributes", which are tag/value pairs stuffed into
the GFF line.  The first tag/value pair is treated as the group, and
anything else is treated as an attribute (weird, huh?).

 CHR_I assembly_tag Finished     2032 2036 . + . Note "Right: cTel33B"
 CHR_I assembly_tag Polymorphism 668  668  . + . Note "A->C in cTel33B"

The columns of this table are:

    fid                 feature ID (integer)
    fattribute_id       ID of the attribute (integer)
    fattribute_value    text of the attribute (text)

The fdata.fid column joins with fattribute_to_feature.fid.

=item fattribute

This table holds the normalized names of the attributes.  Fields are:

  fattribute_id      ID of the attribute (integer)
  fattribute_name    Name of the attribute (varchar)

=back

=head2 Data Loading Methods

In addition to implementing the abstract SQL-generating methods of
Bio::DB::GFF::Adaptor::dbi, this module also implements the data
loading functionality of Bio::DB::GFF.

=cut


=head2 new

 Title   : new
 Usage   : $db = Bio::DB::GFF->new(@args)
 Function: create a new adaptor
 Returns : a Bio::DB::GFF object
 Args    : see below
 Status  : Public

The new constructor is identical to the "dbi" adaptor's new() method,
except that the prefix "dbi:mysql" is added to the database DSN identifier
automatically if it is not there already.

  Argument       Description
  --------       -----------

  -dsn           the DBI data source, e.g. 'dbi:mysql:ens0040' or "ens0040"

  -user          username for authentication

  -pass          the password for authentication

=cut

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

  UNIQUE KEY map_set_id (map_set_id,species_id,short_name,accession_id),
  KEY cmap_map_set_idx (can_be_reference_map,is_enabled,species_id,display_order,published_on,short_name)
) TYPE=MyISAM;
} # table
},


cmap_next_number => {
table=>q{
create table cmap_next_number (
  table_name varchar(40) NOT NULL default '',
  next_number int(11) NOT NULL default '0',
  PRIMARY KEY  (table_name)
) TYPE=MyISAM;
}, # table
insert=>{next_num=>q[ insert into cmap_next_number (table_name,next_number) VALUES ('cmap_feature',82);]}
},


cmap_species => {
table=>q{
create table cmap_species (
  species_id int(11) NOT NULL default '0',
  accession_id varchar(20) NOT NULL default '',
  common_name varchar(64) NOT NULL default '',
  full_name varchar(64) NOT NULL default '',
  display_order int(11) NOT NULL default '1',
  PRIMARY KEY  (species_id),
  KEY acc_id_species_id (accession_id,species_id)
) TYPE=MyISAM;
} # table
},


cmap_xref => {
table=>q{
create table cmap_xref (
  xref_id int(11) NOT NULL default '0',
  table_name varchar(30) NOT NULL default '',
  object_id int(11) default NULL,
  display_order int(11) NOT NULL default '1',
  xref_name varchar(200) NOT NULL default '',
  xref_url text NOT NULL,
  PRIMARY KEY  (xref_id),
  KEY table_name (table_name,object_id,display_order)
) TYPE=MyISAM;
} # table
},


);
  return \%schema;
}



=head2 make_classes_query

 Title   : make_classes_query
 Usage   : ($query,@args) = $db->make_classes_query
 Function: return query fragment for generating list of reference classes
 Returns : a query and args
 Args    : none
 Status  : public

=cut

sub make_classes_query {
  my $self = shift;
  return 'SELECT DISTINCT gclass FROM cmap_feature WHERE NOT ISNULL(gclass)';
}


=head2 setup_load

 Title   : setup_load
 Usage   : $db->setup_load
 Function: called before load_gff_line()
 Returns : void
 Args    : none
 Status  : protected

This method performs schema-specific initialization prior to loading a
set of GFF records.  It prepares a set of DBI statement handlers to be 
used in loading the data.

=cut

sub setup_load {
  my $self      = shift;

  my $dbh = $self->features_db;

  if ($self->lock_on_load) {
    my @tables = map { "$_ WRITE"} $self->tables;
    my $tables = join ', ',@tables;
    $dbh->do("LOCK TABLES $tables");
  }

#xx1
  my $lookup_type = $dbh->prepare_delayed('SELECT ftypeid FROM ftype WHERE fmethod=? AND fsource=?');
  my $insert_type = $dbh->prepare_delayed('INSERT INTO ftype (fmethod,fsource) VALUES (?,?)');

  my $lookup_group = $dbh->prepare_delayed('SELECT feature_id FROM cmap_feature WHERE feature_name=? AND gclass=?');
  my $insert_group = $dbh->prepare_delayed(' INSERT into cmap_feature (feature_id, accession_id,feature_name, gclass ) VALUES (?,feature_id,?,?)');
  my $aux_insert_group = $dbh->prepare_delayed(' update cmap_next_number set next_number = next_number +1 where table_name=\'cmap_feature\'');
  my $next_id_group = $dbh->prepare_delayed('select next_number from cmap_next_number where table_name=\'cmap_feature\'');

  my $lookup_attribute = $dbh->prepare_delayed('SELECT fattribute_id FROM fattribute WHERE fattribute_name=?');
  my $insert_attribute = $dbh->prepare_delayed('INSERT INTO fattribute (fattribute_name) VALUES (?)');
  my $insert_attribute_value = $dbh->prepare_delayed('INSERT INTO fattribute_to_feature (fid,fattribute_id,fattribute_value) VALUES (?,?,?)');

  my $insert_data  = $dbh->prepare_delayed(<<END);
INSERT INTO fdata (fref,fstart,fstop,fbin,ftypeid,fscore,
		   fstrand,fphase,feature_id,ftarget_start,ftarget_stop)
       VALUES(?,?,?,?,?,?,?,?,?,?,?)
END
;


  $self->{load_stuff}{sth}{lookup_ftype}     = $lookup_type;

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

# get the object ID from a named table
sub get_table_id {
  my $self   = shift;
  my $table  = shift;
  my @ids    = @_;

  # irritating warning for null id
  my $id_key;
  {
    local $^W=0;
    $id_key = join ':',@ids;
  }

  my $s   = $self->{load_stuff};
  my $sth = $s->{sth};
  my $dbh = $self->features_db;

  unless (defined($s->{$table}{$id_key})) {

    #########################################
    # retrieval of the last inserted id is now located at the adaptor and not in caching_handle
    #######################################
    if ( (my $result = $sth->{"lookup_$table"}->execute(@ids)) > 0) {
      $s->{$table}{$id_key} = ($sth->{"lookup_$table"}->fetchrow_array)[0];
    } else {
      if (defined($sth->{"next_id_$table"})){

        $sth->{"insert_$table"}->execute(3,'string1','string2');
        # Can't use auto incrementing
        $sth->{"next_id_$table"}->execute();
        $s->{$table}{$id_key} = ($sth->{"next_id_$table"}->fetchrow_array)[0];
        if ($s->{$table}{$id_key}){
            $sth->{"insert_$table"}->execute($s->{$table}{$id_key},@ids);
            $sth->{"aux_insert_$table"}->execute() if $sth->{"aux_insert_$table"};
        }
      }
      else{
          $sth->{"insert_$table"}->execute(@ids);
          $s->{$table}{$id_key} = $self->insertid($sth->{"insert_$table"}) unless $s->{$table}{$id_key};
          $sth->{"aux_insert_$table"}->execute() if $sth->{"aux_insert_$table"};
      }
    }
  }

  my $id = $s->{$table}{$id_key};
  unless (defined $id) {
    warn "No $table id for $id_key ",$dbh->errstr," Record skipped.\n";
    return;
  }
  $id;
}



#-----------------------------------

=head2 make_features_by_name_where_part

 Title   : make_features_by_name_where_part
 Usage   : $db->make_features_by_name_where_part
 Function: create the SQL fragment needed to select a feature by its group name & class
 Returns : a SQL fragment and bind arguments
 Args    : see below
 Status  : Protected

=cut

sub make_features_by_name_where_part {
  my $self = shift;
  my ($class,$name) = @_;
  if ($name =~ /\*/) {
    $name =~ tr/*/%/;
    return ("cmap_feature.gclass=? AND cmap_feature.feature_name LIKE ?",$class,$name);
  } else {
    return ("cmap_feature.gclass=? AND cmap_feature.feature_name=?",$class,$name);
  }
}

=head2 make_features_join_part

 Title   : make_features_join_part
 Usage   : $string = $db->make_features_join_part()
 Function: make join part of the features query
 Returns : a string
 Args    : none
 Status  : protected

This method creates the part of the features query that immediately
follows the WHERE keyword.

=cut

sub make_features_join_part {
  my $self = shift;
  my $options = shift || {};
  return !$options->{attributes} ? <<END1 : <<END2;
  cmap_feature.feature_id = fdata.feature_id
  AND ftype.ftypeid = fdata.ftypeid
END1
  cmap_feature.feature_id = fdata.feature_id
  AND ftype.ftypeid = fdata.ftypeid
  AND fattribute.fattribute_id=fattribute_to_feature.fattribute_id
  AND fdata.fid=fattribute_to_feature.fid
END2
}

sub getseqcoords_query {
   my $self = shift;
   return GETSEQCOORDS ;
}

sub getaliascoords_query{
  my $self = shift;
  return GETALIASCOORDS ;
}

sub getforcedseqcoords_query{
  my $self = shift;
  return GETFORCEDSEQCOORDS ;
}

sub getaliaslike_query{

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

  column 1     A Bio::DB::GFF::Featname object, suitable for passing to segment()
  column 2     The text of the note
  column 3     A relevance score.

=cut

sub search_notes {
  my $self = shift;
  my ($search_string,$limit) = @_;

  $search_string =~ tr/*?//d;

  my @words  = $search_string =~ /(\w+)/g;
  my $regex  = join '|',@words;
  my @searches = map {"fattribute_value LIKE '%${_}%'"} @words;
  my $search   = join(' OR ',@searches);

  my $query = <<END;
SELECT distinct gclass,feature_name as gname,fattribute_value
  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_'



( run in 0.584 second using v1.01-cache-2.11-cpan-364913b4093 )