lib/CXGN/Bulk/BACEndRaw.pm

   1 # bulk BAC End Raw download script for SGN database
   2 # Lukas Mueller, August 12, 2003
   3
   4 # This bulk download option handles the query
   5 # Of BAC Ends of type Raw.
   6 # Many of its methods are in the Bulk object.
   7
   8 # Modified July 15, 2005
   9 # Modified more August 11, 2005
  10 # Summer Intern Caroline N. Nyenke
  11
  12 # Modified July 7, 2006
  13 # Summer Intern Emily Hart
  14
  15 # Modified July 3rd, 2007
  16 # Alexander Naydich and Matthew Crumb
  17
  18 =head1 NAME
  19
  20   /CXGN/Bulk/BACEndRaw.pm
  21   (A subclass of Bulk)
  22
  23 =head1 DESCRIPTION
  24
  25   This perl script is used on the bulk download page. The script collects
  26   identifiers submitted by the user and returns information based on the
  27   BAC End Raw Ids entered. It then determines the information the user is
  28   searching for (Bac Id, Clone Type, Orgonism Name, Accession Name,
  29   Library Name, Estimated Length, Genbank Accession, Bac End Sequence,
  30   and Qual Value Sequence) and preforms the appropriate querying of the
  31   database. The results of the database query are formated and presented
  32   to the user on a separate page. Options of viewing or downloading
  33   in text or fasta are available.
  34
  35 =cut
  36
  37 use strict;
  38 use warnings;
  39 use CXGN::Bulk;
  40 use CXGN::DB::DBICFactory;
  41 use CXGN::Genomic::CloneNameParser;
  42 use CXGN::Genomic::Chromat;
  43 use CXGN::Genomic::GSS;
  44
  45 package CXGN::Bulk::BACEndRaw;
  46 use base "CXGN::Bulk";
  47
  48 sub new
  49 {
  50     my $class = shift;
  51     my $self = $class->SUPER::new(@_);
  52     return $self;
  53 }
  54
  55 =head2 process_parameters
  56
  57   Desc:
  58   Args: none
  59   Ret : 1 if the parameters were OK, 0 if not
  60
  61   Modifies some of the parameters received set in get_parameters. Preparing
  62   data for the database query.
  63
  64 =cut
  65
  66 sub process_parameters
  67 {
  68     my $self = shift;
  69
  70     # @output_list defines the identity on order of all fields that can be output
  71
  72     my @output_list = ('bac_id', 'clone_type', 'org_name',
  73                                 'accession_name', 'library_name', 'estimated_length',
  74                                 'genbank_accession', 'overgo_matches',
  75                                 'bac_end_sequence', 'qual_value_seq');
  76
  77     my @output_fields = ();
  78
  79     $self->debug("Type of identifier: ".($self->{idType})."");
  80
  81     # @output_fields is the sub-set of fields that will actually be output.
  82     for my $o (@output_list)
  83     {
  84         if (my $value = $self->{$o})
  85         {
  86             if ($value eq "on")
  87             {
  88             push @output_fields, $o;
  89             }
  90         }
  91     }
  92
  93     $self->{output_list} = \@output_list;
  94     $self->{output_fields} = \@output_fields;
  95
  96     my @ids = $self->check_ids();
  97     if (@ids == ()) {return 0;}
  98     $self->debug("IDs to be processed:");
  99     foreach my $i (@ids)
 100     {
 101         $self->debug($i);
 102     }
 103     my $has_valid_id = 0;
 104     foreach my $i(@ids)
 105     {
 106         if ($i ne "")
 107         {
 108             $has_valid_id = 1;
 109         }
 110     }
 111     if(!$has_valid_id)
 112     {
 113         return 0;
 114     }
 115     $self->{ids} = \@ids;
 116
 117     return 1; #params were OK if we got here
 118 }
 119
 120 =head2 process_ids
 121
 122   Desc: sub process_ids
 123   Args: default;
 124   Ret : data from database printed to a file;
 125
 126   Queries database using Persistent (see perldoc Persistent) and
 127   object oriented perl to obtain data on Bulk Objects using formatted
 128   IDs.
 129
 130 =cut
 131
 132 sub process_ids
 133 {
 134     my $self = shift;
 135     $self->{query_start_time} = time();
 136     my $dbh = $self->{db};
 137     my $chado = CXGN::DB::DBICFactory->open_schema('Bio::Chado::Schema');
 138     my @output_fields = @{$self->{output_fields}};
 139     my @notfound = ();
 140     my @return_data = ();
 141     my ($dump_fh, $notfound_fh) = $self->create_dumpfile();
 142     my @bac_output;
 143     # time counting
 144     my $current_time= time() - $self->{query_start_time};
 145     my $foundcount=0;
 146     my $notfoundcount=0;
 147     my $count=0;
 148
 149     # iterate through identifiers
 150     foreach my $id (@{$self->{ids}}) {
 151       $count++;
 152       my $bac_end_parser = CXGN::Genomic::CloneNameParser->new(); # parse name
 153       my $parsed_bac_end = $bac_end_parser->BAC_end_external_id ($id);
 154
 155       # parsed clone returns undef if parsing did not succeed
 156       unless ($parsed_bac_end) {
 157         print $notfound_fh (">$id\n");
 158         next;
 159       }
 160
 161       #look up the chromat
 162       my $chromat = CXGN::Genomic::Chromat->retrieve($parsed_bac_end->{chromat_id});
 163       unless ($chromat) {
 164         print $notfound_fh (">$id\n");
 165         next;
 166       }
 167
 168       my $clone = $chromat->clone_object;
 169       my $lib = $clone->library_object;
 170       my ($gss) = CXGN::Genomic::GSS->search(chromat_id => $chromat->chromat_id,
 171                                              version    => $parsed_bac_end->{version},
 172                                             );
 173       unless($gss) {
 174         print $notfound_fh ">$id\n";
 175         next;
 176       }
 177
 178       # get organism name and accession
 179       my (undef, $oname, $cname) = $lib->accession_name();
 180
 181       # raw seq and qual value
 182       my $bacseq = $gss->seq;
 183       my $qualvalue = $gss->qual;
 184
 185
 186       print STDERR "GENBANK ACCESSION:". ref($clone->genbank_accession($chado)) ."\n";
 187 #       # check which parameters were selected
 188 #       my @use_flags = @{$self}{qw/ bac_id
 189 #                                  clone_type
 190 #                                  org_name
 191 #                                  accession_name
 192 #                                  library_name
 193 #                                  estimated_length
 194 #                                  genbank_accession
 195 #                                  overgo_matches
 196 #                                  bac_end_sequence
 197 #                                  qual_value_seq
 198 #                                  /};
 199
 200       # will be added soon
 201       my $bac_id = $chromat->clone_read_external_identifier();
 202       my $clone_type = $parsed_bac_end->{clonetype};
 203       my $library_name = $lib->name();
 204       my $estimated_length = $clone->estimated_length();
 205       my $genbank_accession = $clone->genbank_accession($chado);
 206       my $overgo = "overgo";
 207
 208       my %field_vals = ( "bac_id" => $bac_id,
 209                          "clone_type" => $clone_type,
 210                          "org_name" => $oname,
 211                          "accession_name" => $cname,
 212                          "library_name" => $library_name,
 213                          "estimated_length" => $estimated_length,
 214                          "genbank_accession" =>  $genbank_accession ,
 215                          "overgo_matches" => $overgo,
 216                          "bac_end_sequence" =>  $bacseq,
 217                          "qual_value_seq" => $qualvalue,
 218                                         );
 219       #warn 'made field vals ',join(', ',@field_vals);
 220
 221       my @data_array = ();
 222
 223       print STDERR "OUTPUT FIELDS: ". (join "\t", @output_fields)."\n\n";
 224       foreach my $selected_field (@output_fields) {
 225           print STDERR "PUSHING $selected_field = $field_vals{$selected_field}\n";
 226           push @data_array, $field_vals{$selected_field};
 227       }
 228
 229 #       my @field_vals = map { $_ || '' } ($chromat->clone_read_external_identifier,
 230 #                                        $parsed_bac_end->{clonetype},
 231 #                                        $oname,
 232 #                                        $cname,
 233 #                                        $lib->name,
 234 #                                        $clone->estimated_length,
 235 #                                        $clone->genbank_accession,
 236 #                                        $overgo,
 237 #                                        $bacseq,
 238 #                                        $qualvalue,
 239 #                                       );
 240 #       #warn 'made field vals ',join(', ',@field_vals);
 241 #       my @data_array = map { my $val = shift @field_vals;
 242 #                            $_ ? ($val) : ()
 243 #                          } @output_fields;
 244       # warn "information from query: $oname, $cname,\n";
 245
 246       # print query results to dumpfile
 247       my $linecolumns = join("\t", @data_array)."\n";
 248       print $dump_fh $linecolumns ;
 249       print STDERR "LINE: ". $linecolumns;
 250
 251
 252     }
 253     $current_time = time() - $self->{query_start_time};
 254     close($dump_fh);
 255     close($notfound_fh);
 256     $self->{foundcount}= $foundcount;
 257     $self->{notfoundcount}= $notfoundcount;
 258     $current_time = time() - $self->{query_start_time};
 259     $self->{query_time} = time() - $self->{query_start_time};
 260 }
 261
 262 1;