lib/CXGN/Tools/FeatureTree.pm

   1 package CXGN::Tools::FeatureTree;
   2 use strict;
   3
   4 use XML::Twig;
   5
   6 use CXGN::Chado::Feature;
   7
   8 use CXGN::Tools::Entrez;
   9
  10
  11
  12 =head1 CXGN::Tools::FeatureTree
  13
  14 get data from the NucleotideCore site and parse the necessary fields to fill  feature objects
  15
  16
  17 =head2
  18
  19
  20 =head1 Authors
  21
  22
  23 Naama Menda (nm249@cornell.edu)
  24
  25 =cut
  26
  27 =head2 new
  28
  29  Usage: my $feature_fetch = CXGN::Tools::FeatureTree->new($GBaccession);
  30  Desc:
  31  Ret:
  32  Args: genbank accession
  33  Side Effects:
  34  Example:
  35
  36 =cut
  37
  38 #our $feature_object=undef;
  39 our @Ftree=();
  40
  41 sub new {
  42     my $class = shift;
  43     my $gb= shift;
  44
  45     my $args = {};
  46     my $self = bless $args, $class;
  47
  48     if ($gb) {
  49         @Ftree=();
  50         $self->fetch($gb);
  51     }
  52     return $self;
  53 }
  54
  55 sub fetch {
  56     my $self=shift;
  57     my $gb=shift; #GenBank accessions are stored in feature.name!
  58
  59     my $feature_xml = `wget "eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&id=$gb&rettype=xml&retmode=text"  -O -  `;
  60
  61     eval{
  62         my $twig=XML::Twig->new(
  63                             twig_roots   =>
  64                                 {
  65                                     'Textseq-id/Textseq-id_accession'   => \&name,
  66                                     'Textseq-id/Textseq-id_version'     => \&version,
  67                                     'Seq-data_iupacna/IUPACna'  => \&residues,
  68                                     'Seq-inst/Seq-inst_length'          => \&seqlen,
  69                                     'Seqdesc/Seqdesc_title'             => \&description,
  70                                     'Org-ref/Org-ref_taxname'       => \&organism_name,
  71                                     'Org-ref_db/Dbtag/Dbtag_tag/Object-id/Object-id_id'   => \&organism_taxon_id,
  72                                     'PubMedId'                     => \&pubmed_id,
  73                                     'Bioseq_id/Seq-id/Seq-id_gi'   =>\&accession,  # accession refers to genBnk GI number
  74                                     'MolInfo/MolInfo_biomol'       =>\&molecule_type,
  75                                 },
  76                                 twig_handlers =>
  77                             {
  78                                 # AbstractText     => \&abstract,
  79
  80                             },
  81                                 pretty_print => 'indented',  # output will be nicely formatted
  82                                 );
  83
  84         $twig->parse($feature_xml );
  85     };
  86     if($@) {
  87         my $message= "!!NCBI server seems to be down. Please try again later!!.\n $@";
  88         print STDERR $message;
  89         return $message;
  90     }else {
  91         print STDERR "exiting FeatureTree.pm!\n";
  92         return undef ;
  93     }
  94 }
  95
  96 sub get_feature_list {
  97     my $self=shift;
  98     return @Ftree;
  99 }
 100
 101 =head2 organism_name
 102
 103  Usage:
 104  Desc: Store the scientific organism name. This is used only for cleaner error messages.
 105  Ret:
 106  Args:
 107  Side Effects:
 108  Example:
 109
 110 =cut
 111
 112 sub organism_name {
 113     my ($twig, $elt) = @_;
 114     my $o_name=$elt->text;
 115     push @ {$Ftree[0] }, $o_name;
 116     $twig->purge();
 117 }
 118
 119
 120 =head2 organism_taxon_id
 121
 122  Usage:
 123  Desc: Store the genbank taxon_id
 124  Ret:
 125  Args:
 126  Side Effects:
 127  Example:
 128
 129 =cut
 130
 131 sub organism_taxon_id {
 132     my ($twig, $elt) = @_;
 133     my $o_taxon_id=$elt->text;
 134     push @ {$Ftree[1] }, $o_taxon_id;
 135     $twig->purge();
 136 }
 137
 138 sub name {
 139     my ($twig, $elt)= @_;
 140
 141     my $name_data=  $elt->text;
 142     push @{ $Ftree[2] }, $name_data;
 143     #print STDERR "**name (genbank accession) $name_data\n";
 144     $twig->purge;
 145 }
 146
 147
 148 sub accession {
 149     my ($twig, $elt)= @_;
 150
 151     my $gi=  $elt->text;
 152     push @{ $Ftree[3] }, $gi if (!grep{/^$gi$/ } @{ $Ftree[3] } );
 153     $twig->purge;
 154 }
 155
 156 sub pubmed_id {
 157     my ($twig, $elt)= @_;
 158     my $pubmed_id = $elt->text;
 159
 160    # my @pubmed_ids = $feature_object->get_pubmed_ids();
 161    # my @already_exists = grep(/$pubmed_id/, @pubmed_ids);
 162     #if(!@already_exists){
 163     #   $feature_object->add_pubmed_id($pubmed_id);
 164     push @ { $Ftree[4] }, $pubmed_id if (!grep{/^$pubmed_id$/ } @{ $Ftree[4] } );
 165     $twig->purge;
 166 }
 167
 168
 169 sub version {
 170     my ($twig, $elt)= @_;
 171     my $version= $elt->text;
 172     push @ { $Ftree[5] }, $version;
 173     $twig->purge;
 174 }
 175
 176
 177 sub residues {
 178     my ($twig, $elt)= @_;
 179     my $res=$elt->text;
 180     push @ { $Ftree[6] } , $res;
 181     $twig->purge;
 182 }
 183
 184
 185 sub seqlen {
 186     my ($twig, $elt)= @_;
 187     my $seqlen=$elt->text;
 188     push @ { $Ftree[7] } , $seqlen;
 189     $twig->purge;
 190 }
 191
 192 sub description {
 193     my ($twig, $elt)= @_;
 194     my $desc=$elt->text;
 195     push @ { $Ftree[8] } , $desc;
 196
 197     $twig->purge;
 198 }
 199
 200
 201 sub molecule_type {
 202     my ($twig, $elt)= @_;
 203
 204     my %mol_hash = (
 205                     'mRNA'        => 'mRNA',
 206                     '3'           => 'mRNA',
 207                     'rRNA'        => 'rRNA',
 208                     '4'        => 'rRNA',
 209                     'scRNA'       => 'scRNA',
 210                     '7'       => 'scRNA',
 211                     'genomic DNA' => 'genomic_clone',
 212                     'genomic clone' => 'genomic_clone',
 213                     '1' => 'genomic_clone',
 214                     'genomic RNA' => 'RNA',
 215                     'Pre-RNA'     => 'PRE-RNA',
 216                     'unassigned DNA' => 'DNA',
 217                     'unassigned RNA' => 'RNA',
 218                     'ss-RNA'      => 'RNA',
 219                     'RNA'         => 'RNA',
 220                     'DNA'         =>'DNA',
 221                     'snRNA'       =>'snRNA',
 222                     '8'           => 'protein'
 223                     );
 224     my $mol_text= ($elt->text);
 225     my $molecule = $mol_hash{$mol_text};
 226     if (!$molecule) {
 227         warn "no molecule type found for type $mol_text!!\n";}
 228     else {
 229         print STDERR "molecule type = $molecule\n\n";
 230         push @ { $Ftree[9] } , $molecule;
 231     }
 232     $twig->purge;
 233 }
 234
 235 #### DO NOT REMOVE
 236 return 1;
 237 ####