scripts/taxa/bp_taxid4species.pl

   1 #!/usr/bin/perl
   2 # Author:  Jason Stajich <jason@bioperl.org>
   3 # Purpose: Retrieve the NCBI Taxa ID for organism(s)
   4
   5 # TODO: add rest of POD
   6 #
   7
   8 use LWP::UserAgent;
   9 use XML::Twig;
  10 use strict;
  11 use warnings;
  12 use Getopt::Long;
  13 use Data::Dumper;
  14 my $verbose = 0;
  15 my $plain   = 0;
  16 my $help    = 0;
  17 my $USAGE = "taxid4species: [-v] [-p] \"Genus1 species1\" \"Genus2 species2\"";
  18
  19 GetOptions('v|verbose' => \$verbose,
  20            'p|plain'   => \$plain,
  21            'h|help'    => \$help);
  22 die("$USAGE\n") if $help;
  23
  24 my $ua = new LWP::UserAgent();
  25
  26 my $urlbase = 'https://www.ncbi.nlm.nih.gov/entrez/eutils/';
  27 my $esearch = 'esearch.fcgi?db=taxonomy&usehistory=y&term=';
  28 my $esummary = 'esummary.fcgi?db=taxonomy&query_key=QUERYKEY&WebEnv=WEBENV';
  29
  30 my (@organisms) = @ARGV;
  31 die("must provide valid organism") unless @organisms;
  32 my $organismstr = join(" OR ", @organisms);
  33 $organismstr =~ s/\s/\+/g;
  34
  35 # Esearch
  36 my $response = $ua->get($urlbase . $esearch . $organismstr);
  37 my $t = XML::Twig->new();
  38 print $response->content,"\n"if($verbose);
  39 $t->parse($response->content);
  40 my $root = $t->root;
  41 my $querykey = $root->first_child('QueryKey')->text;
  42 my $webenv = $root->first_child('WebEnv')->text;
  43
  44 # Esummary
  45 $esummary =~ s/QUERYKEY/$querykey/;
  46 $esummary =~ s/WEBENV/$webenv/;
  47 $response = $ua->get($urlbase . $esummary);
  48 $t = XML::Twig->new();
  49 print $response->content,"\n"if($verbose);
  50 $t->parse($response->content);
  51 $root = $t->root;
  52
  53 # Parse XML
  54 my %taxinfo;
  55 foreach my $docsum ($root->children) {
  56     foreach my $item ($docsum->children('Item')) {
  57         if ($item->{att}{Name} eq 'ScientificName') {
  58             my $sciname = $item->text;
  59             $taxinfo{lc $sciname}{sciname} = $sciname;
  60             $taxinfo{lc $sciname}{tid} = $docsum->first_child_text('Id');
  61             last;
  62         }
  63     }
  64 }
  65
  66 # Output in same order as given on command line
  67 foreach my $orgn (@organisms) {
  68     if (exists $taxinfo{lc $orgn}) {
  69         my $tid = $taxinfo{lc $orgn}{tid};
  70
  71         if ($plain) { print $tid, "\n"; }
  72         else { print join(", ", "'$orgn'", $tid), "\n"; }
  73     }
  74     else { print "'$orgn' not found\n"; }
  75 }
  76
  77
  78
  79 =head1 NAME
  80
  81 bp_taxid4species - simple script which returns the NCBI Taxonomic id for a requested species
  82
  83 =head1 SYNOPSIS
  84
  85 bp_taxid4species [-v] [-p] [-h] "Genus1 species1" "Genus2 species2"
  86
  87 Options:
  88   -v   verbose
  89   -p   plain
  90   -h   help
  91
  92 =head1 DESCRIPTION
  93
  94 This simple script shows how to get the taxa id from NCBI Entrez and
  95 will return a list of taxa ids for requested organisms.
  96
  97 =head1 FEEDBACK
  98
  99 =head2 Mailing Lists
 100
 101 User feedback is an integral part of the evolution of this and other
 102 Bioperl modules. Send your comments and suggestions preferably to
 103 the Bioperl mailing list.  Your participation is much appreciated.
 104
 105   bioperl-l@bioperl.org                  - General discussion
 106   http://bioperl.org/wiki/Mailing_lists  - About the mailing lists
 107
 108 =head2 Reporting Bugs
 109
 110 Report bugs to the Bioperl bug tracking system to help us keep track
 111 of the bugs and their resolution. Bug reports can be submitted via the
 112 web:
 113
 114   https://github.com/bioperl/bioperl-live/issues
 115
 116 =head1 AUTHOR
 117
 118  Jason Stajich jason-at-bioperl-dot-org
 119
 120 =cut
 121