bio 1.1.0 → 1.2.0

data/lib/bio/io/flatfile.rb

@@ -5,7 +5,7 @@
 #
 # License:: The Ruby License
 #
-#  $Id: flatfile.rb,v 1.60 2007/07/09 14:08:34 ngoto Exp $
+#  $Id: flatfile.rb,v 1.61 2007/11/15 07:07:16 k Exp $
 #
 #
 # Bio::FlatFile is a helper and wrapper class to read a biological data file.
@@ -1130,7 +1130,7 @@ module Bio
           genpept  = RuleRegexp[ 'Bio::GenPept',
             /^LOCUS       .+ aa .+/ ],
           medline  = RuleRegexp[ 'Bio::MEDLINE',
-            /^UI  \- [0-9]+$/ ],
+            /^PMID\- [0-9]+$/ ],
           embl     = RuleRegexp[ 'Bio::EMBL',
             /^ID   .+\; .*(DNA|RNA|XXX)\;/ ],
           sptr     = RuleRegexp2[ 'Bio::SPTR',

data/lib/bio/io/flatfile/indexer.rb

@@ -4,7 +4,7 @@
 # Copyright:: Copyright (C) 2002 GOTO Naohisa <ng@bioruby.org> 
 # License::   The Ruby License
 # 
-#  $Id: indexer.rb,v 1.25 2007/04/05 23:35:41 trevor Exp $ 
+#  $Id: indexer.rb,v 1.26 2007/12/11 15:13:32 ngoto Exp $ 
 # 
 
 require 'bio/io/flatfile/index'
@@ -714,7 +714,7 @@ module Bio
 
     ##############################################################
     def self.formatstring2class(format_string)
-      case format
+      case format_string
       when /genbank/i
         dbclass = Bio::GenBank
       when /genpept/i

data/lib/bio/io/keggapi.rb

@@ -4,7 +4,7 @@
 # Copyright::  Copyright (C) 2003, 2004 Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: keggapi.rb,v 1.14 2007/04/05 23:35:41 trevor Exp $
+# $Id: keggapi.rb,v 1.15 2007/07/20 21:56:45 k Exp $
 #
 
 require 'bio/io/soapwsdl'
@@ -331,6 +331,7 @@ class API < Bio::SOAPWSDL
   def add_filter(results)
     if results.is_a?(Array)
       results.each do |result|
+	next if result.is_a?(Fixnum)
         def result.filter(fields)
           fields.collect { |field| self.send(field) }
         end

data/lib/bio/io/pubmed.rb

@@ -1,16 +1,15 @@
 #
 # = bio/io/pubmed.rb - NCBI Entrez/PubMed client module
 #
-# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# Copyright::  Copyright (C) 2001, 2007 Toshiaki Katayama <k@bioruby.org>
 # Copyright::  Copyright (C) 2006 Jan Aerts <jan.aerts@bbsrc.ac.uk>
 # License::    The Ruby License
 #
-# $Id: pubmed.rb,v 1.16 2007/04/05 23:35:41 trevor Exp $
+# $Id: pubmed.rb,v 1.23 2007/12/12 13:53:26 k Exp $
 #
 
-require 'net/http'
-require 'cgi' unless defined?(CGI)
 require 'bio/command'
+require 'cgi' unless defined?(CGI)
 
 module Bio
 
@@ -18,18 +17,19 @@ module Bio
 #
 # The Bio::PubMed class provides several ways to retrieve bibliographic
 # information from the PubMed database at
-# http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed. Basically, two
-# types of queries are possible:
+#   http://www.ncbi.nlm.nih.gov/sites/entrez?db=PubMed
+#
+# Basically, two types of queries are possible:
 #
 # * searching for PubMed IDs given a query string:
-#   * Bio::PubMed#search
-#   * Bio::PubMed#esearch
+#   * Bio::PubMed#esearch  (recommended)
+#   * Bio::PubMed#search   (only retrieves top 20 hits)
 #
 # * retrieving the MEDLINE text (i.e. authors, journal, abstract, ...)
 #   given a PubMed ID
-#   * Bio::PubMed#query
-#   * Bio::PubMed#pmfetch
-#   * Bio::PubMed#efetch
+#   * Bio::PubMed#efetch   (recommended)
+#   * Bio::PubMed#query    (unstable for the change of the HTML design)
+#   * Bio::PubMed#pmfetch  (still working but could be obsoleted by NCBI)
 #
 # The different methods within the same group are interchangeable and should
 # return the same result.
@@ -37,54 +37,61 @@ module Bio
 # Additional information about the MEDLINE format and PubMed programmable
 # APIs can be found on the following websites:
 #
-# * Overview: http://www.ncbi.nlm.nih.gov/entrez/query/static/overview.html
-# * How to link: http://www.ncbi.nlm.nih.gov/entrez/query/static/linking.html
-# * MEDLINE format: http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html#MEDLINEDisplayFormat
-# * Search field descriptions and tags: http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html#SearchFieldDescriptionsandTags
-# * Entrez utilities index: http://www.ncbi.nlm.nih.gov/entrez/utils/utils_index.html
-# * PmFetch CGI help: http://www.ncbi.nlm.nih.gov/entrez/utils/pmfetch_help.html
-# * E-Utilities CGI help: http://eutils.ncbi.nlm.nih.gov/entrez/query/static/eutils_help.html
+# * PubMed Overview:
+#     http://www.ncbi.nlm.nih.gov/entrez/query/static/overview.html
+# * PubMed help:
+#     http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html
+# * Entrez utilities index:
+#      http://www.ncbi.nlm.nih.gov/entrez/utils/utils_index.html
+# * How to link:
+#     http://www.ncbi.nlm.nih.gov/books/bv.fcgi?rid=helplinks.chapter.linkshelp
 #
 # == Usage
 #
 #   require 'bio'
 #
 #   # If you don't know the pubmed ID:
-#   Bio::PubMed.search("(genome AND analysis) OR bioinformatics)").each do |x|
+#   Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
 #     p x
 #   end
-#   Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics)").each do |x|
+#
+#   Bio::PubMed.search("(genome AND analysis) OR bioinformatics").each do |x|
 #     p x
 #   end
 #   
 #   # To retrieve the MEDLINE entry for a given PubMed ID:
+#   puts Bio::PubMed.efetch("10592173", "14693808")
 #   puts Bio::PubMed.query("10592173")
 #   puts Bio::PubMed.pmfetch("10592173")
-#   puts Bio::PubMed.efetch("10592173", "14693808")
+#
 #   # This can be converted into a Bio::MEDLINE object:
 #   manuscript = Bio::PubMed.query("10592173")
-#   medline = Bio::MEDLINE(manuscript)
+#   medline = Bio::MEDLINE.new(manuscript)
 #  
 class PubMed
 
-  # Search the PubMed database by given keywords using entrez query and returns
-  # an array of PubMed IDs.
-  # ---
-  # *Arguments*:
-  # * _id_: query string (required)
-  # *Returns*:: array of PubMed IDs
-  def self.search(str)
-    host = "www.ncbi.nlm.nih.gov"
-    path = "/entrez/query.fcgi?tool=bioruby&cmd=Search&doptcmdl=MEDLINE&db=PubMed&term="
+  # Run retrieval scripts on weekends or between 9 pm and 5 am Eastern Time
+  # weekdays for any series of more than 100 requests.
+  # -> Not implemented yet in BioRuby
 
-    http = Bio::Command.new_http(host)
-    response, = http.get(path + CGI.escape(str))
-    result = response.body
-    result = result.gsub("\r", "\n").squeeze("\n")
-    result = result.scan(/<pre>(.*?)<\/pre>/m).flatten
-    return result
+  # Make no more than one request every 3 seconds.
+  NCBI_INTERVAL = 3
+  @@last_access = nil
+
+  private
+
+  def ncbi_access_wait(wait = NCBI_INTERVAL)
+    if @@last_access
+      duration = Time.now - @@last_access
+      if wait > duration
+        sleep wait - duration
+      end
+    end
+    @@last_access = Time.now
   end
 
+  public
+
   # Search the PubMed database by given keywords using E-Utils and returns 
   # an array of PubMed IDs.
   # 
@@ -102,22 +109,80 @@ class PubMed
   # * _retmax_ (default 100)
   # * _retmode_
   # * _rettype_
-  # *Returns*:: array of PubMed IDs
-  def self.esearch(str, hash = {})
-    hash['retmax'] = 100 unless hash['retmax']
+  # *Returns*:: array of PubMed IDs or a number of results
+  def esearch(str, hash = {})
+    return nil if str.empty?
 
-    opts = []
-    hash.each do |k, v|
-      opts << "#{k}=#{v}"
+    serv = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
+    opts = {
+      "retmax" => 100,
+      "tool"   => "bioruby",
+      "db"     => "pubmed",
+      "term"   => str
+    }
+    opts.update(hash)
+
+    ncbi_access_wait
+
+    response, = Bio::Command.post_form(serv, opts)
+    result = response.body
+    if opts['rettype'] == 'count'
+      result = result.scan(/<Count>(.*?)<\/Count>/m).flatten.first.to_i
+    else
+      result = result.scan(/<Id>(.*?)<\/Id>/m).flatten
     end
+    return result
+  end
+
+  # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
+  # entrez efetch. Multiple PubMed IDs can be provided:
+  #   Bio::PubMed.efetch(123)
+  #   Bio::PubMed.efetch([123,456,789])
+  # ---
+  # *Arguments*:
+  # * _ids_: list of PubMed IDs (required)
+  # *Returns*:: Array of MEDLINE formatted String
+  def efetch(ids, hash = {})
+    return nil if ids.to_s.empty?
+    ids = ids.join(",") if ids === Array
+
+    serv = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
+    opts = {
+      "tool"     => "bioruby",
+      "db"       => "pubmed",
+      "retmode"  => "text",
+      "rettype"  => "medline",
+      "id"       => ids,
+    }
+    opts.update(hash)
+
+    ncbi_access_wait
+
+    response, = Bio::Command.post_form(serv, opts)
+    result = response.body
+    if opts["retmode"] == "text"
+      result = result.split(/\n\n+/)
+    end
+    return result
+  end
+
+  # Search the PubMed database by given keywords using entrez query and returns
+  # an array of PubMed IDs. Caution: this method returns the first 20 hits only.
+  # Instead, use of the 'esearch' method is strongly recomended.
+  # ---
+  # *Arguments*:
+  # * _id_: query string (required)
+  # *Returns*:: array of PubMed IDs
+  def search(str)
+    host = "www.ncbi.nlm.nih.gov"
+    path = "/sites/entrez?tool=bioruby&cmd=Search&doptcmdl=Brief&db=PubMed&term="
 
-    host = "eutils.ncbi.nlm.nih.gov"
-    path = "/entrez/eutils/esearch.fcgi?tool=bioruby&db=pubmed&#{opts.join('&')}&term="
+    ncbi_access_wait
 
     http = Bio::Command.new_http(host)
     response, = http.get(path + CGI.escape(str))
     result = response.body
-    result = result.scan(/<Id>(.*?)<\/Id>/m).flatten
+    result = result.scan(/value="(\d+)" id="UidCheckBox"/m).flatten
     return result
   end
 
@@ -127,18 +192,27 @@ class PubMed
   # *Arguments*:
   # * _id_: PubMed ID (required)
   # *Returns*:: MEDLINE formatted String
-  def self.query(id)
+  def query(*ids)
     host = "www.ncbi.nlm.nih.gov"
-    path = "/entrez/query.fcgi?tool=bioruby&cmd=Text&dopt=MEDLINE&db=PubMed&uid="
+    path = "/sites/entrez?tool=bioruby&cmd=Text&dopt=MEDLINE&db=PubMed&uid="
+    list = ids.join(",")
+
+    ncbi_access_wait
 
     http = Bio::Command.new_http(host)
-    response, = http.get(path + id.to_s)
+    response, = http.get(path + list)
     result = response.body
-    if result =~ /#{id}\s+Error/
+    result = result.scan(/<pre>\s*(.*?)<\/pre>/m).flatten
+
+    if result =~ /id:.*Error occurred/
+      # id: xxxxx Error occurred: Article does not exist
       raise( result )
     else
-      result = result.gsub("\r", "\n").squeeze("\n").gsub(/<\/?pre>/, '')
-      return result
+      if ids.size > 1
+        return result
+      else
+        return result.first
+      end
     end
   end
 
@@ -148,10 +222,12 @@ class PubMed
   # *Arguments*:
   # * _id_: PubMed ID (required)
   # *Returns*:: MEDLINE formatted String
-  def self.pmfetch(id)
+  def pmfetch(id)
     host = "www.ncbi.nlm.nih.gov"
     path = "/entrez/utils/pmfetch.fcgi?tool=bioruby&mode=text&report=medline&db=PubMed&id="
 
+    ncbi_access_wait
+
     http = Bio::Command.new_http(host)
     response, = http.get(path + id.to_s)
     result = response.body
@@ -163,28 +239,24 @@ class PubMed
     end
   end
 
-  # Retrieve PubMed entry by PMID and returns MEDLINE formatted string using
-  # entrez efetch. Multiple PubMed IDs can be provided:
-  #   Bio::PubMed.efetch(123)
-  #   Bio::PubMed.efetch(123,456,789)
-  #   Bio::PubMed.efetch([123,456,789])
-  # ---
-  # *Arguments*:
-  # * _ids_: list of PubMed IDs (required)
-  # *Returns*:: MEDLINE formatted String
-  def self.efetch(*ids)
-    return [] if ids.empty?
+  def self.esearch(*args)
+    self.new.esearch(*args)
+  end
+
+  def self.efetch(*args)
+    self.new.efetch(*args)
+  end
 
-    host = "eutils.ncbi.nlm.nih.gov"
-    path = "/entrez/eutils/efetch.fcgi?tool=bioruby&db=pubmed&retmode=text&rettype=medline&id="
+  def self.search(*args)
+    self.new.search(*args)
+  end
 
-    ids = ids.join(",")
+  def self.query(*args)
+    self.new.query(*args)
+  end
 
-    http = Bio::Command.new_http(host)
-    response, = http.get(path + ids)
-    result = response.body
-    result = result.split(/\n\n+/)
-    return result
+  def self.pmfetch(*args)
+    self.new.pmfetch(*args)
   end
 
 end # PubMed
@@ -194,18 +266,88 @@ end # Bio
 
 if __FILE__ == $0
 
-  puts Bio::PubMed.query("10592173")
-  puts "--- ---"
-  puts Bio::PubMed.pmfetch("10592173")
-  puts "--- ---"
-  Bio::PubMed.search("(genome AND analysis) OR bioinformatics)").each do |x|
+  puts "=== instance methods ==="
+
+  pubmed = Bio::PubMed.new
+
+  puts "--- Search PubMed by E-Utils ---"
+  opts = {"rettype" => "count"}
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts pubmed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  pubmed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
+    puts x
+  end
+
+  puts "--- Retrieve PubMed entry by E-Utils ---"
+  puts Time.now
+  puts pubmed.efetch(16381885)
+  puts Time.now
+  puts pubmed.efetch("16381885")
+  puts Time.now
+  puts pubmed.efetch("16381885")
+  puts Time.now
+  opts = {"retmode" => "xml"}
+  puts pubmed.efetch([10592173, 14693808], opts)
+  puts Time.now
+  puts pubmed.efetch(["10592173", "14693808"], opts)
+
+  puts "--- Search PubMed by Entrez CGI ---"
+  pubmed.search("(genome AND analysis) OR bioinformatics").each do |x|
     p x
   end
-  puts "--- ---"
-  Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics)").each do |x|
+
+  puts "--- Retrieve PubMed entry by Entrez CGI ---"
+  puts pubmed.query("16381885")
+
+
+  puts "--- Retrieve PubMed entry by PMfetch ---"
+  puts pubmed.pmfetch("16381885")
+
+
+  puts "=== class methods ==="
+
+
+  puts "--- Search PubMed by E-Utils ---"
+  opts = {"rettype" => "count"}
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  puts Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics", opts)
+  puts Time.now
+  Bio::PubMed.esearch("(genome AND analysis) OR bioinformatics").each do |x|
+    puts x
+  end
+
+  puts "--- Retrieve PubMed entry by E-Utils ---"
+  puts Time.now
+  puts Bio::PubMed.efetch(16381885)
+  puts Time.now
+  puts Bio::PubMed.efetch("16381885")
+  puts Time.now
+  puts Bio::PubMed.efetch("16381885")
+  puts Time.now
+  opts = {"retmode" => "xml"}
+  puts Bio::PubMed.efetch([10592173, 14693808], opts)
+  puts Time.now
+  puts Bio::PubMed.efetch(["10592173", "14693808"], opts)
+
+  puts "--- Search PubMed by Entrez CGI ---"
+  Bio::PubMed.search("(genome AND analysis) OR bioinformatics").each do |x|
     p x
   end
-  puts "--- ---"
-  puts Bio::PubMed.efetch("10592173", "14693808")
+
+  puts "--- Retrieve PubMed entry by Entrez CGI ---"
+  puts Bio::PubMed.query("16381885")
+
+
+  puts "--- Retrieve PubMed entry by PMfetch ---"
+  puts Bio::PubMed.pmfetch("16381885")
 
 end