bio 1.4.0 → 1.4.1

data/lib/bio/db/kegg/genes.rb

@@ -1,7 +1,7 @@
 #
 # = bio/db/kegg/genes.rb - KEGG/GENES database class
 #
-# Copyright::   Copyright (C) 2001, 2002, 2006
+# Copyright::   Copyright (C) 2001, 2002, 2006, 2010
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
@@ -29,8 +29,7 @@
 # 
 #  # NAME
 #  p entry.name        # => String
-#  p entry.genes       # => Array
-#  p entry.gene        # => String
+#  p entry.names       # => Array
 # 
 #  # DEFINITION
 #  p entry.definition  # => String
@@ -47,7 +46,7 @@
 #  p entry.locations   # => Bio::Locations
 #
 #  # MOTIF
-#  p entry.motif       # => Hash of Array
+#  p entry.motifs      # => Hash of Array
 #
 #  # DBLINKS
 #  p entry.dblinks     # => Hash of Array
@@ -169,10 +168,24 @@ class GENES < KEGGDB
   #
   # ---
   # *Returns*:: Array containing String
-  def genes
+  def names_as_array
     name.split(', ')
   end
+  alias names names_as_array
+
+  # The method will be deprecated. Use Bio::KEGG::GENES#names.
+  #
+  # Names of the entry as an Array, described in the NAME line.
+  #
+  # ---
+  # *Returns*:: Array containing String
+  def genes
+    names_as_array
+  end
 
+  # The method will be deprecated.
+  # Use <tt>entry.names.first</tt> instead.
+  #
   # Returns the first gene name described in the NAME line.
   # ---
   # *Returns*:: String
@@ -191,12 +204,14 @@ class GENES < KEGGDB
   # ---
   # *Returns*:: Array containing String
   def eclinks
-    ec_list = definition.slice(/\[EC:(.*?)\]/, 1)
-    if ec_list
-      ec_list.strip.split(/\s+/)
-    else
-      []
+    unless defined? @eclinks
+      ec_list = 
+        definition.slice(/\[EC\:([^\]]+)\]/, 1) ||
+        definition.slice(/\(EC\:([^\)]+)\)/, 1)
+      ary = ec_list ? ec_list.strip.split(/\s+/) : []
+      @eclinks = ary
     end
+    @eclinks
   end
 
   # Orthologs described in the ORTHOLOGY lines.
@@ -210,7 +225,10 @@ class GENES < KEGGDB
   # ---
   # *Returns*:: String
   def pathway
-    field_fetch('PATHWAY')
+    unless defined? @pathway
+      @pathway = fetch('PATHWAY')
+    end
+    @pathway
   end
 
   # Pathways described in the PATHWAY lines.
@@ -220,6 +238,16 @@ class GENES < KEGGDB
     lines_fetch('PATHWAY')
   end
 
+  # Returns CLASS field of the entry.
+  def keggclass
+    field_fetch('CLASS')
+  end
+
+  # Returns an Array of biological classes in CLASS field.
+  def keggclasses
+    keggclass.gsub(/ \[[^\]]+/, '').split(/\] ?/)
+  end
+
   # The position in the genome described in the POSITION line.
   # ---
   # *Returns*:: String
@@ -259,16 +287,23 @@ class GENES < KEGGDB
     Bio::Locations.new(gbposition)
   end
 
+  # Motif information described in the MOTIF lines.
+  # ---
+  # *Returns*:: Strings
+  def motifs_as_strings
+    lines_fetch('MOTIF')
+  end
+
   # Motif information described in the MOTIF lines.
   # ---
   # *Returns*:: Hash
-  def motif
+  def motifs_as_hash
     unless @data['MOTIF']
       hash = {}
       db = nil
-      lines_fetch('MOTIF').each do |line|
+      motifs_as_strings.each do |line|
         if line[/^\S+:/]
-          db, str = line.split(/:/)
+          db, str = line.split(/:/, 2)
         else
           str = line
         end
@@ -279,6 +314,17 @@ class GENES < KEGGDB
     end
     @data['MOTIF']		# Hash of Array of IDs in MOTIF
   end
+  alias motifs motifs_as_hash
+
+  # The specification of the method will be changed in the future.
+  # Please use Bio::KEGG::GENES#motifs.
+  #
+  # Motif information described in the MOTIF lines.
+  # ---
+  # *Returns*:: Hash
+  def motif
+    motifs
+  end
 
   # Links to other databases described in the DBLINKS lines.
   # ---
@@ -298,7 +344,7 @@ class GENES < KEGGDB
   end
   alias structures structure
 
-  # Codon usage data described in the CODON_USAGE lines.
+  # Codon usage data described in the CODON_USAGE lines. (Deprecated: no more exists)
   # ---
   # *Returns*:: Hash
   def codon_usage(codon = nil)

data/lib/bio/db/kegg/genome.rb

@@ -8,6 +8,8 @@
 #
 
 require 'bio/db'
+require 'bio/reference'
+require 'bio/db/kegg/common'
 
 module Bio
 class KEGG
@@ -27,10 +29,37 @@ class GENOME < KEGGDB
   DELIMITER	= RS = "\n///\n"
   TAGSIZE	= 12
 
+  include Common::References
+  # REFERENCE -- Returns contents of the REFERENCE records as an Array of
+  # Bio::Reference objects.
+  def references; super; end if false #dummy for RDoc
+
+
   def initialize(entry)
     super(entry, TAGSIZE)
   end
 
+  # (private) Returns a tag name of the field as a String.
+  # Needed to redefine because of the PLASMID field.
+  def tag_get(str)
+    if /\APLASMID\s+/ =~ str.to_s then
+      'PLASMID'
+    else
+      super(str)
+    end
+  end
+  private :tag_get
+
+  # (private) Returns a String of the field without a tag name.
+  # Needed to redefine because of the PLASMID field.
+  def tag_cut(str)
+    if /\APLASMID\s+/ =~ str.to_s then
+      $'
+    else
+      super(str)
+    end
+  end
+  private :tag_cut
 
   # ENTRY -- Returns contents of the ENTRY record as a String.
   def entry_id
@@ -80,7 +109,20 @@ class GENOME < KEGGDB
 
   # ORIGINAL_DB -- Returns contents of the ORIGINAL_DB record as a String.
   def original_db
-    field_fetch('ORIGINAL_DB')
+    #field_fetch('ORIGINAL_DB')
+    unless defined?(@original_db)
+      @original_db = fetch('ORIGINAL_DB')
+    end
+    @original_db
+  end
+
+  # Returns ORIGINAL_DB record as an Array containing String objects.
+  #
+  # ---
+  # *Arguments*:
+  # *Returns*:: Array containing String objects
+  def original_databases
+    lines_fetch('ORIGINAL_DB')
   end
 
   # DISEASE -- Returns contents of the COMMENT record as a String.
@@ -93,43 +135,6 @@ class GENOME < KEGGDB
     field_fetch('COMMENT')
   end
   
-  # REFERENCE -- Returns contents of the REFERENCE records as an Array of
-  # Bio::Reference objects.
-  def references
-    unless @data['REFERENCE']
-      ary = []
-      toptag2array(get('REFERENCE')).each do |ref|
-        hash = Hash.new('')
-        subtag2array(ref).each do |field|
-          case tag_get(field)
-          when /AUTHORS/
-            authors = truncate(tag_cut(field))
-            authors = authors.split(', ')
-            authors[-1] = authors[-1].split(/\s+and\s+/)
-            authors = authors.flatten.map { |a| a.sub(',', ', ') }
-            hash['authors']	= authors
-          when /TITLE/
-            hash['title']	= truncate(tag_cut(field))
-          when /JOURNAL/
-            journal = truncate(tag_cut(field))
-            if journal =~ /(.*) (\d+):(\d+)-(\d+) \((\d+)\) \[UI:(\d+)\]$/
-              hash['journal']	= $1
-              hash['volume']	= $2
-              hash['pages']	= $3
-              hash['year']	= $5
-              hash['medline']	= $6
-            else
-              hash['journal'] = journal
-            end
-          end
-        end
-        ary.push(Reference.new(hash))
-      end
-      @data['REFERENCE'] = References.new(ary)
-    end
-    @data['REFERENCE']
-  end
-
   # CHROMOSOME -- Returns contents of the CHROMOSOME records as an Array
   # of Hash.
   def chromosomes

data/lib/bio/db/kegg/module.rb

@@ -0,0 +1,158 @@
+#
+# = bio/db/kegg/module.rb - KEGG MODULE database class
+#
+# Copyright::  Copyright (C) 2010 Kozo Nishida <kozo-ni@is.naist.jp>
+# Copyright::  Copyright (C) 2010 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id:$
+#
+
+require 'bio/db'
+require 'bio/db/kegg/common'
+
+module Bio
+class KEGG
+
+# == Description
+#
+# Bio::KEGG::MODULE is a parser class for the KEGG MODULE database entry.
+#
+# == References
+#
+# * http://www.kegg.jp/kegg-bin/get_htext?ko00002.keg
+# * ftp://ftp.genome.jp/pub/kegg/pathway/module
+#
+class MODULE < KEGGDB
+
+  DELIMITER = RS = "\n///\n"
+  TAGSIZE = 12
+
+  #--
+  # for a private method strings_as_hash.
+  #++
+  include Common::StringsAsHash
+
+  # Creates a new Bio::KEGG::MODULE object.
+  # ---
+  # *Arguments*:
+  # * (required) _entry_: (String) single entry as a string
+  # *Returns*:: Bio::KEGG::MODULE object
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # Return the ID, described in the ENTRY line.
+  # ---
+  # *Returns*:: String
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
+
+  # Name of the module, described in the NAME line.
+  # ---
+  # *Returns*:: String
+  def name
+    field_fetch('NAME')
+  end
+
+  # Definition of the module, described in the DEFINITION line.
+  # ---
+  # *Returns*:: String
+  def definition
+    field_fetch('DEFINITION')
+  end
+
+  # Name of the KEGG class, described in the CLASS line.
+  # ---
+  # *Returns*:: String
+  def keggclass
+    field_fetch('CLASS')
+  end
+
+  # Pathways described in the PATHWAY lines.
+  # ---
+  # *Returns*:: Array containing String
+  def pathways_as_strings
+    lines_fetch('PATHWAY')
+  end
+
+  # Pathways described in the PATHWAY lines.
+  # ---
+  # *Returns*:: Hash of pathway ID and its definition
+  def pathways_as_hash
+    unless @pathways_as_hash
+      @pathways_as_hash = strings_as_hash(pathways_as_strings)
+    end
+    @pathways_as_hash
+  end
+  alias pathways pathways_as_hash
+
+
+  # Orthologs described in the ORTHOLOGY lines.
+  # ---
+  # *Returns*:: Array containing String
+  def orthologs_as_strings
+    lines_fetch('ORTHOLOGY')
+  end
+
+  # Orthologs described in the ORTHOLOGY lines.
+  # ---
+  # *Returns*:: Hash of orthology ID and its definition
+  def orthologs_as_hash
+    unless @orthologs_as_hash
+      @orthologs_as_hash = strings_as_hash(orthologs_as_strings)
+    end
+    @orthologs_as_hash
+  end
+  alias orthologs orthologs_as_hash
+
+  # All KO IDs in the ORTHOLOGY lines.
+  # ---
+  # *Returns*:: Array of orthology IDs
+  def orthologs_as_array
+    orthologs_as_hash.keys.map{|x| x.split(/\+|\-|,/)}.flatten.sort.uniq
+  end
+
+
+  # Reactions described in the REACTION lines.
+  # ---
+  # *Returns*:: Array containing String
+  def reactions_as_strings
+    lines_fetch('REACTION')
+  end
+
+  # Reactions described in the REACTION lines.
+  # ---
+  # *Returns*:: Hash of reaction ID and its definition
+  def reactions_as_hash
+    unless @reactions_as_hash
+      @reactions_as_hash = strings_as_hash(reactions_as_strings)
+    end
+    @reactions_as_hash
+  end
+  alias reactions reactions_as_hash
+
+
+  # Compounds described in the COMPOUND lines.
+  # ---
+  # *Returns*:: Array containing String
+  def compounds_as_strings
+    lines_fetch('COMPOUND')
+  end
+
+  # Compounds described in the COMPOUND lines.
+  # ---
+  # *Returns*:: Hash of compound ID and its definition
+  def compounds_as_hash
+    unless @compounds_as_hash
+      @compounds_as_hash = strings_as_hash(compounds_as_strings)
+    end
+    @compounds_as_hash
+  end
+  alias compounds compounds_as_hash
+
+end # MODULE
+
+end # KEGG
+end # Bio

data/lib/bio/db/kegg/orthology.rb

@@ -38,6 +38,27 @@ class ORTHOLOGY < KEGGDB
   def genes_as_hash; super; end if false #dummy for RDoc
   alias genes genes_as_hash
 
+  include Common::PathwaysAsHash
+  # Returns a Hash of the pathway ID and name in PATHWAY field.
+  def pathways_as_hash; super; end if false #dummy for RDoc
+  alias pathways pathways_as_hash
+
+  include Common::ModulesAsHash
+  # Returns MODULE field as a Hash.
+  # Each key of the hash is KEGG MODULE ID,
+  # and each value is the name of the Pathway Module.
+  # ---
+  # *Returns*:: Hash
+  def modules_as_hash; super; end if false #dummy for RDoc
+  alias modules modules_as_hash
+
+  include Common::References
+  # REFERENCE -- Returns contents of the REFERENCE records as an Array of
+  # Bio::Reference objects.
+  # ---
+  # *Returns*:: an Array containing Bio::Reference objects
+  def references; super; end if false #dummy for RDoc
+
   # Reads a flat file format entry of the KO database.
   def initialize(entry)
     super(entry, TAGSIZE)
@@ -73,10 +94,28 @@ class ORTHOLOGY < KEGGDB
     keggclass.gsub(/ \[[^\]]+/, '').split(/\] ?/)
   end
 
+  # Pathways described in the PATHWAY field.
+  # ---
+  # *Returns*:: Array containing String
+  def pathways_as_strings
+    lines_fetch('PATHWAY')
+  end
+
+  # *OBSOLETE* Do not use this method.
+  # Because KEGG ORTHOLOGY format is changed and PATHWAY field is added,
+  # older "pathways" method is renamed and remain only for compatibility.
+  # 
   # Returns an Array of KEGG/PATHWAY ID in CLASS field.
-  def pathways
+  def pathways_in_keggclass
     keggclass.scan(/\[PATH:(.*?)\]/).flatten
   end
+
+  # Returns MODULE field of the entry.
+  # ---
+  # *Returns*:: Array containing String objects
+  def modules_as_strings
+    lines_fetch('MODULE')
+  end
   
   # Returns an Array of a database name and entry IDs in DBLINKS field.
   def dblinks_as_strings