bio 1.3.1 → 1.4.0

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

@@ -4,7 +4,7 @@
 # Copyright::  Copyright (C) 2001, 2002, 2007 Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: genome.rb,v 0.18 2007/06/28 11:27:24 k Exp $
+# $Id:$
 #
 
 require 'bio/db'
@@ -19,6 +19,8 @@ class KEGG
 # == References
 #
 # * ftp://ftp.genome.jp/pub/kegg/genomes/genome
+# * http://www.genome.jp/dbget-bin/www_bfind?genome
+# * http://www.genome.jp/kegg/catalog/org_list.html
 #
 class GENOME < KEGGDB
 
@@ -199,43 +201,3 @@ end # GENOME
 end # KEGG
 end # Bio
 
-
-
-if __FILE__ == $0
-
-  begin
-    require 'pp'
-    def p(arg); pp(arg); end
-  rescue LoadError
-  end
-
-  require 'bio/io/flatfile'
-
-  ff = Bio::FlatFile.new(Bio::KEGG::GENOME, ARGF)
-
-  ff.each do |genome|
-
-    puts "### Tags"
-    p genome.tags
-
-    [
-      %w( ENTRY entry_id ),
-      %w( NAME name ),
-      %w( DEFINITION definition ),
-      %w( TAXONOMY taxonomy taxid lineage ),
-      %w( REFERENCE references ),
-      %w( CHROMOSOME chromosomes ),
-      %w( PLASMID plasmids ),
-      %w( STATISTICS statistics nalen num_gene num_rna ),
-    ].each do |x|
-      puts "### " + x.shift
-      x.each do |m|
-        p genome.send(m)
-      end
-    end
-
-  end
-
-end
-
-

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

@@ -8,6 +8,7 @@
 #
 
 require 'bio/db'
+require 'bio/db/kegg/common'
 
 module Bio
 class KEGG
@@ -17,6 +18,21 @@ class GLYCAN < KEGGDB
   DELIMITER	= RS = "\n///\n"
   TAGSIZE	= 12
 
+  include Common::DblinksAsHash
+  # Returns a Hash of the DB name and an Array of entry IDs in DBLINKS field.
+  def dblinks_as_hash; super; end if false #dummy for RDoc
+  alias dblinks dblinks_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::OrthologsAsHash
+  # Returns a Hash of the orthology ID and definition in ORTHOLOGY field.
+  def orthologs_as_hash; super; end if false #dummy for RDoc
+  alias orthologs orthologs_as_hash
+
   def initialize(entry)
     super(entry, TAGSIZE)
   end
@@ -73,7 +89,7 @@ class GLYCAN < KEGGDB
   end
 
   # PATHWAY
-  def pathways
+  def pathways_as_strings
     lines_fetch('PATHWAY') 
   end
 
@@ -91,7 +107,7 @@ class GLYCAN < KEGGDB
   end
 
   # ORTHOLOGY
-  def orthologs
+  def orthologs_as_strings
     unless @data['ORTHOLOGY']
       @data['ORTHOLOGY'] = lines_fetch('ORTHOLOGY')
     end
@@ -126,7 +142,7 @@ class GLYCAN < KEGGDB
   end
 
   # DBLINKS
-  def dblinks
+  def dblinks_as_strings
     unless @data['DBLINKS']
       @data['DBLINKS'] = lines_fetch('DBLINKS')
     end
@@ -143,24 +159,3 @@ end # GLYCAN
 end # KEGG
 end # Bio
 
-
-if __FILE__ == $0
-  entry = ARGF.read	# gl:G00024
-  gl = Bio::KEGG::GLYCAN.new(entry)
-  p gl.entry_id
-  p gl.name
-  p gl.composition
-  p gl.mass
-  p gl.keggclass
-  p gl.bindings
-  p gl.compounds
-  p gl.reactions
-  p gl.pathways
-  p gl.enzymes
-  p gl.orthologs
-  p gl.references
-  p gl.dblinks
-  p gl.kcf
-end
-
-

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

@@ -5,10 +5,11 @@
 # Copyright::  Copyright (C) 2003 Masumi Itoh <m@bioruby.org>
 # License::    The Ruby License
 #
-# $Id: orthology.rb,v 1.10 2007/12/14 16:19:54 k Exp $
+# $Id:$
 #
 
 require 'bio/db'
+require 'bio/db/kegg/common'
 
 module Bio
 class KEGG
@@ -27,6 +28,16 @@ class ORTHOLOGY < KEGGDB
   DELIMITER	= RS = "\n///\n"
   TAGSIZE	= 12
 
+  include Common::DblinksAsHash
+  # Returns a Hash of the DB name and an Array of entry IDs in DBLINKS field.
+  def dblinks_as_hash; super; end if false #dummy for RDoc
+  alias dblinks dblinks_as_hash
+
+  include Common::GenesAsHash
+  # Returns a Hash of the organism ID and an Array of entry IDs in GENES field.
+  def genes_as_hash; super; end if false #dummy for RDoc
+  alias genes genes_as_hash
+
   # Reads a flat file format entry of the KO database.
   def initialize(entry)
     super(entry, TAGSIZE)
@@ -68,69 +79,18 @@ class ORTHOLOGY < KEGGDB
   end
   
   # Returns an Array of a database name and entry IDs in DBLINKS field.
-  def dblinks
-    unless @data['DBLINKS']
-      @data['DBLINKS'] = lines_fetch('DBLINKS')
-    end
-    @data['DBLINKS']
-  end
-
-  # Returns a Hash of the DB name and an Array of entry IDs in DBLINKS field.
-  def dblinks_as_hash
-    hash = {}
-    dblinks.each do |line|
-      name, *list = line.split(/\s+/)
-      db = name.downcase.sub(/:/, '')
-      hash[db] = list
-    end
-    return hash
+  def dblinks_as_strings
+    lines_fetch('DBLINKS')
   end
 
   # Returns an Array of the organism ID and entry IDs in GENES field.
-  def genes
-    unless @data['GENES']
-      @data['GENES'] = lines_fetch('GENES')
-    end
-    @data['GENES']
+  def genes_as_strings
+    lines_fetch('GENES')
   end
 
-  # Returns a Hash of the organism ID and an Array of entry IDs in GENES field.
-  def genes_as_hash
-    hash = {}
-    genes.each do |line|
-      name, *list = line.split(/\s+/)
-      org = name.downcase.sub(/:/, '')
-      genes = list.map {|x| x.sub(/\(.*\)/, '')}
-      #names = list.map {|x| x.scan(/.*\((.*)\)/)}
-      hash[org] = genes
-    end
-    return hash
-  end
-  
 end # ORTHOLOGY
     
 end # KEGG
 end # Bio
 
 
-
-if __FILE__ == $0
-
-  require 'bio/io/fetch'
-
-  flat = Bio::Fetch.query('ko', 'K00001')
-  entry = Bio::KEGG::ORTHOLOGY.new(flat)
-
-  p entry.entry_id
-  p entry.name
-  p entry.names
-  p entry.definition
-  p entry.keggclass
-  p entry.keggclasses
-  p entry.pathways
-  p entry.dblinks
-  p entry.genes
-
-end
-
-

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

@@ -2,12 +2,15 @@
 # = bio/db/kegg/reaction.rb - KEGG REACTION database class
 #
 # Copyright::  Copyright (C) 2004 Toshiaki Katayama <k@bioruby.org>
+# Copyright::  Copyright (C) 2009 Kozo Nishida <kozo-ni@is.naist.jp>
 # License::    The Ruby License
 #
-# $Id: reaction.rb,v 1.6 2007/06/28 11:27:24 k Exp $
+# $Id:$
 #
 
 require 'bio/db'
+require 'bio/db/kegg/common'
+require 'enumerator'
 
 module Bio
 class KEGG
@@ -17,44 +20,100 @@ class REACTION < KEGGDB
   DELIMITER	= RS = "\n///\n"
   TAGSIZE	= 12
 
+  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::OrthologsAsHash
+  # Returns a Hash of the orthology ID and definition in ORTHOLOGY field.
+  def orthologs_as_hash; super; end if false #dummy for RDoc
+  alias orthologs orthologs_as_hash
+
+  # Creates a new Bio::KEGG::REACTION object.
+  # ---
+  # *Arguments*:
+  # * (required) _entry_: (String) single entry as a string
+  # *Returns*:: Bio::KEGG::REACTION object
   def initialize(entry)
     super(entry, TAGSIZE)
   end
 
-  # ENTRY
+  # ID of the entry, described in the ENTRY line.
+  # ---
+  # *Returns*:: String
   def entry_id
     field_fetch('ENTRY')[/\S+/]
   end
 
-  # NAME
+  # Name of the reaction, described in the NAME line.
+  # ---
+  # *Returns*:: String
   def name
-    field_fetch('NAME') 
+    field_fetch('NAME')
   end
 
-  # DEFINITION
+  # Definition of the reaction, described in the DEFINITION line.
+  # ---
+  # *Returns*:: String
   def definition
     field_fetch('DEFINITION')
   end
 
-  # EQUATION
+  # Chemical equation, described in the EQUATION line.
+  # ---
+  # *Returns*:: String
   def equation
     field_fetch('EQUATION')
   end
 
-  # RPAIR
-  def rpairs
-    unless @data['RPAIR']
-      @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
+  # KEGG RPAIR (ReactantPair) information, described in the RPAIR lines.
+  # ---
+  # *Returns*:: Array containing String
+  def rpairs_as_strings
+    lines_fetch('RPAIR')
+  end
+
+  # KEGG RPAIR (ReactantPair) information, described in the RPAIR lines.
+  # Returns a hash of RPair IDs and [ name, type ] informations, for example,
+  #   { "RP12733" => [ "C00022_C00900", "trans" ],
+  #     "RP05698" => [ "C00011_C00022", "leave" ],
+  #     "RP00440" => [ "C00022_C00900", "main" ]
+  #   }
+  # ---
+  # *Returns*:: Hash
+  def rpairs_as_hash
+    unless defined? @rpairs_as_hash
+      rps = {}
+      rpairs_as_strings.each do |line|
+        namespace, entry_id, name, rptype = line.split(/\s+/)
+        rps[entry_id] = [ name, rptype ]
+      end
+      @rpairs_as_hash = rps
     end
-    @data['RPAIR']
+    @rpairs_as_hash
+  end
+
+  alias rpairs rpairs_as_hash
+
+  # Returns the content of the RPAIR entry as tokens
+  # (RPair signature, RPair ID, , RPair type).
+  # ---
+  # *Returns*:: Array containing String
+  def rpairs_as_tokens
+    fetch('RPAIR').split(/\s+/)
   end
 
-  # PATHWAY
-  def pathways
-    lines_fetch('PATHWAY') 
+  # Pathway information, described in the PATHWAY lines.
+  # ---
+  # *Returns*:: Array containing String
+  def pathways_as_strings
+    lines_fetch('PATHWAY')
   end
 
-  # ENZYME
+  # Enzymes described in the ENZYME line.
+  # ---
+  # *Returns*:: Array containing String
   def enzymes
     unless @data['ENZYME']
       @data['ENZYME'] = fetch('ENZYME').scan(/\S+/)
@@ -62,21 +121,15 @@ class REACTION < KEGGDB
     @data['ENZYME']
   end
 
+  # Orthologs described in the ORTHOLOGY lines.
+  # ---
+  # *Returns*:: Array containing String
+  def orthologs_as_strings
+    lines_fetch('ORTHOLOGY')
+  end
+
 end # REACTION
 
 end # KEGG
 end # Bio
 
-
-if __FILE__ == $0
-  entry = ARGF.read
-  rn = Bio::KEGG::REACTION.new(entry)
-  p rn.entry_id
-  p rn.name
-  p rn.definition
-  p rn.equation
-  p rn.rpairs
-  p rn.pathways
-  p rn.enzymes
-end
-

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

@@ -4,7 +4,7 @@
 # Copyright::  Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
 # License::    The Ruby License
 #
-#  $Id: taxonomy.rb,v 1.2 2007/07/09 10:29:16 k Exp $
+#  $Id:$
 #
 
 module Bio
@@ -278,54 +278,3 @@ end # Taxonomy
 end # KEGG
 end # Bio
 
-
-
-if __FILE__ == $0
-
-  # Usage:
-  # % wget ftp://ftp.genome.jp/pub/kegg/genes/taxonomy
-  # % ruby taxonomy.rb taxonomy | less -S
-
-  taxonomy = ARGV.shift
-  org_list = ARGV.shift || nil
-
-  if org_list
-    orgs = File.readlines(org_list).map{|x| x.strip}
-  else
-    orgs = nil
-  end
-
-  tree = Bio::KEGG::Taxonomy.new(taxonomy, orgs)
-
-  puts ">>> tree - original"
-  puts tree
-
-  puts ">>> tree - after compact"
-  tree.compact
-  puts tree
-
-  puts ">>> tree - after reduce"
-  tree.reduce
-  puts tree
-
-  puts ">>> path - sorted"
-  tree.path.sort.each do |path|
-    puts path.join("/")
-  end
-
-  puts ">>> group : orgs"
-  tree.dfs(tree.root) do |parent, children|
-    if orgs = tree.organisms(parent)
-      puts "#{parent.ljust(30)} (#{orgs.size})\t#{orgs.join(', ')}"
-    end
-  end
-
-  puts ">>> group : subgroups"
-  tree.dfs_with_level(tree.root) do |parent, children, level|
-    subgroups = children.keys.sort
-    indent = " " * level
-    label  = "#{indent} #{level} #{parent}"
-    puts "#{label.ljust(35)}\t#{subgroups.join(', ')}"
-  end
-
-end