bio 1.0.0 → 1.1.0

data/lib/bio/db/go.rb

@@ -1,33 +1,17 @@
 #
 # = bio/db/go.rb - Classes for Gene Ontology
 #
-# Copyright::   Copyright (C) 2003 Mitsuteru C. Nakao <n@bioruby.org>
-# License::
+# Copyright::   Copyright (C) 2003 
+#               Mitsuteru C. Nakao <n@bioruby.org>
+# License::     The Ruby License
 #
-#  $Id: go.rb,v 1.9 2005/10/31 18:32:36 nakao Exp $
+#  $Id: go.rb,v 1.11 2007/04/05 23:35:40 trevor Exp $
 #
 # == Gene Ontology
 #
 # == Example
 #
 # == References
-#--
-#
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#++
 #
 
 require 'bio/pathway'

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

@@ -1,51 +1,41 @@
 #
-# bio/db/kegg/brite.rb - KEGG/BRITE database class
+# = bio/db/kegg/brite.rb - KEGG/BRITE database class
 #
-#   Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
+# Copyright::  Copyright (C) 2001 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
 #
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#  $Id: brite.rb,v 0.6 2005/09/08 01:22:11 k Exp $
+# $Id: brite.rb,v 0.8 2007/04/05 23:35:41 trevor Exp $
 #
 
 require 'bio/db'
 
 module Bio
+class KEGG
 
-  class KEGG
-
-    class BRITE < KEGGDB
-
-      DELIMITER	= RS = "\n///\n"
-      TAGSIZE	= 12
+# == Note
+#
+# This class is not completely implemented, but obsolete as the original
+# database BRITE has changed it's meaning.
+#
+class BRITE < KEGGDB
 
-      def initialize(entry)
-        super(entry, TAGSIZE)
-      end
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
 
-      # ENTRY
-      # DEFINITION
-      # RELATION
-      # FACTORS
-      # INTERACTION
-      # SOURCE
-      # REFERENCE
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
 
-    end
+  # ENTRY
+  # DEFINITION
+  # RELATION
+  # FACTORS
+  # INTERACTION
+  # SOURCE
+  # REFERENCE
 
-  end
+end # BRITE
 
-end
+end # KEGG
+end # Bio
 

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

@@ -1,115 +1,111 @@
 #
-# bio/db/kegg/compound.rb - KEGG COMPOUND database class
+# = bio/db/kegg/compound.rb - KEGG COMPOUND database class
 #
-#   Copyright (C) 2001, 2002, 2004 KATAYAMA Toshiaki <k@bioruby.org>
+# Copyright::  Copyright (C) 2001, 2002, 2004, 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
 #
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#  $Id: compound.rb,v 0.11 2005/09/08 01:22:11 k Exp $
+# $Id: compound.rb,v 0.16 2007/06/28 11:27:24 k Exp $
 #
 
 require 'bio/db'
 
 module Bio
+class KEGG
 
-  class KEGG
+class COMPOUND < KEGGDB
 
-    class COMPOUND < KEGGDB
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
 
-      DELIMITER	= RS = "\n///\n"
-      TAGSIZE	= 12
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
 
-      def initialize(entry)
-        super(entry, TAGSIZE)
-      end
+  # ENTRY
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
 
-      # ENTRY
-      def entry_id
-        unless @data['ENTRY']
-          @data['ENTRY'] = fetch('ENTRY').split(/\s+/).first
-        end
-        @data['ENTRY']
-      end
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
 
-      # NAME
-      def names
-        lines_fetch('NAME') 
-      end
-      def name
-        names[0]
-      end
+  def name
+    names.first
+  end
 
-      # FORMULA
-      def formula
-        field_fetch('FORMULA')
-      end
+  # FORMULA
+  def formula
+    field_fetch('FORMULA')
+  end
 
-      # MASS
-      def mass
-        field_fetch('MASS').to_f
-      end
+  # MASS
+  def mass
+    field_fetch('MASS').to_f
+  end
 
-      # REACTION
-      def reactions
-        unless @data['REACTION']
-          @data['REACTION'] = fetch('REACTION').split(/\s+/)
-        end
-        @data['REACTION']
-      end
+  # GLYCAN
+  def glycans
+    unless @data['GLYCAN']
+      @data['GLYCAN'] = fetch('GLYCAN').split(/\s+/)
+    end
+    @data['GLYCAN']
+  end
 
-      # RPAIR
-      def rpairs
-        unless @data['RPAIR']
-          @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
-        end
-        @data['RPAIR']
-      end
+  # REACTION
+  def reactions
+    unless @data['REACTION']
+      @data['REACTION'] = fetch('REACTION').split(/\s+/)
+    end
+    @data['REACTION']
+  end
 
-      # PATHWAY
-      def pathways
-        lines_fetch('PATHWAY') 
-      end
+  # RPAIR
+  def rpairs
+    unless @data['RPAIR']
+      @data['RPAIR'] = fetch('RPAIR').split(/\s+/)
+    end
+    @data['RPAIR']
+  end
 
-      # ENZYME
-      def enzymes
-        unless @data['ENZYME']
-          field = fetch('ENZYME')
-          if /\(/.match(field)	# old version
-            @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
-          else
-            @data['ENZYME'] = field.scan(/\S+/)
-          end
-        end
-        @data['ENZYME']
-      end
+  # PATHWAY
+  def pathways
+    lines_fetch('PATHWAY') 
+  end
 
-      # DBLINKS
-      def dblinks
-        lines_fetch('DBLINKS')
+  # ENZYME
+  def enzymes
+    unless @data['ENZYME']
+      field = fetch('ENZYME')
+      if /\(/.match(field)	# old version
+        @data['ENZYME'] = field.scan(/\S+ \(\S+\)/)
+      else
+        @data['ENZYME'] = field.scan(/\S+/)
       end
+    end
+    @data['ENZYME']
+  end
 
-      # ATOM, BOND
-      def kcf
-        return "#{get('ATOM')}#{get('BOND')}"
-      end
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
 
-    end
+  # ATOM, BOND
+  def kcf
+    return "#{get('ATOM')}#{get('BOND')}"
+  end
 
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
   end
 
-end
+end # COMPOUND
+
+end # KEGG
+end # Bio
 
 
 if __FILE__ == $0

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

@@ -0,0 +1,98 @@
+#
+# = bio/db/kegg/drug.rb - KEGG DRUG database class
+#
+# Copyright::  Copyright (C) 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
+#
+# $Id: drug.rb,v 1.3 2007/06/28 11:27:24 k Exp $
+#
+
+require 'bio/db'
+
+module Bio
+class KEGG
+
+class DRUG < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  def entry_id
+    field_fetch('ENTRY')[/\S+/]
+  end
+
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
+
+  def name
+    names.first
+  end
+
+  # FORMULA
+  def formula
+    field_fetch('FORMULA')
+  end
+
+  # MASS
+  def mass
+    field_fetch('MASS').to_f
+  end
+
+  # ACTIVITY
+  def activity
+    field_fetch('ACTIVITY')
+  end
+
+  # REMARK
+  def remark
+    field_fetch('REMARK')
+  end
+
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
+  end
+
+  # PATHWAY
+  def pathways
+    lines_fetch('DBLINKS')
+  end
+
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
+
+  # ATOM, BOND
+  def kcf
+    return "#{get('ATOM')}#{get('BOND')}"
+  end
+
+end # DRUG
+
+end # KEGG
+end # Bio
+
+
+if __FILE__ == $0
+  entry = ARGF.read	# dr:D00001
+  dr = Bio::KEGG::DRUG.new(entry)
+  p dr.entry_id
+  p dr.names
+  p dr.name
+  p dr.formula
+  p dr.mass
+  p dr.activity
+  p dr.remark
+  p dr.comment
+  p dr.dblinks
+  p dr.kcf
+end
+

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

@@ -1,125 +1,148 @@
 #
-# bio/db/kegg/enzyme.rb - KEGG/ENZYME database class
+# = bio/db/kegg/enzyme.rb - KEGG/ENZYME database class
 #
-#   Copyright (C) 2001, 2002 KATAYAMA Toshiaki <k@bioruby.org>
+# Copyright::  Copyright (C) 2001, 2002, 2007 Toshiaki Katayama <k@bioruby.org>
+# License::    The Ruby License
 #
-#  This library is free software; you can redistribute it and/or
-#  modify it under the terms of the GNU Lesser General Public
-#  License as published by the Free Software Foundation; either
-#  version 2 of the License, or (at your option) any later version.
-#
-#  This library is distributed in the hope that it will be useful,
-#  but WITHOUT ANY WARRANTY; without even the implied warranty of
-#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-#  Lesser General Public License for more details.
-#
-#  You should have received a copy of the GNU Lesser General Public
-#  License along with this library; if not, write to the Free Software
-#  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307  USA
-#
-#  $Id: enzyme.rb,v 0.8 2005/09/08 01:22:11 k Exp $
+# $Id: enzyme.rb,v 0.11 2007/04/05 23:35:41 trevor Exp $
 #
 
 require 'bio/db'
 
 module Bio
+class KEGG
+
+class ENZYME < KEGGDB
+
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
+
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
+
+  # ENTRY
+  def entry
+    field_fetch('ENTRY')
+  end
+
+  def entry_id
+    entry[/EC (\S+)/, 1]
+  end
+
+  def obsolete?
+    entry[/Obsolete/] ? true : false
+  end
 
-  class KEGG
-
-    class ENZYME < KEGGDB
-
-      DELIMITER	= RS = "\n///\n"
-      TAGSIZE	= 12
-
-      def initialize(entry)
-        super(entry, TAGSIZE)
-      end
-
-      # ENTRY
-      def entry_id
-        field_fetch('ENTRY')
-      end
-
-      # NAME
-      def names
-        lines_fetch('NAME')
-      end
-      def name
-        names[0]
-      end
-
-      # CLASS
-      def classes
-        lines_fetch('CLASS')
-      end
-
-      # SYSNAME
-      def sysname
-        field_fetch('SYSNAME')
-      end
-
-      # REACTION ';'
-      def reaction
-        field_fetch('REACTION')
-      end
-      
-      # SUBSTRATE
-      def substrates
-        lines_fetch('SUBSTRATE')
-      end
-
-      # PRODUCT
-      def products
-        lines_fetch('PRODUCT')
-      end
-
-      # COFACTOR
-      def cofactors
-        lines_fetch('COFACTOR')
-      end
-
-      # COMMENT
-      def comment
-        field_fetch('COMMENT')
-      end
-
-      # PATHWAY
-      def pathways
-        lines_fetch('PATHWAY')
-      end
-
-      # GENES
-      def genes
-        lines_fetch('GENES')
-      end
-
-      # DISEASE
-      def diseases
-        lines_fetch('DISEASE')
-      end
-
-      # MOTIF
-      def motifs
-        lines_fetch('MOTIF')
-      end
-
-      # STRUCTURES
-      def structures
-        unless @data['STRUCTURES']
-          @data['STRUCTURES'] =
-            fetch('STRUCTURES').sub(/(PDB: )*/,'').split(/\s+/)
-        end
-        @data['STRUCTURES']
-      end
-
-      # DBLINKS
-      def dblinks
-        lines_fetch('DBLINKS')
-      end
+  # NAME
+  def names
+    field_fetch('NAME').split(/\s*;\s*/)
+  end
+
+  def name
+    names.first
+  end
+
+  # CLASS
+  def classes
+    lines_fetch('CLASS')
+  end
+
+  # SYSNAME
+  def sysname
+    field_fetch('SYSNAME')
+  end
+
+  # REACTION
+  def reaction
+    field_fetch('REACTION')
+  end
+
+  # ALL_REAC ';'
+  def all_reac
+    field_fetch('ALL_REAC')
+  end
+
+  def iubmb_reactions
+    all_reac.sub(/;\s*\(other\).*/, '').split(/\s*;\s*/)
+  end
 
+  def kegg_reactions
+    reac = all_reac
+    if reac[/\(other\)/]
+      reac.sub(/.*\(other\)\s*/, '').split(/\s*;\s*/)
+    else
+      []
     end
+  end
+  
+  # SUBSTRATE
+  def substrates
+    field_fetch('SUBSTRATE').split(/\s*;\s*/)
+  end
+
+  # PRODUCT
+  def products
+    field_fetch('PRODUCT').split(/\s*;\s*/)
+  end
 
+  # INHIBITOR
+  def inhibitors
+    field_fetch('INHIBITOR').split(/\s*;\s*/)
   end
 
-end
+  # COFACTOR
+  def cofactors
+    field_fetch('COFACTOR').split(/\s*;\s*/)
+  end
+
+  # COMMENT
+  def comment
+    field_fetch('COMMENT')
+  end
+
+  # PATHWAY
+  def pathways
+    lines_fetch('PATHWAY')
+  end
+
+  # ORTHOLOG
+  def orthologs
+    lines_fetch('ORTHOLOG')
+  end
+
+  # GENES
+  def genes
+    lines_fetch('GENES')
+  end
+
+  # DISEASE
+  def diseases
+    lines_fetch('DISEASE')
+  end
+
+  # MOTIF
+  def motifs
+    lines_fetch('MOTIF')
+  end
+
+  # STRUCTURES
+  def structures
+    unless @data['STRUCTURES']
+      @data['STRUCTURES'] = fetch('STRUCTURES').sub(/(PDB: )*/,'').split(/\s+/)
+    end
+    @data['STRUCTURES']
+  end
+
+  # REFERENCE
+
+  # DBLINKS
+  def dblinks
+    lines_fetch('DBLINKS')
+  end
+
+end # ENZYME
+
+end # KEGG
+end # Bio