bio 0.7.0 → 0.7.1

data/doc/Changes-0.7.rd

@@ -5,22 +5,22 @@ is released.
 
 --- Ruby 1.6 series are no longer supported.
 
-We use autoload functionality and many other libraries bundled in
-Ruby 1.8.2 (such as SOAP, open-uri, pp etc.) by default.
+We use autoload functionality and many standard (bundled) libraries
+(such as SOAP, open-uri, pp etc.) only in Ruby >1.8.2.
 
 --- BioRuby will be loaded about 30 times faster than before.
 
 As we changed to use autoload instead of require, time required
 to start up the BioRuby library made surprisingly faster.
 
-Other changes (including exciting BioRuby shell etc.) made in this release
-is described in this file.
+Other changes (including newly introduced BioRuby shell etc.) made
+in this series will be described in this file.
 
 == New features
 
 --- BioRuby shell
 
-Command line user interface for the BioRuby is included.
+A new command line user interface for the BioRuby is now included.
 You can invoke the shell by
 
   % bioruby
@@ -139,13 +139,13 @@ as it was a typo.
 
 * lib/bio/db/genbank/common.rb is removed.
 
-Renamed to Bio::NCBIDB::Common for the simple autoload dependency.
+Renamed to Bio::NCBIDB::Common to make simplify the autoload dependency.
 
 --- Bio::EMBL::Common
 
 * lib/bio/db/embl/common.rb is removed.
 
-Renamed to Bio::EMBLDB::Common for the simple autoload dependency.
+Renamed to Bio::EMBLDB::Common to make simplify the autoload dependency.
 
 --- Bio::KEGG::GENES
 
@@ -188,16 +188,21 @@ instead of a Hash of a entry ID string.
 
 --- Bio::PDB
 
+In 0.7.0:
+
 * Bio::PDB::Atom is removed. Instead, please use Bio::PDB::Record::ATOM and
   Bio::PDB::Record::HETATM.
 * Bio::PDB::FieldDef is removed and Bio::PDB::Record is completely
-  changed. Now, Record is changed from hash to Struct, and
-  method_missing is no longer used.
+  changed. Now, records is changed from hash to Struct objects.
+  (Note that method_missing is no longer used.)
+* In records, "do_parse" is now automatically called.
+  Users don't need to call do_parse explicitly.
+  (0.7.0 feature: "inspect" does not call do_parse.)
+  (0.7.1 feature: "inspect" calls do_parse.)
 * In the "MODEL" record, model_serial is changed to serial.
 * In records, record_type is changed to record_name.
-* In any records, record_type is changed to record_name.
-* In most records contains real numbers, changed to return
-  float values instead of strings.
+* In most records contains real numbers, return values are changed
+  to float instead of string.
 * Pdb_AChar, Pdb_Atom, Pdb_Character, Pdb_Continuation,
   Pdb_Date, Pdb_IDcode, Pdb_Integer, Pdb_LString, Pdb_List,
   Pdb_Real, Pdb_Residue_name, Pdb_SList, Pdb_Specification_list,
@@ -205,6 +210,22 @@ instead of a Hash of a entry ID string.
   Bio::PDB::DataType.
 * There are more and more changes to be written...
 
+In 0.7.1:
+
+* Heterogens and HETATMs are completely separeted from residues and ATOMs.
+  HETATMs (Bio::PDB::Record::HETATM objects) are stored in
+  Bio::PDB::Heterogen (which inherits Bio::PDB::Residue).
+* Waters (resName=="HOH") are treated as normal heterogens.
+  Model#solvents is still available but it will be deprecated.
+* In Bio::PDB::Chain, adding "LIGAND" to the heterogen id is no longer
+  available. Instead, please use Chain#get_heterogen_by_id method.
+  In addition, Bio::{PDB|PDB::Model::PDB::Chain}#heterogens, #each_heterogen,
+  #find_heterogen, Bio::{PDB|PDB::Model::PDB::Chain::PDB::Heterogen}#hetatms,
+  #each_hetatm, #find_hetatm methods are added.
+* Bio::PDB#seqres returns Bio::Sequence::NA object if the chain seems to be
+  a nucleic acid sequence.
+* There are more and more changes to be written...
+
 === Deleted files
 
 : lib/bio/db/genbank.rb
@@ -223,7 +244,7 @@ in your code to
 
   require 'bio'
 
-and this change will also speeds up loading time if you only need
+and this change will also speeds up loading time even if you only need
 one of the sub classes under the genbank/ or embl/ directory.
 
 : lib/bio/extend.rb

data/doc/Tutorial.rd.ja

@@ -1,6 +1,6 @@
 =begin
 
-  $Id: Tutorial.rd.ja,v 1.18 2005/12/07 11:40:45 k Exp $
+  $Id: Tutorial.rd.ja,v 1.19 2006/01/16 15:23:11 k Exp $
 
   Copyright (C) 2001-2003, 2005 KATAYAMA Toshiaki <k@bioruby.org>
 
@@ -50,6 +50,18 @@ Ruby ɸ
 
 * ((<URL:http://i.loveruby.net/ja/prog/refe.html>))
 
+=== RubyGems �Υ��󥹥ȡ���
+
+RubyGems �Υڡ�������ǿ��Ǥ����������ɤ��ޤ���
+
+* ((<URL:http://rubyforge.org/projects/rubygems/>))
+
+Ÿ�����ƥ��󥹥ȡ��뤷�ޤ���
+
+  % tar zxvf rubygems-x.x.x.tar.gz
+  % cd rubygems-x.x.x
+  % ruby setup.rb
+
 === BioRuby �Υ��󥹥ȡ���
 
 BioRuby �Υ��󥹥ȡ�����ˡ�� http://bioruby.org/archive/ ����
@@ -64,9 +76,9 @@ BioPerl
   % ruby install.rb setup
   # ruby install.rb install
 
-����ˡ�RubyGems ���Ȥ���Ķ��Ǥ����
+RubyGems ���Ȥ���Ķ��Ǥ����
 
-  % gems install bio
+  % gem install bio
 
 �����ǥ��󥹥ȡ���Ǥ��ޤ���
 
@@ -2048,7 +2060,7 @@ BioFetch
       serv = reg.get_database('genbank')
       entry = serv.get_by_id('AA2CG')
 
-�⤷(4) ��Ȥ��������� seqdatabase.ini ��
+�⤷ (4) ��Ȥ��������� seqdatabase.ini ��
 
     [genbank]
     protocol=biofetch

data/lib/bio.rb

@@ -1,11 +1,11 @@
 #
 # = bio.rb - Loading all BioRuby modules
 #
-# Copyright::	Copyright (C) 2001-2005
+# Copyright::	Copyright (C) 2001-2006
 #		Toshiaki Katayama <k@bioruby.org>
 # License::	LGPL
 #
-# $Id: bio.rb,v 1.58 2005/11/28 04:57:32 k Exp $
+# $Id: bio.rb,v 1.59 2006/01/20 09:57:08 k Exp $
 #
 #--
 #
@@ -28,7 +28,7 @@
 
 module Bio
 
-  BIORUBY_VERSION = [0, 7, 0].extend(Comparable)
+  BIORUBY_VERSION = [0, 7, 1].extend(Comparable)
 
   ### Basic data types
 
@@ -78,19 +78,6 @@ module Bio
 
   ## GenBank/RefSeq/DDBJ
 
-  # module Bio
-  #   autoload :NCBIDB, 'bio/db'
-  #   class GenBank < NCBIDB
-  #     autoload :Common, 'bio/db/genbank/common'
-  #     include Bio::GenBank::Common
-
-  # module Bio
-  #   autoload :NCBIDB, 'bio/db'
-  #  end
-  #  class Bio::GenBank < Bio::NCBIDB
-  #     autoload :Common, 'bio/db/genbank/common'
-  #     include Bio::GenBank::Common
-
   autoload :GenBank,        'bio/db/genbank/genbank'
   autoload :GenPept,        'bio/db/genbank/genpept'
   autoload :RefSeq,         'bio/db/genbank/refseq'
@@ -108,7 +95,6 @@ module Bio
   autoload :UniProt,        'bio/db/embl/uniprot'
   autoload :SwissProt,      'bio/db/embl/swissprot'
 
-
   ## KEGG
 
   class KEGG
@@ -254,3 +240,4 @@ module Bio
   autoload :ColorScheme,    'bio/util/color_scheme'
 
 end
+

data/lib/bio/db.rb

@@ -5,7 +5,7 @@
 #		KATAYAMA Toshiaki <k@bioruby.org>
 # License::	LGPL
 #
-# $Id: db.rb,v 0.31 2005/12/07 11:23:51 k Exp $
+# $Id: db.rb,v 0.32 2006/01/12 08:58:27 k Exp $
 #
 # == On-demand parsing and cache
 #
@@ -210,29 +210,21 @@ class DB
   # Returns a String with successive white spaces are replaced by one
   # space and stripeed.
   def truncate(str)
-    if str
-      str.gsub(/\s+/, ' ').strip
-    else
-      ""
-    end
+    str ||= ""
+    return str.gsub(/\s+/, ' ').strip
   end
 
   # Returns a tag name of the field as a String.
   def tag_get(str)
-    if str
-      str[0,@tagsize].strip
-    else
-      ""
-    end
+    str ||= ""
+    return str[0,@tagsize].strip
   end
 
   # Returns a String of the field without a tag name.
   def tag_cut(str)
-    if str
-      str[0,@tagsize] = ''
-    else
-      ""
-    end
+    str ||= ""
+    str[0,@tagsize] = ''
+    return str
   end
 
   # Returns the content of the field as a String like the fetch method.

data/lib/bio/db/pdb/atom.rb

@@ -1,9 +1,14 @@
 #
-# bio/db/pdb/atom.rb - Coordinate and atom class for PDB
+# = bio/db/pdb/atom.rb - Coordinate class for PDB
 #
-#   Copyright (C) 2004 Alex Gutteridge <alexg@ebi.ac.uk>
-#   Copyright (C) 2004 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+# Copyright::  Copyright (C) 2004, 2006
+#              Alex Gutteridge <alexg@ebi.ac.uk>
+#              Naohisa Goto <ng@bioruby.org>
+# License:: LGPL
 #
+#  $Id: atom.rb,v 1.6 2006/01/08 12:59:04 ngoto Exp $
+#
+#--
 #  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
@@ -17,8 +22,17 @@
 #  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
+#++
+#
+# = Bio::PDB::Coordinate
+#
+# Coordinate class for PDB.
+#
+# = Compatibility Note
+#
+# From bioruby 0.7.0, the Bio::PDB::Atom class is no longer available.
+# Please use Bio::PDB::Record::ATOM and Bio::PDB::Record::HETATM instead.
 #
-#  $Id: atom.rb,v 1.5 2005/12/18 17:33:32 ngoto Exp $
 
 require 'matrix'
 require 'bio/db/pdb'
@@ -26,31 +40,50 @@ require 'bio/db/pdb'
 module Bio
   class PDB
 
+    # Bio::PDB::Coordinate is a class to store a 3D coordinate.
+    # It inherits Vector (in bundled library in Ruby).
+    #
     class Coordinate < Vector
+      # same as Vector.[x,y,z]
       def self.[](x,y,z)
         super
       end
 
+      # same as Vector.elements
       def self.elements(array, *a)
         raise 'Size of given array must be 3' if array.size != 3
         super
       end
-      
+
+      # x
       def x; self[0]; end
+      # y
       def y; self[1]; end
+      # z
       def z; self[2]; end
+      # x=(n)
       def x=(n); self[0]=n; end
+      # y=(n)
       def y=(n); self[1]=n; end
+      # z=(n)
       def z=(n); self[2]=n; end
 
+      # Implicit conversion to an array.
+      #
+      # Note that this method would be deprecated in the future.
+      #
+      #--
       # Definition of 'to_ary' means objects of the class is
       # implicitly regarded as an array.
+      #++
       def to_ary; self.to_a; end
 
+      # returns self.
       def xyz; self; end
-      
+
+      # distance between <em>object2</em>.
       def distance(object2)
-        Utils::to_xyz(object2)
+        Utils::convert_to_xyz(object2)
         (self - object2).r
       end
     end #class Coordinate

data/lib/bio/db/pdb/chain.rb

@@ -1,8 +1,14 @@
 #
-# bio/db/pdb/chain.rb - chain class for PDB
+# = bio/db/pdb/chain.rb - chain class for PDB
 #
-#   Copyright (C) 2004 Alex Gutteridge <alexg@ebi.ac.uk>
+# Copyright:: Copyright (C) 2004, 2006
+#             Alex Gutteridge <alexg@ebi.ac.uk>
+#             Naohisa Goto <ng@bioruby.org>
+# License:: LGPL
+# 
+#  $Id: chain.rb,v 1.6 2006/01/20 13:54:08 ngoto Exp $
 #
+#--
 #  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
@@ -16,8 +22,12 @@
 #  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
+#++
+#
+# = Bio::PDB::Chain
+# 
+# Please refer Bio::PDB::Chain.
 #
-#  $Id: chain.rb,v 1.2 2005/09/26 13:00:08 k Exp $
 
 require 'bio/db/pdb'
 
@@ -25,93 +35,182 @@ module Bio
 
   class PDB
 
+    # Bio::PDB::Chain is a class to store a chain.
+    #
+    # The object would contain some residues (Bio::PDB::Residue objects)
+    # and some heterogens (Bio::PDB::Heterogen objects).
+    # 
     class Chain
       
       include Utils
       include AtomFinder
       include ResidueFinder
+
+      include HetatmFinder
+      include HeterogenFinder
+
       include Enumerable
       include Comparable
-      
-      attr_reader :id, :model
-      attr_writer :id
-      
+
+      # Creates a new chain object.
       def initialize(id = nil, model = nil)
         
-        @id       = id
+        @chain_id  = id
         
         @model    = model
         
-        @residues = Array.new
-        @ligands  = Array.new
-        
+        @residues   = []
+        @residues_hash = {}
+        @heterogens = []
+        @heterogens_hash = {}
       end
+
+      # Identifier of this chain
+      attr_accessor :chain_id
+      # alias
+      alias id chain_id
+
+      # the model to which this chain belongs.
+      attr_reader :model
+
+      # residues in this chain
+      attr_reader :residues
+
+      # heterogens in this chain
+      attr_reader :heterogens
       
-      #Keyed access to residues based on ids
+      # get the residue by id
+      def get_residue_by_id(key)
+        #@residues.find { |r| r.residue_id == key }
+        @residues_hash[key]
+      end
+
+      # get the residue by id.
+      #
+      # Compatibility Note: Now, you cannot find HETATMS in this method.
+      # To add "LIGAND" to the id is no longer available.
+      # To get heterogens, you must use <code>get_heterogen_by_id</code>.
       def [](key)
-        #If you want to find HETATMS you need to add LIGAND to the id
-        if key.to_s[0,6] == 'LIGAND'
-          residue = @ligands.find{ |residue| key.to_s == residue.id }
-        else
-          residue = @residues.find{ |residue| key.to_s == residue.id }
-        end
+        get_residue_by_id(key)
+      end
+
+      # get the heterogen (ligand) by id
+      def get_heterogen_by_id(key)
+        #@heterogens.find { |r| r.residue_id == key }
+        @heterogens_hash[key]
       end
       
       #Add a residue to this chain
       def addResidue(residue)
-        raise "Expecting a Bio::PDB::Residue" if not residue.is_a? Bio::PDB::Residue
+        raise "Expecting a Bio::PDB::Residue" unless residue.is_a? Bio::PDB::Residue
         @residues.push(residue)
+        if @residues_hash[residue.residue_id] then
+          $stderr.puts "Warning: residue_id #{residue.residue_id.inspect} is already used" if $VERBOSE
+        else
+          @residues_hash[residue.residue_id] = residue
+        end
         self
       end
       
-      #Add a ligand to this chain
-      def addLigand(residue)
-        raise "Expecting a Bio::PDB::Residue" if not residue.is_a? Bio::PDB::Residue
-        @ligands.push(residue)
+      #Add a heterogen (ligand) to this chain
+      def addLigand(ligand)
+        raise "Expecting a Bio::PDB::Residue" unless ligand.is_a? Bio::PDB::Residue
+        @heterogens.push(ligand)
+        if @heterogens_hash[ligand.residue_id] then
+          $stderr.puts "Warning: heterogen_id (residue_id) #{ligand.residue_id.inspect} is already used" if $VERBOSE
+        else
+          @heterogens_hash[ligand.residue_id] = ligand
+        end
         self
       end
-      
-      #Residue iterator
-      def each
-        @residues.each{ |residue| yield residue }
+
+      # rehash residues hash
+      def rehash_residues
+        begin
+          residues_bak = @residues
+          residues_hash_bak = @residues_hash
+          @residues = []
+          @residues_hash = {}
+          residues_bak.each do |residue|
+            self.addResidue(residue)
+          end
+        rescue RuntimeError
+          @residues = residues_bak
+          @residues_hash = residues_hash_bak
+          raise
+        end
+        self
+      end
+
+      # rehash heterogens hash
+      def rehash_heterogens
+        begin
+          heterogens_bak = @heterogens
+          heterogens_hash_bak = @heterogens_hash
+          @heterogens = []
+          @heterogens_hash = {}
+          heterogens_bak.each do |heterogen|
+            self.addLigand(heterogen)
+          end
+        rescue RuntimeError
+          @heterogens = heterogens_bak
+          @heterogens_hash = heterogens_hash_bak
+          raise
+        end
+        self
+      end
+
+      # rehash residues hash and heterogens hash
+      def rehash
+        rehash_residues
+        rehash_heterogens
+      end
+
+      # Iterates over each residue
+      def each(&x) #:yields: residue
+        @residues.each(&x)
       end
       #Alias to override ResidueFinder#each_residue
       alias each_residue each
+
+      # Iterates over each hetero-compound
+      def each_heterogen(&x) #:yields: heterogen
+        @heterogens.each(&x)
+      end
       
-      #Sort based on chain id
+      # Operator aimed to sort based on chain id
       def <=>(other)
-        return @id <=> other.id
+        return @chain_id <=> other.chain_id
       end
       
-      #Stringifies each residue
+      # Stringifies each residue
       def to_s
-        string = ""
-        @residues.each{ |residue| string << residue.to_s }
-        string = string << "TER\n"
-        return string
+        @residues.join('') + "TER\n" + @heterogens.join('')
       end
 
-      def atom_seq
-        string = ""
-        last_residue_num = nil
-        @residues.each{ |residue|
-          if last_residue_num and 
-              (residue.resSeq.to_i - last_residue_num).abs > 1
-            (residue.resSeq.to_i - last_residue_num).abs.times{ string << 'X' }
-          end
-          tlc = residue.resName.capitalize
-          olc = AminoAcid.names.invert[tlc]
-          if !olc
-            olc = 'X'
+      # gets an amino acid sequence of this chain from ATOM records
+      def aaseq
+        unless defined? @aaseq
+          string = ""
+          last_residue_num = nil
+          @residues.each do |residue|
+            if last_residue_num and 
+                (x = (residue.resSeq.to_i - last_residue_num).abs) > 1 then
+              x.times { string << 'X' }
+            end
+            tlc = residue.resName.capitalize
+            olc = (Bio::AminoAcid.three2one(tlc) or 'X')
+            string << olc
           end
-          string << olc
-        }
-        Bio::Sequence::AA.new(string)
-        
+          @aaseq = Bio::Sequence::AA.new(string)
+        end
+        @aaseq
       end
+      # for backward compatibility
+      alias atom_seq aaseq
       
-    end
+    end #class Chain
 
-  end
+  end #class PDB
 
-end
+end #module Bio