bio 0.7.1 → 1.0.0

data/lib/bio/db/medline.rb

@@ -1,7 +1,26 @@
 #
-# bio/db/medline.rb - NCBI PubMed/MEDLINE database class
+# = bio/db/medline.rb - NCBI PubMed/MEDLINE database class
 #
-#   Copyright (C) 2001, 2005 KATAYAMA Toshiaki <k@bioruby.org>
+# Copyright::  Copyright (C) 2001, 2005
+#              KATAYAMA Toshiaki <k@bioruby.org>
+# License::    LGPL
+#
+# == Description
+#
+# NCBI PubMed/MEDLINE database class.
+#
+# == Examples
+#
+#   medline = Bio::MEDLINE.new(txt)
+#   medline.reference
+#   medline.pmid == medline.entry_id
+#   medilne.mesh
+#
+# == References
+#
+# $Id: medline.rb,v 1.13 2006/02/18 15:03:47 nakao Exp $
+#
+#++
 #
 #  This library is free software; you can redistribute it and/or
 #  modify it under the terms of the GNU Lesser General Public
@@ -17,15 +36,17 @@
 #  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: medline.rb,v 1.12 2005/09/08 01:22:11 k Exp $
+#--
 #
 
 require 'bio/db'
 
 module Bio
 
+  # NCBI PubMed/MEDLINE database class.
   class MEDLINE < NCBIDB
 
+    # 
     def initialize(entry)
       @pubmed = Hash.new('')
 
@@ -39,7 +60,7 @@ module Bio
     end
 
 
-    # Reference object
+    # returns a Reference object.
     def reference
       hash = Hash.new('')
 

data/lib/bio/db/nbrf.rb

@@ -1,27 +1,11 @@
 #
 # = bio/db/nbrf.rb - NBRF/PIR format sequence data class
 #
-# Copyright:: Copyright (C) 2001-2003 GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+# Copyright:: Copyright (C) 2001-2003,2006 Naohisa Goto <ng@bioruby.org>
 #             Copyright (C) 2001-2002 KATAYAMA Toshiaki <k@bioruby.org>
-# License::   LGPL
+# License::   Ruby's
 #
-#--
-#  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: nbrf.rb,v 1.7 2005/12/18 15:58:41 k Exp $
+#  $Id: nbrf.rb,v 1.8 2006/02/22 08:43:15 ngoto Exp $
 #
 # Sequence data class for NBRF/PIR flatfile format.
 #
@@ -44,7 +28,15 @@ module Bio
     #++
 
     # Delimiter of each entry. Bio::FlatFile uses it.
-    DELIMITER	= RS = "*\n"
+    DELIMITER	= RS = "\n>"
+
+    # (Integer) excess read size included in DELIMITER.
+    DELIMITER_OVERRUN = 1 # '>'
+
+    #--
+    # Note: DELIMITER is changed due to the change of Bio::FlatFile.
+    # DELIMITER	= RS = "*\n"
+    #++
 
     # Creates a new NBRF object. It stores the comment and sequence
     # information from one entry of the NBRF/PIR format string.

data/lib/bio/db/pdb.rb

@@ -17,7 +17,7 @@
 #  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: pdb.rb,v 1.5 2005/12/16 19:23:03 ngoto Exp $
+#  $Id: pdb.rb,v 1.6 2006/01/29 06:54:13 ngoto Exp $
 #
 
 require 'bio/db'
@@ -25,6 +25,9 @@ require 'bio/db'
 # definition of the PDB class
 module Bio
   class PDB #< DB
+
+    autoload :ChemicalComponent, 'bio/db/pdb/chemicalcomponent'
+
   end #class PDB
 end #module Bio
 

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

@@ -0,0 +1,240 @@
+#
+# = bio/db/pdb/chemicalcomponent.rb - PDB Chemical Component Dictionary parser
+#
+# Copyright:: Copyright (C) 2006
+#             GOTO Naohisa <ngoto@gen-info.osaka-u.ac.jp>
+# License:: LGPL
+#
+#  $Id: chemicalcomponent.rb,v 1.1 2006/01/29 06:54:13 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
+#  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
+#++
+#
+# = About Bio::PDB::ChemicalComponent
+#
+# Please refer Bio::PDB::ChemicalComponent.
+#
+# = References
+#
+# * ((<URL:http://deposit.pdb.org/cc_dict_tut.html>))
+# * http://deposit.pdb.org/het_dictionary.txt
+#
+
+require 'bio/db/pdb/pdb'
+
+module Bio
+  class PDB
+
+    # Bio::PDB::ChemicalComponet is a parser for a entry of
+    # the PDB Chemical Component Dictionary.
+    # 
+    # The PDB Chemical Component Dictionary is available in
+    # http://deposit.pdb.org/het_dictionary.txt
+    class ChemicalComponent
+
+      # delimiter for reading via Bio::FlatFile
+      DELIMITER = RS = "\n\n"
+
+      # Single field (normally single line) of a entry
+      class Record < Bio::PDB::Record
+
+        # fetches record name
+        def fetch_record_name(str)
+          str[0..6].strip
+        end
+        private :fetch_record_name
+
+        # fetches record name
+        def self.fetch_record_name(str)
+          str[0..6].strip
+        end
+        private_class_method :fetch_record_name
+
+        # RESIDUE field.
+        # It would be wrong because the definition described in documents
+        # seems ambiguous.
+        RESIDUE =
+          def_rec([ 11, 13, Pdb_LString[3], :hetID ],
+                  [ 16, 20, Pdb_Integer,    :numHetAtoms ]
+                  )
+
+        # CONECT field
+        # It would be wrong because the definition described in documents
+        # seems ambiguous.
+        CONECT =
+          def_rec([ 12, 15, Pdb_Atom,         :name ],
+                  [ 19, 20, Pdb_Integer,      :num ],
+                  [ 21, 24, Pdb_Atom,         :other_atoms ],
+                  [ 26, 29, Pdb_Atom,         :other_atoms ],
+                  [ 31, 34, Pdb_Atom,         :other_atoms ],
+                  [ 36, 39, Pdb_Atom,         :other_atoms ],
+                  [ 41, 44, Pdb_Atom,         :other_atoms ],
+                  [ 46, 49, Pdb_Atom,         :other_atoms ],
+                  [ 51, 54, Pdb_Atom,         :other_atoms ],
+                  [ 56, 59, Pdb_Atom,         :other_atoms ],
+                  [ 61, 64, Pdb_Atom,         :other_atoms ],
+                  [ 66, 69, Pdb_Atom,         :other_atoms ],
+                  [ 71, 74, Pdb_Atom,         :other_atoms ],
+                  [ 76, 79, Pdb_Atom,         :other_atoms ]
+                  )
+
+        # HET field.
+        # It is the same as Bio::PDB::Record::HET.
+        HET    = Bio::PDB::Record::HET
+
+        #--
+        #HETSYN = Bio::PDB::Record::HETSYN
+        #++
+
+        # HETSYN field.
+        # It is very similar to Bio::PDB::Record::HETSYN.
+        HETSYN = 
+            def_rec([  9, 10, Pdb_Continuation, nil ],
+                    [ 12, 14, Pdb_LString(3),   :hetID ],
+                    [ 16, 70, Pdb_String,       :hetSynonyms ]
+                    )
+
+        # HETNAM field.
+        # It is the same as Bio::PDB::Record::HETNAM.
+        HETNAM = Bio::PDB::Record::HETNAM
+
+        # FORMUL field.
+        # It is the same as Bio::PDB::Record::FORMUL.
+        FORMUL = Bio::PDB::Record::FORMUL
+
+        # default definition for unknown fields.
+        Default = Bio::PDB::Record::Default
+
+        # Hash to store allowed definitions.
+        Definition = create_definition_hash
+
+        # END record class.
+        #
+        # Because END is a reserved word of Ruby, it is separately
+        # added to the hash
+        End    = Bio::PDB::Record::End
+        Definition['END'] = End
+
+        # Look up the class in Definition hash
+        def self.get_record_class(str)
+          t = fetch_record_name(str)
+          return Definition[t]
+        end
+      end #class Record
+
+      # Creates a new object.
+      def initialize(str)
+        @data = str.split(/[\r\n]+/)
+        @hash = {}
+
+        #Flag to say whether the current line is part of a continuation
+        cont = false
+        
+        #Goes through each line and replace that line with a PDB::Record
+        @data.collect! do |line|
+          #Go to next if the previous line was contiunation able, and
+          #add_continuation returns true. Line is added by add_continuation
+          next if cont and cont = cont.add_continuation(line)
+
+          #Make the new record
+          f = Record.get_record_class(line).new.initialize_from_string(line)
+          #p f
+          #Set cont
+          cont = f if f.continue?
+          #Set the hash to point to this record either by adding to an
+          #array, or on it's own
+          key = f.record_name
+          if a = @hash[key] then
+            a << f
+          else
+            @hash[key] = [ f ]
+          end
+          f
+        end #each
+        #At the end we need to add the final model
+        @data.compact!
+      end
+
+      # all records in this entry as an array.
+      attr_reader :data
+
+      # all records in this entry as an hash accessed by record names.
+      attr_reader :hash
+
+      # Identifier written in the first line "RESIDUE" record. (e.g. CMP)
+      def entry_id
+        @data[0].hetID
+      end
+
+      # Synonyms for the comical component. Returns an array of strings.
+      def hetsyn
+        unless defined? @hetsyn
+          if r = @hash["HETSYN"]
+            @hetsyn = r[0].hetSynonyms.to_s.split(/\;\s*/)
+          else
+            return []
+          end
+        end
+        @hetsyn
+      end
+      
+      # The name of the chemical component.
+      # Returns a string (or nil, if the entry is something wrong).
+      def hetnam
+        @hash["HETNAM"][0].text
+      end
+
+      # The chemical formula of the chemical component.
+      # Returns a string  (or nil, if the entry is something wrong).
+      def formul
+        @hash["FORMUL"][0].text
+      end
+
+      # Returns an hash of bindings of atoms.
+      # Note that each white spaces are stripped for atom symbols.
+      def conect
+        unless defined? @conect
+          c = {}
+          @hash["CONECT"].each do |e|
+            key = e.name.to_s.strip
+            unless key.empty?
+              val = e.other_atoms.collect { |x| x.strip }
+              #warn "Warning: #{key}: atom name conflict?" if c[key]
+              c[key] = val
+            end
+          end
+          @conect = c
+        end
+        @conect
+      end
+
+      # Gets all records whose record type is _name_.
+      # Returns an array of <code>Bio::PDB::Record::*</code> objects.
+      #
+      # if _name_ is nil, returns hash storing all record data.
+      #
+      # Example:
+      # p pdb.record('CONECT')
+      # p pdb.record['CONECT']
+      #
+      def record(name = nil)
+        name ? @hash[name] : @hash
+      end
+
+    end #class ChemicalComponent
+  end #class PDB
+end #module Bio
+

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

@@ -6,7 +6,7 @@
 #             Alex Gutteridge <alexg@ebi.ac.uk>
 # License:: LGPL
 #
-#  $Id: pdb.rb,v 1.13 2006/01/20 13:54:08 ngoto Exp $
+#  $Id: pdb.rb,v 1.15 2006/02/20 13:00:43 ngoto Exp $
 #
 #--
 #  This library is free software; you can redistribute it and/or
@@ -86,19 +86,19 @@ module Bio
 
       module Pdb_SList
         def self.new(str)
-          str.strip.split(/\;\s*/)
+          str.to_s.strip.split(/\;\s*/)
         end
       end
 
       module Pdb_List
         def self.new(str)
-          str.strip.split(/\,\s*/)
+          str.to_s.strip.split(/\,\s*/)
         end
       end
 
       module Pdb_Specification_list
         def self.new(str)
-          a = str.strip.split(/\;\s*/)
+          a = str.to_s.strip.split(/\;\s*/)
           a.collect! { |x| x.split(/\:\s*/, 2) }
           a
         end
@@ -106,7 +106,7 @@ module Bio
 
       module Pdb_String
         def self.new(str)
-          str.gsub(/\s+\z/, '')
+          str.to_s.gsub(/\s+\z/, '')
         end
 
         #Creates a new module with a string left justified to the
@@ -116,7 +116,7 @@ module Bio
           m.module_eval %Q{
             @@nn = nn
             def self.new(str)
-              str.gsub(/\s+\z/, '').ljust(@@nn)[0, @@nn]
+              str.to_s.gsub(/\s+\z/, '').ljust(@@nn)[0, @@nn]
             end
           }
           m
@@ -129,7 +129,7 @@ module Bio
           m.module_eval %Q{
             @@nn = nn
             def self.new(str)
-              str.ljust(@@nn)[0, @@nn]
+              str.to_s.ljust(@@nn)[0, @@nn]
             end
           }
           m
@@ -157,7 +157,7 @@ module Bio
 
       module Pdb_StringRJ
         def self.new(str)
-          str.gsub(/\A\s+/, '')
+          str.to_s.gsub(/\A\s+/, '')
         end
       end
 
@@ -1807,6 +1807,11 @@ module Bio
       self.record('HEADER').first.classification
     end
 
+    # Get authors in "AUTHOR".
+    def authors
+      self.record('AUTHOR').first.authorList
+    end
+
     #--
     # Bio::DB methods
     #++

data/lib/bio/db/rebase.rb

@@ -1,15 +1,99 @@
-require 'bio/reference'
-module Bio
-
 #
-# bio/db/rebase.rb - Interface for EMBOSS formatted REBASE files
+# = bio/db/rebase.rb - Interface for EMBOSS formatted REBASE files
 #
 # Copyright::  Copyright (C) 2005 Trevor Wennblom <trevor@corevx.com>
 # License::    LGPL
 #
-#  $Id: rebase.rb,v 1.2 2005/12/13 15:02:41 trevor Exp $
+#  $Id: rebase.rb,v 1.3 2006/02/27 13:22:05 k Exp $
 #
 #
+# == Synopsis
+# 
+# Bio::REBASE provides utilties for interacting with REBASE data in EMBOSS
+# format.  REBASE is the Restriction Enzyme Database, more information
+# can be found here:
+# 
+
+# * http://rebase.neb.com
+# 
+# EMBOSS formatted files located at:
+# 
+# * http://rebase.neb.com/rebase/rebase.f37.html
+# 
+# These files are the same as the "emboss_?.???" files located at:
+# 
+# * ftp://ftp.neb.com/pub/rebase/
+# 
+# To easily get started with the data you can simply type this command
+# at your shell prompt:
+# 
+#   % wget ftp://ftp.neb.com/pub/rebase/emboss*
+# 
+# 
+# == Usage
+# 
+#   require 'bio/db/rebase'
+#   require 'pp'
+# 
+#   enz = File.read('emboss_e')
+#   ref = File.read('emboss_r')
+#   sup = File.read('emboss_s')
+# 
+#   # When creating a new instance of Bio::REBASE
+#   # the contents of the enzyme file must be passed.
+#   # The references and suppiers file contents
+#   # may also be passed.
+#   rebase = Bio::REBASE.new( enz )
+#   rebase = Bio::REBASE.new( enz, ref )
+#   rebase = Bio::REBASE.new( enz, ref, sup )
+# 
+#   # The 'read' class method allows you to read in files
+#   # that are REBASE EMBOSS formatted
+#   rebase = Bio::REBASE.read( 'emboss_e' )
+#   rebase = Bio::REBASE.read( 'emboss_e', 'emboss_r' )
+#   rebase = Bio::REBASE.read( 'emboss_e', 'emboss_r', 'emboss_s' )
+# 
+#   # The data loaded may be saved in YAML format
+#   rebase.save_yaml( 'enz.yaml' )
+#   rebase.save_yaml( 'enz.yaml', 'ref.yaml' )
+#   rebase.save_yaml( 'enz.yaml', 'ref.yaml', 'sup.yaml' )
+# 
+#   # YAML formatted files can also be read with the
+#   # class method 'load_yaml'
+#   rebase = Bio::REBASE.load_yaml( 'enz.yaml' )
+#   rebase = Bio::REBASE.load_yaml( 'enz.yaml', 'ref.yaml' )
+#   rebase = Bio::REBASE.load_yaml( 'enz.yaml', 'ref.yaml', 'sup.yaml' )
+# 
+#   pp rebase.enzymes[0..4]                     # ["AarI", "AasI", "AatI", "AatII", "Acc16I"]
+#   pp rebase['AarI'].pattern                   # "CACCTGC"
+#   pp rebase['AarI'].blunt?                    # false
+#   pp rebase['AarI'].organism                  # "Arthrobacter aurescens SS2-322"
+#   pp rebase['AarI'].source                    # "A. Janulaitis"
+#   pp rebase['AarI'].primary_strand_cut1       # 11
+#   pp rebase['AarI'].primary_strand_cut2       # 0
+#   pp rebase['AarI'].complementary_strand_cut1 # 15
+#   pp rebase['AarI'].complementary_strand_cut2 # 0
+#   pp rebase['AarI'].suppliers                 # ["F"]
+#   pp rebase['AarI'].supplier_names            # ["Fermentas International Inc."]
+# 
+#   pp rebase['AarI'].isoschizomers             # Currently none stored in the references file
+#   pp rebase['AarI'].methylation               # ""
+# 
+#   pp rebase['EcoRII'].methylation             # "2(5)"
+#   pp rebase['EcoRII'].suppliers               # ["F", "J", "M", "O", "S"]
+#   pp rebase['EcoRII'].supplier_names  # ["Fermentas International Inc.", "Nippon Gene Co., Ltd.",
+#                                       # "Roche Applied Science", "Toyobo Biochemicals",
+#                                       # "Sigma Chemical Corporation"]
+# 
+#   # Number of enzymes in the database
+#   pp rebase.size                              # 673
+#   pp rebase.enzymes.size                      # 673
+# 
+#   rebase.each do |name, info|
+#     pp "#{name}:  #{info.methylation}" unless info.methylation.empty?
+#   end
+# 
+# 
 #--
 #
 #  This library is free software; you can redistribute it and/or
@@ -28,104 +112,15 @@ module Bio
 #
 #++
 #
-#
-
-=begin rdoc
-bio/db/rebase.rb - Interface for EMBOSS formatted REBASE files
-
-== Synopsis
-
-Bio::REBASE provides utilties for interacting with REBASE data in EMBOSS
-format.  REBASE is the Restriction Enzyme Database, more information
-can be found here:
-* http://rebase.neb.com
-
-EMBOSS formatted files located at:
-* http://rebase.neb.com/rebase/rebase.f37.html
-
-These files are the same as the "emboss_?.???" files located at:
-* ftp://ftp.neb.com/pub/rebase/
-
-To easily get started with the data you can simply type this command at your shell prompt:
-  wget ftp://ftp.neb.com/pub/rebase/emboss*
-
-
-== Usage
-
-  require 'bio/db/rebase'
-  require 'pp'
-
-  enz = File.read('emboss_e')
-  ref = File.read('emboss_r')
-  sup = File.read('emboss_s')
-
-  # When creating a new instance of Bio::REBASE
-  # the contents of the enzyme file must be passed.
-  # The references and suppiers file contents
-  # may also be passed.
-  rebase = Bio::REBASE.new( enz )
-  rebase = Bio::REBASE.new( enz, ref )
-  rebase = Bio::REBASE.new( enz, ref, sup )
-
-  # The 'read' class method allows you to read in files
-  # that are REBASE EMBOSS formatted
-  rebase = Bio::REBASE.read( 'emboss_e' )
-  rebase = Bio::REBASE.read( 'emboss_e', 'emboss_r' )
-  rebase = Bio::REBASE.read( 'emboss_e', 'emboss_r', 'emboss_s' )
-
-  # The data loaded may be saved in YAML format
-  rebase.save_yaml( 'enz.yaml' )
-  rebase.save_yaml( 'enz.yaml', 'ref.yaml' )
-  rebase.save_yaml( 'enz.yaml', 'ref.yaml', 'sup.yaml' )
-
-  # YAML formatted files can also be read with the
-  # class method 'load_yaml'
-  rebase = Bio::REBASE.load_yaml( 'enz.yaml' )
-  rebase = Bio::REBASE.load_yaml( 'enz.yaml', 'ref.yaml' )
-  rebase = Bio::REBASE.load_yaml( 'enz.yaml', 'ref.yaml', 'sup.yaml' )
-
-  pp rebase.enzymes[0..4]                     # ["AarI", "AasI", "AatI", "AatII", "Acc16I"]
-  pp rebase['AarI'].pattern                   # "CACCTGC"
-  pp rebase['AarI'].blunt?                    # false
-  pp rebase['AarI'].organism                  # "Arthrobacter aurescens SS2-322"
-  pp rebase['AarI'].source                    # "A. Janulaitis"
-  pp rebase['AarI'].primary_strand_cut1       # 11
-  pp rebase['AarI'].primary_strand_cut2       # 0
-  pp rebase['AarI'].complementary_strand_cut1 # 15
-  pp rebase['AarI'].complementary_strand_cut2 # 0
-  pp rebase['AarI'].suppliers                 # ["F"]
-  pp rebase['AarI'].supplier_names            # ["Fermentas International Inc."]
-
-  pp rebase['AarI'].isoschizomers             # Currently none stored in the references file
-  pp rebase['AarI'].methylation               # ""
-
-  pp rebase['EcoRII'].methylation             # "2(5)"
-  pp rebase['EcoRII'].suppliers               # ["F", "J", "M", "O", "S"]
-  pp rebase['EcoRII'].supplier_names  # ["Fermentas International Inc.", "Nippon Gene Co., Ltd.",
-                                      # "Roche Applied Science", "Toyobo Biochemicals",
-                                      # "Sigma Chemical Corporation"]
-
-  # Number of enzymes in the database
-  pp rebase.size                              # 673
-  pp rebase.enzymes.size                      # 673
-
-  rebase.each do |name, info|
-    pp "#{name}:  #{info.methylation}" unless info.methylation.empty?
-  end
-
 
-== Author
-Trevor Wennblom <trevor@corevx.com>
+autoload :YAML, 'yaml'
 
+module Bio
 
-== Copyright
-Copyright (C) 2005 Trevor Wennblom
-Licensed under the same terms as BioRuby.
+  autoload :Reference, 'reference'
 
-=end
 
 class REBASE
-  autoload(:YAML, 'yaml')
 
   class DynamicMethod_Hash < Hash
     # Define a writer or reader
@@ -414,4 +409,5 @@ class REBASE
   end
 
 end # REBASE
+
 end # Bio