bio 1.0.0 → 1.1.0

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

@@ -4,27 +4,9 @@
 # Copyright::	Copyright (C) 2001-2003, 2005
 #		Shuichi Kawashima <shuichi@hgc.jp>,
 #		Toshiaki Katayama <k@bioruby.org>
-# License::	LGPL
+# License::	The Ruby License
 #
-# $Id: expression.rb,v 1.9 2005/11/05 08:27:26 k 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
-#
-#++
+# $Id: expression.rb,v 1.11 2007/04/05 23:35:41 trevor Exp $
 #
 
 require "bio/db"

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

@@ -1,293 +1,263 @@
 #
-# bio/db/kegg/genes.rb - KEGG/GENES database class
+# = bio/db/kegg/genes.rb - KEGG/GENES database class
 #
-#   Copyright (C) 2001, 2002 KATAYAMA Toshiaki <k@bioruby.org>
+# Copyright::   Copyright (C) 2001, 2002, 2006
+#               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.
+# $Id: genes.rb,v 0.25 2007/04/05 23:35:41 trevor Exp $
 #
-#  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
+# == KEGG GENES parser
 #
-#  $Id: genes.rb,v 0.22 2005/11/09 12:30:07 k Exp $
+# See http://www.genome.jp/kegg/genes.html
 #
-
-require 'bio/db'
+#
+# === Examples
+# 
+#  require 'bio/io/fetch'
+#  entry_string = Bio::Fetch.query('genes', 'b0002')
+# 
+#  entry = Bio::KEGG::GENES.new(entry_string)
+# 
+#  # ENTRY
+#  p entry.entry       # => Hash
+#
+#  p entry.entry_id    # => String
+#  p entry.division    # => String
+#  p entry.organism    # => String
+# 
+#  # NAME
+#  p entry.name        # => String
+#  p entry.genes       # => Array
+#  p entry.gene        # => String
+# 
+#  # DEFINITION
+#  p entry.definition  # => String
+#  p entry.eclinks     # => Array
+# 
+#  # PATHWAY
+#  p entry.pathway     # => String
+#  p entry.pathways    # => Array
+# 
+#  # POSITION
+#  p entry.position    # => String
+#  p entry.chromosome  # => String
+#  p entry.gbposition  # => String
+#  p entry.locations   # => Bio::Locations
+#
+#  # MOTIF
+#  p entry.motif       # => Hash of Array
+#
+#  # DBLINKS
+#  p entry.dblinks     # => Hash of Array
+# 
+#  # CODON_USAGE
+#  p entry.codon_usage # => Hash
+#  p entry.cu_list     # => Array
+# 
+#  # AASEQ
+#  p entry.aaseq       # => Bio::Sequence::AA
+#  p entry.aalen       # => Fixnum
+# 
+#  # NTSEQ
+#  p entry.ntseq       # => Bio::Sequence::NA
+#  p entry.naseq       # => Bio::Sequence::NA
+#  p entry.ntlen       # => Fixnum
+#  p entry.nalen       # => Fixnum
+# 
 
 module Bio
 
-  class KEGG
+  autoload :KEGGDB,    'bio/db'
+  autoload :Locations, 'bio/location'
+  autoload :Sequence,  'bio/sequence'
 
-    class GENES < KEGGDB
+class KEGG
 
-      DELIMITER	= RS = "\n///\n"
-      TAGSIZE	= 12
+class GENES < KEGGDB
 
-      def initialize(entry)
-        super(entry, TAGSIZE)
-      end
+  DELIMITER	= RS = "\n///\n"
+  TAGSIZE	= 12
 
+  def initialize(entry)
+    super(entry, TAGSIZE)
+  end
 
-      def entry
-        unless @data['ENTRY']
-          hash = Hash.new('')
-          if get('ENTRY').length > 30
-            e = get('ENTRY')
-            hash['id']       = e[12..29].strip
-            hash['division'] = e[30..39].strip
-            hash['organism'] = e[40..80].strip
-          end
-          @data['ENTRY'] = hash
-        end
-        @data['ENTRY']
-      end
 
-      def entry_id
-        entry['id']
+  def entry
+    unless @data['ENTRY']
+      hash = Hash.new('')
+      if get('ENTRY').length > 30
+        e = get('ENTRY')
+        hash['id']       = e[12..29].strip
+        hash['division'] = e[30..39].strip
+        hash['organism'] = e[40..80].strip
       end
+      @data['ENTRY'] = hash
+    end
+    @data['ENTRY']
+  end
 
-      def division
-        entry['division']			# CDS, tRNA etc.
-      end
+  def entry_id
+    entry['id']
+  end
 
-      def organism
-        entry['organism']			# H.sapiens etc.
-      end
+  def division
+    entry['division']			# CDS, tRNA etc.
+  end
 
-      def name
-        field_fetch('NAME')
-      end
+  def organism
+    entry['organism']			# H.sapiens etc.
+  end
 
-      def genes
-        name.split(', ')
-      end
+  def name
+    field_fetch('NAME')
+  end
 
-      def gene
-        genes.first
-      end
+  def genes
+    name.split(', ')
+  end
 
-      def definition
-        field_fetch('DEFINITION')
-      end
+  def gene
+    genes.first
+  end
 
-      def eclinks
-#       definition.slice(/\[EC:(.*?)\]/, 1)	# ruby >= 1.7
-#       definition.scan(/\[EC:(.*?)\]/).flatten
-        if /\[EC:(.*?)\]/.match(definition)
-          $1.split(/\s+/)
-        else
-          []
-        end
-      end
+  def definition
+    field_fetch('DEFINITION')
+  end
 
-      def splinks
-#       definition.slice(/\[SP:(.*?)\]/, 1)	# ruby >= 1.7
-#       definition.scan(/\[SP:(.*?)\]/).flatten
-        if /\[SP:(.*?)\]/.match(definition)
-          $1.split(/\s+/)
-        else
-          []
-        end
-      end
+  def eclinks
+    ec_list = definition.slice(/\[EC:(.*?)\]/, 1)
+    if ec_list
+      ec_list.strip.split(/\s+/)
+    else
+      []
+    end
+  end
 
-      def keggclass
-        field_fetch('CLASS')
-      end
+  def orthologs
+    lines_fetch('ORTHOLOG')
+  end
 
-      def pathways
-        keggclass.scan(/\[PATH:(.*?)\]/).flatten
-      end
+  def pathway
+    field_fetch('PATHWAY')
+  end
 
-      def position
-        unless @data['POSITION']
-          @data['POSITION'] = fetch('POSITION').gsub(/\s/, '')
-        end
-        @data['POSITION']
-      end
+  def pathways
+    pathway.scan(/\[PATH:(.*?)\]/).flatten
+  end
 
-      def gbposition
-        position.sub(/.*?:/, '')
-      end
+  def position
+    unless @data['POSITION']
+      @data['POSITION'] = fetch('POSITION').gsub(/\s/, '')
+    end
+    @data['POSITION']
+  end
 
-      def chromosome
-        if position =~ /:/
-          position.sub(/:.*/, '')
-        else
-          nil
-        end
-      end
+  def chromosome
+    if position[/:/]
+      position.sub(/:.*/, '')
+    elsif ! position[/\.\./]
+      position
+    else
+      nil
+    end
+  end
 
-      def dblinks
-        unless @data['DBLINKS']
-          hash = {}
-          get('DBLINKS').scan(/(\S+):\s*(.*)\n?/).each do |db, str|
-            id_array = str.strip.split(/\s+/)
-            hash[db] = id_array
-          end
-          @data['DBLINKS'] = hash
-        end
-        @data['DBLINKS']		# Hash of Array of DB IDs in DBLINKS
-      end
+  def gbposition
+    position.sub(/.*?:/, '')
+  end
 
-      def codon_usage(codon = nil)
-        unless @data['CODON_USAGE']
-          ary = []
-          get('CODON_USAGE').sub(/.*/,'').each_line do |line|	# cut 1st line
-            line.chomp.sub(/^.{11}/, '').scan(/..../) do |cu|
-              ary.push(cu.to_i)
-            end
-          end
-          @data['CODON_USAGE'] = ary
-        end
+  def locations
+    Bio::Locations.new(gbposition)
+  end
 
-        if codon
-          h = { 't' => 0, 'c' => 1, 'a' => 2, 'g' => 3 }
-          x, y, z = codon.downcase.scan(/\w/)
-          codon_num = h[x] * 16 + h[y] * 4 + h[z]
-          @data['CODON_USAGE'][codon_num]	# CODON_USAGE of the codon
+  def motif
+    unless @data['MOTIF']
+      hash = {}
+      db = nil
+      lines_fetch('MOTIF').each do |line|
+        if line[/^\S+:/]
+          db, str = line.split(/:/)
         else
-          return @data['CODON_USAGE']	# Array of CODON_USAGE (default)
+          str = line
         end
+        hash[db] ||= []
+        hash[db] += str.strip.split(/\s+/)
       end
+      @data['MOTIF'] = hash
+    end
+    @data['MOTIF']		# Hash of Array of IDs in MOTIF
+  end
 
-      def cu
-        hash = Hash.new
-        list = codon_usage
-        base = %w(t c a g)
-        base.each_with_index do |x, i|
-          base.each_with_index do |y, j|
-            base.each_with_index do |z, k|
-              hash["#{x}#{y}#{z}"] = list[i*16 + j*4 + k]
-            end
-          end
-        end
-        return hash
-      end
-
-      def aaseq
-        unless @data['AASEQ']
-          @data['AASEQ'] = Sequence::AA.new(fetch('AASEQ').gsub(/[\s\d\/]+/, ''))
-        end
-        @data['AASEQ']
-      end
-
-      def aalen
-        @data['AALEN'] = aaseq.length
+  def dblinks
+    unless @data['DBLINKS']
+      hash = {}
+      get('DBLINKS').scan(/(\S+):\s*(.*)\n?/).each do |db, str|
+        id_array = str.strip.split(/\s+/)
+        hash[db] = id_array
       end
+      @data['DBLINKS'] = hash
+    end
+    @data['DBLINKS']		# Hash of Array of IDs in DBLINKS
+  end
 
-      def ntseq
-        unless @data['NTSEQ']
-          @data['NTSEQ'] = Sequence::NA.new(fetch('NTSEQ').gsub(/[\s\d\/]+/, ''))
+  def codon_usage(codon = nil)
+    unless @data['CODON_USAGE']
+      hash = Hash.new
+      list = cu_list
+      base = %w(t c a g)
+      base.each_with_index do |x, i|
+        base.each_with_index do |y, j|
+          base.each_with_index do |z, k|
+            hash["#{x}#{y}#{z}"] = list[i*16 + j*4 + k]
+          end
         end
-        @data['NTSEQ']
       end
-      alias naseq ntseq
+      @data['CODON_USAGE'] = hash
+    end
+    @data['CODON_USAGE']
+  end
 
-      def ntlen
-        @data['NTLEN'] = ntseq.length
+  def cu_list
+    ary = []
+    get('CODON_USAGE').sub(/.*/,'').each_line do |line|	# cut 1st line
+      line.chomp.sub(/^.{11}/, '').scan(/..../) do |cu|
+        ary.push(cu.to_i)
       end
-      alias nalen ntlen
-
     end
-
+    return ary
   end
 
-end
-
-
-
-if __FILE__ == $0
+  def aaseq
+    unless @data['AASEQ']
+      @data['AASEQ'] = Bio::Sequence::AA.new(fetch('AASEQ').gsub(/\d+/, ''))
+    end
+    @data['AASEQ']
+  end
 
-  require 'bio/io/fetch'
+  def aalen
+    fetch('AASEQ')[/\d+/].to_i
+  end
 
-  e = Bio::Fetch.query('genes', 'b0002')
-  g = Bio::KEGG::GENES.new(e)
+  def ntseq
+    unless @data['NTSEQ']
+      @data['NTSEQ'] = Bio::Sequence::NA.new(fetch('NTSEQ').gsub(/\d+/, ''))
+    end
+    @data['NTSEQ']
+  end
+  alias naseq ntseq
 
-  p g.entry
-  p g.entry_id
-  p g.division
-  p g.name
-  p g.gene
-  p g.definition
-  p g.keggclass
-  p g.position
-  p g.dblinks
-  p g.codon_usage
-  p g.cu
-  p g.aaseq
-  p g.aalen
-  p g.naseq
-  p g.nalen
-  p g.eclinks
-  p g.splinks
-  p g.pathways
+  def ntlen
+    fetch('NTSEQ')[/\d+/].to_i
+  end
+  alias nalen ntlen
 
 end
 
+end # KEGG
+end # Bio
 
-=begin
-
-= Bio::KEGG::GENES
-
-=== Initialize
-
---- Bio::KEGG::GENES.new
-
-=== ENTRY
-
---- Bio::KEGG::GENES#entry -> Hash
---- Bio::KEGG::GENES#entry_id -> String
---- Bio::KEGG::GENES#division -> String
---- Bio::KEGG::GENES#organism -> String
-
-=== NAME
-
---- Bio::KEGG::GENES#name -> String
---- Bio::KEGG::GENES#genes -> Array
---- Bio::KEGG::GENES#gene -> String
-
-=== DEFINITION
-
---- Bio::KEGG::GENES#definition -> String
---- Bio::KEGG::GENES#eclinks -> Array
---- Bio::KEGG::GENES#splinks -> Array
-
-=== CLASS
-
---- Bio::KEGG::GENES#keggclass -> String
---- Bio::KEGG::GENES#pathways -> Array
-
-=== POSITION
-
---- Bio::KEGG::GENES#position -> String
-
-=== DBLINKS
-
---- Bio::KEGG::GENES#dblinks -> Hash
-
-=== CODON_USAGE
-
---- Bio::KEGG::GENES#codon_usage(codon = nil) -> Array or Fixnum
---- Bio::KEGG::GENES#cu -> Hash
-
-=== AASEQ
-
---- Bio::KEGG::GENES#aaseq -> Bio::Sequence::AA
---- Bio::KEGG::GENES#aalen -> Fixnum
-
-=== NTSEQ
 
---- Bio::KEGG::GENES#ntseq -> Bio::Sequence::NA
---- Bio::KEGG::GENES#naseq -> Bio::Sequence::NA
---- Bio::KEGG::GENES#ntlen -> Fixnum
---- Bio::KEGG::GENES#nalen -> Fixnum
 
-=end