bio 0.7.1 → 1.0.0

data/lib/bio/appl/spidey/report.rb

@@ -2,25 +2,9 @@
 # = bio/appl/spidey/report.rb - SPIDEY result parser
 #
 # Copyright:: Copyright (C) 2004 GOTO Naohisa <ng@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: report.rb,v 1.8 2005/12/18 15:58:41 k Exp $
+#  $Id: report.rb,v 1.9 2006/02/22 08:46:15 ngoto Exp $
 #
 # NCBI Spidey result parser.
 # Currently, output of default (-p 0 option) or -p 1 option are supported.
@@ -44,6 +28,8 @@ module Bio
   class Spidey
 
     # Spidey report parser class.
+    # Please see bio/appl/spidey/report.rb for details.
+    #
     # Its object may contain some Bio::Spidey::Report::Hit objects.
     class Report #< DB
       #--
@@ -53,6 +39,9 @@ module Bio
       # Delimiter of each entry. Bio::FlatFile uses it.
       DELIMITER = RS = "\n--SPIDEY "
 
+      # (Integer) excess read size included in DELIMITER.
+      DELIMITER_OVERRUN = 9 # "--SPIDEY ".length
+
       # Creates a new Bio::Spidey::Report object from String.
       # You can use Bio::FlatFile to read a file.
       def initialize(str)

data/lib/bio/data/na.rb

@@ -3,9 +3,9 @@
 #
 # Copyright::	Copyright (C) 2001, 2005
 #		Toshiaki Katayama <k@bioruby.org>
-# License::	LGPL
+# License::	Ruby's
 #
-# $Id: na.rb,v 0.19 2005/12/10 18:14:22 k Exp $
+# $Id: na.rb,v 0.20 2006/02/08 12:15:42 k Exp $
 #
 # == Synopsis
 #
@@ -38,24 +38,6 @@
 #   puts "# Bio::NucleicAcid.weight('atgc')"
 #   p Bio::NucleicAcid.weight('atgc')
 #
-#--
-#
-#  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
-#
-#++
-#
 
 module Bio
 
@@ -176,7 +158,7 @@ class NucleicAcid
     end
 
     def to_re(seq, rna = false)
-      str = seq.to_s
+      str = seq.to_s.downcase
       str.gsub!(/[^atgcu]/) { |base|
         NAMES[base] || '.'
       }

data/lib/bio/db.rb

@@ -3,9 +3,9 @@
 #
 # Copyright::	Copyright (C) 2001, 2002, 2005
 #		KATAYAMA Toshiaki <k@bioruby.org>
-# License::	LGPL
+# License::	Ruby's
 #
-# $Id: db.rb,v 0.32 2006/01/12 08:58:27 k Exp $
+# $Id: db.rb,v 0.34 2006/02/27 09:13:08 k Exp $
 #
 # == On-demand parsing and cache
 #
@@ -144,24 +144,6 @@
 # 
 # The name of the organism.
 # 
-#--
-#
-#  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/sequence'
 require 'bio/reference'
@@ -267,7 +249,7 @@ class NCBIDB < DB
   # Splits an entry into an Array of Strings at the level of top tags.
   def toptag2array(str)
     sep = "\001"
-    str.gsub(/\n([A-Za-z\/])/, "\n#{sep}\\1").split(sep)
+    str.gsub(/\n([A-Za-z\/\*])/, "\n#{sep}\\1").split(sep)
   end
 
   # Splits a field into an Array of Strings at the level of sub tags.

data/lib/bio/db/aaindex.rb

@@ -1,26 +1,37 @@
 #
 # = bio/db/aaindex.rb - AAindex database class
 #
-# Copyright::  Copyright (C) 2001 KAWASHIMA Shuichi <s@bioruby.org>
+# Copyright::  Copyright (C) 2001 
+#              KAWASHIMA Shuichi <s@bioruby.org>
+# Copyright::  Copyright (C) 2006
+#              Mitsuteru C. Nakao <n@bioruby.org>
 # License::    LGPL
 #
-# $Id: aaindex.rb,v 1.16 2005/12/18 15:58:41 k Exp $
+# $Id: aaindex.rb,v 1.18 2006/02/22 07:35:19 nakao Exp $
 #
 # == Description
+#
 # Classes for Amino Acid Index Database (AAindex and AAindex2).
 # * AAindex Manual: http://www.genome.jp/dbget-bin/show_man?aaindex
 #
 # == Examples
+#
+#  aax1 = Bio::AAindex.auto("PRAM900102.aaindex1")
+#  aax2 = Bio::AAindex.auto("DAYM780301.aaindex2")
+#
 #  aax1 = Bio::AAindex1.new("PRAM900102.aaindex1")
 #  aax1.entry_id
 #  aax1.index
 #
-#  aax2 = Bio::AAindex2.new("HENS920102.aaindex2")
+#  aax2 = Bio::AAindex2.new("DAYM780301.aaindex2")
 #  aax2.entry_id
 #  aax2.matrix
 #  aax2.matrix[2,2]
+#  aax2.matrix('R', 'A')
+#  aax2['R', 'A']
 #
 # == References
+#
 # * http://www.genome.jp/aaindex/
 #
 #--
@@ -47,6 +58,7 @@ require "matrix"
 
 module Bio
 
+  # Super class for AAindex1 and AAindex2
   class AAindex < KEGGDB
 
     # Delimiter
@@ -58,62 +70,117 @@ module Bio
     # Bio::DB API
     TAGSIZE = 2
 
+    # Auto detecter for two AAindex formats.
+    # returns a Bio::AAindex1 object or a Bio::AAindex2 object.
+    def self.auto(str)
+      case str
+      when /^I /m 
+        Bio::AAindex1.new(str)
+      when /^M /m
+        Bio::AAindex2.new(str)
+      else
+        raise
+      end        
+    end
 
+    # 
     def initialize(entry)
       super(entry, TAGSIZE)
     end
 
-    # Returns
+    # Returns entry_id in the H line.
     def entry_id
-      field_fetch('H')
+      if @data['entry_id']
+        @data['entry_id']
+      else
+        @data['entry_id'] = field_fetch('H')
+      end
     end
 
-    # Returns
+    # Returns definition in the D line.
     def definition
-      field_fetch('D')
+      if @data['definition']
+        @data['definition']
+      else
+        @data['definition'] = field_fetch('D')
+      end
     end
 
-    # Returns
+    # Returns database links in the R line.
+    # cf.) ['LIT:123456', 'PMID:12345678']
     def dblinks
-      field_fetch('R')
+      if @data['ref']
+        @data['ref']
+      else
+        @data['ref'] = field_fetch('R').split(' ')
+      end
     end
 
-    # Returns
+    # Returns authors in the A line.
     def author
-      field_fetch('A')
+      if @data['author']
+        @data['author']
+      else
+        @data['author'] = field_fetch('A')
+      end
     end
 
-    # Returns
+    # Returns title in the T line.
     def title
-      field_fetch('T')
+      if @data['title']
+        @data['title']
+      else
+        @data['title'] = field_fetch('T')
+      end
     end
 
-    # Returns
+    # Returns journal name in the J line.
     def journal
-      field_fetch('J')
+      if @data['journal']
+        @data['journal']
+      else
+        @data['journal'] = field_fetch('J')
+      end
     end
 
-    # Returns
+    # Returns comment (if any).
     def comment
-      get('*')
+      if @data['comment']
+        @data['comment']
+      else
+        @data['comment'] = field_fetch('*')
+      end
     end
-
   end
 
 
+  # Class for AAindex1 format.
   class AAindex1 < AAindex
 
-
     def initialize(entry)
       super(entry)
     end
 
-    # Returns
+    # Returns correlation_coefficient (Hash) in the C line.
+    #
+    # cf.) {'ABCD12010203' => 0.999, 'CDEF123456' => 0.543, ...}
     def correlation_coefficient
-      field_fetch('C')
+      if @data['correlation_coefficient']
+        @data['correlation_coefficient']
+      else
+        hash = {}
+        ary = field_fetch('C').split(' ')
+        ary.each do |x|
+          next unless x =~ /^[A-Z]/
+          hash[x] = ary[ary.index(x) + 1].to_f
+        end
+        @data['correlation_coefficient'] = hash
+      end
     end
 
-    # Returns
+    # Returns the index (Array) in the I line.
+    #
+    # an argument: :string, :float, :zscore or :integer
     def index(type = :float)
       aa = %w( A R N D C Q E G H I L K M F P S T W Y V )
       values = field_fetch('I', 1).split(' ')
@@ -162,43 +229,62 @@ module Bio
   end
 
 
+  # Class for AAindex2 format.
   class AAindex2 < AAindex
 
-
     def initialize(entry)
       super(entry)
     end
 
-    # Returns
+    # Returns row labels.
     def rows
-      label_data
-      @rows
+      if @data['rows']
+        @data['rows']
+      else 
+        label_data
+        @rows
+      end
     end
 
-    # Returns
+    # Returns col labels.
     def cols
-      label_data
-      @cols
+      if @data['cols']
+        @data['cols']
+      else 
+        label_data
+        @cols
+      end
     end
 
-    # Returns
-    def matrix
-      ma = Array.new
+    # Returns the value of amino acids substitution (aa1 -> aa2).
+    def [](aa1 = nil, aa2 = nil)
+      matrix[cols.index(aa1), rows.index(aa2)]
+    end
 
-      data = label_data
-      data.each_line do |line|
-        list = line.strip.split(/\s+/).map{|x| x.to_f}
-        ma.push(list)
-      end
+    # Returns amino acids matrix in Matrix.
+    def matrix(aa1 = nil, aa2 = nil)
+      return self[aa1, aa2] if aa1 and aa2
 
-      Matrix[*ma]
+      if @data['matrix'] 
+        @data['matrix'] 
+      else
+        ma = []
+        label_data.each_line do |line|
+          ma << line.strip.split(/\s+/).map {|x| x.to_f }
+        end
+        @data['matrix'] = Matrix[*ma]
+      end
     end
 
-    # Returns
+    # Returns amino acids matrix in Matrix  for the old format (<= ver 5.0).
     def old_matrix # for AAindex <= ver 5.0
+      return @data['matrix'] if @data['matrix']
 
-      @aa = {} # used to determine row/column of the aa
+      @aa = {} 
+      # used to determine row/column of the aa
       attr_reader :aa
+      alias_method :aa, :rows
+      alias_method :aa, :cols
 
       field = field_fetch('I')
 
@@ -222,8 +308,7 @@ module Bio
             ma[j][i] = ma[i][j]
           end
         end
-        Matrix[*ma]
-
+        @data['matrix'] = Matrix[*ma]
       when / -ARNDCQEGHILKMFPSTWYV / # 21x20/2 matrix (with gap)
         raise NotImplementedError
       when / ACDEFGHIKLMNPQRSTVWYJ- / # 21x21 matrix (with gap)
@@ -234,18 +319,22 @@ module Bio
     private
 
     def label_data
-      label, data = get('M').split("\n", 2)
-      if /M rows = (\S+), cols = (\S+)/.match(label)
-        rows, cols = $1, $2
-        @rows = rows.split('')
-        @cols = cols.split('')
+      if @data['data'] 
+        @data['data'] 
+      else
+        label, data = get('M').split("\n", 2)
+        if /M rows = (\S+), cols = (\S+)/.match(label)
+          rows, cols = $1, $2
+          @rows = rows.split('')
+          @cols = cols.split('')
+        end
+        @data['data'] = data
       end
-      return data
     end
 
-  end
+  end # class AAindex2
 
-end
+end # module Bio
 
 
 if __FILE__ == $0
@@ -259,22 +348,28 @@ if __FILE__ == $0
   p aax1.author
   p aax1.title
   p aax1.journal
+  p aax1.comment
   p aax1.correlation_coefficient
   p aax1.index
-  puts "### AAindex2 (HENS920102)"
-  aax2 = Bio::AAindex2.new(Bio::Fetch.query('aaindex', 'HENS920102', 'raw'))
+  p aax1
+  puts "### AAindex2 (DAYM780301)"
+  aax2 = Bio::AAindex2.new(Bio::Fetch.query('aaindex', 'DAYM780301', 'raw'))
   p aax2.entry_id
   p aax2.definition
   p aax2.dblinks
   p aax2.author
   p aax2.title
   p aax2.journal
+  p aax1.comment
   p aax2.rows
   p aax2.cols
   p aax2.matrix
   p aax2.matrix[2,2]
+  p aax2.matrix[2,3]
+  p aax2.matrix[4,3]
   p aax2.matrix.determinant
   p aax2.matrix.rank
   p aax2.matrix.transpose
+  p aax2
 end