bio 1.4.3.0001 → 1.5.0

data/lib/bio/map.rb

@@ -319,7 +319,7 @@ module Bio
         unless other.kind_of?(Bio::Map::Mapping)
           raise "[Error] markers are not comparable"
         end
-	    unless @map.equal?(other.map)
+        unless @map.equal?(other.map)
           raise "[Error] maps have to be the same"
         end
 

data/lib/bio/pathway.rb

@@ -591,7 +591,7 @@ class Pathway
   # problem in the graph in which edge weights can be negative.
   def bellman_ford(root)
     distance, predecessor = initialize_single_source(root)
-    for i in 1 ..(self.nodes - 1) do
+    (self.nodes - 1).times do
       @graph.each_key do |u|
         @graph[u].each do |v, w|
           # relaxing procedure of root -> 'u' -> 'v'

data/lib/bio/sequence/compat.rb

@@ -32,7 +32,7 @@ class Sequence
 
 module Common
 
-  # <b>Bio::Sequence#to_fasta is DEPRECIATED</b>
+  # <b>Bio::Sequence#to_fasta is DEPRECATED</b>
   # Do not use Bio::Sequence#to_fasta ! Use Bio::Sequence#output instead. 
   # Note that Bio::Sequence::NA#to_fasta, Bio::Sequence::AA#to_fasata,
   # and Bio::Sequence::Generic#to_fasta <b>can still be used</b>,

data/lib/bio/sequence/na.rb

@@ -283,6 +283,14 @@ class NA < String
   #
   #   s = Bio::Sequence::NA.new('atggcgtga')
   #   puts s.gc_percent                       #=> 55
+  #
+  # Note that this method only returns an integer value.
+  # When more digits after decimal points are needed,
+  # use gc_content and sprintf like below:
+  #
+  #   s = Bio::Sequence::NA.new('atggcgtga')
+  #   puts sprintf("%3.2f", s.gc_content * 100)  #=> "55.56"
+  # 
   # ---
   # *Returns*:: Fixnum
   def gc_percent
@@ -297,57 +305,100 @@ class NA < String
   # Calculate the ratio of GC / ATGC bases. U is regarded as T.
   #
   #   s = Bio::Sequence::NA.new('atggcgtga')
+  #   puts s.gc_content                       #=> (5/9)
+  #   puts s.gc_content.to_f                  #=> 0.5555555555555556
+  #
+  # In older Ruby versions, Float is always returned.
+  #   
+  #   s = Bio::Sequence::NA.new('atggcgtga')
   #   puts s.gc_content                       #=> 0.555555555555556
+  #
+  # Note that "u" is regarded as "t".
+  # If there are no ATGC bases in the sequence, 0.0 is returned.
+  #
   # ---
-  # *Returns*:: Float
+  # *Returns*:: Rational or Float
   def gc_content
     count = self.composition
     at = count['a'] + count['t'] + count['u']
     gc = count['g'] + count['c']
-    return 0.0 if at + gc == 0
-    return gc.quo(at + gc)
+    total = at + gc
+    return 0.0 if total == 0
+    return gc.quo(total)
   end
 
   # Calculate the ratio of AT / ATGC bases. U is regarded as T.
   #
   #   s = Bio::Sequence::NA.new('atggcgtga')
+  #   puts s.at_content                       #=> 4/9
+  #   puts s.at_content.to_f                  #=> 0.444444444444444
+  #
+  # In older Ruby versions, Float is always returned.
+  #
+  #   s = Bio::Sequence::NA.new('atggcgtga')
   #   puts s.at_content                       #=> 0.444444444444444
+  #
+  # Note that "u" is regarded as "t".
+  # If there are no ATGC bases in the sequence, 0.0 is returned.
+  #
   # ---
-  # *Returns*:: Float
+  # *Returns*:: Rational or Float
   def at_content
     count = self.composition
     at = count['a'] + count['t'] + count['u']
     gc = count['g'] + count['c']
-    return 0.0 if at + gc == 0
-    return at.quo(at + gc)
+    total = at + gc
+    return 0.0 if total == 0
+    return at.quo(total)
   end
 
   # Calculate the ratio of (G - C) / (G + C) bases.
   #
   #   s = Bio::Sequence::NA.new('atggcgtga')
+  #   puts s.gc_skew                          #=> 3/5
+  #   puts s.gc_skew.to_f                     #=> 0.6
+  #
+  # In older Ruby versions, Float is always returned.
+  #
+  #   s = Bio::Sequence::NA.new('atggcgtga')
   #   puts s.gc_skew                          #=> 0.6
+  #
+  # If there are no GC bases in the sequence, 0.0 is returned.
+  #
   # ---
-  # *Returns*:: Float
+  # *Returns*:: Rational or Float
   def gc_skew
     count = self.composition
     g = count['g']
     c = count['c']
-    return 0.0 if g + c == 0
-    return (g - c).quo(g + c)
+    gc = g + c
+    return 0.0 if gc == 0
+    return (g - c).quo(gc)
   end
 
   # Calculate the ratio of (A - T) / (A + T) bases. U is regarded as T.
   #
   #   s = Bio::Sequence::NA.new('atgttgttgttc')
+  #   puts s.at_skew                          #=> (-3/4)
+  #   puts s.at_skew.to_f                     #=> -0.75
+  #
+  # In older Ruby versions, Float is always returned.
+  #
+  #   s = Bio::Sequence::NA.new('atgttgttgttc')
   #   puts s.at_skew                          #=> -0.75
+  #
+  # Note that "u" is regarded as "t".
+  # If there are no AT bases in the sequence, 0.0 is returned.
+  #
   # ---
-  # *Returns*:: Float
+  # *Returns*:: Rational or Float
   def at_skew
     count = self.composition
     a = count['a']
     t = count['t'] + count['u']
-    return 0.0 if a + t == 0
-    return (a - t).quo(a + t)
+    at = a + t
+    return 0.0 if at == 0
+    return (a - t).quo(at)
   end
 
   # Returns an alphabetically sorted array of any non-standard bases 

data/lib/bio/shell.rb

@@ -31,8 +31,6 @@ module Bio::Shell
   require 'bio/shell/plugin/flatfile'
   require 'bio/shell/plugin/obda'
   require 'bio/shell/plugin/das'
-  require 'bio/shell/plugin/keggapi'
-  require 'bio/shell/plugin/soap'
   require 'bio/shell/plugin/emboss'
   require 'bio/shell/plugin/blast'
   require 'bio/shell/plugin/psort'

data/lib/bio/shell/core.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id:$
 #
 
 module Bio::Shell::Core
@@ -195,7 +194,7 @@ module Bio::Shell::Ghost
 
   def find_flat_dir(dbname)
     dir = File.join(bioflat_dir, dbname.to_s.strip)
-    if File.exists?(dir)
+    if File.exist?(dir)
       return dir
     else
       return nil
@@ -209,7 +208,7 @@ module Bio::Shell::Ghost
   end
 
   def load_config_file(file)
-    if File.exists?(file)
+    if File.exist?(file)
       STDERR.print "Loading config (#{file}) ... "
       if hash = YAML.load(File.read(file))
         @config.update(hash)
@@ -312,7 +311,7 @@ module Bio::Shell::Ghost
   end
 
   def load_object_file(file)
-    if File.exists?(file)
+    if File.exist?(file)
       STDERR.print "Loading object (#{file}) ... "
       begin
         bind = Bio::Shell.cache[:binding]
@@ -394,7 +393,7 @@ module Bio::Shell::Ghost
   end
 
   def load_history_file(file)
-    if File.exists?(file)
+    if File.exist?(file)
       STDERR.print "Loading history (#{file}) ... "
       File.open(file).each do |line|
         unless line[/^# /]
@@ -459,7 +458,7 @@ module Bio::Shell::Ghost
 
   def save_script
     if @script_begin and @script_end and @script_begin <= @script_end
-      if File.exists?(script_file)
+      if File.exist?(script_file)
         message = "Overwrite script file (#{script_file})? [y/n] "
       else
         message = "Save script file (#{script_file})? [y/n] "

data/lib/bio/shell/interface.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id: interface.rb,v 1.19 2007/11/15 07:08:49 k Exp $
 #
 
 module Bio::Shell
@@ -101,7 +100,7 @@ module Bio::Shell
         STDOUT.reopen(pg)
         objs.each do |obj|
           if obj.is_a?(String)
-            if File.exists?(obj)
+            if File.exist?(obj)
               system("#{cmd} #{obj}")
             else
               obj.display
@@ -128,7 +127,7 @@ module Bio::Shell
 
   def head(arg, num = 10)
     str = ""
-    if File.exists?(arg)
+    if File.exist?(arg)
       File.open(arg) do |file|
         num.times do
           if line = file.gets
@@ -154,7 +153,7 @@ module Bio::Shell
     if ! file[/^#{datadir}/] and Bio::Shell.ask_yes_or_no(message)
       file = File.join(datadir, file)
     end
-    if File.exists?(file)
+    if File.exist?(file)
       message = "Overwrite existing '#{file}' file? [y/n] "
       if ! Bio::Shell.ask_yes_or_no(message)
         puts " ... save aborted."

data/lib/bio/shell/irb.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id: irb.rb,v 1.3 2007/04/05 23:35:41 trevor Exp $
 #
 
 module Bio::Shell
@@ -48,7 +47,7 @@ module Bio::Shell
         return line
       end
 
-      if File.exists?("./config/boot.rb")
+      if File.exist?("./config/boot.rb")
         require "./config/boot"
         require "./config/environment"
         #require 'commands/console'

data/lib/bio/shell/plugin/entry.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id:$
 #
 
 module Bio::Shell
@@ -31,7 +30,7 @@ module Bio::Shell
     seq = ""
     if arg.kind_of?(Bio::Sequence)
       seq = arg
-    elsif arg.respond_to?(:gets) or File.exists?(arg)
+    elsif arg.respond_to?(:gets) or File.exist?(arg)
       ent = flatauto(arg)
     elsif arg[/:/]
       ent = getobj(arg)
@@ -65,7 +64,7 @@ module Bio::Shell
     db, entry_id = arg.to_s.strip.split(/\:/, 2)
 
     # local file
-    if arg.respond_to?(:gets) or File.exists?(arg)
+    if arg.respond_to?(:gets) or File.exist?(arg)
       puts "Retrieving entry from file (#{arg})"
       entry = flatfile(arg)
 

data/lib/bio/shell/plugin/seq.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id: seq.rb,v 1.21 2007/04/05 23:35:41 trevor Exp $
 #
 
 module Bio::Shell
@@ -161,20 +160,22 @@ end
 class String
 
   def step(window_size)
-    i = 0
+    j = 0
     0.step(self.length - window_size, window_size) do |i|
       yield self[i, window_size]
+      j = i
     end
-    yield self[i + window_size .. -1] if i + window_size < self.length
+    yield self[j + window_size .. -1] if j + window_size < self.length
   end
 
   def skip(window_size, step_size = 1)
-    i = 0
+    j = 0
     0.step(self.length - window_size, step_size) do |i|
       yield [self[i, window_size], i + 1, i + window_size]
+      j = i
     end
-    from = i + step_size
-    to  = [self.length, i + step_size + window_size].min
+    from = j + step_size
+    to  = [self.length, j + step_size + window_size].min
     yield [self[from, window_size], from + 1, to] if from + 1 <= to
   end
 

data/lib/bio/shell/setup.rb

@@ -5,7 +5,6 @@
 #               Toshiaki Katayama <k@bioruby.org>
 # License::     The Ruby License
 #
-# $Id: setup.rb,v 1.8 2007/06/28 11:21:40 k Exp $
 #
 
 require 'getoptlong'
@@ -25,7 +24,7 @@ class Bio::Shell::Setup
     Bio::Shell.configure(savedir)
 
     # set default to irb mode
-    Bio::Shell.cache[:mode] = @mode || :irb
+    Bio::Shell.cache[:mode] = ((defined? @mode) && @mode) || :irb
 
     case Bio::Shell.cache[:mode]
     when :web

data/lib/bio/tree.rb

@@ -614,7 +614,7 @@ module Bio
       raise IndexError, 'node2 not found' unless @pathway.graph[node2]
       return [ node1 ] if node1 == node2
       return [ node1, node2 ] if @pathway.graph[node1][node2]
-      step, path = @pathway.bfs_shortest_path(node1, node2)
+      _, path = @pathway.bfs_shortest_path(node1, node2)
       unless path[0] == node1 and path[-1] == node2 then
         raise NoPathError, 'node1 and node2 are not connected'
       end
@@ -765,7 +765,7 @@ module Bio
     # The result is unspecified for cyclic trees.
     def lowest_common_ancestor(node1, node2, root = nil)
       root ||= @root
-      distance, route = @pathway.breadth_first_search(root)
+      _, route = @pathway.breadth_first_search(root)
       x = node1; r1 = []
       begin; r1 << x; end while x = route[x]
       x = node2; r2 = []

data/lib/bio/util/contingency_table.rb

@@ -331,8 +331,6 @@ class ContingencyTable
   # *Returns*:: +Float+ chi square value
   def chi_square
     total = 0
-    c = @characters
-    max = c.size - 1
     @characters.each do |i|    # Loop through every row in the ContingencyTable
       @characters.each do |j|  # Loop through every column in the ContingencyTable
         total += chi_square_element(i, j)

data/lib/bio/util/restriction_enzyme/range/sequence_range.rb

@@ -196,7 +196,7 @@ class SequenceRange
     c_cut = cc.vc_complement_as_original_class
     h_cut = cc.hc_between_strands_as_original_class
     
-    if @circular
+    if (defined? @circular) && @circular
       # NOTE
       # if it's circular we should start at the beginning of a cut for orientation
       # scan for it, hack off the first set of hcuts and move them to the back
@@ -238,7 +238,7 @@ class SequenceRange
   
     # Bin "-1" is an easy way to indicate the start of a strand just in case
     # there is a horizontal cut at position 0
-    bins.delete(-1) unless @circular
+    bins.delete(-1) unless ((defined? @circular) && @circular)
     bins
   end
   

data/lib/bio/util/sirna.rb

@@ -1,8 +1,9 @@
 #
 # = bio/util/sirna.rb - Class for designing small inhibitory RNAs
 #
-# Copyright::   Copyright (C) 2004, 2005
+# Copyright::   Copyright (C) 2004-2013
 #               Itoshi NIKAIDO <dritoshi@gmail.com>
+#               Yuki NAITO <y-naito@rnai.jp>
 # License::     The Ruby License
 #
 # $Id:$
@@ -33,10 +34,10 @@
 # 
 # * Kumiko Ui-Tei et al.  Guidelines for the selection of highly effective
 #   siRNA sequences for mammalian and chick RNA interference.
-#   Nucl. Acids. Res. 2004 32: 936-948.
+#   Nucleic Acids Res. 2004 32: 936-948.
 #    
 # * Angela Reynolds et al.  Rational siRNA design for RNA interference.
-#   Nature Biotech. 2004 22: 326-330.
+#   Nat. Biotechnol. 2004 22: 326-330.
 #
 
 require 'bio/sequence'
@@ -71,24 +72,64 @@ module Bio
 
     # Ui-Tei's rule.
     def uitei?(target)
-      return false unless /^.{2}[GC]/i =~ target
-      return false unless /[AU].{2}$/i =~ target
-      return false if     /[GC]{9}/i   =~ target
-
-      one_third  = target.size * 1 / 3
-      start_pos  = @target_size - one_third - 1
-      remain_seq = target.subseq(start_pos, @target_size - 2)
-      au_number  = remain_seq.scan(/[AU]/i).size
-      return false if au_number < 5
-  
+      return false if target.length != 23  # 21 nt target + 2 nt overhang
+
+      seq19 = target[2..20]  # 19 nt double-stranded region of siRNA
+
+      # criteria i
+      return false unless seq19[18..18].match(/[AU]/i)
+
+      # criteria ii
+      return false unless seq19[0..0].match(/[GC]/i)
+
+      # criteria iii
+      au_number = seq19[12..18].scan(/[AU]/i).size
+      return false unless au_number >= 4
+
+      # criteria iv
+      return false if seq19.match(/[GC]{10}/i)
+
       return true
     end
 
     # Reynolds' rule.
     def reynolds?(target)
-      return false if /[GC]{9}/i =~ target
-      return false unless /^.{4}A.{6}U.{2}[AUC].{5}[AU].{2}$/i =~ target
-      return true
+      return false if target.length != 23  # 21 nt target + 2 nt overhang
+
+      seq19 = target[2..20]  # 19 nt double-stranded region of siRNA
+      score = 0
+
+      # criteria I
+      gc_number = seq19.scan(/[GC]/i).size
+      score += 1 if (7 <= gc_number and gc_number <= 10)
+
+      # criteria II
+      au_number = seq19[14..18].scan(/[AU]/i).size
+      score += au_number
+
+      # criteria III
+      # NotImpremented: Tm
+
+      # criteria IV
+      score += 1 if seq19[18..18].match(/A/i)
+
+      # criteria V
+      score += 1 if seq19[2..2].match(/A/i)
+
+      # criteria VI
+      score += 1 if seq19[9..9].match(/[U]/i)
+
+      # criteria VII
+      score -= 1 if seq19[18..18].match(/[GC]/i)
+
+      # criteria VIII
+      score -= 1 if seq19[12..12].match(/G/i)
+
+      if score >= 6
+        return score
+      else
+        return false
+      end
     end
 
     # same as design('uitei').
@@ -254,6 +295,25 @@ end # module Bio
 
 = ChangeLog
 
+  2013/04/03 Yuki NAITO <y-naito@rnai.jp>
+  Modified siRNA design rules:
+
+  - Ui-Tei's rule:
+    - Restricted target length to 23 nt (21 nt plus 2 nt overhang)
+      for selecting functional siRNAs.
+    - Avoided contiguous GCs 10 nt or more. (not 9 nt or more)
+
+  - Reynolds' rule:
+    - Restricted target length to 23 nt (21 nt plus 2 nt overhang)
+      for selecting functional siRNAs.
+    - Reynolds' rule does not require to fulfill all the criteria
+      simultaneously. Total score of eight criteria is calculated
+      and used for the siRNA efficacy prediction. This change may
+      significantly alter an output.
+    - Returns total score of eight criteria for functional siRNA,
+      instead of returning 'true'.
+    - Returns 'false' for non-functional siRNA, as usual.
+
   2005/03/21 Itoshi NIKAIDO <itoshi.nikaido@nifty.com>
   Bio::SiRNA#ShRNA_designer method was changed design method.