bio 0.7.1 → 1.0.0

data/lib/bio/shell/rails/public/robots.txt

@@ -0,0 +1 @@
+# See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file

data/lib/bio/shell/rails/public/stylesheets/main.css

@@ -0,0 +1,187 @@
+body { background-color: #fff; color: #333; }
+
+body, p, td {
+  font-family: verdana, arial, helvetica, sans-serif;
+  font-size:   13px;
+  line-height: 18px;
+}
+
+pre {
+  background-color: #eee;
+  padding: 10px;
+  font-size: 11px;
+}
+
+a { color: #000; }
+a:visited { color: #666; }
+a:hover { color: #fff; background-color:#000; }
+
+.fieldWithErrors {
+  padding: 2px;
+  background-color: red;
+  display: table;
+}
+
+table {
+     text-align: top;
+     }
+
+#ErrorExplanation {
+  width: 400px;
+  border: 2px solid red;
+  padding: 7px;
+  padding-bottom: 12px;
+  margin-bottom: 20px;
+  background-color: #f0f0f0;
+}
+
+#ErrorExplanation h2 {
+  text-align: left;
+  font-weight: bold;
+  padding: 5px 5px 5px 15px;
+  font-size: 12px;
+  margin: -7px;
+  background-color: #c00;
+  color: #fff;
+}
+
+#ErrorExplanation p {
+  color: #333;
+  margin-bottom: 0;
+  padding: 5px;
+}
+
+#ErrorExplanation ul li {
+  font-size: 12px;
+  list-style: square;
+}
+
+h1{
+    color: #333;
+    padding: 10px;
+    margin: 12px;
+    }
+
+#banner{
+         margin-left: 5em;
+         margin-right: -6px;
+         text-align: center;
+         font-size: 30px;
+         border-top: 1px solid silver;
+         border-bottom: 1px solid silver;
+         padding: 10px 0px 10px 0px;
+         }
+
+tr{
+    vertical-align: top;
+    text-align: left;
+    }
+
+#side img{
+           background-color: black;
+           width:12em;
+           }
+
+#side{
+       position: absolute;
+       margin: -13px;
+       top: 1em;
+       left: 1em;
+       width: 10em;
+       }
+
+#side ul{
+          font-size: 13px;
+          margin: 0em;
+          }
+
+#side h2{
+          font-size: 12px;
+          text-align: center;
+          width: 13em;
+          background-color: black;
+          color: white;
+          }
+#side input{
+             text-align: center;
+             }
+
+#main {
+        margin-left: 10em;
+        padding-top: 4x;
+        padding-left: 2em;
+        background: white;
+        }
+
+.main {
+        margin-left: 10em;
+        padding-top: 4x;
+        padding-left: 2em;
+        background: white;
+        }
+
+#menu {
+        margin-left: 10em;
+        padding-top: 4x;
+        padding-left: 2em;
+        background: white;
+        }
+
+div.uploadStatus {
+  margin: 5px;
+}
+
+div.progressBar {
+  margin: 5px;
+}
+
+div.progressBar div.border {
+  background-color: #fff;
+  border: 1px solid grey;
+  width: 100%;
+}
+
+div.progressBar div.background {
+  background-color: #333;
+  height: 18px;
+  width: 0%;
+}
+
+.tabs {
+        position:relative;
+        height: 20px;
+        margin: 0;
+        padding: 0;
+        background: #aaa repeat-x;
+        overflow:hidden
+        }
+
+.tabs li {
+           display:inline;
+           }
+
+.tabs a:hover, .tabs a.tab-active {
+                                    color:#333;
+                                    background:#fff url("bar_on.gif") repeat-x;
+                                    border-right: 1px solid #fff
+                                    }
+
+
+.tabs a  {
+           height: 27px;
+           font:12px verdana, helvetica, sans-serif;
+           font-weight:bold;
+           position:relative;
+           padding:6px 10px 10px 10px;
+           margin: 0px -4px 0px 0px;
+           color:#333;
+           text-decoration:none;
+           border-left:1px solid #fff;
+           border-right:1px solid #333;
+           }
+.tab-container {
+                 background: #fff;
+                 border:1px solid #555;
+                 }
+.tab-panes {
+             margin: 3px }

data/lib/bio/shell/rails/script/about

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/about'

data/lib/bio/shell/rails/script/breakpointer

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/breakpointer'

data/lib/bio/shell/rails/script/console

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/console'

data/lib/bio/shell/rails/script/destroy

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/destroy'

data/lib/bio/shell/rails/script/generate

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/generate'

data/lib/bio/shell/rails/script/performance/benchmarker

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../../config/boot'
+require 'commands/performance/benchmarker'

data/lib/bio/shell/rails/script/performance/profiler

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../../config/boot'
+require 'commands/performance/profiler'

data/lib/bio/shell/rails/script/plugin

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/plugin'

data/lib/bio/shell/rails/script/process/reaper

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../../config/boot'
+require 'commands/process/reaper'

data/lib/bio/shell/rails/script/process/spawner

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../../config/boot'
+require 'commands/process/spawner'

data/lib/bio/shell/rails/script/process/spinner

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../../config/boot'
+require 'commands/process/spinner'

data/lib/bio/shell/rails/script/runner

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require File.dirname(__FILE__) + '/../config/boot'
+require 'commands/runner'

data/lib/bio/shell/rails/script/server

@@ -0,0 +1,42 @@
+#!/usr/bin/env ruby
+#
+# = BioRuby shell on Rails server - GUI for the BioRuby shell
+#
+# Copyright::   Copyright (C) 2006
+#               Nobuya Tanaka <t@chemruby.org>,
+#               Toshiaki Katayama <k@bioruby.org>
+# License::     Ruby's
+#
+# $Id: server,v 1.1 2006/02/27 11:16:23 k Exp $
+#
+
+require 'bio/shell'
+require 'drb/drb'
+
+require './app/models/shell_connection'
+$drb_server = ShellConnection.new
+
+## Access Control List
+#
+# require 'drb/acl'
+#
+# list = %w(deny all
+#           allow 127.0.0.1
+#          )
+# acl = ACL.new(list, ACL::DENY_ALLOW)
+# DRb.install_acl(acl)
+#
+
+STDOUT.sync = true
+
+#uri = "druby://localhost:0"
+uri = 'druby://localhost:81064' # baioroji-
+DRb.start_service(uri, $drb_server)
+puts DRb.uri
+
+puts "starting ..."
+
+require './config/boot'
+require 'commands/server'
+
+puts "exiting ..."

data/lib/bio/shell/rails/test/test_helper.rb

@@ -0,0 +1,28 @@
+ENV["RAILS_ENV"] = "test"
+require File.expand_path(File.dirname(__FILE__) + "/../config/environment")
+require 'test_help'
+
+class Test::Unit::TestCase
+  # Transactional fixtures accelerate your tests by wrapping each test method
+  # in a transaction that's rolled back on completion.  This ensures that the
+  # test database remains unchanged so your fixtures don't have to be reloaded
+  # between every test method.  Fewer database queries means faster tests.
+  #
+  # Read Mike Clark's excellent walkthrough at
+  #   http://clarkware.com/cgi/blosxom/2005/10/24#Rails10FastTesting
+  #
+  # Every Active Record database supports transactions except MyISAM tables
+  # in MySQL.  Turn off transactional fixtures in this case; however, if you
+  # don't care one way or the other, switching from MyISAM to InnoDB tables
+  # is recommended.
+  self.use_transactional_fixtures = true
+
+  # Instantiated fixtures are slow, but give you @david where otherwise you
+  # would need people(:david).  If you don't want to migrate your existing
+  # test cases which use the @david style and don't mind the speed hit (each
+  # instantiated fixtures translates to a database query per test method),
+  # then set this back to true.
+  self.use_instantiated_fixtures  = false
+
+  # Add more helper methods to be used by all tests here...
+end

data/lib/bio/shell/web.rb

@@ -0,0 +1,90 @@
+#
+# = bio/shell/web.rb - GUI for the BioRuby shell
+#
+# Copyright::   Copyright (C) 2006
+#               Nobuya Tanaka <t@chemruby.org>,
+#               Toshiaki Katayama <k@bioruby.org>
+# License::     Ruby's
+#
+# $Id: web.rb,v 1.1 2006/02/27 09:22:42 k Exp $
+#
+
+
+module Bio::Shell
+
+  private
+
+  def rails_directory_setup
+    server = "script/server"
+    unless File.exists?(server)
+      require 'fileutils'
+      basedir = File.dirname(__FILE__)
+      print "Copying web server files ... "
+      FileUtils.cp_r("#{basedir}/rails/.", ".")
+      puts "done"
+    end
+  end
+
+  def rails_server_setup
+    require 'open3'
+    $web_server = Open3.popen3(server)
+
+    $web_error_log = File.open("log/web-error.log", "a")
+    $web_server[2].reopen($web_error_log)
+
+    while line = $web_server[1].gets
+      if line[/druby:\/\/localhost/]
+        uri = line.chomp
+        puts uri if $DEBUG
+        break
+      end
+    end
+
+    $web_access_log = File.open("log/web-access.log", "a")
+    $web_server[1].reopen($web_access_log)
+
+    return uri
+  end
+
+  def web
+    return if $web_server
+
+    require 'drb/drb'
+    # $SAFE = 1   # disable eval() and friends
+
+    rails_directory_setup
+    #uri = rails_server_setup
+    uri = 'druby://localhost:81064' # baioroji-
+
+    $drb_server = DRbObject.new_with_uri(uri)
+    $drb_server.puts_remote("Connected")
+
+    puts "Connected to server #{uri}"
+    puts "Open http://localhost:3000/shell/"
+
+    io = IRB.conf[:MAIN_CONTEXT].io
+
+    io.class.class_eval do
+      alias_method :shell_original_gets, :gets
+    end
+
+    def io.gets
+      bind = IRB.conf[:MAIN_CONTEXT].workspace.binding
+      vars = eval("local_variables", bind)
+      vars.each do |var|
+        next if var == "_"
+        if val = eval("#{var}", bind)
+          $drb_server[var] = val
+        else
+          $drb_server.delete(var)
+        end
+      end
+      line = shell_original_gets
+      line
+    end
+  end
+  
+end
+
+
+

data/lib/bio/util/contingency_table.rb

@@ -1,14 +1,236 @@
-module Bio
-
 #
-# bio/util/contingency_table.rb - Statistical contingency table analysis for aligned sequences
+# = bio/util/contingency_table.rb - Statistical contingency table analysis for aligned sequences
 #
 # Copyright::  Copyright (C) 2005 Trevor Wennblom <trevor@corevx.com>
 # License::    LGPL
 #
-#  $Id: contingency_table.rb,v 1.2 2005/12/13 14:58:37 trevor Exp $
-#
+#  $Id: contingency_table.rb,v 1.4 2006/02/27 13:23:01 k Exp $
 #
+# == Synopsis
+# 
+# The Bio::ContingencyTable class provides basic statistical contingency table
+# analysis for two positions within aligned sequences.
+# 
+# When ContingencyTable is instantiated the set of characters in the
+# aligned sequences may be passed to it as an array.  This is
+# important since it uses these characters to create the table's rows
+# and columns.  If this array is not passed it will use it's default
+# of an amino acid and nucleotide alphabet in lowercase along with the
+# clustal spacer '-'.
+# 
+# To get data from the table the most used functions will be
+# chi_square and contingency_coefficient:
+# 
+#   ctable = Bio::ContingencyTable.new()
+#   ctable['a']['t'] += 1
+#   # .. put more values into the table
+#   puts ctable.chi_square
+#   puts ctable.contingency_coefficient  # between 0.0 and 1.0
+# 
+# The contingency_coefficient represents the degree of correlation of
+# change between two sequence positions in a multiple-sequence
+# alignment.  0.0 indicates no correlation, 1.0 is the maximum
+# correlation.
+# 
+# 
+# == Further Reading
+# 
+# * http://en.wikipedia.org/wiki/Contingency_table
+# * http://www.physics.csbsju.edu/stats/exact.details.html
+# * Numerical Recipes in C by Press, Flannery, Teukolsky, and Vetterling
+# # 
+# == Usage
+# 
+# What follows is an example of ContingencyTable in typical usage
+# analyzing results from a clustal alignment.
+# 
+#   require 'bio'
+#   require 'bio/contingency_table'
+# 
+#   seqs = {}
+#   max_length = 0
+#   Bio::ClustalW::Report.new( IO.read('sample.aln') ).to_a.each do |entry|
+#     data = entry.data.strip
+#     seqs[entry.definition] = data.downcase
+#     max_length = data.size if max_length == 0
+#     raise "Aligned sequences must be the same length!" unless data.size == max_length
+#   end
+# 
+#   VERBOSE = true
+#   puts "i\tj\tchi_square\tcontingency_coefficient" if VERBOSE
+#   correlations = {}
+# 
+#   0.upto(max_length - 1) do |i|
+#     (i+1).upto(max_length - 1) do |j|
+#       ctable = Bio::ContingencyTable.new()
+#       seqs.each_value { |seq| ctable.table[ seq[i].chr ][ seq[j].chr ] += 1 }
+# 
+#       chi_square = ctable.chi_square
+#       contingency_coefficient = ctable.contingency_coefficient
+#       puts [(i+1), (j+1), chi_square, contingency_coefficient].join("\t") if VERBOSE
+# 
+#       correlations["#{i+1},#{j+1}"] = contingency_coefficient
+#       correlations["#{j+1},#{i+1}"] = contingency_coefficient  # Both ways are accurate
+#     end
+#   end
+# 
+#   require 'yaml'
+#   File.new('results.yml', 'a+') { |f| f.puts correlations.to_yaml }
+# 
+# 
+# == Tutorial
+# 
+
+# ContingencyTable returns the statistical significance of change
+# between two positions in an alignment.  If you would like to see how
+# every possible combination of positions in your alignment compares
+# to one another you must set this up yourself.  Hopefully the
+# provided examples will help you get started without too much
+# trouble.
+# 
+#   def lite_example(sequences, max_length, characters)
+# 
+#     %w{i j chi_square contingency_coefficient}.each { |x| print x.ljust(12) }
+#     puts
+# 
+#     0.upto(max_length - 1) do |i|
+#       (i+1).upto(max_length - 1) do |j|
+#         ctable = Bio::ContingencyTable.new( characters )
+#         sequences.each do |seq|
+#           i_char = seq[i].chr
+#           j_char = seq[j].chr
+#           ctable.table[i_char][j_char] += 1
+#         end
+#         chi_square = ctable.chi_square
+#         contingency_coefficient = ctable.contingency_coefficient
+#         [(i+1), (j+1), chi_square, contingency_coefficient].each { |x| print x.to_s.ljust(12) }
+#         puts
+#       end
+#     end
+# 
+#   end
+# 
+#   allowed_letters = Array.new
+#   allowed_letters = 'abcdefghijk'.split('')
+# 
+#   seqs = Array.new
+#   seqs << 'abcde'
+#   seqs << 'abcde'
+#   seqs << 'aacje'
+#   seqs << 'aacae'
+# 
+#   length_of_every_sequence = seqs[0].size  # 5 letters long
+# 
+#   lite_example(seqs, length_of_every_sequence, allowed_letters)
+# 
+# 
+# Producing the following results:
+# 
+#   i           j           chi_square  contingency_coefficient
+#   1           2           0.0         0.0
+#   1           3           0.0         0.0
+#   1           4           0.0         0.0
+#   1           5           0.0         0.0
+#   2           3           0.0         0.0
+#   2           4           4.0         0.707106781186548
+#   2           5           0.0         0.0
+#   3           4           0.0         0.0
+#   3           5           0.0         0.0
+#   4           5           0.0         0.0
+# 
+# The position i=2 and j=4 has a high contingency coefficient
+# indicating that the changes at these positions are related.  Note
+# that i and j are arbitrary, this could be represented as i=4 and j=2
+# since they both refer to position two and position four in the
+# alignment.  Here are some more examples:
+# 
+#   seqs = Array.new
+#   seqs << 'abcde'
+#   seqs << 'abcde'
+#   seqs << 'aacje'
+#   seqs << 'aacae'
+#   seqs << 'akcfe'
+#   seqs << 'akcfe'
+# 
+#   length_of_every_sequence = seqs[0].size  # 5 letters long
+# 
+#   lite_example(seqs, length_of_every_sequence, allowed_letters)
+# 
+# 
+# Results:
+# 
+#   i           j           chi_square  contingency_coefficient
+#   1           2           0.0         0.0
+#   1           3           0.0         0.0
+#   1           4           0.0         0.0
+#   1           5           0.0         0.0
+#   2           3           0.0         0.0
+#   2           4           12.0        0.816496580927726
+#   2           5           0.0         0.0
+#   3           4           0.0         0.0
+#   3           5           0.0         0.0
+#   4           5           0.0         0.0
+# 
+# Here we can see that the strength of the correlation of change has
+# increased when more data is added with correlated changes at the
+# same positions.
+# 
+#   seqs = Array.new
+#   seqs << 'abcde'
+#   seqs << 'abcde'
+#   seqs << 'kacje'  # changed first letter
+#   seqs << 'aacae'
+#   seqs << 'akcfa'  # changed last letter
+#   seqs << 'akcfe'
+# 
+#   length_of_every_sequence = seqs[0].size  # 5 letters long
+# 
+#   lite_example(seqs, length_of_every_sequence, allowed_letters)
+# 
+# 
+# Results:
+# 
+#   i           j           chi_square  contingency_coefficient
+#   1           2           2.4         0.534522483824849
+#   1           3           0.0         0.0
+#   1           4           6.0         0.707106781186548
+#   1           5           0.24        0.196116135138184
+#   2           3           0.0         0.0
+#   2           4           12.0        0.816496580927726
+#   2           5           2.4         0.534522483824849
+#   3           4           0.0         0.0
+#   3           5           0.0         0.0
+#   4           5           2.4         0.534522483824849
+# 
+# With random changes it becomes more difficult to identify correlated
+# changes, yet positions two and four still have the highest
+# correlation as indicated by the contingency coefficient.  The best
+# way to improve the accuracy of your results, as is often the case
+# with statistics, is to increase the sample size.
+# 
+# 
+# == A Note on Efficiency
+# 
+
+# ContingencyTable is slow.  It involves many calculations for even a
+# seemingly small five-string data set.  Even worse, it's very
+# dependent on matrix traversal, and this is done with two dimensional
+# hashes which dashes any hope of decent speed.
+# 
+
+# Finally, half of the matrix is redundant and positions could be
+# summed with their companion position to reduce calculations.  For
+# example the positions (5,2) and (2,5) could both have their values
+# added together and just stored in (2,5) while (5,2) could be an
+# illegal position.  Also, positions (1,1), (2,2), (3,3), etc.  will
+# never be used.
+# 
+# The purpose of this package is flexibility and education.  The code
+# is short and to the point in aims of achieving that purpose.  If the
+# BioRuby project moves towards C extensions in the future a
+# professional caliber version will likely be created.
+# 
+# 
 #--
 #
 #  This library is free software; you can redistribute it and/or
@@ -29,225 +251,7 @@ module Bio
 #
 #
 
-=begin rdoc
-bio/util/contingency_table.rb - Statistical contingency table analysis for aligned sequences
-
-== Synopsis
-
-The Bio::ContingencyTable class provides basic statistical contingency table
-analysis for two positions within aligned sequences.
-
-When ContingencyTable is instantiated the set of characters in the aligned sequences may be
-passed to it as an array.  This is important since it uses these characters
-to create the table's rows and columns.  If this array is not passed it will
-use it's default of an amino acid and nucleotide alphabet in lowercase along with the
-clustal spacer '-'.
-
-To get data from the table the most used functions will be chi_square and contingency_coefficient:
-  ctable = Bio::ContingencyTable.new()
-  ctable['a']['t'] += 1
-  # .. put more values into the table
-  puts ctable.chi_square
-  puts ctable.contingency_coefficient  # between 0.0 and 1.0
-
-The contingency_coefficient represents the degree of correlation of change between two
-sequence positions in a multiple-sequence alignment.  0.0 indicates no correlation,  1.0 is the
-maximum correlation.
-
-
-== Further Reading
-
-* http://en.wikipedia.org/wiki/Contingency_table
-* http://www.physics.csbsju.edu/stats/exact.details.html
-* Numerical Recipes in C by Press, Flannery, Teukolsky, and Vetterling
-
-
-== Usage
-
-What follows is an example of ContingencyTable in typical usage analyzing results from a clustal alignment.
-
-  require 'bio'
-  require 'bio/contingency_table'
-
-  seqs = {}
-  max_length = 0
-  Bio::ClustalW::Report.new( IO.read('sample.aln') ).to_a.each do |entry|
-    data = entry.data.strip
-    seqs[entry.definition] = data.downcase
-    max_length = data.size if max_length == 0
-    raise "Aligned sequences must be the same length!" unless data.size == max_length
-  end
-
-  VERBOSE = true
-  puts "i\tj\tchi_square\tcontingency_coefficient" if VERBOSE
-  correlations = {}
-
-  0.upto(max_length - 1) do |i|
-    (i+1).upto(max_length - 1) do |j|
-      ctable = Bio::ContingencyTable.new()
-      seqs.each_value { |seq| ctable.table[ seq[i].chr ][ seq[j].chr ] += 1 }
-
-      chi_square = ctable.chi_square
-      contingency_coefficient = ctable.contingency_coefficient
-      puts [(i+1), (j+1), chi_square, contingency_coefficient].join("\t") if VERBOSE
-
-      correlations["#{i+1},#{j+1}"] = contingency_coefficient
-      correlations["#{j+1},#{i+1}"] = contingency_coefficient  # Both ways are accurate
-    end
-  end
-
-  require 'yaml'
-  File.new('results.yml', 'a+') { |f| f.puts correlations.to_yaml }
-
-
-== Tutorial
-
-ContingencyTable returns the statistical significance of change between two positions in an alignment.
-If you would like to see how every possible combination of positions in your alignment compares to one another
-you must set this up yourself.  Hopefully the provided examples will help you get started without
-too much trouble.
-
-  def lite_example(sequences, max_length, characters)
-
-    %w{i j chi_square contingency_coefficient}.each { |x| print x.ljust(12) }
-    puts
-
-    0.upto(max_length - 1) do |i|
-      (i+1).upto(max_length - 1) do |j|
-        ctable = Bio::ContingencyTable.new( characters )
-        sequences.each do |seq|
-          i_char = seq[i].chr
-          j_char = seq[j].chr
-          ctable.table[i_char][j_char] += 1
-        end
-        chi_square = ctable.chi_square
-        contingency_coefficient = ctable.contingency_coefficient
-        [(i+1), (j+1), chi_square, contingency_coefficient].each { |x| print x.to_s.ljust(12) }
-        puts
-      end
-    end
-
-  end
-
-  allowed_letters = Array.new
-  allowed_letters = 'abcdefghijk'.split('')
-
-  seqs = Array.new
-  seqs << 'abcde'
-  seqs << 'abcde'
-  seqs << 'aacje'
-  seqs << 'aacae'
-
-  length_of_every_sequence = seqs[0].size  # 5 letters long
-
-  lite_example(seqs, length_of_every_sequence, allowed_letters)
-
-
-Producing the following results:
-
-  i           j           chi_square  contingency_coefficient
-  1           2           0.0         0.0
-  1           3           0.0         0.0
-  1           4           0.0         0.0
-  1           5           0.0         0.0
-  2           3           0.0         0.0
-  2           4           4.0         0.707106781186548
-  2           5           0.0         0.0
-  3           4           0.0         0.0
-  3           5           0.0         0.0
-  4           5           0.0         0.0
-
-The position i=2 and j=4 has a high contingency coefficient indicating that the changes at these 
-positions are related.  Note that i and j are arbitrary, this could be represented as i=4 and j=2
-since they both refer to position two and position four in the alignment.  Here are some more examples:
-
-  seqs = Array.new
-  seqs << 'abcde'
-  seqs << 'abcde'
-  seqs << 'aacje'
-  seqs << 'aacae'
-  seqs << 'akcfe'
-  seqs << 'akcfe'
-
-  length_of_every_sequence = seqs[0].size  # 5 letters long
-
-  lite_example(seqs, length_of_every_sequence, allowed_letters)
-
-
-Results:
-
-  i           j           chi_square  contingency_coefficient
-  1           2           0.0         0.0
-  1           3           0.0         0.0
-  1           4           0.0         0.0
-  1           5           0.0         0.0
-  2           3           0.0         0.0
-  2           4           12.0        0.816496580927726
-  2           5           0.0         0.0
-  3           4           0.0         0.0
-  3           5           0.0         0.0
-  4           5           0.0         0.0
-
-Here we can see that the strength of the correlation of change has increased when more data is added with correlated changes at the same positions.
-
-  seqs = Array.new
-  seqs << 'abcde'
-  seqs << 'abcde'
-  seqs << 'kacje'  # changed first letter
-  seqs << 'aacae'
-  seqs << 'akcfa'  # changed last letter
-  seqs << 'akcfe'
-
-  length_of_every_sequence = seqs[0].size  # 5 letters long
-
-  lite_example(seqs, length_of_every_sequence, allowed_letters)
-
-
-Results:
-
-  i           j           chi_square  contingency_coefficient
-  1           2           2.4         0.534522483824849
-  1           3           0.0         0.0
-  1           4           6.0         0.707106781186548
-  1           5           0.24        0.196116135138184
-  2           3           0.0         0.0
-  2           4           12.0        0.816496580927726
-  2           5           2.4         0.534522483824849
-  3           4           0.0         0.0
-  3           5           0.0         0.0
-  4           5           2.4         0.534522483824849
-
-With random changes it becomes more difficult to identify correlated changes, yet positions two 
-and four still have the highest correlation as indicated by the contingency coefficient.  The 
-best way to improve the accuracy of your results, as is often the case with statistics, is to 
-increase the sample size.
-
-
-== A Note on Efficiency
-
-ContingencyTable is slow.  It involves many calculations for even a seemingly small five-string data set.
-Even worse, it's very dependent on matrix traversal, and this is done with two dimensional hashes which
-dashes any hope of decent speed.  
-
-Finally, half of the matrix is redundant and positions could be summed with their companion position to reduce
-calculations.  For example the positions (5,2) and (2,5) could both have their values added together and
-just stored in (2,5) while (5,2) could be an illegal position.  Also, positions (1,1), (2,2), (3,3), etc.
-will never be used.
-
-The purpose of this package is flexibility and education.  The code is short and to the point in
-aims of achieving that purpose.  If the BioRuby project moves towards C extensions in the future a
-professional caliber version will likely be created.
-
-
-== Author
-Trevor Wennblom <trevor@corevx.com>
-
-
-== Copyright
-Copyright (C) 2005 Trevor Wennblom
-Licensed under the same terms as BioRuby.
-
-=end
+module Bio
 
 class ContingencyTable
   # Since we're making this math-notation friendly here is the layout of @table:
@@ -334,4 +338,6 @@ class ContingencyTable
   end
 
 end
-end
+
+end # Bio
+