isoelectric_point 0.0.3 → 0.0.4

data/README.rdoc

@@ -1,26 +1,39 @@
-== isoelectric_point
-A ruby class for calculating the isoelectric point of a protein. It's based on bioperl and the library from GeorgeG.
+= isoelectric_point
+A ruby class for calculating the isoelectric point of a protein. It's based on bioperl.
+It's currently beeing refactored to fit into bioruby.
 
-= PKA Sets
+== PKA Sets
 The available pka sets are:
-* dta_select_pkas
-* emboss_pkas
-* rodwell_pkas
-* wikipedia_pkas
-* sillero_pkas
+* dta_select
+* emboss
+* rodwell
+* wikipedia
+* sillero
 
-= Installation
+== Installation
  gem install isoelectric_point
 
-= Usage
+== Usage
  require 'isoelectric_point'
  # Either prefix or include namespace
- include IsoelectricPoint
- #initialize a pka clculator object with dtaselect pkas and the KKGFTCGELA as an amino acid sequence
- sequence = Sequence.new("KKGFTCGELA")
+ include Bio::Sequence
+ aa = AA.new("KKGFTCGELA")
 
  #what is the protein charge at ph 14?
- charge = sequence.calculate_charge_at(14)
+ charge = aa.calculate_charge_at(14)
 
  #calculate the ph and round off to 7 decimal places
- ph = sequence.calculate_iep(7)
+ ph = aa.calculate_iep(7)
+
+ # calculate the ph with a custom set
+ custom = { "N_TERMINUS" => 8.1,
+            "K" => 10.1,
+            "R" => 12.1,
+            "H" => 6.4,
+            "C_TERMINUS" => 3.15,
+            "D" => 4.34,
+            "E" => 4.33,
+            "C" => 8.33,
+            "Y" => 9.5
+          }
+ ph = aa.calculate_iep(7, custom)

data/lib/isoelectric_point/aa.rb

@@ -0,0 +1,84 @@
+module Bio
+  module Sequence
+    class AA < String
+      CHARGED_GROUPS = ['K', 'R', 'H', 'D', 'E', 'C', 'Y']
+
+      def initialize(sequence)
+        raise ArgumentError.new("sequence is required") if sequence.nil? || sequence.strip == ''
+        super(sequence.upcase.gsub(/\s/, ''))
+      end
+
+      # Calculate the Isoelectric Point
+      # pka_name_or_set: the name of a PKA set or a custom PKA set
+      # places: specify the number of decimal places the value should be rounded to.
+      # loop_limit: how man iterations should be made to find the point. You should not need to tweak this.
+      def calculate_iep(pka_name_or_set = 'dtaselect', places = 2, loop_limit = 100)
+        loops = 0
+        ph = 7.5
+        step = 3.5
+        begin
+          current_charge = calculate_charge_at(ph, pka_name_or_set)
+          if current_charge > 0
+            ph += step
+          else
+            ph -= step
+          end
+          step /= 2.0
+          loops += 1
+          raise "Could not find a result within #{loop_limit} loops using #{pka_name_or_set.inspect}" if loops == loop_limit
+        end while not iep_reached?(current_charge)
+        ph.round_to_places(places)
+      end
+
+      # Calculate the charge of the sequence at a given ph
+      # As a second argument you can pass the name of the PKA set or a custom PKA set
+      def calculate_charge_at(ph, pka_name_or_set = 'dtaselect')
+        ['K', 'R', 'H'].inject(partial_charge(select_pka(pka_name_or_set)['N_TERMINUS'], ph)) do |memo, item|
+          memo += partial_charge(select_pka(pka_name_or_set)[item], ph) * charged_residue_frequencies[item]
+        end -
+        ['D', 'E', 'C', 'Y'].inject(partial_charge(ph, select_pka(pka_name_or_set)['C_TERMINUS'])) do |memo, item|
+          memo += partial_charge(ph, select_pka(pka_name_or_set)[item]) * charged_residue_frequencies[item]
+        end
+      end
+
+      private
+      def iep_reached?(current_charge)
+        current_charge =! nil && 0.0.round_to_places(5) == current_charge.round_to_places(5)
+      end
+
+      def charged_residue_frequencies
+        @charged_residue_frequency ||= calculate_charged_residue_frequencies
+      end
+
+      def partial_charge(a, b)
+        x = 10 ** (a - b)
+        x / (x + 1).to_f
+      end
+
+      # Count the occurences of the charged groups in the AA.
+      # Returns a Hash where the key is the group and the value is the number of
+      # occurences in self.
+      def calculate_charged_residue_frequencies
+        CHARGED_GROUPS.inject(Hash.new(0)) do |memo, item|
+          memo[item] = self.count(item)
+          memo
+        end
+      end
+
+      #
+      # Select a PKA set according to the name or supply a custom set.
+      # Raises ArgumentError if the name can not be mapped to a PKA set.
+      # If the argument is a String it is used as a key to lookup the set,
+      # if it's a Hash then it's assumed a custom set has been supplied.
+      def select_pka(pka_name_or_set = 'dtaselect')
+        if pka_name_or_set.is_a?(Hash)
+          pka_name_or_set
+        else
+          set = PkaData::PKAS[pka_name_or_set]
+          raise ArgumentError.new("Set '#{pka_name_or_set}' is unknown. Please specify one of #{PkaData::PKAS.keys.join(', ')} or pass a custom set") unless set
+          set
+        end
+      end
+    end
+  end
+end

data/lib/isoelectric_point/pka_data.rb

@@ -0,0 +1,58 @@
+module Bio
+  module Sequence
+    module PkaData
+      PKAS = {
+        'dtaselect' => { 'N_TERMINUS' => 8.0,
+                          'K' => 10.0,
+                          'R' => 12.0,
+                          'H' => 6.5,
+                          'C_TERMINUS' => 3.1,
+                          'D' => 4.4,
+                          'E' => 4.4,
+                          'C' => 8.5,
+                          'Y' => 10.0
+                       }.freeze,
+        'emboss' =>   { 'N_TERMINUS' => 8.0,
+                        'K' => 10.0,
+                        'R' => 12.0,
+                        'H' => 6.5,
+                        'C_TERMINUS' => 3.1,
+                        'D' => 4.4,
+                        'E' => 4.4,
+                        'C' => 8.5,
+                        'Y' => 10.0
+                      }.freeze,
+        'rodwell' =>  { 'N_TERMINUS' => 8.0,
+                        'K' => 11.5,
+                        'R' => 11.5,
+                        'H' => 6.0,
+                        'C_TERMINUS' => 3.1,
+                        'D' => 3.68,
+                        'E' => 4.25,
+                        'C' => 8.33,
+                        'Y' => 10.07
+                      }.freeze,
+        'wikipedia' => { 'N_TERMINUS' => 8.2,
+                         'K' => 10.54,
+                         'R' => 12.48,
+                         'H' => 6.04,
+                         'C_TERMINUS' => 3.65,
+                         'D' => 3.9,
+                         'E' => 4.07,
+                         'C' => 8.18,
+                         'Y' => 10.47
+                      }.freeze,
+        'silerio' =>  { 'N_TERMINUS' => 8.2,
+                        'K' => 10.4,
+                        'R' => 12.0,
+                        'H' => 6.4,
+                        'C_TERMINUS' => 3.2,
+                        'D' => 4.0,
+                        'E' => 4.5,
+                        'C' => 9.0,
+                        'Y' => 10.0
+                      }.freeze
+      }.freeze
+    end
+  end
+end

data/lib/isoelectric_point.rb

@@ -1,3 +1,3 @@
-['data', 'extensions', 'sequence'].each do |name|
+['pka_data', 'extensions', 'aa'].each do |name|
   require File.join(File.dirname(__FILE__), 'isoelectric_point', name)
 end

data/test/{sequence_test.rb → aa_test.rb}

@@ -1,6 +1,6 @@
 require 'test_helper'
-include IsoelectricPoint
-class SequenceTest < Test::Unit::TestCase
+include Bio::Sequence
+class AATest < Test::Unit::TestCase
 
   context 'some known sequences' do
     setup do
@@ -23,10 +23,10 @@ class SequenceTest < Test::Unit::TestCase
         MMS'      => 8.30908203125
       }
     end
-    should 'calculate' do
+    should 'calculate iep' do
       places = 2
       @known.each do |sequence, expected|
-        actual = Sequence.new(sequence).calculate_iep(places)
+        actual = AA.new(sequence).calculate_iep('dtaselect', places)
         assert_equal expected.round_to_places(places), actual, "Expected the iep to be #{expected} but was #{actual} for #{sequence}"
       end
     end
@@ -34,33 +34,65 @@ class SequenceTest < Test::Unit::TestCase
 
   should "Raise if not sequence given" do
     assert_raise ArgumentError do
-      Sequence.new(nil)
+      AA.new(nil)
     end
   end
 
   should "Raise if empty sequence given" do
     assert_raise ArgumentError do
-      Sequence.new(' ')
+      AA.new(' ')
     end
   end
 
 
   should "Raise if unknown pks used" do
     assert_raise ArgumentError do
-      Sequence.new('PG', 'youdontknowme')
+      AA.new('PG', 'youdontknowme')
     end
   end
 
   context "a Sequence" do
     setup do
-      @sequence = Sequence.new("PGAKAAAKKPKKAAG")
+      @sequence = AA.new("PGAKAAAKKPKKAAG")
     end
 
     should "calculates the isolectric point to 0 places" do
-      assert_equal 11, @sequence.calculate_iep(0)
+      assert_equal 11, @sequence.calculate_iep('dtaselect', 0)
     end
     should "calculates the isolectric pointto 3 places" do
-      assert_equal 10.603, @sequence.calculate_iep(3)
+      assert_equal 10.603, @sequence.calculate_iep('dtaselect', 3)
+    end
+
+    context 'use a custom pka set' do
+      setup do
+        @custom = { "N_TERMINUS" => 8.0,
+                    "K" => 9.5,     # changed from dta_select where it is 10.0
+                    "R" => 12.0,
+                    "H" => 6.5,
+                    "C_TERMINUS" => 3.1,
+                    "D" => 4.4,
+                    "E" => 4.4,
+                    "C" => 8.5,
+                    "Y" => 10.1
+                  }
+      end
+      should 'accept a custom pka set and use it for calculation' do
+        assert_equal 10.106, @sequence.calculate_iep(@custom, 3)
+      end
+
+      should 'raise when no result can be found due to a invalid set' do
+        @custom['K'] = 20
+        assert_raises RuntimeError do
+          @sequence.calculate_iep(@custom, 3)
+        end
+      end
+    end
+    context 'use another pka set' do
+      should 'work with all provided sets without raising' do
+        Bio::Sequence::PkaData::PKAS.keys.each do |key|
+          @sequence.calculate_iep(key, 3, 25)
+        end
+      end
     end
   end
 end

metadata

@@ -1,22 +1,22 @@
 --- !ruby/object:Gem::Specification 
 name: isoelectric_point
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 23
   prerelease: false
   segments: 
   - 0
   - 0
-  - 3
-  version: 0.0.3
+  - 4
+  version: 0.0.4
 platform: ruby
 authors: 
-- GeorgeR
+- GeorgeG
 - pascalbetz
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2010-10-05 00:00:00 +02:00
+date: 2010-10-07 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -60,14 +60,14 @@ files:
 - LICENSE
 - README.rdoc
 - lib/isoelectric_point.rb
-- lib/isoelectric_point/data.rb
+- lib/isoelectric_point/pka_data.rb
 - lib/isoelectric_point/extensions.rb
-- lib/isoelectric_point/sequence.rb
-- test/sequence_test.rb
+- lib/isoelectric_point/aa.rb
+- test/aa_test.rb
 - test/extensions_test.rb
 - test/test_helper.rb
 has_rdoc: true
-homepage: http://github.com/simplificator/isoelectric_point
+homepage: http://github.com/GeorgeG/isoelectric_point_4_R
 licenses: []
 
 post_install_message: 
@@ -99,8 +99,8 @@ rubyforge_project:
 rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
-summary: Calculate isoelectric point. Based on code frmo GeorgeR. We just took it and made a gem of it.
+summary: Calculate isoelectric point.
 test_files: 
-- test/sequence_test.rb
+- test/aa_test.rb
 - test/extensions_test.rb
 - test/test_helper.rb

data/lib/isoelectric_point/data.rb

@@ -1,56 +0,0 @@
-module IsoelectricPoint
-  module Data
-    PKAS = {
-      'dtaselect' => { "N_TERMINUS" => 8.0,
-                        "K" => 10.0,
-                        "R" => 12.0,
-                        "H" => 6.5,
-                        "C_TERMINUS" => 3.1,
-                        "D" => 4.4,
-                        "E" => 4.4,
-                        "C" => 8.5,
-                        "Y" => 10.0
-                     }.freeze,
-      'emboss' =>   { "N_TERMINUS" => 8.0,
-                      "K" => 10.0,
-                      "R" => 12.0,
-                      "H" => 6.5,
-                      "C_TERMINUS" => 3.1,
-                      "D" => 4.4,
-                      "E" => 4.4,
-                      "C" => 8.5,
-                      "Y" => 10.0
-                    }.freeze,
-      'rodwell' =>  { "N_TERMINUS" => 8.0,
-                      "K" => 11.5,
-                      "R" => 11.5,
-                      "H" => 6.0,
-                      "C_TERMINUS" => 3.1,
-                      "D" => 3.68,
-                      "E" => 4.25,
-                      "C" => 8.33,
-                      "Y" => 10.07
-                    }.freeze,
-      'wikipedia' => { "N_TERMINUS" => 8.2,
-                       "K" => 10.54,
-                       "R" => 12.48,
-                       "H" => 6.04,
-                       "C_TERMINUS" => 3.65,
-                       "D" => 3.9,
-                       "E" => 4.07,
-                       "C" => 8.18,
-                       "Y" => 10.47
-                    }.freeze,
-      'silerio' =>  { "N_TERMINUS" => 8.2,
-                      "K" => 10.4,
-                      "R" => 12.0,
-                      "H" => 6.4,
-                      "C_TERMINUS" => 3.2,
-                      "D" => 4.0,
-                      "E" => 4.5,
-                      "C" => 9.0,
-                      "Y" => 10.0
-                    }.freeze
-    }.freeze
-  end
-end

data/lib/isoelectric_point/sequence.rb

@@ -1,67 +0,0 @@
-#calculates the isoelectric point of a given protein sequence
-module IsoelectricPoint
-  class Sequence
-    CHARGED_GROUPS = %w{K R H D E C Y}
-    KEYS_PLUS = ['K', 'R', 'H']
-    KEYS_MINUS = ['D', 'E', 'C', 'Y']
-
-    attr_accessor :value
-    attr_reader :pks
-
-    def initialize(sequence, pka_set_name = 'dtaselect')
-      raise ArgumentError.new("pka_set_name is required") if pka_set_name.nil? || pka_set_name.strip == ''
-      raise ArgumentError.new("sequence is required") if sequence.nil? || sequence.strip == ''
-      @pks = Data::PKAS[pka_set_name]
-      @value = sequence.upcase.gsub(/\s/, '')
-      raise ArgumentError.new("pka_set '#{pka_set_name}' is unknown. Please specify one of #{Data::PKAS.keys.join(', ')}") unless self.pks
-    end
-
-    def calculate_iep(places = 2)
-      precission = 15
-      ph = 7.5
-      step = 3.5
-      target_charge = 0.0
-      begin
-        current_charge = calculate_charge_at(ph)
-        if current_charge > 0
-          ph += step
-        else
-          ph -= step
-        end
-        step /= 2.0
-        #puts "#{self.value}: %.10f / %.10f / %.10f : direction was #{current_charge > 0 ? '+' : '-'}" % [current_charge, step, ph]
-        #sleep 0.1
-      end while current_charge == nil || target_charge.round_to_places(precission) != current_charge.round_to_places(precission)
-      ph.round_to_places(places)
-    end
-
-
-    def calculate_charge_at(ph)
-      KEYS_PLUS.inject(partial_charge(pks['N_TERMINUS'], ph)) do |memo, item|
-        memo += partial_charge(self.pks[item], ph) * charged_residue_frequencies[item]
-      end -
-      KEYS_MINUS.inject(partial_charge(ph, pks['C_TERMINUS'])) do |memo, item|
-        memo += partial_charge(ph, self.pks[item]) * charged_residue_frequencies[item]
-      end
-    end
-
-    private
-
-    def charged_residue_frequencies
-      @charged_residue_frequency ||= calculate_charged_residue_frequencies
-    end
-
-    def partial_charge(a, b)
-      x = 10 ** (a - b)
-      x / (x + 1).to_f
-    end
-
-    def calculate_charged_residue_frequencies
-      CHARGED_GROUPS.inject(Hash.new(0)) do |memo, item|
-        memo[item] = self.value.count(item)
-        memo
-      end
-    end
-
-  end
-end