mspire 0.7.4 → 0.7.5

data/VERSION

@@ -1 +1 @@
-0.7.4
+0.7.5

data/lib/mspire/isotope/distribution.rb

@@ -10,7 +10,6 @@ module Mspire
   class Isotope
     module Distribution
       NORMALIZE = :total
-      PERCENT_CUTOFF = 0.001
     end
   end
 end
@@ -20,42 +19,53 @@ module Mspire
 
     # takes any element composition (see any_to_num_elements).
     #
-    # returns isotopic distribution beginning with monoisotopic peak and
-    # finishing when the peak contributes less than percent_cutoff to the total
-    # distribution.  Then, normalization occurs.
+    # returns isotopic distribution beginning with monoisotopic peak.  It cuts
+    # off when no more peaks contribute more than percent_cutoff to the total
+    # distribution.  After that, normalization is performed.
     #
     # all values will be fractional.  normalize may be one of:
     #
     #     :total   normalize to the total intensity
     #     :max     normalize to the highest peak intensity
-    #     :low     normalize to the intensity of the lowest m/z peak 
+    #     :first   normalize to the intensity of the first peak 
     #             (this is typically the monoisotopic peak)
-    def isotope_distribution(normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=Mspire::Isotope::Distribution::PERCENT_CUTOFF)
+    def isotope_distribution(normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=nil)
       mono_dist = raw_isotope_distribution
-      # percent_cutoff:
-      final_output = []
-      sum = 0.0
-      mono_dist.each do |peak|
-        break if (peak / sum)*100 < percent_cutoff
-        final_output << peak
-        sum += peak 
+
+      if percent_cutoff
+        total_signal = mono_dist.reduce(:+)
+        cutoff_index = (mono_dist.size-1).downto(0).find do |i|
+          (mono_dist[i] / total_signal) >= (percent_cutoff/100.0)
+        end
+        # deletes these elements
+        if cutoff_index
+          mono_dist.slice!((cutoff_index+1)..-1)
+        else
+          # no peaks pass that percent cutoff threshold!
+          mono_dist = []
+        end
       end
 
       # normalization
       norm_by =
         case normalize
         when :total
-          sum
+          total_signal || mono_dist.reduce(:+)
         when :max
-          final_output.max
-        when :low
-          final_output.first
+          mono_dist.max
+        when :first
+          mono_dist.first
         end
-      final_output.map {|i| i / norm_by }
+      mono_dist.map do |i| 
+        v = i / norm_by
+        (v > 0) ? v : 0
+      end
     end
 
     # returns a spectrum object with mass values and intensity values.
     # Arguments are passed directly to isotope_distribution.
+    # the molecule has a charge, this will be used to adjust the m/z values
+    # (by removing or adding electrons to the m/z and as the z)
     def isotope_distribution_spectrum(*args)
       intensities = isotope_distribution(*args)
       mono = self.map {|el,cnt| Mspire::Mass::MONO[el]*cnt }.reduce(:+)
@@ -63,6 +73,11 @@ module Mspire
       neutron = Mspire::Mass::NEUTRON
       masses[0] = mono
       (1...masses.size).each {|i| masses[i] = masses[i-1] + neutron }
+      if self.charge && self.charge != 0
+        masses.map! do |mass| 
+          (mass - (self.charge * Mspire::Mass::ELECTRON)) / self.charge 
+        end
+      end
       Mspire::Spectrum.new [masses, intensities]
     end
 
@@ -92,12 +107,14 @@ module Mspire
 
   class Isotope
     module Distribution
-      def self.calculate(molecular_formula_like, normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=Mspire::Isotope::Distribution::PERCENT_CUTOFF)
-        Mspire::MolecularFormula.new(molecular_formula_like).isotope_distribution(normalize, percent_cutoff)
+      def self.calculate(molecular_formula_like, normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=nil)
+        mf = molecular_formula_like.is_a?(Mspire::MolecularFormula) ? molecular_formula_like : Mspire::MolecularFormula.new(molecular_formula_like)
+        mf.isotope_distribution(normalize, percent_cutoff)
       end
 
-      def self.spectrum(molecular_formula_like, normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=Mspire::Isotope::Distribution::PERCENT_CUTOFF)
-        Mspire::MolecularFormula.new(molecular_formula_like).isotope_distribution_spectrum(normalize, percent_cutoff)
+      def self.spectrum(molecular_formula_like, normalize=Mspire::Isotope::Distribution::NORMALIZE, percent_cutoff=nil)
+        mf = molecular_formula_like.is_a?(Mspire::MolecularFormula) ? molecular_formula_like : Mspire::MolecularFormula.new(molecular_formula_like)
+        mf.isotope_distribution_spectrum(normalize, percent_cutoff)
       end
     end
   end

data/mspire.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "mspire"
-  s.version = "0.7.4"
+  s.version = "0.7.5"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["John T. Prince", "Simon Chiang"]
-  s.date = "2012-03-21"
+  s.date = "2012-03-23"
   s.description = "mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire, merging of ms-* gems"
   s.email = "jtprince@gmail.com"
   s.extra_rdoc_files = [

data/spec/mspire/isotope/distribution_spec.rb

@@ -4,17 +4,56 @@ require 'mspire/isotope/distribution'
 
 describe 'Mspire::Isotope::Distribution class methods' do
   before do 
-    @data = [1.0, 0.08919230588715311, 0.017894161377222138, 0.0013573997600723345, 0.0001398330738144181]
+    @first = [1.0, 0.08919230588715311, 0.017894161377222138, 0.0013573997600723345, 0.0001398330738144181]
   end
+  # can also be used on a real MolecularFormula object
+  subject { 'C102H120O15' }
 
-  it 'can calculate isotope distributions' do
-    Mspire::Isotope::Distribution.calculate('C8O7', :max).should == @data
+  describe 'normalizing isotope distributions' do
+
+    it 'defaults to normalizing by total signal with no cutoff' do
+      dist = Mspire::Isotope::Distribution.calculate( subject )
+      dist.size.should == 253
+      dist[0,5].should == [0.31740518639058685, 0.35635707398291416, 0.20793431846543858, 0.08373257192958428, 0.026084566135229446]
+    end
+
+    it 'can normalize by first peak' do
+      dist = Mspire::Isotope::Distribution.calculate( subject, :first )
+      dist.size.should == 253
+      dist[0].should == 1.0
+      dist[1].should_not == 1.0
+    end
+
+    it 'can normalize by the max peak' do
+      dist = Mspire::Isotope::Distribution.calculate( subject, :max)
+      dist.size.should == 253
+      dist[0].should_not == 1.0
+      dist[1].should == 1.0
+    end
+
+    it 'can cutoff based on percent of total signal' do
+      Mspire::Isotope::Distribution.calculate(subject, :max, 100).should == []
+      Mspire::Isotope::Distribution.calculate(subject, :max, 20).should == [0.8906942209481861, 1.0, 0.5834999040187656]
+      Mspire::Isotope::Distribution.calculate(subject, :max, 5).should == [0.8906942209481861, 1.0, 0.5834999040187656, 0.23496817670469172]
+      Mspire::Isotope::Distribution.calculate(subject, :max, 0.0001).size.should == 11
+    end
   end
 
-  # no m/z values, just mass values
-  it 'can calculate isotope distribution spectrum' do
-    spec = Mspire::Isotope::Distribution.spectrum('C8O7', :max)
-    spec.mzs.should == [207.96440233692, 208.97306725252, 209.98173216812, 210.99039708372, 211.99906199932002]
-    spec.intensities.should == [1.0, 0.08919230588715311, 0.017894161377222138, 0.0013573997600723345, 0.0001398330738144181]
+  describe 'calculating an isotope distribution spectrum' do
+
+    it 'gives neutral masses if no charge' do
+      spec = Mspire::Isotope::Distribution.spectrum( subject )
+      [:mzs, :intensities].each {|att| spec.send(att).size.should == 253 }
+      spec.mzs[0,5].should == [1584.8627231418, 1585.8713880574, 1586.8800529730001, 1587.8887178886002, 1588.8973828042003]
+      spec.intensities[0,5].should == [0.31740518639058685, 0.35635707398291416, 0.20793431846543858, 0.08373257192958428, 0.026084566135229446]
+    end
+
+    it 'gives proper m/z values if the molecule is charged' do
+      charged_molecule = Mspire::MolecularFormula.new( subject )
+      charged_molecule.charge = -3
+      spec = Mspire::Isotope::Distribution.spectrum( charged_molecule )
+      [:mzs, :intensities].each {|att| spec.send(att).size.should == 253 }
+      spec.mzs[0,5].should == [-528.2881229806, -528.6243446191334, -528.9605662576668, -529.2967878962, -529.6330095347334]
+    end
   end
 end

data/spec/mspire/molecular_formula_spec.rb

@@ -12,4 +12,12 @@ describe Mspire::MolecularFormula do
     mf.should == data
   end
 
+  it 'expects properly capitalized abbreviations' do
+    Mspire::MolecularFormula.new('Ni7Se3').should == {:ni=>7, :se=>3}
+    # there is no such thing as the E element, so this is going to get the
+    # user in trouble.  However, this is the proper interpretation of the
+    # formula.
+    Mspire::MolecularFormula.new('Ni7SE3').should == {:ni=>7, :s=>1, :e=>3}
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.7.4
+  version: 0.7.5
   prerelease: 
 platform: ruby
 authors:
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-21 00:00:00.000000000 Z
+date: 2012-03-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri