mspire 0.6.24 → 0.6.25

data/VERSION

@@ -1 +1 @@
-0.6.24
+0.6.25

data/lib/ms/isotope/distribution.rb

@@ -0,0 +1,105 @@
+
+require 'ms/mass'
+require 'ms/isotope'
+require 'ms/molecular_formula'
+require 'ms/spectrum'
+
+require 'fftw3'
+
+module MS
+  class Isotope
+    module Distribution
+      NORMALIZE = :total
+      PERCENT_CUTOFF = 0.001
+    end
+  end
+end
+
+module MS
+  class MolecularFormula < Hash
+
+    # 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.
+    #
+    # 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 
+    #             (this is typically the monoisotopic peak)
+    def isotope_distribution(normalize=MS::Isotope::Distribution::NORMALIZE, percent_cutoff=MS::Isotope::Distribution::PERCENT_CUTOFF)
+      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 
+      end
+
+      # normalization
+      norm_by =
+        case normalize
+        when :total
+          sum
+        when :max
+          final_output.max
+        when :low
+          final_output.first
+        end
+      final_output.map {|i| i / norm_by }
+    end
+
+    # returns a spectrum object with mass values and intensity values.
+    # Arguments are passed directly to isotope_distribution.
+    def isotope_distribution_spectrum(*args)
+      intensities = isotope_distribution(*args)
+      mono = self.map {|el,cnt| MS::Mass::MONO[el]*cnt }.reduce(:+)
+      masses = Array.new(intensities.size)
+      neutron = MS::Mass::NEUTRON
+      masses[0] = mono
+      (1...masses.size).each {|i| masses[i] = masses[i-1] + neutron }
+      MS::Spectrum.new [masses, intensities]
+    end
+
+    # returns relative ratios from low nominal mass to high nominal mass.
+    # These are *not* normalized at all.
+    def raw_isotope_distribution
+      low_nominal = 0
+      high_nominal = 0
+      self.each do |el,cnt|
+        isotopes = MS::Isotope::BY_ELEMENT[el]
+        low_nominal += (isotopes.first.mass_number * cnt)
+        high_nominal += (isotopes.last.mass_number * cnt)
+      end
+
+      ffts = self.map do |el, cnt|
+        isotope_el_ar = NArray.float(high_nominal)
+        MS::Isotope::BY_ELEMENT[el].each do |isotope|
+          isotope_el_ar[isotope.mass_number] = isotope.relative_abundance
+        end
+        FFTW3.fft(isotope_el_ar)**cnt
+      end
+      FFTW3.ifft(ffts.reduce(:*)).real.to_a[low_nominal..high_nominal]
+    end
+
+  end
+
+
+  class Isotope
+    module Distribution
+      def self.calculate(molecular_formula_like, normalize=MS::Isotope::Distribution::NORMALIZE, percent_cutoff=MS::Isotope::Distribution::PERCENT_CUTOFF)
+        MS::MolecularFormula.new(molecular_formula_like).isotope_distribution(normalize, percent_cutoff)
+      end
+
+      def self.spectrum(molecular_formula_like, normalize=MS::Isotope::Distribution::NORMALIZE, percent_cutoff=MS::Isotope::Distribution::PERCENT_CUTOFF)
+        MS::MolecularFormula.new(molecular_formula_like).isotope_distribution_spectrum(normalize, percent_cutoff)
+      end
+    end
+  end
+
+end

data/lib/ms/mass.rb

@@ -1,56 +1,50 @@
+require 'ms/isotope'
+require 'ms/molecular_formula'
+
 module MS
   module Mass
 
     # takes a molecular formula in this format: C2BrH12O
     def self.formula_to_exact_mass(formula)
-      # TODO: add other input methods
-      pairs = formula.scan(/([A-Z][a-z]?)(\d*)/).map do |match|
-        if match.last == ''
-          match[-1] = 1
-        end
-        [match[0], match[1].to_i]
-      end
-      pairs.map do |pair|
-        MONO[pair.first.downcase] * pair.last
+      MS::MolecularFormula.new(formula).map do |el,cnt|
+        MONO[el] * cnt
       end.reduce(:+)
     end
 
-    ELECTRON = 0.0005486 # www.mikeblaber.org/oldwine/chm1045/notes/Atoms/.../Atoms03.htm
-    H_PLUS = 1.00727646677
-    #  + http://www.unimod.org/masses.html
     MONO_STR = {
-      'c' => 12.0,  # +
-      'br' => 78.9183361,  # +
-      'd' => 2.014101779,  # +
-      'f' => 18.99840322,  # +
-      'n' => 14.003074,  # +
-      'o' => 15.99491463,  # +
-      'na' => 22.9897677,  # +
-      'p' => 30.973762,  # +
-      's' => 31.9720707,  # +
-      'li' => 7.016003,  # +
-      'cl' => 34.96885272,  # +
-      'k' => 38.9637074,  # +
-      'si' => 27.9769265325, # http://physics.nist.gov/cgi-bin/Compositions/stand_alone.pl?ele=Si&ascii=html&isotype=some
-      'i' => 126.904473,  # +
       'h+' => 1.00727646677,
-      'h' => 1.007825035,  # +
-      'h2o' => 18.0105647,
-      'oh' => 17.002739665,
-      'e' => 0.0005486,
-      'se' => 79.9165196
+      'e' => 0.0005486,   # www.mikeblaber.org/oldwine/chm1045/notes/Atoms/.../Atoms03.htm
+      'neutron' => 1.0086649156,
     }
+    MS::Isotope::BY_ELEMENT.each do |el, isotopes|
+      MONO_STR[el.to_s] = isotopes.find {|iso| iso.mono }.atomic_mass
+    end
+    MONO_STR['h2o'] = %w(h h o).map {|el| MONO_STR[el] }.reduce(:+)
+    MONO_STR['oh'] = %w(o h).map {|el| MONO_STR[el] }.reduce(:+)
+    # add on deuterium
+    MONO_STR['d'] = MS::Isotope::BY_ELEMENT[:h].find {|iso| iso.element == :h && iso.mass_number == 2 }.atomic_mass
+
     AVG_STR = {
       'h+' => 1.007276, # using Mascot_H_plus mass (is this right for AVG??)
-      'h' => 1.00794,
-      'h2o' => 18.01528, 
-      'oh' => 17.00734,
+      'e' => 0.0005486,
+      'neutron' => 1.0086649156,
     }
-    # sets MONO_STR, MONO, AVG_STR, and AVG
+    MS::Isotope::BY_ELEMENT.each do |el, isotopes|
+      AVG_STR[el.to_s] = isotopes.first.average_mass
+    end
+    AVG_STR['h2o'] = %w(h h o).map {|el| AVG_STR[el] }.reduce(:+)
+    AVG_STR['oh'] = %w(o h).map {|el| AVG_STR[el] }.reduce(:+)
+
+    # sets MONO_SYM, MONO, AVG_SYM, and AVG
     %w(MONO AVG).each do |type|
       const_set "#{type}_SYM", Hash[ const_get("#{type}_STR").map {|k,v| [k.to_sym, v] } ]
       const_set type, const_get("#{type}_STR").merge( const_get("#{type}_SYM") )
     end
+
+    ELECTRON = MONO[:e]
+    NEUTRON = MONO[:neutron]
+    H_PLUS = MONO['h+']
+
   end
 end
 

data/lib/ms/molecular_formula.rb

@@ -0,0 +1,21 @@
+require 'ms/isotope'
+
+module MS
+  class MolecularFormula < Hash
+
+    # takes a string or a hash:
+    #
+    #     "H22C12N1O3S2BeLi2"                    # <= order doesn't matter
+    #     {h: 22, c: 12, n: 1, o: 3, s: 2}  # case and string/sym doesn't matter
+    def initialize(arg)
+      if arg.is_a?(String)
+        arg.scan(/([A-Z][a-z]?)(\d*)/).each do |k,v| 
+          self[k.downcase.to_sym] = (v == '' ? 1 : v.to_i)
+        end
+      else
+        self.merge!(arg)
+      end
+    end
+
+  end
+end

data/lib/ms/spectrum_like.rb

@@ -39,12 +39,20 @@ module MS
     def mzs
       @data_arrays[0]
     end
+
+    def mzs=(ar)
+      @data_arrays[0] = ar
+    end
       
     # An array of the intensities data, corresponding to mzs.
     def intensities
       @data_arrays[1]
     end
 
+    def intensities=(ar)
+      @data_arrays[1] = ar
+    end
+
     def mzs_and_intensities
       [@data_arrays[0], @data_arrays[1]]
     end

data/mspire.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "mspire"
-  s.version = "0.6.24"
+  s.version = "0.6.25"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["John T. Prince", "Simon Chiang"]
@@ -58,10 +58,12 @@ Gem::Specification.new do |s|
     "lib/ms/ident/search.rb",
     "lib/ms/isotope.rb",
     "lib/ms/isotope/aa.rb",
+    "lib/ms/isotope/distribution.rb",
     "lib/ms/isotope/nist_isotope_info.yml",
     "lib/ms/mascot.rb",
     "lib/ms/mass.rb",
     "lib/ms/mass/aa.rb",
+    "lib/ms/molecular_formula.rb",
     "lib/ms/mzml.rb",
     "lib/ms/mzml/activation.rb",
     "lib/ms/mzml/chromatogram.rb",
@@ -126,8 +128,10 @@ Gem::Specification.new do |s|
     "spec/ms/ident/pepxml_spec.rb",
     "spec/ms/ident/protein_group_spec.rb",
     "spec/ms/isotope/aa_spec.rb",
+    "spec/ms/isotope/distribution_spec.rb",
     "spec/ms/isotope_spec.rb",
     "spec/ms/mass_spec.rb",
+    "spec/ms/molecular_formula_spec.rb",
     "spec/ms/mzml/cv_spec.rb",
     "spec/ms/mzml/data_array_spec.rb",
     "spec/ms/mzml/file_content_spec.rb",

data/spec/ms/isotope/distribution_spec.rb

@@ -0,0 +1,20 @@
+require 'spec_helper'
+
+require 'ms/isotope/distribution'
+
+describe 'MS::Isotope::Distribution class methods' do
+  before do 
+    @data = [1.0, 0.08919230588715289, 0.017894161377222082, 0.0013573997600723623, 0.0001398330738144092]
+  end
+
+  it 'can calculate isotope distributions' do
+    MS::Isotope::Distribution.calculate('C8O7', :max).should == @data
+  end
+
+  # no m/z values, just mass values
+  it 'can calculate isotope distribution spectrum' do
+    spec = MS::Isotope::Distribution.spectrum('C8O7', :max)
+    spec.mzs.should == [207.96440233692, 208.97306725252, 209.98173216812, 210.99039708372, 211.99906199932002]
+    spec.intensities.should == [1.0, 0.08919230588715289, 0.017894161377222082, 0.0013573997600723623, 0.0001398330738144092]
+  end
+end

data/spec/ms/mass_spec.rb

@@ -1,8 +1,42 @@
 require 'spec_helper'
 
+require 'ms/mass'
+
 describe 'MS::Mass' do
   it 'can access elemental masses by string or symbol' do
-    MS::Mass::MONO['h'].should be_a_kind_of Float
-    MS::Mass::MONO[:h].should be_a_kind_of Float
+    {
+      'c' => 12.0,  # +
+      'br' => 78.9183361,  # +
+      'd' => 2.014101779,  # +
+      'f' => 18.99840322,  # +
+      'n' => 14.003074,  # +
+      'o' => 15.99491463,  # +
+      'na' => 22.9897677,  # +
+      'p' => 30.973762,  # +
+      's' => 31.9720707,  # +
+      'li' => 7.016003,  # +
+      'cl' => 34.96885272,  # +
+      'k' => 38.9637074,  # +
+      'si' => 27.9769265325, 
+      'i' => 126.904473,  # +
+      'h+' => 1.00727646677,
+      'h' => 1.007825035,  # +
+      'h2o' => 18.0105647,
+      'oh' => 17.002739665,
+      'e' => 0.0005486,
+      'se' => 79.9165196
+    }.each do |el, mass|
+      MS::Mass::MONO[el].should_not be_nil
+      MS::Mass::MONO[el].should == MS::Mass::MONO[el.to_sym]
+      MS::Mass::MONO[el].should be_within(0.00001).of(mass) 
+    end
+
+
+    { h: 1.00794, he: 4.002602, ni: 58.6934 }.each do |el, mass|
+      MS::Mass::AVG[el].should_not be_nil
+      MS::Mass::AVG[el].should == MS::Mass::AVG[el.to_sym]
+      MS::Mass::AVG[el].should be_within(0.00001).of(mass) 
+    end
+
   end
 end

data/spec/ms/molecular_formula_spec.rb

@@ -0,0 +1,15 @@
+require 'spec_helper'
+
+require 'ms/molecular_formula'
+
+describe MS::MolecularFormula do
+
+  it 'can be initialized with a String or Hash' do
+    data = {h: 22, c: 12, n: 1, o: 3, s: 2}
+    mf = MS::MolecularFormula.new "H22BeC12N1O3S2Li2"
+    mf.should == {:h=>22, :be=>1, :c=>12, :n=>1, :o=>3, :s=>2, :li=>2}
+    mf = MS::MolecularFormula.new(data)
+    mf.should == data
+  end
+
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.6.24
+  version: 0.6.25
   prerelease: 
 platform: ruby
 authors:
@@ -14,7 +14,7 @@ date: 2012-03-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &13307340 !ruby/object:Gem::Requirement
+  requirement: &13676060 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +22,10 @@ dependencies:
         version: '1.5'
   type: :runtime
   prerelease: false
-  version_requirements: *13307340
+  version_requirements: *13676060
 - !ruby/object:Gem::Dependency
   name: bsearch
-  requirement: &13323080 !ruby/object:Gem::Requirement
+  requirement: &13674700 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: 1.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *13323080
+  version_requirements: *13674700
 - !ruby/object:Gem::Dependency
   name: andand
-  requirement: &13322420 !ruby/object:Gem::Requirement
+  requirement: &13673200 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +44,10 @@ dependencies:
         version: 1.3.1
   type: :runtime
   prerelease: false
-  version_requirements: *13322420
+  version_requirements: *13673200
 - !ruby/object:Gem::Dependency
   name: obo
-  requirement: &13321500 !ruby/object:Gem::Requirement
+  requirement: &13672440 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +55,10 @@ dependencies:
         version: 0.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *13321500
+  version_requirements: *13672440
 - !ruby/object:Gem::Dependency
   name: builder
-  requirement: &13320060 !ruby/object:Gem::Requirement
+  requirement: &13671860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -66,10 +66,10 @@ dependencies:
         version: 3.0.0
   type: :runtime
   prerelease: false
-  version_requirements: *13320060
+  version_requirements: *13671860
 - !ruby/object:Gem::Dependency
   name: trollop
-  requirement: &13319460 !ruby/object:Gem::Requirement
+  requirement: &13687020 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -77,10 +77,10 @@ dependencies:
         version: 1.16.2
   type: :runtime
   prerelease: false
-  version_requirements: *13319460
+  version_requirements: *13687020
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &13318520 !ruby/object:Gem::Requirement
+  requirement: &13685880 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -88,10 +88,10 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *13318520
+  version_requirements: *13685880
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &13317560 !ruby/object:Gem::Requirement
+  requirement: &13684660 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -99,10 +99,10 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *13317560
+  version_requirements: *13684660
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &13316940 !ruby/object:Gem::Requirement
+  requirement: &13683500 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -110,7 +110,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *13316940
+  version_requirements: *13683500
 description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire,
   merging of ms-* gems
 email: jtprince@gmail.com
@@ -161,10 +161,12 @@ files:
 - lib/ms/ident/search.rb
 - lib/ms/isotope.rb
 - lib/ms/isotope/aa.rb
+- lib/ms/isotope/distribution.rb
 - lib/ms/isotope/nist_isotope_info.yml
 - lib/ms/mascot.rb
 - lib/ms/mass.rb
 - lib/ms/mass/aa.rb
+- lib/ms/molecular_formula.rb
 - lib/ms/mzml.rb
 - lib/ms/mzml/activation.rb
 - lib/ms/mzml/chromatogram.rb
@@ -229,8 +231,10 @@ files:
 - spec/ms/ident/pepxml_spec.rb
 - spec/ms/ident/protein_group_spec.rb
 - spec/ms/isotope/aa_spec.rb
+- spec/ms/isotope/distribution_spec.rb
 - spec/ms/isotope_spec.rb
 - spec/ms/mass_spec.rb
+- spec/ms/molecular_formula_spec.rb
 - spec/ms/mzml/cv_spec.rb
 - spec/ms/mzml/data_array_spec.rb
 - spec/ms/mzml/file_content_spec.rb