mspire 0.9.1 → 0.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c336dad2fe75675083d7a794707b30f1a8c66146
-  data.tar.gz: c20655cf68c224ef11fcfa72fcaf9434b2ae8a23
+  metadata.gz: cacdee4487f5e6a98d31c9649cb02390bce1dd9d
+  data.tar.gz: 64ae39986bc3bb20dcbcff972ef8162bdd36609b
 SHA512:
-  metadata.gz: ddd03724a6b05881f64cd09deb3bf9d8f17e77d515a22419f95cf02f505d780bc347e8b9afd3f0d387d947d00166b0f36340f7ec81dbd1d47022e2333a3425a7
-  data.tar.gz: 7a110c0640b43c775c37deb63d3e5eb53c7f0d7f1e9aa5debd65707428bc25590db626f78701156c0354383d5e9d30128fcb741bc647ce8c331638b401ba05b3
+  metadata.gz: 6523afd75ba3fd0f179d587413b6c85f7bf77152e8c97a155152352498742ff3c53d628b49b9d613f51a1f9d33fde5d7e2f9911c9055d0b751979ad2127faac4
+  data.tar.gz: fae953898b991b9f0cb6917fc8eaf4ff2e8557c6f73f82b750abe22b68f5f435de300c36c0b7835751b7a48ac22e40d59d340e4f4d6898478615fe6cbf66e892

data/Gemfile

@@ -2,3 +2,7 @@ source 'https://rubygems.org'
 
 # Specify your gem's dependencies in mspire.gemspec
 gemspec
+
+group :messing_around do
+  gem "pry"
+end

data/README.md

@@ -125,12 +125,15 @@ Mspire::Mass::Subatomic::MONO[:electron]
 
 ### Isotopes and molecular formulas
 
+Uses Richard Neese biological isotope ratios by default.  All other isotope information culled from NIST.
+
 ```ruby
 require 'mspire/isotope'
 isotopes = Mspire::Isotope::ISOTOPES  # 288 isotopes
-hydrogen_isotopes = isotopes.select {|iso| iso.element == :h }
+# same as Mspire::Isotope::Neese::ISOTOPES ; compare to Mspire::Isotope::NIST::ISOTOPES
+hydrogen_isotopes = isotopes.select {|iso| iso.element == :H }
 
-c12 = Mspire::Isotope::BY_ELEMENT[:c].first
+c12 = Mspire::Isotope::BY_ELEMENT[:C].first
 c12.atomic_number # also: mass_number atomic_mass relative_abundance average_mass
 c12.mono   # => true (this is the monoisotopic isotope)
 

data/lib/mspire/isotope/distribution.rb

@@ -106,14 +106,21 @@ module Mspire
 
   class Isotope
     module Distribution
-      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.from_any(molecular_formula_like)
-        mf.isotope_distribution(normalize, percent_cutoff)
-      end
 
-      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.from_any(molecular_formula_like)
-        mf.isotope_distribution_spectrum(normalize, percent_cutoff)
+      class << self
+        def to_mf(obj)
+          obj.is_a?(Mspire::MolecularFormula) ? obj : Mspire::MolecularFormula.from_any(obj)
+        end
+
+        def calculate(molecular_formula_like, normalize=NORMALIZE, percent_cutoff=nil, isotope_table=Mspire::Isotope::BY_ELEMENT)
+          mf = to_mf(molecular_formula_like)
+          mf.isotope_distribution(normalize, percent_cutoff, isotope_table)
+        end
+
+        def spectrum(molecular_formula_like, normalize=NORMALIZE, percent_cutoff=nil, isotope_table=Mspire::Isotope::BY_ELEMENT)
+          mf = to_mf(molecular_formula_like)
+          mf.isotope_distribution_spectrum(normalize, percent_cutoff, isotope_table)
+        end
       end
     end
   end

data/lib/mspire/isotope/neese.rb

@@ -0,0 +1,33 @@
+require 'mspire/isotope/nist'
+
+module Mspire
+  class Isotope
+    module Neese
+      RATIOS = {
+        H: [0.999844, 0.000156],
+        C: [0.9891, 0.0109],
+        N: [0.99635, 0.00365],
+        O: [0.99759, 0.00037, 0.00204],
+        S: [0.9493, 0.0076, 0.0429, 0.0002]
+      }
+
+      BY_ELEMENT = Mspire::Isotope::NIST::BY_ELEMENT.dup  # shallow copy on purpose
+
+      RATIOS.each do |el, abundances| 
+        BY_ELEMENT[el] = Mspire::Isotope::NIST::BY_ELEMENT[el].
+          zip(abundances).map do |isotope, abundance|
+          if abundance
+            new_isotope = isotope.dup
+            new_isotope.relative_abundance = abundance 
+            new_isotope
+          else
+            isotope
+          end
+        end
+      end
+
+      ISOTOPES = BY_ELEMENT.values.flatten(1).sort_by {|ist| [ist.atomic_number, ist.mass_number] }
+    end
+  end
+end
+

data/lib/mspire/isotope/nist/updater.rb

@@ -0,0 +1,67 @@
+require 'mspire/isotope'
+
+class Mspire::Isotope::NIST::Updater
+  NIST_ISOTOPE_SITE = 'http://physics.nist.gov/cgi-bin/Compositions/stand_alone.pl?ele=&all=all&ascii=ascii2&isotype=some'
+
+  class << self
+
+    # Creates an isotope from a nist entry.  Sets mono to false, which is not
+    # always correct (but needs to be corrected with additional info)
+    def isotope_from_nist_line(*args)
+      # atomic_number and mass_number are ints
+      [0,2].each {|i| args[i] = args[i].to_i }
+      # element is a downcase sym
+      args[1] = args[1].to_sym
+      # atomic_mass, relative_abundance, and average_mass as floats
+      [3, 4, 5].each {|i| args[i] = args[i][/([\w.]*)/].to_f }
+      # by default call every isotope the non-monoisotopic peak
+      # (will correct it as a group)
+      args << false
+      Mspire::Isotope.new(*args)
+    end
+
+    def write_nist_info(filename)
+      isotopes = isotopes_from_nist_site
+      File.write(filename, isotopes.map {|isotope| Mspire::Isotope::MEMBERS.map {|key| isotope.send(key) }}.to_yaml)
+    end
+
+    def isotopes_from_nist_site(deuterium_is_kind_of_hydrogen=true)
+      require 'mechanize'
+      body = Mechanize.new.get(NIST_ISOTOPE_SITE).body.split("\n")
+      body.delete_if {|l| l[/^(<|\/)/]}
+      body.shift(22)
+      isotopes = body.each_slice(8).map do |lines|
+        arr = (1..4).to_a.map {|i| match lines[i] }
+        rel, avg = match(lines[5]), match(lines[6])
+        next if rel.nil?
+        rel.size > 0 ? isotope_from_nist_line(*arr, rel, avg) : nil
+      end.compact!
+
+      # deuterium should be grouped with hydrogen, not as its own element!
+      isotopes.find {|iso| iso.element == :D }.element = :H if deuterium_is_kind_of_hydrogen
+
+      # update the mono boolean if this is the highest abundance peak
+      isotopes.group_by(&:element).values.each do |set|
+        set.max_by(&:relative_abundance).mono = true
+      end
+      isotopes
+    end
+
+    private
+
+    def match(string)
+      unless string.nil?
+        if string.empty?
+          nil
+        else
+          string[/= (.*)/,1]
+        end
+      end
+    end 
+  end 
+end
+
+if __FILE__ == $0
+  require 'mspire/isotope/nist'
+  Mspire::Isotope::NIST::Updater.write_nist_info(Mspire::Isotope::NIST::INFO_FILE_FULL_PATH)
+end

data/lib/mspire/isotope/nist.rb

@@ -0,0 +1,19 @@
+require 'mspire/isotope'
+
+module Mspire::Isotope::NIST
+  INFO_FILE = 'isotope_info.yml'
+  INFO_FILE_FULL_PATH = File.expand_path(File.dirname(__FILE__) + "/nist/#{INFO_FILE}")
+
+  if File.exist?(INFO_FILE_FULL_PATH)
+
+    ISOTOPES = YAML.load_file(INFO_FILE_FULL_PATH).map {|ar| Mspire::Isotope.new *ar }
+    BY_ELEMENT = ISOTOPES.group_by(&:element)
+
+  else
+    unless __FILE__ == $0
+      warn "no file #{INFO_FILE_FULL_PATH} to read isotope information from!"
+      warn "Note that directly running the file: lib/mspire/isotope/nist/updater.rb"
+      warn "will autogenerate this file from NIST data"
+    end
+  end
+end 

data/lib/mspire/isotope.rb

@@ -2,92 +2,30 @@ require 'yaml'
 
 module Mspire
   class Isotope
-    MEMBERS = [:atomic_number, :element, :mass_number, :atomic_mass, :relative_abundance, :average_mass, :mono]
-    MEMBERS.each {|key| attr_accessor key }
-
-    INFO_FILE = 'nist_isotope_info.yml'
-    INFO_FILE_FULL_PATH = File.expand_path(File.dirname(__FILE__) + "/isotope/#{INFO_FILE}")
-
+    MEMBERS = [
+      :atomic_number, 
+      :element, 
+      :mass_number, 
+      :atomic_mass, 
+      :relative_abundance, 
+      :average_mass, 
+      :mono
+    ].each {|key| attr_accessor key }
 
     def initialize(*args)
       MEMBERS.zip(args) {|k,val| self.send("#{k}=", val) }
     end
+  end
+end
 
-    # Creates an isotope from a nist entry.  Sets mono to false, which is not
-    # always correct (but needs to be corrected with additional info)
-    def self.from_nist_line(*args)
-      # atomic_number and mass_number are ints
-      [0,2].each {|i| args[i] = args[i].to_i }
-      # element is a downcase sym
-      args[1] = args[1].to_sym
-      # atomic_mass, relative_abundance, and average_mass as floats
-      [3, 4, 5].each {|i| args[i] = args[i][/([\w.]*)/].to_f }
-      # by default call every isotope the non-monoisotopic peak
-      # (will correct it as a group)
-      args << false
-      self.new(*args)
-    end
-
-    if File.exist?(INFO_FILE_FULL_PATH)
-
-      ISOTOPES = YAML.load_file(INFO_FILE_FULL_PATH).map {|ar| Mspire::Isotope.new *ar }
-      BY_ELEMENT = ISOTOPES.group_by(&:element)
-
-    else
-      unless __FILE__ == $0
-        warn "no file #{INFO_FILE_FULL_PATH} to read isotope information from"
-        warn "directly running the file: #{__FILE__}"
-        warn "will generate the file from NIST data"
-      end
-    end
-
-    class Updater
-      NIST_ISOTOPE_SITE = 'http://physics.nist.gov/cgi-bin/Compositions/stand_alone.pl?ele=&all=all&ascii=ascii2&isotype=some'
-      class << self
-
-        def write_nist_info(filename)
-          isotopes = isotopes_from_nist_site
-          File.write(filename, isotopes.map {|isotope| MEMBERS.map {|key| isotope.send(key) }}.to_yaml)
-        end
-
-        def isotopes_from_nist_site(deuterium_is_kind_of_hydrogen=true)
-          require 'mechanize'
-          body = Mechanize.new.get(NIST_ISOTOPE_SITE).body.split("\n")
-          body.delete_if {|l| l[/^(<|\/)/]}
-          body.shift(22)
-          isotopes = body.each_slice(8).map do |lines|
-            arr = (1..4).to_a.map {|i| match lines[i] }
-            rel, avg = match(lines[5]), match(lines[6])
-            next if rel.nil?
-            rel.size > 0 ? Isotope.from_nist_line(*arr, rel, avg) : nil
-          end.compact!
-
-          # deuterium should be grouped with hydrogen, not as its own element!
-          isotopes.find {|iso| iso.element == :D }.element = :H if deuterium_is_kind_of_hydrogen
-
-          # update the mono boolean if this is the highest abundance peak
-          isotopes.group_by(&:element).values.each do |set|
-            set.max_by(&:relative_abundance).mono = true
-          end
-          isotopes
-        end
-
-        private
+require 'mspire/isotope/neese'
+# sets Mspire::Isotope::BY_ELEMENTS and Mspire::Isotope::ISOTOPES
 
-        def match(string)
-          unless string.nil?
-            if string.empty?
-              nil
-            else
-              string[/= (.*)/,1]
-            end
-          end
-        end 
-      end 
-    end 
+module Mspire
+  class Isotope
+    BY_ELEMENT = Mspire::Isotope::Neese::BY_ELEMENT
+    ISOTOPES = Mspire::Isotope::Neese::ISOTOPES
   end
 end
 
-if __FILE__ == $0
-  Mspire::Isotope::Updater.write_nist_info(Mspire::Isotope::INFO_FILE_FULL_PATH)
-end
+

data/lib/mspire/version.rb

@@ -1,3 +1,3 @@
 module Mspire
-  VERSION = "0.9.1"
+  VERSION = "0.9.2"
 end

data/spec/mspire/isotope/distribution_spec.rb

@@ -3,46 +3,54 @@ require 'spec_helper'
 require 'mspire/isotope/distribution'
 
 describe 'Mspire::Isotope::Distribution class methods' do
+
+  before(:all) do
+    @nist = Mspire::Isotope::NIST::BY_ELEMENT
+    @norm = Mspire::Isotope::Distribution::NORMALIZE
+    @pcut = nil # percent cutoff
+  end
+
   before do 
     @first = [1.0, 0.08919230588715311, 0.017894161377222138, 0.0013573997600723345, 0.0001398330738144181]
   end
+
   # can also be used on a real MolecularFormula object
   subject { 'C102H120O15' }
 
   describe 'normalizing isotope distributions' do
 
     it 'defaults to normalizing by total signal with no cutoff' do
-      dist = Mspire::Isotope::Distribution.calculate( subject )
+      dist = Mspire::Isotope::Distribution.calculate( subject, @norm, @pcut, @nist )
       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 = Mspire::Isotope::Distribution.calculate( subject, :first, @pcut, @nist )
       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 = Mspire::Isotope::Distribution.calculate( subject, :max, @pcut, @nist )
       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
+      Mspire::Isotope::Distribution.calculate(subject, :max, 100, @nist).should == []
+      Mspire::Isotope::Distribution.calculate(subject, :max, 20, @nist).should == [0.8906942209481861, 1.0, 0.5834999040187656]
+      Mspire::Isotope::Distribution.calculate(subject, :max, 5, @nist).should == [0.8906942209481861, 1.0, 0.5834999040187656, 0.23496817670469172]
+      Mspire::Isotope::Distribution.calculate(subject, :max, 0.0001, @nist).size.should == 11
     end
   end
 
   describe 'calculating an isotope distribution spectrum' do
 
     it 'gives neutral masses if no charge' do
-      spec = Mspire::Isotope::Distribution.spectrum( subject )
+      spec = Mspire::Isotope::Distribution.spectrum( subject, @norm, @pcut, @nist )
       [: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]
@@ -51,7 +59,7 @@ describe 'Mspire::Isotope::Distribution class methods' do
     it 'gives proper m/z values if the molecule is charged' do
       charged_molecule = Mspire::MolecularFormula.from_any( subject )
       charged_molecule.charge = -3
-      spec = Mspire::Isotope::Distribution.spectrum( charged_molecule )
+      spec = Mspire::Isotope::Distribution.spectrum( charged_molecule, @norm, @pcut, @nist )
       [: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

data/spec/mspire/isotope/nist_spec.rb

@@ -0,0 +1,32 @@
+require 'spec_helper'
+
+require 'mspire/isotope/nist'
+
+describe 'Mspire::Isotope::NIST' do
+
+  it 'has all the common isotopes: Mspire::Isotope::NIST::ISOTOPES' do
+    # frozen
+    Mspire::Isotope::NIST::ISOTOPES.size.should == 288
+    hydrogen_isotopes = Mspire::Isotope::NIST::ISOTOPES.select {|iso| iso.element == :H }
+    hydrogen_isotopes.size.should == 2
+
+    { atomic_number: 1, element: :H, mass_number: 1, atomic_mass: 1.00782503207, relative_abundance: 0.999885, average_mass: 1.00794, mono: true }.each do |k,v|
+      hydrogen_isotopes.first.send(k).should == v
+    end
+    {atomic_number: 1, element: :H, mass_number: 2, atomic_mass: 2.0141017778, relative_abundance: 0.000115, average_mass: 1.00794, mono: false}.each do |k,v|
+      hydrogen_isotopes.last.send(k).should == v
+    end
+    u = Mspire::Isotope::NIST::ISOTOPES.last
+    {atomic_number: 92, element: :U, mass_number: 238, atomic_mass: 238.0507882, relative_abundance: 0.992742, average_mass: 238.02891, mono: true}.each do |k,v|
+      u.send(k).should == v
+    end
+  end
+  it 'has all common isotopes by element: Mspire::Isotope::BY_ELEMENT' do
+    [{atomic_number: 6, element: :C, mass_number: 12, atomic_mass: 12.0, relative_abundance: 0.9893, average_mass: 12.0107, mono: true}, {atomic_number: 6, element: :C, mass_number: 13, atomic_mass: 13.0033548378, relative_abundance: 0.0107, average_mass: 12.0107, mono: false}].zip(Mspire::Isotope::NIST::BY_ELEMENT[:C]) do |hash, iso|
+      hash.each do |k,v|
+        iso.send(k).should == v
+      end
+    end
+    Mspire::Isotope::NIST::BY_ELEMENT[:H].size.should == 2
+  end
+end

data/spec/mspire/isotope_spec.rb

@@ -3,16 +3,16 @@ require 'spec_helper'
 require 'mspire/isotope'
 
 describe 'Mspire::Isotope constants' do
-  it 'has all the common isotopes: Mspire::Isotope::ISOTOPES' do
+  it 'Mspire::Isotope::ISOTOPES has all the common isotopes and uses Neese by default' do
     # frozen
     Mspire::Isotope::ISOTOPES.size.should == 288
     hydrogen_isotopes = Mspire::Isotope::ISOTOPES.select {|iso| iso.element == :H }
     hydrogen_isotopes.size.should == 2
 
-    { atomic_number: 1, element: :H, mass_number: 1, atomic_mass: 1.00782503207, relative_abundance: 0.999885, average_mass: 1.00794, mono: true }.each do |k,v|
+    { atomic_number: 1, element: :H, mass_number: 1, atomic_mass: 1.00782503207, relative_abundance: 0.999844, average_mass: 1.00794, mono: true }.each do |k,v|
       hydrogen_isotopes.first.send(k).should == v
     end
-    {atomic_number: 1, element: :H, mass_number: 2, atomic_mass: 2.0141017778, relative_abundance: 0.000115, average_mass: 1.00794, mono: false}.each do |k,v|
+    {atomic_number: 1, element: :H, mass_number: 2, atomic_mass: 2.0141017778, relative_abundance: 0.000156, average_mass: 1.00794, mono: false}.each do |k,v|
       hydrogen_isotopes.last.send(k).should == v
     end
     u = Mspire::Isotope::ISOTOPES.last
@@ -21,7 +21,7 @@ describe 'Mspire::Isotope constants' do
     end
   end
   it 'has all common isotopes by element: Mspire::Isotope::BY_ELEMENT' do
-    [{atomic_number: 6, element: :C, mass_number: 12, atomic_mass: 12.0, relative_abundance: 0.9893, average_mass: 12.0107, mono: true}, {atomic_number: 6, element: :C, mass_number: 13, atomic_mass: 13.0033548378, relative_abundance: 0.0107, average_mass: 12.0107, mono: false}].zip(Mspire::Isotope::BY_ELEMENT[:C]) do |hash, iso|
+    [{atomic_number: 6, element: :C, mass_number: 12, atomic_mass: 12.0, relative_abundance: 0.9891, average_mass: 12.0107, mono: true}, {atomic_number: 6, element: :C, mass_number: 13, atomic_mass: 13.0033548378, relative_abundance: 0.0109, average_mass: 12.0107, mono: false}].zip(Mspire::Isotope::BY_ELEMENT[:C]) do |hash, iso|
       hash.each do |k,v|
         iso.send(k).should == v
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.9.2
 platform: ruby
 authors:
 - John T. Prince
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-15 00:00:00.000000000 Z
+date: 2013-08-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -268,7 +268,10 @@ files:
 - lib/mspire/isotope.rb
 - lib/mspire/isotope/aa.rb
 - lib/mspire/isotope/distribution.rb
-- lib/mspire/isotope/nist_isotope_info.yml
+- lib/mspire/isotope/neese.rb
+- lib/mspire/isotope/nist.rb
+- lib/mspire/isotope/nist/isotope_info.yml
+- lib/mspire/isotope/nist/updater.rb
 - lib/mspire/mascot.rb
 - lib/mspire/mass.rb
 - lib/mspire/mass/aa.rb
@@ -370,6 +373,7 @@ files:
 - spec/mspire/imzml/writer_spec.rb
 - spec/mspire/isotope/aa_spec.rb
 - spec/mspire/isotope/distribution_spec.rb
+- spec/mspire/isotope/nist_spec.rb
 - spec/mspire/isotope_spec.rb
 - spec/mspire/mass/aa_spec.rb
 - spec/mspire/mass/all_spec.rb
@@ -476,6 +480,7 @@ test_files:
 - spec/mspire/imzml/writer_spec.rb
 - spec/mspire/isotope/aa_spec.rb
 - spec/mspire/isotope/distribution_spec.rb
+- spec/mspire/isotope/nist_spec.rb
 - spec/mspire/isotope_spec.rb
 - spec/mspire/mass/aa_spec.rb
 - spec/mspire/mass/all_spec.rb
@@ -539,3 +544,4 @@ test_files:
 - spec/testfiles/mspire/quant/unlog_transform.rb
 - spec/testfiles/plms1/output.key
 - spec/testfiles/processed_binary.tmp.ibd
+has_rdoc: