ms-in_silico 0.3.0 → 0.4.0

data/.gitignore

@@ -0,0 +1,5 @@
+.DS_Store
+pkg/
+rdoc/
+backup/
+.*.swp

data/History

@@ -1,3 +1,7 @@
+== 0.4.0 / 2010-06-23
+
+* moving to jeweler and specs
+
 == 0.3.0 / 2009-05-25
 
 * updates to use tap-0.17.0
@@ -18,4 +22,4 @@
 Maintenance release with minor updates to use
 Tap 0.12.0.
 
-* Added History
+* Added History

data/Rakefile

@@ -0,0 +1,43 @@
+require 'rake'
+require 'jeweler'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rcov/rcovtask'
+
+Jeweler::Tasks.new do |gem|
+  gem.name = "ms-in_silico"
+  gem.summary = 'in-silico calculations for mass spec data'
+  gem.description = 'peptide fragmentation and protein digestion'
+  gem.email = "jtprince@gmail.com"
+  gem.homepage = "http://github.com/jtprince/ms-in_silico"
+  gem.authors = ["Simon Chiang"]
+  gem.rubyforge_project = "mspire"
+  gem.add_dependency("molecules", ">= 0.2.0")
+  gem.add_dependency("tap", ">= 0.17.0")
+  gem.add_development_dependency("tap-test", ">= 0.1.0")
+  gem.add_development_dependency("spec-more", ">= 0")
+end
+Jeweler::GemcutterTasks.new
+
+Rake::TestTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+Rcov::RcovTask.new do |spec|
+  spec.libs << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+task :default => :spec
+
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "ms-in_silico #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.4.0

data/lib/ms/in_silico/digester.rb

@@ -239,25 +239,49 @@ module Ms
         end
       end
       
-      ARG_C =         mascot_parse('Arg-C 	C-Term 	R 	P 	 no 	 no')
-      ASP_N =         mascot_parse('Asp-N 	N-Term 	BD 	  	no 	no')
-      ASP_N_AMBIC =   mascot_parse('Asp-N_ambic 	N-Term 	DE 	  	no 	no')
-      CHYMOTRYPSIN =  mascot_parse('Chymotrypsin 	C-Term 	FLWY 	P 	no 	no')
-      CNBR =          mascot_parse('CNBr 	C-Term 	M 	  	no 	no')
-      LYS_C =         mascot_parse('Lys-C 	C-Term 	K 	P 	no 	no')
-      LYS_C_P =       mascot_parse('Lys-C/P 	C-Term 	K 	  	no 	no')
-      PEPSIN_A =      mascot_parse('PepsinA 	C-Term 	FL 	  	no 	no')
-      TRYP_CNBR =     mascot_parse('Tryp-CNBr 	C-Term 	KMR 	P 	no 	no')
-      TRYP_CHYMO =    mascot_parse('TrypChymo 	C-Term 	FKLRWY 	P 	no 	no')
-      TRYPSIN_P =     mascot_parse('Trypsin/P 	C-Term 	KR 	  	no 	no')
-      V8_DE =         mascot_parse('V8-DE 	C-Term 	BDEZ 	P 	no 	no')
-      V8_E =          mascot_parse('V8-E 	C-Term 	EZ 	P 	no 	no')
-      TRYPSIN =       mascot_parse('Trypsin 	C-Term	KR 	P 	no 	no')
-      V8_E_TRYPSIN =  mascot_parse('V8-E+Trypsin 	C-Term 	EKRZ 	P 	no 	no')
-      V8_DE_TRYPSIN = mascot_parse('V8-DE+Trypsin 	C-Term 	BDEKRZ 	P 	no 	no')
-      
+      # ARG_C = mascot_parse('Arg-C 	C-Term 	R 	P 	 no 	 no')
+      # ENZYMES[:arg_c] = ARG_C
+      ENZYMES = {
+        :arg_c => 'Arg-C 	C-Term 	R 	P 	 no 	 no',
+        :asp_n => 'Asp-N 	N-Term 	BD 	  	no 	no',
+        :asp_n_ambic => 'Asp-N_ambic 	N-Term 	DE 	  	no 	no',
+        :chymotrypsin => 'Chymotrypsin 	C-Term 	FLWY 	P 	no 	no',
+        :cnbr => 'CNBr 	C-Term 	M 	  	no 	no',
+        :lys_c => 'Lys-C 	C-Term 	K 	P 	no 	no',
+        :lys_c_p => 'Lys-C/P 	C-Term 	K 	  	no 	no',
+        :pepsin_a => 'PepsinA 	C-Term 	FL 	  	no 	no',
+        :tryp_cnbr => 'Tryp-CNBr 	C-Term 	KMR 	P 	no 	no',
+        :tryp_chymo => 'TrypChymo 	C-Term 	FKLRWY 	P 	no 	no',
+        :trypsin_p => 'Trypsin/P 	C-Term 	KR 	  	no 	no',
+        :v8_de => 'V8-DE 	C-Term 	BDEZ 	P 	no 	no',
+        :v8_e => 'V8-E 	C-Term 	EZ 	P 	no 	no',
+        :trypsin => 'Trypsin 	C-Term	KR 	P 	no 	no',
+        :v8_e_trypsin => 'V8-E+Trypsin 	C-Term 	EKRZ 	P 	no 	no',
+        :v8_de_trypsin => 'V8-DE+Trypsin 	C-Term 	BDEKRZ 	P 	no 	no',
+        :arg_c => 'Arg-C 	C-Term 	R 	P 	 no 	 no',
+        :asp_n => 'Asp-N 	N-Term 	BD 	  	no 	no',
+        :asp_n_ambic => 'Asp-N_ambic 	N-Term 	DE 	  	no 	no',
+        :chymotrypsin => 'Chymotrypsin 	C-Term 	FLWY 	P 	no 	no',
+        :cnbr => 'CNBr 	C-Term 	M 	  	no 	no',
+        :lys_c => 'Lys-C 	C-Term 	K 	P 	no 	no',
+        :lys_c_p => 'Lys-C/P 	C-Term 	K 	  	no 	no',
+        :pepsin_a => 'PepsinA 	C-Term 	FL 	  	no 	no',
+        :tryp_cnbr => 'Tryp-CNBr 	C-Term 	KMR 	P 	no 	no',
+        :tryp_chymo => 'TrypChymo 	C-Term 	FKLRWY 	P 	no 	no',
+        :trypsin_p => 'Trypsin/P 	C-Term 	KR 	  	no 	no',
+        :v8_de => 'V8-DE 	C-Term 	BDEZ 	P 	no 	no',
+        :v8_e => 'V8-E 	C-Term 	EZ 	P 	no 	no',
+        :trypsin => 'Trypsin 	C-Term	KR 	P 	no 	no',
+        :v8_e_trypsin => 'V8-E+Trypsin 	C-Term 	EKRZ 	P 	no 	no',
+        :v8_de_trypsin => 'V8-DE+Trypsin 	C-Term 	BDEKRZ 	P 	no 	no',
+      }
+      ENZYMES.each do |k,v| 
+        self.const_set(k.upcase, mascot_parse(v))
+        ENZYMES[k] = self.const_get(k.upcase)
+      end
+
       include Constants::Library  
       library.index_by_attribute :name
     end
   end
-end
+end

data/lib/ms/in_silico/spectrum.rb

@@ -149,7 +149,7 @@ module Ms
           hash = {}
           0.upto(residues_to_locate.length-1) do |index|
             letter = residues_to_locate[index, 1]
-            byte = letter[0]
+            byte = letter[0,1].ord
             hash[letter] = locations[byte]
           end
 
@@ -454,4 +454,4 @@ module Ms
       end
     end
   end
-end
+end

data/spec/ms/in_silico/digester_spec.rb

@@ -0,0 +1,301 @@
+require File.dirname(__FILE__) + '/../../spec_helper.rb'
+
+require 'ms/in_silico/digester'
+require 'pp'
+
+describe 'a digester' do
+  before do
+    @digester = Ms::InSilico::Digester.new('arg', 'R')
+  end
+  
+  def spp(input, str="")
+    PP.singleline_pp(input, str)
+  end
+
+  def nk_string(n, split)
+    str = []
+    count = 0
+  
+    (n * 1000).times do 
+      count += 1
+      if count < split
+        str << 'A'
+      else
+        count = 0
+        str << 'R'
+      end
+    end
+        
+    str.join('')
+  end
+  
+  it 'performs digestion and can specify sites of digestion' do
+    trypsin = Ms::InSilico::Digester['Trypsin']
+    
+    expected = [
+    'MIVIGR',
+    'SIVHPYITNEYEPFAAEK',
+    'QQILSIMAG']
+    trypsin.digest('MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG').is expected
+    
+    expected =  [
+    'MIVIGR',
+    'MIVIGRSIVHPYITNEYEPFAAEK',
+    'SIVHPYITNEYEPFAAEK',
+    'SIVHPYITNEYEPFAAEKQQILSIMAG',
+    'QQILSIMAG']
+    trypsin.digest('MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG', 1).is expected
+    
+    expected = [
+    [0,6],
+    [0,24],
+    [6,24],
+    [6,33],
+    [24,33]]
+    trypsin.site_digest('MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG', 1).is expected
+  end
+  
+  it 'completely ignores whitespace inside protein sequences' do
+    expected = [
+    "\tMIVIGR",
+    "SIVHP\nYITNEYEPFAAE K",
+    "QQILSI\rMAG"]
+    Ms::InSilico::Digester['Trypsin'].digest("\tMIVIGRSIVHP\nYITNEYEPFAAE KQQILSI\rMAG").is expected
+  end
+  
+  it 'runs cleavage sites documentation' do
+    d = Ms::InSilico::Digester.new('Trypsin', 'KR', 'P')
+    seq = "AARGGR"
+    sites = d.cleavage_sites(seq)
+    sites.is [0, 3, 6]
+    
+    seq[sites[0], sites[0+1] - sites[0]].is "AAR"
+    seq[sites[1], sites[1+1] - sites[1]].is "GGR"
+    
+    seq = "AAR  \n  GGR"
+    sites = d.cleavage_sites(seq)
+    sites.is [0, 8, 11]
+
+    seq[sites[0], sites[0+1] - sites[0]].is "AAR  \n  "
+    seq[sites[1], sites[1+1] - sites[1]].is "GGR"
+  end
+  
+  it 'finds cleavage site indices' do
+    {
+      "" => [0,0],
+      "A" => [0,1],
+      "R" => [0,1],
+      "AAA" => [0,3],
+      "RAA" => [0,1,3],
+      "ARA" => [0,2,3],
+      "AAR" => [0,3],
+      "RRA" => [0,1,2,3],
+      "RAR" => [0,1,3],
+      "RRR" => [0,1,2,3],
+      
+      "R\nR\nR" => [0,2,4,5],
+      "R\n\n\nR\nR\n\n" => [0,4,6,9]
+   }.each do |sequence, expected|
+       @digester.cleavage_sites(sequence).is expected
+    end
+  end
+
+  it 'finds cleavage sites with exception' do
+    @digester = Ms::InSilico::Digester.new('argp', 'R', 'P')
+    {
+      "" => [0,0],
+      "A" => [0,1],
+      "R" => [0,1],
+      "AAA" => [0,3],
+      "RAA" => [0,1,3],
+      "ARA" => [0,2,3],
+      "AAR" => [0,3],
+      "RRA" => [0,1,2,3],
+      "RAR" => [0,1,3],
+      "RRR" => [0,1,2,3],
+      
+      "PR" => [0,1,2],
+      "PR" => [0,2],
+      "PRR" => [0,2,3],
+      "RPR" => [0,3],
+      "RRP" => [0,1,3],
+      "APRA" => [0,3,4],
+      "ARPA" => [0,4],
+      "ARPARA" => [0,5,6],
+      "R\nPR\nR" => [0,5,6],
+      "RP\nR\nR" => [0,5,6],
+      "RP\nR\nR\n" => [0,5,7]
+    }.each do |sequence, expected|
+       @digester.cleavage_sites(sequence).is expected
+    end
+  end
+  
+  it 'finds cleavage sites with offset and limit' do
+    {
+      "RxxR" => [2,4],
+      "RxAxR" => [2,4],
+      "RxAAAxR" => [2,4],
+      "RxRRRxR" => [2,3,4]
+    }.each do |sequence, expected|
+       @digester.cleavage_sites(sequence, 2, 2).is expected
+    end
+  end
+  
+  it 'finds cleavage sites fast' do
+    str = nk_string(10, 1000)
+     @digester.cleavage_sites(str).length.is 11
+    benchmark(20) do |x|
+      x.report("10kx - fragments") do 
+        10000.times { @digester.cleavage_sites(str) }
+      end
+    end
+  end
+
+  it 'digests proteins' do
+    {
+      "" => [''],
+      "A" => ["A"],
+      "R" => ["R"],
+      "AAA" => ["AAA"],
+      "RAA" => ["R", "AA"],
+      "ARA" => ["AR", "A"],
+      "AAR" => ["AAR"],
+      "RRA" => ["R", "R", "A"],
+      "RAR" => ["R", "AR"],
+      "RRR" => ["R", "R", "R"]
+    }.each do |sequence, expected|
+      # spp(sequence)
+       @digester.digest(sequence) {|frag, s, e| frag}.is expected
+    end
+  end
+
+  it 'digests with missed cleavages' do
+    {
+      "" => [''],
+      "A" => ["A"],
+      "R" => ["R"],
+      "AAA" => ["AAA"],
+      "RAA" => ["R", "RAA", "AA"],
+      "ARA" => ["AR", "ARA", "A"],
+      "AAR" => ["AAR"],
+      "RRA" => ["R", "RR", "R", "RA", "A"],
+      "RAR" => ["R", "RAR", "AR"],
+      "RRR" => ["R", "RR", "R", "RR", "R"]
+    }.each do |sequence, expected|
+       @digester.digest(sequence, 1) {|frag, s, e| frag}.is expected
+    end
+  end
+  
+  it 'digests with two missed cleavages' do
+    {
+      "" => [''],
+      "A" => ["A"],
+      "R" => ["R"],
+      "AAA" => ["AAA"],
+      "RAA" => ["R", "RAA", "AA"],
+      "ARA" => ["AR", "ARA", "A"],
+      "AAR" => ["AAR"],
+      "RRA" => ["R", "RR", "RRA", "R", "RA", "A"],
+      "RAR" => ["R", "RAR", "AR"],
+      "RRR" => ["R", "RR", "RRR", "R", "RR", "R"]
+    }.each do |sequence, expected|
+       @digester.digest(sequence, 2) {|frag, s, e| frag}.is expected
+    end
+  end
+  
+  it 'digests fast' do
+    str = nk_string(10, 1000)
+     @digester.digest(str).length.is 10
+    benchmark(20) do |x|
+      x.report("10kx - fragments") do 
+        10000.times { @digester.digest(str) }
+      end
+    end
+  end
+
+  it 'finds sites to be digested' do
+    {
+      "" => [[0,0]],
+      "A" => [[0,1]],
+      "R" => [[0,1]],
+      "AAA" => [[0,3]],
+      "RAA" => [[0,1],[1,3]],
+      "ARA" => [[0,2],[2,3]],
+      "AAR" => [[0,3]],
+      "RRA" => [[0,1],[1,2],[2,3]],
+      "RAR" => [[0,1],[1,3]],
+      "RRR" => [[0,1],[1,2],[2,3]]
+    }.each do |sequence, expected|
+       @digester.site_digest(sequence).is expected
+    end
+  end
+  
+  it 'finds sites to be digested with missed cleavages' do
+    {
+      "" => [[0,0]],
+      "A" => [[0,1]],
+      "R" => [[0,1]],
+      "AAA" => [[0,3]],
+      "RAA" => [[0,1],[0,3],[1,3]],
+      "ARA" => [[0,2],[0,3],[2,3]],
+      "AAR" => [[0,3]],
+      "RRA" => [[0,1],[0,2],[1,2],[1,3],[2,3]],
+      "RAR" => [[0,1],[0,3],[1,3]],
+      "RRR" => [[0,1],[0,2],[1,2],[1,3],[2,3]]
+    }.each do |sequence, expected|
+       @digester.site_digest(sequence, 1).is expected
+    end
+  end
+  
+  it 'finds sites to be digested with two missed cleavages' do
+    {
+      "" => [[0,0]],
+      "A" => [[0,1]],
+      "R" => [[0,1]],
+      "AAA" => [[0,3]],
+      "RAA" => [[0,1],[0,3],[1,3]],
+      "ARA" => [[0,2],[0,3],[2,3]],
+      "AAR" => [[0,3]],
+      "RRA" => [[0,1],[0,2],[0,3],[1,2],[1,3],[2,3]],
+      "RAR" => [[0,1],[0,3],[1,3]],
+      "RRR" => [[0,1],[0,2],[0,3],[1,2],[1,3],[2,3]]
+    }.each do |sequence, expected|
+       @digester.site_digest(sequence, 2).is expected
+    end
+  end
+  
+  it 'does site digestion fast' do
+    str = nk_string(10, 1000)
+     @digester.site_digest(str).length.is 10
+    benchmark(20) do |x|
+      x.report("10kx - fragments") do 
+        10000.times { @digester.site_digest(str) }
+      end
+    end
+  end
+  
+  it 'does a trypsin digest' do
+    trypsin = Ms::InSilico::Digester::TRYPSIN
+    {
+      "" => [''],
+      "A" => ["A"],
+      "R" => ["R"],
+      "AAA" => ["AAA"],
+      "RAA" => ["R", "AA"],
+      "ARA" => ["AR", "A"],
+      "AAR" => ["AAR"],
+      "RRA" => ["R", "R", "A"],
+      "RAR" => ["R", "AR"],
+      "RRR" => ["R", "R", "R"],
+      "RKR" => ["R", "K", "R"],
+      
+      "ARP" => ["ARP"],
+      "PRA" => ["PR","A"],
+      "ARPARAA" => ["ARPAR", "AA"],
+      "RPRRR" => ["RPR", "R", "R"]
+    }.each do |sequence, expected|
+       trypsin.digest(sequence) {|frag, s, e| frag}.is expected
+    end
+  end
+ 
+end

data/spec/ms/in_silico/fragment_spec.rb

@@ -0,0 +1,19 @@
+require File.dirname(__FILE__) + '/../../spec_helper.rb'
+
+require 'ms/in_silico/fragment'
+
+describe 'creating fragmentation spectra' do
+
+  it 'creates tandem mass spectra from a peptide' do
+    frag = Ms::InSilico::Fragment.new :charge => 1, :series => ['b']
+    spec = Ms::InSilico::Spectrum.new('TVQQEL', 'H', 'HO')
+    
+    headers = frag.headers(spec)
+    headers[:charge].is 1
+    headers[:nterm].is 'H'
+    headers[:cterm].is 'HO'
+    headers[:parent_ion_mass].should.be.close 717.377745628191, 0.000000000001
+    headers[:series].is ['b']
+  end
+end
+  

data/spec/ms/in_silico/spectrum_spec.rb

@@ -0,0 +1,68 @@
+require File.dirname(__FILE__) + '/../../spec_helper'
+require 'ms/in_silico/spectrum'
+
+# class locate_residues tests
+class Subclass < Ms::InSilico::Spectrum
+  locate_residues "PS"
+end
+
+class Cumulative < Ms::InSilico::Spectrum
+  locate_residues "PS"
+end
+
+
+describe 'creating spectral fragmentation ladders' do
+  
+  it 'locates residues' do
+    Subclass.new('RPPGFSPFR').residue_locations.is( {'P' => [1, 2, 6], 'S' => [5]} )
+  end
+  
+  it 'does cumulative locate calls' do
+    Cumulative.residues_to_locate.is "PS"
+    Cumulative.locate_residues "R"
+    Cumulative.residues_to_locate.is "PSR"
+
+    Cumulative.locate_residues "G"
+    Cumulative.residues_to_locate.is "PSRG"
+  end
+
+  it 'creates spectral series' do
+    f = Ms::InSilico::Spectrum.new 'RPPGFSPFR' 
+    f.y_series.is f.series('y')
+    f.b_series(2).is f.series('b++')
+    f.nladder_series(-1).is f.series('nladder-')
+  end
+
+  it 'specifies charges' do
+    f = Ms::InSilico::Spectrum.new 'RPPGFSPFR' 
+    f.y_series.is f.series('y')
+
+    f.y_series(-1).is f.series('y-')
+    f.y_series(-2).is f.series('y--')
+
+    f.y_series(1).is f.series('y+')
+    f.y_series(2).is f.series('y++')
+
+    f.y_series(-1).is f.series('y++---')
+  end
+
+  it 'raises an error for zero charge or unknown series' do
+    f = Ms::InSilico::Spectrum.new('SAMPLE')
+    lambda { f.series 'y+-' }.should.raise ArgumentError
+    lambda { f.series 'q' }.should.raise ArgumentError
+  end
+
+  it 'handles whitespace in the peptide spec' do
+    s = Ms::InSilico::Spectrum.new('SAMPLE')
+    s1 = Ms::InSilico::Spectrum.new(" SA\n  MPL\t \rE  ")
+    s1.series('y').is s.series('y')
+  end
+
+  it 'is fast' do
+    1.is 1
+    benchmark(20) do |x|
+      x.report("1k RPPGFSPFR * 10") { 1000.times { Ms::InSilico::Spectrum.new("RPPGFSPFR" * 10) } }
+    end
+  end
+
+end

data/spec/readme_spec.rb

@@ -0,0 +1,30 @@
+require File.dirname(__FILE__) + '/spec_helper.rb'
+require 'ms/in_silico/digester'
+require 'ms/in_silico/spectrum'
+
+describe 'readme documentation' do
+  
+  it 'works' do
+    trypsin = Ms::InSilico::Digester['Trypsin']
+    peptides = trypsin.digest('MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG')
+    expected = [
+    'MIVIGR',
+    'SIVHPYITNEYEPFAAEK',
+    'QQILSIMAG']
+    peptides.sort.is expected.sort
+  
+    spectrum = Ms::InSilico::Spectrum.new(peptides[0])
+    spectrum.parent_ion_mass.should.be.close 688.417442373391, 10**-12
+  
+    expected = [
+    132.047761058391,
+    245.131825038791,
+    344.200238954991,
+    457.284302935391,
+    514.305766658991,
+    670.406877687091]
+    spectrum.series('b').zip(expected) do |o,e|
+      o.should.be.close e, 10**-12
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,19 @@
+require 'rubygems'
+require 'spec/more'
+
+require 'benchmark'
+
+Bacon.summary_on_exit
+
+module Bacon
+  class Context
+    def benchmark(width=7, &block)
+      if ENV['BENCHMARK']
+        Benchmark.bm(width, &block) 
+      end
+    end
+    def assert_equal(x,y)
+      x.is y
+    end
+  end
+end

data/spec/tap_test_helper.rb

@@ -0,0 +1,2 @@
+require 'rubygems'
+require 'tap/test/unit'

data/test/ms/in_silico/digest_test.rb

@@ -0,0 +1,72 @@
+require File.join(File.dirname(__FILE__), '../../tap_test_helper.rb') 
+require 'ms/in_silico/digest'
+
+class Ms::InSilico::DigestTest < Test::Unit::TestCase
+  include Ms::InSilico
+  acts_as_tap_test
+  acts_as_shell_test(
+    :cmd_pattern => '% ',
+    :env => {'TAP_GEMS' => ''}
+  )
+  
+  attr_accessor :d
+  
+  def setup
+    super
+    @d = Digest.new
+  end
+  
+  def test_digest_documentation
+    sh_test %q{
+% rap digest MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG --:i dump
+MIVIGR
+SIVHPYITNEYEPFAAEK
+QQILSIMAG
+}
+  end
+  
+  #
+  # process test
+  #
+  
+  def test_process_returns_array_of_peptide_fragments
+    assert_equal %w{
+      MIVIGR
+      SIVHPYITNEYEPFAAEK
+      QQILSIMAG
+    }, d.process("MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG")
+  end
+  
+  def test_process_removes_whitespace_from_sequence
+    assert_equal %w{
+      MIVIGR
+      SIVHPYITNEYEPFAAEK
+      QQILSIMAG
+    }, d.process("  MIVI\nGRSIVHP  YITNEYEPFA \n\r\nAEKQQILSIMAG\n")
+  end
+  
+  def test_process_skips_header_of_fasta_entries
+    assert_equal %w{
+      MIVIGR
+      SIVHPYITNEYEPFAAEK
+      QQILSIMAG
+    }, d.process(">header\nMIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG")
+  end
+  
+  def test_process_filters_on_min_max_length
+    d.min_length = 9
+    d.max_length = 9
+    assert_equal %w{
+      QQILSIMAG
+    }, d.process("MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG")
+    
+    d.min_length = 6
+    d.max_length = 18
+    assert_equal %w{
+      MIVIGR
+      SIVHPYITNEYEPFAAEK
+      QQILSIMAG
+    }, d.process("MIVIGRSIVHPYITNEYEPFAAEKQQILSIMAG")
+  end
+  
+end

data/test/ms/in_silico/fragment_test.rb

@@ -0,0 +1,36 @@
+require File.join(File.dirname(__FILE__), '../../tap_test_helper.rb') 
+require 'ms/in_silico/fragment'
+
+class FragmentTest < Test::Unit::TestCase
+  include Ms::InSilico
+  acts_as_tap_test
+
+  #
+  # process test
+  #
+  
+  def test_process_returns_data_and_a_hash_of_headers
+    data, headers = Fragment.new.process('TVQQEL')
+    
+    assert_equal %w{
+      102.054954926291
+      132.101905118891
+      201.123368842491
+      261.144498215091
+      329.181946353891
+      389.203075726491
+      457.240523865291
+      517.261653237891
+      586.283116961491
+      616.330067154091
+      699.367180941891
+      717.377745628191
+    }, data.collect {|mass| mass.to_s }
+    
+    assert_equal 1, headers[:charge]
+    assert_equal 'H', headers[:nterm]
+    assert_equal 'HO', headers[:cterm]
+    assert_in_delta 717.377745628191, headers[:parent_ion_mass], 0.000000000001
+    assert_equal ['y', 'b'], headers[:series]
+  end
+end

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: ms-in_silico
 version: !ruby/object:Gem::Version 
-  version: 0.3.0
+  prerelease: false
+  segments: 
+  - 0
+  - 4
+  - 0
+  version: 0.4.0
 platform: ruby
 authors: 
 - Simon Chiang
@@ -9,84 +14,131 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-05-25 00:00:00 -06:00
+date: 2010-06-23 00:00:00 -06:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: tap
+  name: molecules
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 2
+        - 0
+        version: 0.2.0
   type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: tap
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 17
+        - 0
         version: 0.17.0
-    version: 
+  type: :runtime
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: tap-test
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 1
+        - 0
         version: 0.1.0
-    version: 
+  type: :development
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
-  name: molecules
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  name: spec-more
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: 0.2.0
-    version: 
-description: 
-email: simon.a.chiang@gmail.com
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id004
+description: peptide fragmentation and protein digestion
+email: jtprince@gmail.com
 executables: []
 
 extensions: []
 
 extra_rdoc_files: 
-- README
-- MIT-LICENSE
-- History
+- LICENSE
+- README.rdoc
 files: 
+- .gitignore
+- History
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
 - lib/ms/in_silico.rb
 - lib/ms/in_silico/digest.rb
 - lib/ms/in_silico/digester.rb
 - lib/ms/in_silico/fragment.rb
 - lib/ms/in_silico/spectrum.rb
+- spec/ms/in_silico/digester_spec.rb
+- spec/ms/in_silico/fragment_spec.rb
+- spec/ms/in_silico/spectrum_spec.rb
+- spec/readme_spec.rb
+- spec/spec_helper.rb
+- spec/tap_test_helper.rb
+- spec/tap_test_suite.rb
 - tap.yml
-- README
-- MIT-LICENSE
-- History
+- test/ms/in_silico/digest_test.rb
+- test/ms/in_silico/fragment_test.rb
 has_rdoc: true
-homepage: http://mspire.rubyforge.org/projects/ms-in_silico/
-post_install_message: 
-rdoc_options: []
+homepage: http://github.com/jtprince/ms-in_silico
+licenses: []
 
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: mspire
-rubygems_version: 1.3.1
+rubygems_version: 1.3.6
 signing_key: 
-specification_version: 2
+specification_version: 3
 summary: in-silico calculations for mass spec data
 test_files: 
-- test/tap_test_suite.rb
+- spec/tap_test_suite.rb
+- spec/ms/in_silico/fragment_spec.rb
+- spec/ms/in_silico/spectrum_spec.rb
+- spec/ms/in_silico/digester_spec.rb
+- spec/readme_spec.rb
+- spec/tap_test_helper.rb
+- spec/spec_helper.rb
+- test/ms/in_silico/digest_test.rb
+- test/ms/in_silico/fragment_test.rb