mspire 0.6.21 → 0.6.22

data/VERSION

@@ -1 +1 @@
-0.6.21
+0.6.22

data/lib/ms/error_rate/decoy.rb

@@ -0,0 +1,40 @@
+
+module MS
+  module ErrorRate
+    module Decoy
+      module_function
+
+      # this is the # true positives (found by estimating the number of false
+      # hits using the # decoy)
+      # pi_not is the ratio of decoy hits to the estimated false hits in the
+      # target set.  A data set with a small fraction of true hits will have a
+      # pi_not close to 1.  A data set where 40% of the hits are correct
+      # should have a pi_not of 0.6.
+      # For instance, Spivak uses a fixed pi_not of 0.9 in J. Proteome Res.,
+      # 2009, 8 (7), pp 3737–3745
+      def precision(num_target, num_decoy, pi_not=1.0)
+        num_target_f = num_target.to_f
+        num_true_pos = num_target_f - (num_decoy.to_f * pi_not)
+        precision =
+          if num_target_f == 0.0
+            if num_decoy.to_f > 0.0
+              0.0
+            else
+              1.0
+            end
+          else
+            num_true_pos/num_target_f
+          end
+        precision
+      end
+
+      # the false positive predictive rate (sometimes called the false
+      # positive rate).  This is 1 - precision
+      def fppr(num_target, num_decoy, pi_not=1.0)
+        1.0 - precision(num_target, num_decoy, pi_not=1.0)
+      end
+
+      extend(self)
+    end
+  end
+end

data/lib/ms/error_rate/qvalue.rb

@@ -0,0 +1,81 @@
+require 'set'
+require 'ms/error_rate/decoy'
+
+module MS
+
+  module ErrorRate
+    # For generating and working with q-value calculations.  The q-value is the global false discovery rate when accepting that particular ID.  We do not necessarily distinguish here between *how* the FDR is generated (i.e., Storey's pFDR "the occurrence of false positives" vs. Benjamini-Hochberg's FDR "the rate of false positives" [except to prefer Storey when possible] ).  The main point is that we sort and threshold based on a global FDR.
+    module Qvalue
+      module_function
+         
+      # returns a parallel array to target hits with qvalues
+      # opts = :z_together true/false (default false) group all charges
+      # together.
+      # the sort block should sort from worst to best
+      # by default, sorting is: {|hit| hit.score} if not provided
+      # options also passed through to mixed_target_decoy
+      def target_decoy_qvalues(target_hits, decoy_hits, opts={}, &sorting)
+        sorting ||= :score
+        opts = {:z_together => false}.merge(opts)
+        target_set = Set.new(target_hits)
+
+        # Proc.new doesn't do arity checking
+        hit_with_qvalue_pairs = Proc.new do |hits|
+          sorted_best_to_worst = (hits.sort_by(&sorting)).reverse
+          (target_hits, qvalues) = MS::ErrorRate::Qvalue.mixed_target_decoy(sorted_best_to_worst, target_set, opts)
+          target_hits.zip(qvalues)
+        end
+
+        all_together = target_hits + decoy_hits
+        if !opts[:z_together]
+          hit_with_qvalue_pairs.call(all_together)
+        else
+          all_hits = []
+          by_charge = all_together.group_by(&:charge)
+          by_charge.each do |charge,hits|
+            all_hits.push(*(hit_with_qvalue_pairs.call(hits)))
+          end
+          all_hits
+        end
+      end
+
+      # returns [target_hits, qvalues] (parallel arrays sorted from best hit to
+      # worst hit).  expects an array-like object of hits sorted from best to worst
+      # hit with decoys interspersed and a target_setlike object that responds to
+      # :include? for the hit object assumes the hit is a decoy if not found
+      # in the target set!  if monotonic is false, then the guarantee that
+      # qvalues be monotonically increasing is not respected.
+      def mixed_target_decoy(best_to_worst, target_setlike, opts={})
+        opts = {:monotonic => true}.merge(opts)
+        num_target = 0 ; num_decoy = 0
+        monotonic = opts[:monotonic]
+        target_hits = []
+        qvalues = []
+        best_to_worst.each do |hit|
+          if target_setlike.include?(hit) 
+            num_target += 1
+            precision = MS::ErrorRate::Decoy.precision(num_target, num_decoy)
+            target_hits << hit
+            qvalues << (1.0 - precision)
+          else
+            num_decoy += 1
+          end
+        end
+        if opts[:monotonic]
+          min_qvalue = qvalues.last 
+          qvalues = qvalues.reverse.map do |val| # from worst to best score
+            if min_qvalue < val 
+              min_qvalue
+            else
+              min_qvalue = val
+              val
+            end
+          end.reverse
+        end
+        [target_hits, qvalues]
+      end
+
+
+    end
+  end
+end

data/lib/ms/spectrum.rb

@@ -45,7 +45,7 @@ module MS
       #                                     number of spectra
       #     :return_data => false           returns a parallel array containing
       #                                     the peaks associated with each returned point
-      #     :split => :share | :greedy_y    see MS::Peak#split
+      #     :split => false | :share | :greedy_y   see MS::Peak#split
       #
       # The binning algorithm is the fastest possible algorithm that would allow
       # for arbitrary, non-constant bin widths (a ratcheting algorithm O(n + m))

data/mspire.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "mspire"
-  s.version = "0.6.20"
+  s.version = "0.6.22"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["John T. Prince", "Simon Chiang"]
-  s.date = "2012-02-24"
+  s.date = "2012-02-29"
   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 = [
@@ -33,6 +33,8 @@ Gem::Specification.new do |s|
     "lib/ms/cv/param.rb",
     "lib/ms/cv/paramable.rb",
     "lib/ms/digester.rb",
+    "lib/ms/error_rate/decoy.rb",
+    "lib/ms/error_rate/qvalue.rb",
     "lib/ms/fasta.rb",
     "lib/ms/ident.rb",
     "lib/ms/ident/peptide.rb",
@@ -106,12 +108,14 @@ Gem::Specification.new do |s|
     "lib/obo/unit.rb",
     "lib/openany.rb",
     "lib/write_file_or_string.rb",
+    "mspire.gemspec",
     "obo/ims.obo",
     "obo/ms.obo",
     "obo/unit.obo",
     "spec/bin_spec.rb",
     "spec/ms/cv/param_spec.rb",
     "spec/ms/digester_spec.rb",
+    "spec/ms/error_rate/qvalue_spec.rb",
     "spec/ms/fasta_spec.rb",
     "spec/ms/ident/peptide/db_spec.rb",
     "spec/ms/ident/pepxml/sample_enzyme_spec.rb",

data/spec/ms/error_rate/qvalue_spec.rb

@@ -0,0 +1,35 @@
+require 'spec_helper'
+
+require 'ms/error_rate/qvalue'
+
+Hit = Struct.new(:score, :charge)
+HitWeird = Struct.new(:some_obscure_score, :charge)
+
+describe 'calculating q-values' do
+
+  before do
+    scores = [14,15,13,12,11]
+    qvals_expected = [0.5 ,0.0, 2.0/3.0, 3.0/4, 4.0/5]
+    @target_hits = scores.zip(Array.new(scores.size, 2)).map {|pair| Hit.new(*pair) } 
+    @decoy_hits = scores.zip(Array.new(scores.size, 2)).map {|pair| Hit.new(pair.first-0.5, pair.last) }
+    @target_hits_weird = scores.zip(Array.new(scores.size, 2)).map {|pair| HitWeird.new(*pair) } 
+    @decoy_hits_weird = scores.zip(Array.new(scores.size, 2)).map {|pair| HitWeird.new(pair.first-0.5, pair.last) }
+    @qval_by_hit = {}
+    @target_hits.zip(qvals_expected) {|hit, qval|  @qval_by_hit[hit] = qval }
+    @target_hits_weird.zip(qvals_expected) {|hit, qval|  @qval_by_hit[hit] = qval }
+  end
+
+  it 'can calculate qvalues on target/decoy sets (:score is default)' do
+    pairs = MS::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits, @decoy_hits)
+    pairs.each do |hit, qval|
+      @qval_by_hit[hit].should be_within(0.00000001).of(qval)
+    end
+  end
+
+  it 'can calculate qvalues on target/decoy sets with custom sorting' do
+    pairs = MS::ErrorRate::Qvalue.target_decoy_qvalues(@target_hits_weird, @decoy_hits_weird) {|hit| hit.some_obscure_score }
+    pairs.each do |hit, qval|
+      @qval_by_hit[hit].should be_within(0.00000001).of(qval)
+    end
+  end
+end

data/spec/ms/mzml_spec.rb

@@ -77,10 +77,8 @@ describe MS::Mzml do
     end
 
     it 'writes MS1 and MS2 spectra' do
-      # profile and ms_level 1
-      spec_params = ['MS:1000128', ['MS:1000511', 1]]
-
-      spec1 = MS::Mzml::Spectrum.new('scan=1', params: spec_params) do |spec|
+      # params: profile and ms_level 1
+      spec1 = MS::Mzml::Spectrum.new('scan=1', params: ['MS:1000128', ['MS:1000511', 1]]) do |spec|
         spec.data_arrays = [[1,2,3], [4,5,6]]
         spec.scan_list = MS::Mzml::ScanList.new do |sl|
           scan = MS::Mzml::Scan.new do |scan|

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.6.21
+  version: 0.6.22
   prerelease: 
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-27 00:00:00.000000000 Z
+date: 2012-02-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &8601020 !ruby/object:Gem::Requirement
+  requirement: &20175840 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +22,10 @@ dependencies:
         version: '1.5'
   type: :runtime
   prerelease: false
-  version_requirements: *8601020
+  version_requirements: *20175840
 - !ruby/object:Gem::Dependency
   name: bsearch
-  requirement: &8615260 !ruby/object:Gem::Requirement
+  requirement: &20175280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: 1.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *8615260
+  version_requirements: *20175280
 - !ruby/object:Gem::Dependency
   name: andand
-  requirement: &8612840 !ruby/object:Gem::Requirement
+  requirement: &20174800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +44,10 @@ dependencies:
         version: 1.3.1
   type: :runtime
   prerelease: false
-  version_requirements: *8612840
+  version_requirements: *20174800
 - !ruby/object:Gem::Dependency
   name: obo
-  requirement: &8611480 !ruby/object:Gem::Requirement
+  requirement: &20174320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +55,10 @@ dependencies:
         version: 0.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *8611480
+  version_requirements: *20174320
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &8609880 !ruby/object:Gem::Requirement
+  requirement: &20173800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -66,10 +66,10 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *8609880
+  version_requirements: *20173800
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &8624220 !ruby/object:Gem::Requirement
+  requirement: &20173240 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -77,10 +77,10 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *8624220
+  version_requirements: *20173240
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &8617960 !ruby/object:Gem::Requirement
+  requirement: &20172740 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -88,7 +88,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *8617960
+  version_requirements: *20172740
 description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire,
   merging of ms-* gems
 email: jtprince@gmail.com
@@ -114,6 +114,8 @@ files:
 - lib/ms/cv/param.rb
 - lib/ms/cv/paramable.rb
 - lib/ms/digester.rb
+- lib/ms/error_rate/decoy.rb
+- lib/ms/error_rate/qvalue.rb
 - lib/ms/fasta.rb
 - lib/ms/ident.rb
 - lib/ms/ident/peptide.rb
@@ -194,6 +196,7 @@ files:
 - spec/bin_spec.rb
 - spec/ms/cv/param_spec.rb
 - spec/ms/digester_spec.rb
+- spec/ms/error_rate/qvalue_spec.rb
 - spec/ms/fasta_spec.rb
 - spec/ms/ident/peptide/db_spec.rb
 - spec/ms/ident/pepxml/sample_enzyme_spec.rb