mascot-dat 0.1.3 → 0.2.0

data/.gitignore

@@ -1,4 +1,5 @@
 *~
+.DS_Store
 pkg/*
 *.gem
 .bundle

data/lib/mascot/dat/peptides.rb

@@ -6,7 +6,7 @@ module Mascot
     # access this section as one big chunk in memory. It is often quite large and
     # needs to be accessed using Enumerable methods.
     #
-    # From the Mascot documentation, results are CSV list with the following information
+    # From the Mascot documentation, the following represents a reasonably complete PSM
     #     q1_p1_db=01  # two digit integer of the search DB index, zero filled and retarded.
     #     q1_p1=missed cleavages, (–1 indicates no match)
     #           peptide Mr,
@@ -76,11 +76,17 @@ module Mascot
         @file.pos = @byteoffset + @boundary_line.length
       end
 
+      # Return a specific {Mascot::DAT::PSM} identified for query <code>q</code> and peptide number <code>p</code>
+      # @param q Fixnum
+      # @param p Fixnum
+      # @return Mascot::DAT::PSM
       def psm q,p
         @file.pos  =  @psmidx[q][p]
         next_psm
       end
 
+      # Returns the next {Mascot::DAT::PSM} from the DAT file. If there is no other PSM, then it returns nil.
+      # @return Mascot::DAT::PSM
       def next_psm
         return nil if @file.pos >= @endbytepos
         # get the initial values for query & rank
@@ -106,7 +112,10 @@ module Mascot
         Mascot::DAT::PSM.parse(tmp)
       end
 
+      # Iterate through all of the {Mascot::DAT::PSM} entries in the DAT file.
+      # @return Enumerator
       def each
+        @file.pos = @byteoffset
         while @file.pos < @endbytepos
           psm = next_psm()
           next if psm.nil?

data/lib/mascot/dat/psm.rb

@@ -34,8 +34,9 @@ module Mascot
       end
       def self.parse psm_arr
         psm_result =  self.new()
-
         psm_arr.each do |l|
+          next unless l =~ /^q/
+
           k,v = l.split "="
           case k
           when /^q(\d+)_p(\d+)$/
@@ -69,6 +70,7 @@ module Mascot
             psm_result.terms = v.split(":").collect {|t| t.split(",") }
           else
             # returns the smaller key
+            puts "****#{k}***"
             k_sym = k.slice(/q\d+_p\d+_?(.+)/,1).to_sym
             psm_result.attrs[k_sym] = v
           end

data/lib/mascot/dat/query.rb

@@ -0,0 +1,118 @@
+module Mascot
+  class DAT
+
+    # A class to represent mass spectrum query objects in Mascot DAT files.
+    # Here is an example:
+    #
+    #     --gc0p4Jq0M2Yt08jU534c0p
+    #     Content-Type: application/x-Mascot; name="query3"
+    #
+    #     title=253%2e131203405971_503
+    #     rtinseconds=503
+    #     index=5
+    #     charge=2+
+    #     mass_min=88.063115
+    #     mass_max=392.171066
+    #     int_min=6.064e+05
+    #     int_max=6.064e+05
+    #     num_vals=10
+    #     num_used1=-1
+    #     Ions1=88.063115:6.064e+05,196.589171:6.064e+05,331.143454:6.064e+05,392.171066:6.064e+05,114.570773:6.064e+05,228.134269:6.064e+05,139.567707:6.064e+05,278.128138:6.064e+05,166.075365:6.064e+05,175.118953:6.064e+05
+    #
+    # Things to note are:
+    #
+    #  * the spectrum title is encoded to produce nice output in HTML
+    #  * the m/z and intensity values are given as pairs of values
+    #  * the m/z and intensity values are not in increasing values of m/z
+    #
+    # This parser accounts for these in the attributes like so:
+    #
+    #  * spectrum title is de-encoded
+    #  * the pairs of m/z and intensity are accessible via the {#peaks} method
+    #  * the {#peaks} are ordered in accordance to increasing m/z
+    #  * there are {#mz} and {#intensity} methods to get the individual array of values for each
+    #
+    class Query
+      # The name of the query in Mascot DAT file, e.g. the MIME section header
+      attr_reader :name
+      # The spectrum title from the source mass spectrum file
+      attr_reader :title
+      # No clue what this is
+      attr_reader :index
+      # Retention time in seconds
+      attr_reader :rtinseconds
+      # Charge state of the parent MS1 ion
+      attr_reader :charge
+      # The minimum m/z of the values
+      attr_reader :mass_min
+      # The maximum m/z of the values
+      attr_reader :mass_max
+      # The minimum intensity of the values
+      attr_reader :int_min
+      # The maximum intensity of the values
+      attr_reader :int_max
+      # The number of peaks
+      attr_reader :num_vals
+      # No clue what this is
+      attr_reader :num_used1
+      # An Array of [m/z, intensity] tuples, ordered by increasing m/z values
+      attr_reader :peaks
+      # An Array of m/z values, ordered by increasing m/z
+      attr_reader :mz
+      # An Array of intensity values, ordered by the corresponding m/z value in the {#mz} Array
+      attr_reader :intensity
+
+      # All other attributes from DAT query sections not covered above
+      attr_reader :attributes
+
+      def initialize(query_str)
+        query_str.split(/\n/).each do |l|
+          next unless l =~ /(\w+)\=(.+)$/
+          k,v = $1,$2
+          case k
+          when "name"
+            @name = v.gsub('"','')
+          when "title"
+            @title = URI.decode(v)
+          when "index"
+            @index = v.to_i
+          when "rtinseconds"
+            @rtinseconds = v.to_i
+          when "charge"
+            @charge = v
+          when "mass_min"
+            @mass_min = v.to_f
+          when "mass_max"
+            @mass_max = v.to_f
+          when "int_min"
+            @int_min = v.to_f
+          when "int_max"
+            @int_max = v.to_f
+          when "num_vals"
+            @num_vals = v.to_i
+          when "num_used1"
+            @num_used1 = v.to_i
+          when "Ions1"
+            parse_ions1(v)
+          else
+            @attributes[k.to_sym] = v
+          end
+        end
+      end
+
+      private
+      def parse_ions1(ions1)
+        @peaks = []
+        ions1.split(",").collect do |mzpair|
+          @peaks <<  mzpair.split(":").collect {|e| e.to_f}
+        end
+        # now sort the mz_tmp array as ascending m/z, and return the array
+        @peaks.sort!
+        # once sorted by increasing m/z, populate the individual arrays
+        @mz = @peaks.collect {|p| p[0]}
+        @intensity = @peaks.collect {|p| p[1]}
+      end
+    end
+  end
+end
+

data/lib/mascot/dat/version.rb

@@ -1,6 +1,6 @@
 module Mascot
   class DAT
-    VERSION = "0.1.3"
+    VERSION = "0.2.0"
   end
 end
 

data/lib/mascot/dat.rb

@@ -6,6 +6,7 @@ require 'mascot/dat/parameters'
 require 'mascot/dat/peptides'
 require 'mascot/dat/proteins'
 require 'mascot/dat/psm'
+require "mascot/dat/query"
 require 'mascot/dat/search_databases'
 require 'mascot/dat/summary'
 require 'mascot/dat/version'
@@ -48,41 +49,15 @@ module Mascot
       @dat_file.close
     end
 
-    # Read in the query spectrum from the DAT file
+    # Return a specific query spectrum from the DAT file
     #
     # @param n  The query spectrum numerical index
-    # @return   Hash of the spectrum. The hash has
+    # @return  {Mascot::DAT::Query}
     def query(n)
-      # search index for this
-      bytepos = @idx["query#{n}".to_sym]
-      @dat_file.pos = bytepos + @boundary_string.length
-      att_rx = /(\w+)\=(.+)/
-      q = {}
-      @dat_file.each do |l|
-        l.chomp
-        case l
-        when att_rx
-          k,v = $1,$2
-          case k
-          when "title"
-            q[k.to_sym] = URI.decode(v)
-          when "Ions1"
-            q[:peaks] = parse_mzi(v)
-          else
-            q[k.to_sym] = v
-          end
-        when @boundary
-          break
-        else
-          next
-        end
-      end
-      q
+      return Mascot::DAT::Query.new(self.read_section(:"query#{n}"))
     end
-
     alias_method :spectrum, :query
 
-
     # Go to a section of the Mascot DAT file
     def goto(key)
       if @idx.has_key?(key.to_sym)
@@ -189,15 +164,6 @@ module Mascot
       @dat_file.rewind
     end
 
-    # Parse the ion string of mz/intensity peaks in Ions section
-    # Peaks are not ordered, so we must account for that.
-    def parse_mzi(ions_str)
-      mzi_tmp = []
-      ions_str.split(",").collect do |mzpair|
-        mzi_tmp <<  mzpair.split(":").collect {|e| e.to_f}
-      end
-      # now sort the mz_tmp array as ascending m/z, and return the array
-      mzi_tmp.sort
-    end
+
   end
 end

data/test/test_mascot-dat-query.rb

@@ -0,0 +1,65 @@
+require 'test_mascot-dat-helper'
+
+class TestMascotDatQuery < TestMascotDatHelper
+  def setup
+    super
+    @query = @dat.query(23)
+  end
+  def test_name
+    assert_equal("query23", @query.name)
+  end
+  def test_title
+    assert_equal("281.832701459371_513",@query.title)
+  end
+  def test_rtinseconds
+    assert_equal(513, @query.rtinseconds)
+  end
+  def test_index
+    assert_equal(30,@query.index)
+  end
+  def test_charge
+    assert_equal("3+",@query.charge)
+  end
+  def test_mass_min
+    assert_equal(59.044502, @query.mass_min)
+  end
+  def test_mass_max
+    assert_equal(730.399487,@query.mass_max)
+  end
+  def test_int_min
+    assert_equal(1.951e+05, @query.int_min)
+  end
+  def test_int_max
+    assert_equal(1.951e+05, @query.int_max)
+  end
+  def test_num_vals
+    assert_equal(33,@query.num_vals)
+  end
+  def test_num_used1
+    assert_equal(-1, @query.num_used1)
+  end
+
+  def test_peaks
+    expected_peaks = Marshal.load(File.read("test/fixtures/query23_peaks.dmp"))
+    assert_equal(expected_peaks,@query.peaks)
+  end
+
+  def test_mz_array
+    mz_expected = [59.044502, 76.396653, 88.063115, 92.727062, 111.734216,
+      114.091341, 122.082957, 138.586954, 160.757021, 167.097686, 171.105762,
+      175.118953, 182.620797, 190.112916, 206.443325, 223.795476, 227.175405,
+      240.631893, 244.138013, 256.155004, 276.166632, 284.665736, 309.16135,
+      333.188096, 335.189576, 364.234317, 365.703382, 480.256511, 511.302732,
+      568.324196, 617.315423, 669.371875, 730.399487]
+      assert_equal(mz_expected,@query.mz)
+  end
+
+  def test_intensity_array
+    intensity_expected = [195100.0, 195100.0, 195100.0, 195100.0, 195100.0,
+      195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0,
+      195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0,
+      195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0,
+      195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0, 195100.0]
+      assert_equal(intensity_expected,@query.intensity)
+  end
+end

data/test/test_mascot-dat.rb

@@ -9,6 +9,10 @@ class TestMascotDat < TestMascotDatHelper
     assert_equal(Regexp.new("--gc0p4Jq0M2Yt08jU534c0p"), @dat.boundary)
   end
 
+  def test_dat_boundary_string
+    assert_equal("--gc0p4Jq0M2Yt08jU534c0p", @dat.boundary_string)
+  end
+
   def test_dat_byteoffset_index_is_created
     File.unlink(@dat.dat_file.path + ".idx") if File.exists?(@dat.dat_file.path + ".idx")
     @dat = Mascot::DAT.open("test/fixtures/example.dat")
@@ -42,10 +46,4 @@ class TestMascotDat < TestMascotDatHelper
     assert_equal(expected_section, @dat.read_section(:masses))
   end
 
-  def test_peaks
-    expected_peaks = Marshal.load(File.read("test/fixtures/query23_peaks.dmp"))
-    query23 = @dat.query(23)
-    assert_equal(expected_peaks,query23[:peaks])
-  end
-
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mascot-dat
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-03 00:00:00.000000000 Z
+date: 2012-07-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
-  requirement: &70330121470000 !ruby/object:Gem::Requirement
+  requirement: &70340237935320 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,10 +21,10 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70330121470000
+  version_requirements: *70340237935320
 - !ruby/object:Gem::Dependency
   name: yard
-  requirement: &70330121469460 !ruby/object:Gem::Requirement
+  requirement: &70340237934880 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -32,7 +32,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *70330121469460
+  version_requirements: *70340237934880
 description: Mascot DAT file format parser
 email:
 - angel@upenn.edu
@@ -53,6 +53,7 @@ files:
 - lib/mascot/dat/peptides.rb
 - lib/mascot/dat/proteins.rb
 - lib/mascot/dat/psm.rb
+- lib/mascot/dat/query.rb
 - lib/mascot/dat/search_databases.rb
 - lib/mascot/dat/summary.rb
 - lib/mascot/dat/version.rb
@@ -69,6 +70,7 @@ files:
 - test/test_mascot-dat-parameters.rb
 - test/test_mascot-dat-peptides.rb
 - test/test_mascot-dat-proteins.rb
+- test/test_mascot-dat-query.rb
 - test/test_mascot-dat-search_databases.rb
 - test/test_mascot-dat-summary.rb
 - test/test_mascot-dat.rb
@@ -86,7 +88,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -998556290879411337
+      hash: -3741896018441832167
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -95,7 +97,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -998556290879411337
+      hash: -3741896018441832167
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.11
@@ -115,6 +117,7 @@ test_files:
 - test/test_mascot-dat-parameters.rb
 - test/test_mascot-dat-peptides.rb
 - test/test_mascot-dat-proteins.rb
+- test/test_mascot-dat-query.rb
 - test/test_mascot-dat-search_databases.rb
 - test/test_mascot-dat-summary.rb
 - test/test_mascot-dat.rb