mspire 0.6.18 → 0.6.19

data/VERSION

@@ -1 +1 @@
-0.6.18
+0.6.19

data/lib/ms/mzml/spectrum.rb

@@ -64,6 +64,30 @@ module MS
       # currently being described, ordered.
       attr_accessor :products
 
+      # takes a Nokogiri node and sets relevant properties
+      def self.from_xml(xml)
+        spec = MS::Mzml::Spectrum.new(xml[:id])
+
+        params = {}
+        xml.xpath("./cvParam").each do |cvparam|
+          params[cvparam[:accession]] = cvparam[:value]
+        end
+        spec.ms_level = params['MS:1000511'].to_i
+        # TODO: need to slot in all the other info in reasonable ways
+
+        data_arrays = xml.xpath('./binaryDataArrayList/binaryDataArray').map do |binary_data_array_n|
+          accessions = binary_data_array_n.xpath('./cvParam').map {|node| node['accession'] }
+          base64 = binary_data_array_n.xpath('./binary').text
+          MS::Mzml.unpack_binary(base64, accessions)
+        end
+        # if there is no spectrum, we will still return a spectrum object, it
+        # just has no mzs or intensities
+        data_arrays = [[], []] if data_arrays.size == 0
+        spec.data_arrays = data_arrays
+        spec
+      end
+
+
       # the most common param to pass in would be ms level: 'MS:1000511'
       #
       # This would generate a spectrum of ms_level=2 :
@@ -76,6 +100,7 @@ module MS
         block.call(self) if block
       end
 
+
       # see SpectrumList for generating the entire list
       def to_xml(builder)
         atts = {}

data/lib/ms/mzml.rb

@@ -4,7 +4,7 @@ require 'nokogiri'
 require 'io/bookmark'
 require 'zlib'
 require 'ms/mzml/index_list'
-require 'ms/spectrum'
+require 'ms/mzml/spectrum'
 require 'ms/mzml/file_description'
 require 'ms/mzml/software'
 require 'ms/mzml/scan_list'
@@ -161,6 +161,7 @@ module MS
     end
 
     class << self
+
       # read-only right now
       def open(filename, &block)
         File.open(filename) do |io|
@@ -169,6 +170,7 @@ module MS
       end
 
       def foreach(filename, &block)
+        block or return enum_for(__method__, filename)
         open(filename) do |mzml|
           mzml.each(&block)
         end
@@ -208,9 +210,14 @@ module MS
     end
 
     def each_spectrum(&block)
+      block or return enum_for(__method__)
       (0...@index_list[:spectrum].size).each do |int|
-        block.call spectrum(int)
+        block.call(spectrum(int))
       end
+      #block_given? or return enum_for(__method__)
+      #(0...@index_list[:spectrum].size).each do |int|
+      #  yield spectrum(int)
+      #end
     end
 
     # returns the Nokogiri::XML::Node object associated with each spectrum
@@ -231,17 +238,9 @@ module MS
     # @param [Object] arg an index number (Integer) or id string (String)
     # @return [MS::Spectrum] a spectrum object
     def spectrum(arg)
-      ################### trouble
       start_byte = index_list[0].start_byte(arg)
-      data_arrays = spectrum_node_from_start_byte(start_byte).xpath('//binaryDataArray').map do |binary_data_array_n|
-        accessions = binary_data_array_n.xpath('./cvParam').map {|node| node['accession'] }
-        base64 = binary_data_array_n.xpath('./binary').text
-        MS::Mzml.unpack_binary(base64, accessions)
-      end
-      # if there is no spectrum, we will still return a spectrum object, it
-      # just has no mzs or intensities
-      data_arrays = [[], []] if data_arrays.size == 0
-      MS::Spectrum.new(data_arrays)
+      spec_n = spectrum_node_from_start_byte(start_byte)
+      MS::Mzml::Spectrum.from_xml(spec_n)
     end
 
     # returns the number of spectra

data/lib/ms/spectrum.rb

@@ -156,7 +156,7 @@ module MS
 
         if opt[:normalize]
           sz = spectra.size
-          spectrum.data[1].map! {|v| v.to_f / sz }
+          spectrum.intensities.map! {|v| v.to_f / sz }
         end
         if opt[:return_data]
           $stderr.puts "returning spectrum (#{spectrum.mzs.size}) and data" if $VERBOSE

data/lib/ms/spectrum_like.rb

@@ -10,24 +10,25 @@ module MS
     # boolean for if the spectrum represents centroided data or not
     attr_accessor :centroided
 
-    # The underlying data store. methods are implemented so that data[0] is
-    # the m/z's and data[1] is intensities
-    attr_accessor :data
+    # The underlying data store. methods are implemented so that data_arrays[0] is
+    # the m/z's and data_arrays[1] is intensities
+    attr_accessor :data_arrays
+
 
     def centroided?() centroided end
 
-    # data takes an array: [mzs, intensities]
     # @return [MS::Spectrum]
     # @param [Array] data two element array of mzs and intensities
-    def initialize(data, centroided=true)
-      @data = data
+    # @param [Boolean] centroided is the spectrum centroided or not
+    def initialize(data_arrays, centroided=true)
+      @data_arrays = data_arrays
       @centroided = centroided
     end
 
        # found by querying the size of the data store.  This should almost always
     # be 2 (m/z and intensities)
     def size
-      @data.size
+      @data_arrays.size
     end
 
     def ==(other)
@@ -36,26 +37,26 @@ module MS
       
     # An array of the mz data.
     def mzs
-      @data[0]
+      @data_arrays[0]
     end
       
     # An array of the intensities data, corresponding to mzs.
     def intensities
-      @data[1]
+      @data_arrays[1]
     end
 
     def mzs_and_intensities
-      [@data[0], @data[1]]
+      [@data_arrays[0], @data_arrays[1]]
     end
 
     # retrieve an m/z and intensity doublet at that index
     def [](array_index)
-      [@data[0][array_index], @data[1][array_index]]
+      [@data_arrays[0][array_index], @data_arrays[1][array_index]]
     end
 
     # yields(mz, inten) across the spectrum, or array of doublets if no block
     def points(&block)
-      @data[0].zip(@data[1], &block)
+      @data_arrays[0].zip(@data_arrays[1], &block)
     end
 
     alias_method :each, :points
@@ -84,7 +85,7 @@ module MS
     def sort!
       _points = points.to_a
       _points.sort!
-      _points.each_with_index {|(mz,int), i| @data[0][i] = mz ; @data[1][i] = int }
+      _points.each_with_index {|(mz,int), i| @data_arrays[0][i] = mz ; @data_arrays[1][i] = int }
       self
     end
 

data/spec/ms/mzml/plms1_spec.rb

@@ -23,7 +23,7 @@ describe 'converting mzml to plms1' do
       plms1.scan_numbers.should == scan_nums
       plms1.spectra.each do |spec|
         spec.size.should == 2
-        spec.class.should == MS::Spectrum
+        spec.should be_a_kind_of(MS::SpectrumLike)
         spec.mzs.should == []
         spec.intensities.should == []
       end
@@ -51,7 +51,7 @@ describe 'converting mzml to plms1' do
       plms1.scan_numbers.should == [1, 2, 3] 
       sizes = [20168, 315, 634]
       plms1.spectra.zip(sizes).each do |spec,exp_size|
-        spec.class.should == MS::Spectrum
+        spec.should be_a_kind_of(MS::SpectrumLike)
         spec.size.should == 2
         spec.mzs.size.should == exp_size
         spec.intensities.size.should == exp_size

data/spec/ms/mzml_spec.rb

@@ -19,9 +19,10 @@ describe MS::Mzml do
 
       it '#spectrum (or #[]) returns a spectrum when queried by index (Integer)' do
         spectrum = @mzml.spectrum(1) # getting the second spectrum
-        spectrum1 = @mzml[1]
+        spectrum1 = @mzml[1] # can get with brackets
+        spectrum.ms_level.should == 2
         spectrum.should == spectrum1
-        spectrum.should be_a(MS::Spectrum)
+        spectrum.should be_a(MS::Mzml::Spectrum)
         spectrum.should respond_to(:mzs)
         spectrum.should respond_to(:intensities)
         spectrum.mzs.size.should == 315
@@ -32,8 +33,9 @@ describe MS::Mzml do
       it '#spectrum (or #[]) returns a spectrum when queried by id (String)' do
         spectrum = @mzml.spectrum("controllerType=0 controllerNumber=1 scan=2")
         spectrum1 = @mzml["controllerType=0 controllerNumber=1 scan=2"]
+        spectrum.ms_level.should == 2
         spectrum.should == spectrum1
-        spectrum.should be_a(MS::Spectrum)
+        spectrum.should be_a(MS::Mzml::Spectrum)
       end
 
       it 'goes through spectrum with #each or #each_spectrum' do
@@ -42,6 +44,27 @@ describe MS::Mzml do
           spec.mzs.size.should == mz_sizes.shift
         end
       end
+
+      it 'gets an enumerator if called without a block' do
+        mz_sizes = [20168, 315, 634]
+        iter = @mzml.each
+        3.times { iter.next.mzs.size.should == mz_sizes.shift }
+        lambda {iter.next}.should raise_error
+      end
+
+      it 'iterates with foreach' do
+        mz_sizes = [20168, 315, 634]
+        iter = MS::Mzml.foreach(@file)
+        3.times { iter.next.mzs.size.should == mz_sizes.shift }
+        lambda {iter.next}.should raise_error
+      end
+
+      it 'can gracefully determine the m/z with highest peak in select scans' do
+        highest_mzs = MS::Mzml.foreach(@file).select {|v| v.ms_level > 1 }.map do |spec|
+          spec.points.sort_by(&:last).first.first
+        end
+        highest_mzs.map(&:round).should == [453, 866]
+      end
     end
   end
 
@@ -51,7 +74,7 @@ describe MS::Mzml do
       string.gsub(/"mspire" version="([\.\d]+)"/, %Q{"mspire" version="X.X.X"})    
     end
 
-    it 'reads MS1 spectra and retention times' do
+    it 'writes MS1 spectra and retention times' do
 
       spec_params = ['MS:1000127', ['MS:1000511', 1]]
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mspire
 version: !ruby/object:Gem::Version
-  version: 0.6.18
+  version: 0.6.19
   prerelease: 
 platform: ruby
 authors:
@@ -10,11 +10,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-23 00:00:00.000000000 Z
+date: 2012-02-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &19554840 !ruby/object:Gem::Requirement
+  requirement: &10271800 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -22,10 +22,10 @@ dependencies:
         version: '1.5'
   type: :runtime
   prerelease: false
-  version_requirements: *19554840
+  version_requirements: *10271800
 - !ruby/object:Gem::Dependency
   name: bsearch
-  requirement: &19553820 !ruby/object:Gem::Requirement
+  requirement: &10656900 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -33,10 +33,10 @@ dependencies:
         version: 1.5.0
   type: :runtime
   prerelease: false
-  version_requirements: *19553820
+  version_requirements: *10656900
 - !ruby/object:Gem::Dependency
   name: andand
-  requirement: &19552180 !ruby/object:Gem::Requirement
+  requirement: &10739280 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -44,10 +44,10 @@ dependencies:
         version: 1.3.1
   type: :runtime
   prerelease: false
-  version_requirements: *19552180
+  version_requirements: *10739280
 - !ruby/object:Gem::Dependency
   name: obo
-  requirement: &19550640 !ruby/object:Gem::Requirement
+  requirement: &10814460 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -55,10 +55,10 @@ dependencies:
         version: 0.1.0
   type: :runtime
   prerelease: false
-  version_requirements: *19550640
+  version_requirements: *10814460
 - !ruby/object:Gem::Dependency
   name: rspec
-  requirement: &19565640 !ruby/object:Gem::Requirement
+  requirement: &10811160 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -66,10 +66,10 @@ dependencies:
         version: '2.6'
   type: :development
   prerelease: false
-  version_requirements: *19565640
+  version_requirements: *10811160
 - !ruby/object:Gem::Dependency
   name: jeweler
-  requirement: &19564260 !ruby/object:Gem::Requirement
+  requirement: &10888880 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ~>
@@ -77,10 +77,10 @@ dependencies:
         version: 1.5.2
   type: :development
   prerelease: false
-  version_requirements: *19564260
+  version_requirements: *10888880
 - !ruby/object:Gem::Dependency
   name: rcov
-  requirement: &19563540 !ruby/object:Gem::Requirement
+  requirement: &10902860 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -88,7 +88,7 @@ dependencies:
         version: '0'
   type: :development
   prerelease: false
-  version_requirements: *19563540
+  version_requirements: *10902860
 description: mass spectrometry proteomics, lipidomics, and tools, a rewrite of mspire,
   merging of ms-* gems
 email: jtprince@gmail.com