mspire 0.6.22 → 0.6.24

data/lib/ms/mzml.rb

@@ -176,24 +176,6 @@ module MS
           mzml.each(&block)
         end
       end
-
-      # unpack binary data based on an accesions.  accessions must only
-      # respond to :include?  So, hash keys, a set, or an array will all work.
-      def unpack_binary(base64string, accessions)
-        compressed =
-          if accessions.include?('MS:1000574') then true # zlib compression
-          elsif accessions.include?('MS:1000576') then false # no compression
-          else raise 'no compression info: check your MS accession numbers'
-          end
-        precision_unpack = 
-          if accessions.include?('MS:1000523') then 'E*'
-          elsif accessions.include?('MS:1000521') then 'e*'
-          else raise 'unrecognized precision: check your MS accession numbers'
-          end
-        data = base64string.unpack("m*").first
-        unzipped = compressed ? Zlib::Inflate.inflate(data) : data
-        unzipped.unpack(precision_unpack)
-      end
     end
 
     # name can be :spectrum or :chromatogram

data/lib/ms/mzml/data_array.rb

@@ -5,6 +5,7 @@ require 'ms/cv/paramable'
 module MS
   class Mzml
     class DataArray < Array
+      alias_method :array_initialize, :initialize
       include MS::CV::Paramable
 
       DEFAULT_DTYPE = :float64
@@ -17,17 +18,76 @@ module MS
         int32: 'MS:1000519', # signed
       }
 
-      # the type of data array (:mz or :intensity)
+      # the type of data array (:mz, :intensity, :mz_external, or :intensity_external)
       attr_accessor :type
 
-      # requires a type, :mz, :intensity, :mz_external, or :intensity_external
-      # (external types used in imzml)
-      def initialize(_type, opts={params: []})
-        @type = _type
-        @external = !!(@type.to_s =~ /external$/)
+      def initialize(*args)
+        array_initialize(*args)
       end
 
-      def self.to_binary(array_ish, dtype=DEFAULT_DTYPE, compression=DEFAULT_COMPRESSION)
+      # returns a new MS::Mzml::DataArray object (an array)
+      #
+      #     args:
+      #       base64, set-like               # where set-like responds to include?
+      #       base64, type=:float64, compression=true
+      #
+      #     examples:
+      #     MS::Mzml::Spectrum.unpack_binary('eJxjYACBD/YMEOAAoTgcABe3Abg=', ['MS:1000574', MS:1000523']).
+      #     MS::Mzml::Spectrum.unpack_binary("ADBA/=", :float32, true)
+      #     MS::Mzml::Spectrum.unpack_binary("ADBA/=") # uses float64 and compression
+      def self.from_binary(base64, *args)
+        if args.first.respond_to?(:include?)
+          accessions = args.first
+          compressed =
+            if accessions.include?('MS:1000574') then true # zlib compression
+            elsif accessions.include?('MS:1000576') then false # no compression
+            else raise 'no compression info: check your MS accession numbers'
+            end
+          precision_unpack = 
+            if accessions.include?('MS:1000523') then 'E*'
+            elsif accessions.include?('MS:1000521') then 'e*'
+            else raise 'unrecognized precision: check your MS accession numbers'
+            end
+        else
+          compressed = args.last || true
+          precision_unpack =
+            case args.first
+            when :float64
+              'E*'
+            when :float32
+              'e*'
+            when nil
+              'E*'
+            else
+              raise ArgumentError, "#{args.first} must be one of :float64, :float32 or other acceptable type"
+            end
+        end
+        data = base64.unpack("m*").first
+        unzipped = compressed ? Zlib::Inflate.inflate(data) : data
+        self.new( unzipped.unpack(precision_unpack) )
+      end
+
+      # returns a base64 string that can be used for xml representations of
+      # the data
+      #
+      #     args:
+      #       array-like  set-like               # where set-like responds to include?
+      #       array-like  type=:float64, compression=true
+      def self.to_binary(array_ish, *args)
+        if args.first.respond_to?(:include?)
+          accessions = args.first
+          dtype = 
+            if accessions.include?('MS:1000521') 
+              :float32
+            else
+              :float64
+            end
+          compression = accessions.include?('MS:1000576') ? false : true 
+        else
+          dtype = args[0] || DEFAULT_DTYPE
+          compression = args[1] || DEFAULT_COMPRESSION
+        end
+
         pack_code = 
           case dtype
           when :float64 ; 'E*'
@@ -42,6 +102,11 @@ module MS
         Base64.strict_encode64(string)
       end
 
+      # calls the class to_binary method with self and the given args
+      def to_binary(*args)
+        self.class.to_binary(self, *args)
+      end
+
       def to_xml(builder, dtype=DEFAULT_DTYPE, compression=DEFAULT_COMPRESSION)
         encoded_length = 
           if @external
@@ -56,8 +121,11 @@ module MS
           unless @external
             MS::CV::Param[ DTYPE_TO_ACC[dtype] ].to_xml(bda_n)
             MS::CV::Param[ compression ? 'MS:1000574' : 'MS:1000576' ].to_xml(bda_n)
-            MS::CV::Param[ (@type == :mz) ? 'MS:1000514' : 'MS:1000515' ].to_xml(bda_n) # must be m/z or intensity 
-            bda_n.binary(base64)
+            if @type
+              accession = ( (@type == :mz) ? 'MS:1000514' : 'MS:1000515' )
+              MS::CV::Param[accession].to_xml(bda_n)
+              bda_n.binary(base64)
+            end
           end
         end
       end
@@ -70,8 +138,8 @@ module MS
               if data_ar.is_a?(MS::Mzml::DataArray)
                 data_ar
               else
-                real_data_array = MS::Mzml::DataArray.new(typ)
-                real_data_array.replace(data_ar)
+                real_data_array = MS::Mzml::DataArray.new(data_ar)
+                real_data_array.type = typ
                 real_data_array
               end
             ar.type = typ unless ar.type

data/lib/ms/mzml/spectrum.rb

@@ -83,16 +83,15 @@ module MS
         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)
+          MS::Mzml::DataArray.from_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
+        data_arrays = [MS::Mzml::DataArray.new, MS::Mzml::DataArray.new] 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 :

data/mspire.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "mspire"
-  s.version = "0.6.22"
+  s.version = "0.6.24"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["John T. Prince", "Simon Chiang"]
-  s.date = "2012-02-29"
+  s.date = "2012-03-13"
   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 = [
@@ -56,7 +56,9 @@ Gem::Specification.new do |s|
     "lib/ms/ident/protein.rb",
     "lib/ms/ident/protein_group.rb",
     "lib/ms/ident/search.rb",
+    "lib/ms/isotope.rb",
     "lib/ms/isotope/aa.rb",
+    "lib/ms/isotope/nist_isotope_info.yml",
     "lib/ms/mascot.rb",
     "lib/ms/mass.rb",
     "lib/ms/mass/aa.rb",
@@ -112,6 +114,7 @@ Gem::Specification.new do |s|
     "obo/ims.obo",
     "obo/ms.obo",
     "obo/unit.obo",
+    "script/mzml_read_binary.rb",
     "spec/bin_spec.rb",
     "spec/ms/cv/param_spec.rb",
     "spec/ms/digester_spec.rb",
@@ -123,8 +126,10 @@ Gem::Specification.new do |s|
     "spec/ms/ident/pepxml_spec.rb",
     "spec/ms/ident/protein_group_spec.rb",
     "spec/ms/isotope/aa_spec.rb",
+    "spec/ms/isotope_spec.rb",
     "spec/ms/mass_spec.rb",
     "spec/ms/mzml/cv_spec.rb",
+    "spec/ms/mzml/data_array_spec.rb",
     "spec/ms/mzml/file_content_spec.rb",
     "spec/ms/mzml/file_description_spec.rb",
     "spec/ms/mzml/index_list_spec.rb",
@@ -142,7 +147,7 @@ Gem::Specification.new do |s|
     "spec/testfiles/ms/ident/peptide/db/uni_11_sp_tr.fasta",
     "spec/testfiles/ms/ident/peptide/db/uni_11_sp_tr.msd_clvg2.min_aaseq4.yml",
     "spec/testfiles/ms/mzml/j24z.idx_comp.3.mzML",
-    "spec/testfiles/ms/mzml/mspire_simulated.noidx.check.mzML",
+    "spec/testfiles/ms/mzml/mspire_simulated.MSn.check.mzML",
     "spec/testfiles/ms/mzml/openms.noidx_nocomp.12.mzML",
     "spec/testfiles/ms/quant/kill_extra_tabs.rb",
     "spec/testfiles/ms/quant/max_quant_output.provenance.txt",
@@ -179,6 +184,8 @@ Gem::Specification.new do |s|
       s.add_runtime_dependency(%q<bsearch>, [">= 1.5.0"])
       s.add_runtime_dependency(%q<andand>, [">= 1.3.1"])
       s.add_runtime_dependency(%q<obo>, [">= 0.1.0"])
+      s.add_runtime_dependency(%q<builder>, [">= 3.0.0"])
+      s.add_runtime_dependency(%q<trollop>, [">= 1.16.2"])
       s.add_development_dependency(%q<rspec>, ["~> 2.6"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_development_dependency(%q<rcov>, [">= 0"])
@@ -187,6 +194,8 @@ Gem::Specification.new do |s|
       s.add_dependency(%q<bsearch>, [">= 1.5.0"])
       s.add_dependency(%q<andand>, [">= 1.3.1"])
       s.add_dependency(%q<obo>, [">= 0.1.0"])
+      s.add_dependency(%q<builder>, [">= 3.0.0"])
+      s.add_dependency(%q<trollop>, [">= 1.16.2"])
       s.add_dependency(%q<rspec>, ["~> 2.6"])
       s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
       s.add_dependency(%q<rcov>, [">= 0"])
@@ -196,6 +205,8 @@ Gem::Specification.new do |s|
     s.add_dependency(%q<bsearch>, [">= 1.5.0"])
     s.add_dependency(%q<andand>, [">= 1.3.1"])
     s.add_dependency(%q<obo>, [">= 0.1.0"])
+    s.add_dependency(%q<builder>, [">= 3.0.0"])
+    s.add_dependency(%q<trollop>, [">= 1.16.2"])
     s.add_dependency(%q<rspec>, ["~> 2.6"])
     s.add_dependency(%q<jeweler>, ["~> 1.5.2"])
     s.add_dependency(%q<rcov>, [">= 0"])

data/script/mzml_read_binary.rb

@@ -0,0 +1,34 @@
+#!/usr/bin/env ruby
+
+require 'trollop'
+require 'ms/mzml/data_array'
+
+parser = Trollop::Parser.new do
+  banner "usage: #{File.basename(__FILE__)} [OPTIONS] <base64> ..."
+  banner "output: space separated data, one line per base64 string"
+  banner ""
+  opt :type, "kind of data (float32|float64|int8|int16|int32|int64)", :default => 'float64'
+  opt :not_compressed, "zlib compression was *not* used"
+end
+
+begin
+  opts = parser.parse(ARGV)
+rescue help=Trollop::HelpNeeded 
+end
+
+if help || ARGV.size == 0
+  parser.educate && exit
+end
+
+type = opts[:type].to_sym
+compressed = !opts[:not_compressed]
+
+ARGV.each do |base64|
+  puts MS::Mzml::DataArray.from_binary(base64, type, compressed).join(" ")
+end
+
+
+
+
+
+

data/spec/ms/isotope_spec.rb

@@ -0,0 +1,31 @@
+require 'spec_helper'
+
+require 'ms/isotope'
+
+describe 'MS::Isotope constants' do
+  it 'has all the common isotopes: MS::Isotope::ISOTOPES' do
+    # frozen
+    MS::Isotope::ISOTOPES.size.should == 288
+    hydrogen_isotopes = MS::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|
+      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 = MS::Isotope::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: MS::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(MS::Isotope::BY_ELEMENT[:c]) do |hash, iso|
+      hash.each do |k,v|
+        iso.send(k).should == v
+      end
+    end
+    MS::Isotope::BY_ELEMENT[:h].size.should == 2
+  end
+end

data/spec/ms/mzml/data_array_spec.rb

@@ -0,0 +1,38 @@
+require 'spec_helper'
+
+require 'ms/mzml/data_array'
+
+describe MS::Mzml::DataArray do
+
+  it 'can be created from base64 binary data' do
+    d_ar = MS::Mzml::DataArray.from_binary('eJxjYACBD/YMEOAAoTgcABe3Abg=', :float64, zlib=true)
+    d_ar.is_a?(Array)
+    d_ar.should == [1.0, 2.0, 3.0]
+    d_ar = MS::Mzml::DataArray.from_binary('eJxjYACBD/YMEOAAoTgcABe3Abg=', ['MS:1000523', 'MS:1000574'])
+    d_ar.is_a?(Array)
+    d_ar.should == [1.0, 2.0, 3.0]
+  end
+
+  it "can be initialized like any ol' array" do
+    data = [1,2,3]
+    d_ar = MS::Mzml::DataArray.new( data )
+    d_ar.should == data
+  end
+
+  describe 'an instantiated MS::Mzml::DataArray' do
+    subject { MS::Mzml::DataArray.new [1,2,3] }
+
+    it "can have a 'type'" do
+      subject.type = :mz
+      subject.type.should == :mz
+    end
+
+    it 'can be converted to a binary string' do
+      string = subject.to_binary
+      # frozen
+      string.should == "eJxjYACBD/YMEOAAoTgcABe3Abg="
+    end
+
+  end
+
+end

data/spec/ms/mzml_spec.rb

@@ -136,70 +136,13 @@ describe MS::Mzml do
       #check = TESTFILES + '/ms/mzml/mspire_simulated.noidx.check.mzML'
       tmpfile = TESTFILES + '/ms/mzml/mspire_simulated.MSn.TMP.mzML'
       mzml.to_xml(tmpfile)
-      p tmpfile
-      #xml = sanitize_version(IO.read(tmpfile))
-      #xml.should be_a(String)
-      #sanitize_version(mzml.to_xml).should == xml
-      #xml.should == sanitize_version(IO.read(check))
-      #xml.should match(/<mzML/)
-      #File.unlink(tmpfile)
-    end
-
-
-    it 'writes MS1 spectra and retention times' do
+      as_string = mzml.to_xml
+      check_string = IO.read(TESTFILES + '/ms/mzml/mspire_simulated.MSn.check.mzML')
 
-      spec_params = ['MS:1000127', ['MS:1000511', 1]]
-
-      spec1 = MS::Mzml::Spectrum.new('scan=1', params: spec_params) 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|
-            # retention time of 42 seconds
-            scan.describe! ['MS:1000016', 40.0, 'UO:0000010']
-          end
-          sl << scan
-        end
-      end
-      spec2 = MS::Mzml::Spectrum.new('scan=2', params: spec_params) do |spec| 
-        spec.data_arrays = [[1,2,3.5], [5,6,5]]
-        spec.scan_list = MS::Mzml::ScanList.new do |sl|
-          scan = MS::Mzml::Scan.new do |scan|
-            # retention time of 42 seconds
-            scan.describe! ['MS:1000016', 45.0, 'UO:0000010']
-          end
-          sl << scan
-        end
+      [IO.read(tmpfile), as_string].each do |st|
+        sanitize_version(check_string).should == sanitize_version(st)
       end
-
-      mzml = MS::Mzml.new do |mzml|
-        mzml.id = 'the_little_one'
-        mzml.cvs = MS::Mzml::CV::DEFAULT_CVS
-        mzml.file_description = MS::Mzml::FileDescription.new  do |fd|
-          fd.file_content = MS::Mzml::FileContent.new
-          fd.source_files << MS::Mzml::SourceFile.new
-        end
-        default_instrument_config = MS::Mzml::InstrumentConfiguration.new("IC",[], params: ['MS:1000031'])
-        mzml.instrument_configurations << default_instrument_config
-        software = MS::Mzml::Software.new
-        mzml.software_list << software
-        default_data_processing = MS::Mzml::DataProcessing.new("did_nothing")
-        mzml.data_processing_list << default_data_processing
-        mzml.run = MS::Mzml::Run.new("little_run", default_instrument_config) do |run|
-          spectrum_list = MS::Mzml::SpectrumList.new(default_data_processing)
-          spectrum_list.push(spec1, spec2)
-          run.spectrum_list = spectrum_list
-        end
-      end
-
-      check = TESTFILES + '/ms/mzml/mspire_simulated.noidx.check.mzML'
-      tmpfile = TESTFILES + '/ms/mzml/mspire_simulated.TMP.mzML'
-      mzml.to_xml(tmpfile)
-      xml = sanitize_version(IO.read(tmpfile))
-      xml.should be_a(String)
-      sanitize_version(mzml.to_xml).should == xml
-      xml.should == sanitize_version(IO.read(check))
-      xml.should match(/<mzML/)
-      File.unlink(tmpfile)
+      File.unlink(tmpfile) if File.exist?(tmpfile)
     end
   end
 end

data/spec/testfiles/ms/mzml/{mspire_simulated.noidx.check.mzML → mspire_simulated.MSn.check.mzML}

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" version="1.1.0" id="the_little_one">
+<mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" version="1.1.0" id="ms1_and_ms2">
   <cvList count="3">
     <cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo" version="3.18.0"/>
     <cv id="UO" fullName="Unit Ontology" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo" version="16:02:2012"/>
@@ -14,7 +14,7 @@
     </sourceFileList>
   </fileDescription>
   <softwareList count="1">
-    <software id="mspire" version="0.6.7">
+    <software id="mspire" version="0.6.22">
     </software>
   </softwareList>
   <instrumentConfigurationList count="1">
@@ -31,7 +31,7 @@
   <run id="little_run" defaultInstrumentConfigurationRef="IC">
     <spectrumList count="2" defaultDataProcessingRef="did_nothing">
       <spectrum id="scan=1" index="0" defaultArrayLength="3">
-        <cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum"/>
+        <cvParam cvRef="MS" accession="MS:1000128" name="profile spectrum"/>
         <cvParam cvRef="MS" accession="MS:1000511" name="ms level" value="1"/>
         <scanList count="1">
           <scan>
@@ -55,12 +55,22 @@
       </spectrum>
       <spectrum id="scan=2" index="1" defaultArrayLength="3">
         <cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum"/>
-        <cvParam cvRef="MS" accession="MS:1000511" name="ms level" value="1"/>
+        <cvParam cvRef="MS" accession="MS:1000511" name="ms level" value="2"/>
+        <cvParam cvRef="MS" accession="MS:1000580" name="MSn spectrum"/>
         <scanList count="1">
           <scan>
             <cvParam cvRef="MS" accession="MS:1000016" name="scan start time" value="45.0" unitCvRef="UO" unitAccession="UO:0000010" unitName="second"/>
           </scan>
         </scanList>
+        <precursorList count="1">
+          <precursor spectrumRef="scan=1">
+            <selectedIonList count="1">
+              <cvParam cvRef="MS" accession="MS:1000744" name="selected ion m/z" value="2.0"/>
+              <cvParam cvRef="MS" accession="MS:1000041" name="charge state" value="2"/>
+              <cvParam cvRef="MS" accession="MS:1000042" name="peak intensity" value="5"/>
+            </selectedIonList>
+          </precursor>
+        </precursorList>
         <binaryDataArrayList count="2">
           <binaryDataArray encodedLength="28">
             <cvParam cvRef="MS" accession="MS:1000523" name="64-bit float"/>