ms-msrun 0.2.1 → 0.2.4

data/.gitignore

@@ -2,3 +2,4 @@ rdoc
 *.swp
 pkg
 *.gemspec
+doc

data/README.rdoc

@@ -4,8 +4,7 @@ A library for working with LC/MS runs.
 
 == Examples
 
-The following example will work on *mzXML*, *mzData* (and hope to support mzML
-in the future)
+The following example works on any version of *mzXML* (doesn't support mzXML 3.1 compression just yet).
 
     require "ms/msrun" 
 
@@ -61,10 +60,11 @@ in the future)
     # Quicker way to get at scans:
     Ms::Msrun.foreach("file.mzXML") {|scan|  scan <do something> }
 
+mzData support to be re-included in the future and mzML support planned.
+
 == Features
 
-[<b>Fast</b>] uses Nokogiri and a dash of regular expressions to achieve very
-fast random access of scans and full access.
+[<b>Fast</b>] uses Nokogiri and a dash of regular expressions to achieve very fast random access of scans and full access.
 [<b>Unified</b>] one interface for all formats.
 [<b>Lazy evaluation at scan and spectrum level</b>] Scans are only read from IO when requested.  Spectra are also decoded only when explicitly accessed.
 
@@ -75,3 +75,7 @@ fast random access of scans and full access.
 == Copying
 
     See LICENSE
+
+== See also
+
+mzml[http://github.com/delagoya/mzml]

data/Rakefile

@@ -12,11 +12,11 @@ gemspec = Gem::Specification.new do |s|
   s.name = NAME
   s.authors = ["John T. Prince"]
   s.email = "jtprince@gmail.com"
-  s.homepage = "http://jtprince.github.com/" + NAME + "/"
+  s.homepage = "http://jtprince.github.com/" + NAME + "/rdoc"
   s.summary = "an mspire library for working with LC/MS runs (mzxml, mzData, mzML)"
   s.description = 'A library for working with LC/MS runs. Part of mspire.  Has parsers for mzXML v1, 2, and 3, mzData (currently broken) and mzML (planned).  Can convert to commonly desired search output (such as mgf).  Fast random access of scans, and fast reading of the entire file.'
   s.rubyforge_project = 'mspire'
-  s.add_dependency 'ms-core'
+  s.add_dependency 'ms-core', ">= 0.0.3"
   s.add_dependency 'nokogiri'
   s.add_dependency 'narray'
   s.add_development_dependency("spec-more")

data/VERSION

@@ -1 +1 @@
-0.2.1
+0.2.4

data/lib/ms/msrun.rb

@@ -278,8 +278,8 @@ class Ms::Msrun
       io.rewind
       found
     else
-      File.open(file_or_io) do |io|
-        filetype_and_version(io)
+      File.open(file_or_io) do |_io|
+        filetype_and_version(_io)
       end
     end
   end

data/lib/ms/msrun/index.rb

@@ -35,8 +35,8 @@ class Ms::Msrun::Index < Array
   def initialize(filename_or_io)
     (ft, version) = Ms::Msrun.filetype_and_version(filename_or_io)
     tag = case ft
-          when :mzml : MZML_INDEX_TAG
-          when :mzxml : MZXML_INDEX_TAG
+          when :mzml ; MZML_INDEX_TAG
+          when :mzxml ; MZXML_INDEX_TAG
           end
     fn = 
       if filename_or_io.is_a? String

data/lib/ms/msrun/nokogiri/mzxml.rb

@@ -7,7 +7,7 @@ require 'ms/data'
 require 'ms/data/lazy_io'
 require 'ms/precursor'
 require 'ms/mzxml'
-
+require 'narray'
 
 class Ms::Msrun::Nokogiri::Mzxml
   NetworkOrder = true
@@ -75,7 +75,6 @@ class Ms::Msrun::Nokogiri::Mzxml
     opts = {:spectrum => true, :precursor => true}.merge(options)
     start_io_pos = @io.pos
     @io.pos = start_byte
-
     # read in the data keeping track of peaks start and stop
     string = ""
     if opts[:spectrum]
@@ -132,7 +131,9 @@ class Ms::Msrun::Nokogiri::Mzxml
       # data is stored as the base64 string until we actually try to access
       # it!  At that point the string is decoded and knows it is interleaved
       # data.  So, no spectrum is actually decoded unless it is accessed!
-      peaks_data = Ms::Data.new_interleaved(Ms::Data::LazyString.new(peaks_n.text, Ms::Data::LazyIO.unpack_code(peaks_n['precision'].to_i, NetworkOrder)))
+      compression_type = peaks_n['compressionType']
+      lazy_string = Ms::Data::LazyString.new(peaks_n.text, Ms::Data::LazyIO.unpack_code(peaks_n['precision'].to_i, NetworkOrder), compression_type == 'zlib')
+      peaks_data = Ms::Data.new_interleaved(lazy_string)
       spec = Ms::Spectrum.new(peaks_data)
       scan[8] = Ms::Spectrum.new(peaks_data)
     end

data/spec/ms/msrun_spec.rb

@@ -55,7 +55,7 @@ module MsrunSpec
     end
 
     it 'can avoid reading spectra' do 
-      nums = @nums.map
+      nums = @nums.dup
       Ms::Msrun.foreach(@file, :spectrum => false) do |scan|
         scan.spectrum.nil?.ok
         scan.num.is nums.shift

data/spec/ms/spectrum/compare_spec.rb

@@ -10,16 +10,15 @@ class Array
 end
 
 module CompareSpec
-  include Ms
 
   describe 'comparison of spectra' do
 
     before do
-      @a = Spectrum.new([[0,2,3,4], [5,6,7,8]])
-      @b = Spectrum.new([[0, 1.5, 3.5, 5.5], [9,10,11,12]])
+      @a = Ms::Spectrum.new([[0,2,3,4], [5,6,7,8]])
+      @b = Ms::Spectrum.new([[0, 1.5, 3.5, 5.5], [9,10,11,12]])
 
-      @c = Spectrum.new([[0, 1], [8,9]])
-      @d = Spectrum.new([[0.6, 0.75], [10,11]])
+      @c = Ms::Spectrum.new([[0, 1], [8,9]])
+      @d = Ms::Spectrum.new([[0.6, 0.75], [10,11]])
     end
 
     it 'compares spectra' do

data/spec/ms/spectrum/filter_spec.rb

@@ -11,12 +11,11 @@ class Array
 end
 
 class FilterSpec
-  include Ms
 
   describe 'filtering spectra' do
     before do
-      @a = Spectrum.new([[0,5,10, 15,16,17,18, 20.1], [0,1,2, 3,8,10,4, 0]])
-      @null = Spectrum.new([[],[]])
+      @a = Ms::Spectrum.new([[0,5,10, 15,16,17,18, 20.1], [0,1,2, 3,8,10,4, 0]])
+      @null = Ms::Spectrum.new([[],[]])
     end
 
     it 'filters spectra' do

metadata

@@ -1,7 +1,12 @@
 --- !ruby/object:Gem::Specification 
 name: ms-msrun
 version: !ruby/object:Gem::Version 
-  version: 0.2.1
+  prerelease: false
+  segments: 
+  - 0
+  - 2
+  - 4
+  version: 0.2.4
 platform: ruby
 authors: 
 - John T. Prince
@@ -9,55 +14,65 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-07 00:00:00 -07:00
+date: 2010-06-23 00:00:00 -06:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: ms-core
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: "0"
-    version: 
+        segments: 
+        - 0
+        - 0
+        - 3
+        version: 0.0.3
+  type: :runtime
+  version_requirements: *id001
 - !ruby/object:Gem::Dependency 
   name: nokogiri
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :runtime
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: narray
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :runtime
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: spec-more
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :development
+  version_requirements: *id004
 description: A library for working with LC/MS runs. Part of mspire.  Has parsers for mzXML v1, 2, and 3, mzData (currently broken) and mzML (planned).  Can convert to commonly desired search output (such as mgf).  Fast random access of scans, and fast reading of the entire file.
 email: jtprince@gmail.com
 executables: 
 - base64_to_array.rb
-- ms_to_search.rb
 - ms_to_obiwarp.rb
+- ms_to_search.rb
 extensions: []
 
 extra_rdoc_files: 
@@ -74,7 +89,6 @@ files:
 - bin/base64_to_array.rb
 - bin/ms_to_obiwarp.rb
 - bin/ms_to_search.rb
-- lib/lmat.rb
 - lib/ms/msrun.rb
 - lib/ms/msrun/axml/mzxml.rb
 - lib/ms/msrun/index.rb
@@ -91,7 +105,6 @@ files:
 - lib/ms/scan.rb
 - lib/ms/spectrum/compare.rb
 - lib/ms/spectrum/filter.rb
-- spec/lmat_spec.rb
 - spec/metadata/opd1/000.v1.mzXML.yml
 - spec/metadata/opd1/000.v2.1.mzXML.yml
 - spec/metadata/opd1/020.mzData.xml.yml
@@ -125,7 +138,7 @@ files:
 - spec/testfiles/opd1/020.v2.0.readw.mzXML
 - spec/testfiles/opd1/020.v2.0.readw.mzXML.key.yml
 has_rdoc: true
-homepage: http://jtprince.github.com/ms-msrun/
+homepage: http://jtprince.github.com/ms-msrun/rdoc
 licenses: []
 
 post_install_message: 
@@ -137,33 +150,34 @@ 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: 1.3.5
+rubygems_version: 1.3.6
 signing_key: 
 specification_version: 3
 summary: an mspire library for working with LC/MS runs (mzxml, mzData, mzML)
 test_files: 
-- spec/ms/scan_spec.rb
-- spec/ms/msrun_spec.rb
 - spec/ms/msrun_bm.rb
+- spec/ms/msrun/test_parsing_xml_frags/test_failures.rb
+- spec/ms/msrun/test_parsing_xml_frags/parse_test.rb
 - spec/ms/msrun/search_spec.rb
 - spec/ms/msrun/index_spec.rb
 - spec/ms/msrun/hpricot.rb
-- spec/ms/msrun/scan_spec.rb
 - spec/ms/msrun/sha1_spec.rb
-- spec/ms/msrun/test_parsing_xml_frags/parse_test.rb
-- spec/ms/msrun/test_parsing_xml_frags/test_failures.rb
-- spec/ms/spectrum/compare_spec.rb
+- spec/ms/msrun/scan_spec.rb
 - spec/ms/spectrum/filter_spec.rb
-- spec/lmat_spec.rb
+- spec/ms/spectrum/compare_spec.rb
+- spec/ms/msrun_spec.rb
+- spec/ms/scan_spec.rb
 - spec/spec_helper.rb

data/lib/lmat.rb

@@ -1,267 +0,0 @@
-
-require 'gsl'
-require 'narray'
-#include Runarray
-
-include Math
-include GSL
-
-## Labeled matrix
-
-class Lmat
-
-  NUM_BYTE_SIZE = 4
-
-  # an narray object numerically labelling the m-axis
-  attr_accessor :mvec
-  # an narray object numerically labelling the n-axis
-  attr_accessor :nvec
-  # an mvec.size X nvec.size narray
-  attr_accessor :mat
-
-  ## Takes an array of narray objects
-  def initialize(mat=nil, mvec=nil, nvec=nil)
-    @mat = mat
-    @mvec = mvec
-    @nvec = nvec
-  end
-
-  class << self
-    def [](*args)
-      mat = NArray[*args]
-      (nlen, mlen) = mat.shape
-      obj = new(mat)
-      obj.mvec = NArray[0...mlen]
-      obj.nvec = NArray[0...nlen]
-      obj
-    end
-  end
-
-  def [](*args)
-    @mat[*args]
-  end
-
-  def []=(*args)
-    @mat.send('[]=', *args)
-  end
-
-  def slice=(*args)
-    @mat.send(:slice, *args)
-  end
-
-  def slice(*args)
-    @mat.slice(*args)
-  end
-
-  def inspect
-    # TODO: needs work (see ruport pivotted table output)
-    ["nvec=#{@nvec.inspect}", "mvec=#{@mvec.inspect}", "mat=#{@mat.inspect}"].join("\n")
-
-    start = '   ' << nvec.to_a.join(", ") << "\n"
-    start << ("    " + ("-" * (start.size - 4))) << "\n"
-    mvec[].indgen!.each do |i|
-      start << "#{mvec[i]} | " << @mat[true, i].to_a.join(" ") << "\n"
-    end
-    start
-  end
-
-  def max
-    @mat.max
-  end
-
-  def dup
-    a = Lmat.new
-    a.mvec = self.mvec[]
-    a.nvec = self.nvec[]
-    a.mat = self.mat[]
-    a
-  end
-
-  # returns self
-  def from_lmat(file)
-    File.open(file) do |io|
-      (@mvec, @nvec) = [true, true].map do |iv|
-        _len = io.read(4).unpack('I').first
-        NArray.to_na( io.read(_len*NUM_BYTE_SIZE), 'sfloat' )
-      end
-      @mat = NArray.to_na(io.read, 'sfloat', @nvec.size, @mvec.size)
-    end
-    self
-  end
-
-  # returns self
-  def from_lmata(file)
-    # this can probably be made faster
-    File.open(file) do |io|
-      num_m = io.readline.to_i
-      mline = io.readline.chomp
-      @mvec = NArray.to_na( mline.split(' ').map {|v| v.to_f } )
-      raise RuntimeError, "bad m vec size" if mvec.size != num_m
-      num_n = io.readline.to_i
-      nline = io.readline.chomp
-      @nvec = NArray.to_na( nline.split(' ').map {|v| v.to_f } )
-      raise RuntimeError, "bad n vec size" if nvec.size != num_n
-      @mat = NArray.float(num_n, num_m)
-      num_m.times do |m|
-        line = io.readline.chomp!
-        @mat[true, m] = line.split(' ').map {|v| v.to_f }
-      end
-    end
-    self
-  end
-
-  # converts msrun object to a labeled matrix
-  # takes hash with symbols as keys
-  def from_msrun(msrun, args)
-    opt = {
-      :inc_mz => 1.0,
-      :behave_mz => 'sum', 
-      :baseline=> 0.0,
-
-      #:start_tm => 0.0, 
-      #:end_tm => 3600.0,
-      #:inc_tm => nil,
-      
-      #:start_mz => 400.0, 
-      #:end_mz => 1500.0,
-    }
-    opt.merge!(args)
-
-    (st, en) = msrun.start_and_end_mz
-    unless st && en
-      msg = ["scanning spectrum for start and end m/z values"]
-      msg << "(use :start_mz and :end_mz options to avoid this)"
-      warn msg
-      (st, en) = msrun.start_and_end_mz_brute_force
-    end
-    opt[:start_mz] ||= st
-    opt[:end_mz] ||= en
-
-    #unless opt[:start_tm] then opt[:start_tm] = times.first end
-    #unless opt[:end_tm] then opt[:end_tm] = times.last end
-
-    if opt[:inc_tm]
-      raise NotImplementedError, "haven't implemented interpolation in ruby yet! (#{File.basename(__FILE__)}: #{__LINE__})"
-    else ## No interpolation
-      times = []
-      @nvec = nil
-      vecs = []
-      num_scans = msrun.scan_count
-      printf "Reading #{num_scans} spectra [.=100]" if $VERBOSE
-      spectrum_cnt = 0
-      msrun.each(:ms_level => 1) do |scan|
-        spectrum = scan.spectrum
-        times << scan.time
-        #(mz,inten) = spectrum_to_mz_and_inten(spectrum, VecD)
-        # TODO: Figure out a shallow copy here:
-        # perhaps we'll make spectra Vec objects by default in future and
-        # then we'd be set...
-        mzs = NArray.new(spectrum.mzs)
-        intens = NArray.new(spectrum.intensities)
-        (x,y) = mzs.inc_x(intens, opt[:start_mz], opt[:end_mz], opt[:inc_mz], opt[:baseline], opt[:behave_mz])
-        spectrum_cnt += 1
-        if spectrum_cnt % 100 == 0
-          printf "." if $VERBOSE ; $stdout.flush
-        end
-        @nvec ||= x # just need the first one for the x values
-        vecs << y
-      end
-      puts "DONE!" if $VERBOSE
-      @mvec = NArray.new(times)
-      @mat = vecs
-    end
-    self  
-  end
-
-  # outputs vec lengths if set to true
-  def to_s(with_vec_lengths=false)
-    arr = []
-    arr.push(@mvec.size) if with_vec_lengths
-    arr.push(@mvec.to_a.join(" "))
-    arr.push(@nvec.size) if with_vec_lengths
-    arr.push(@nvec.to_a.join(" "))
-    (0...@mvec.size).each do |m_index|
-      arr.push(@mat[true, m_index].to_a.join(" "))
-    end
-    arr.join("\n")
-  end
-
-  def ==(other)
-     other != nil && self.class == other.class && @nvec == other.nvec && @mvec == other.mvec && @mat == other.mat
-  end
-
-  # returns a fresh lmat object
-  def warp_cols(new_m_values, deep_copy=false)
-    new_guy = self.dup
-    new_guy.warp_cols!(new_m_values, deep_copy)
-    new_guy
-  end
-
-  # warps the data in self based on interpolation of the cols.  Evaluates the
-  # new_m_values for each column and returns a new lmat object with the m
-  # values set to new_m_values.  nvec will be the same is in self.
-  def warp_cols!(new_m_values, deep_copy=false)
-    nvec[].indgen.each do |n|
-      self[n,true] = Spline.alloc(Interp::AKIMA, mvec, self[n, true]).eval(new_m_values)
-    end
-    self.nvec = deep_copy ? self.nvec[] : self.nvec
-    self.mvec = deep_copy ? new_m_values[] : new_m_values
-    self
-  end
-
-  def write(file=nil, int_format_string='i')
-    handle = $>
-    if file; handle = File.open(file, "wb") end
-    bin_string = ""
-    bin_string << [@mvec.size].pack(int_format_string)
-    bin_string << @mvec.to_s
-    bin_string << [@nvec.size].pack(int_format_string)
-    bin_string << @nvec.to_s
-    bin_string << @mat.to_s
-    handle.print bin_string
-    if file; handle.close end
-  end
-
-  def print(file=nil)
-    handle = $>
-    handle = File.new(file, "w") if file
-    handle.print( self.to_s(true) )
-    handle.close if file
-  end
-end
-
-class Lmat
-  module Gnuplot
-
-    # png output only right now, given no outfile, plot to X11
-    def plot(outfile=nil)
-      # modified from Hornet's eye
-      require 'gnuplot'
-      ::Gnuplot.open do |gp| 
-        ::Gnuplot::SPlot.new(gp) do |plot|
-          if outfile
-            plot.terminal 'png'
-            plot.output outfile
-          end
-          plot.pm3d
-          plot.hidden3d
-          plot.palette 'defined ( 0 "black", 51 "blue", 102 "green", ' +
-            '153 "yellow", 204 "red", 255 "white" )'
-          plot.xlabel 'n'
-          plot.ylabel 'm'
-          plot.data << ::Gnuplot::DataSet.new( self ) do |ds|
-            ds.with = 'pm3d'
-            ds.matrix = true
-          end
-        end
-      end
-    end
-
-    def to_gsplot
-      require 'gnuplot'
-      [@mvec.to_a, @nvec.to_a, @mat.to_a].to_gsplot
-    end
-  end
-  include Gnuplot
-end
-

data/spec/lmat_spec.rb

@@ -1,105 +0,0 @@
-require File.expand_path( File.dirname(__FILE__) + '/spec_helper' )
-
-require 'lmat'
-
-describe 'an lmat' do
-
-  @klass = Lmat
-  @lmatfile = TESTFILES + "/lmat/tmp1.lmat"
-  @lmatafile = TESTFILES + "/lmat/tmp1.lmata"
-  @lmatafile_small = TESTFILES + "/lmat/tmp2.lmata"
-
-  before do
-    @lmat = Lmat.new
-  end
-
-  it 'can be created with no arguments' do
-    obj1 = @klass.new
-    obj1.class.is @klass
-  end
-
-  it 'can be created with arrays' do
-    obj = @klass[[1,2,3],[4,5,6]]
-    obj[0,0].is 1
-    obj[2,1].is 6
-    obj[1,0].is 2
-    obj.mvec.enums [0,1]
-    obj.nvec.enums [0,1,2]
-  end
-
-  it 'can find the max value' do
-    obj = @klass[[1,2,3],[1,8,3]]
-    obj.max.is 8
-  end
-
-  it 'can be read from lmat file' do
-    x = Lmat.new
-    x.from_lmat(@lmatfile)
-    x.nvec.size.is 30
-    x.mvec.size.is 40
-    x.mat.size.is 1200
-    x.mat.shape.is [30,40]
-  end
-
-  it 'can write an lmat file' do
-    begin
-      output = @lmatfile + ".TMP"
-      @lmat.from_lmat(@lmatfile) 
-      @lmat.write(output)
-      IO.read(output).is IO.read(@lmatfile)
-    ensure
-      File.unlink(output) if File.exist?(output)
-    end
-  end
-
-  it 'can be read from an lmata file' do
-    x = Lmat.new.from_lmata(@lmatafile)
-    x.nvec.size.is 30
-    x.mvec.size.is 40
-    x.mat.size.is 1200
-    x.mat.shape.is [30,40]
-  end
-
-  it 'can print an lmata file' do
-    begin
-      output = @lmatafile_small + ".TMP"
-      @lmat.from_lmata(@lmatafile_small) 
-      @lmat.print(output)
-      ars = [output, @lmatafile_small].map do |file|
-        IO.read(file).chomp.gsub("\n", " ").split(/\s+/).map {|v| v.to_f }
-      end
-      ars.first.enums ars.last
-    ensure
-      File.unlink(output) if File.exist?(output)
-    end
-  end
-
-  xit 'can warp data columns' do
-    @lmat.from_lmata(@lmatafile_small)
-    puts "Warp before"
-    p @lmat
-    deep_copy = true
-    @lmat.plot("before.png")
-    new_lmat = @lmat.warp_cols(NArray.float(7).indgen(12).collect {|v| v + 2.5 }, deep_copy)
-    new_lmat.isa Lmat
-    new_lmat.plot("after.png")
-    puts "Warp after"
-    p new_lmat
-    ## TODO: NEEEED tests HERE
-  end
-
-  begin
-    require 'gnuplot'
-    it 'can plot' do
-      file = "mypng.png"
-      @lmat.from_lmata(@lmatafile_small)
-      @lmat.plot(file)
-      @lmat.isa Lmat
-      ok File.exist?(file)
-      File.unlink(file) if File.exist?(file)
-    end
-  rescue
-    puts "SKIPPING: plotting (since gnuplot gem not found)"
-  end
-
-end