mzml 0.1.0

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,22 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+doc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 Angel Pizarro
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,20 @@
+= mzml
+
+MzML is a standard data format for encoding mass spectrometry data. For more information see mzML the specification at http://psidev.info/index.php?q=node/257
+
+This library is a non-validating mzML version 1.1 parser/reader.
+
+
+== Note on Patches/Pull Requests
+ 
+* Fork the project. It is hosted @ http://github.com/delagoya/mzml
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Copyright
+
+Copyright (c) 2009 Angel Pizarro. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,44 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "mzml"
+    gem.summary = %Q{A non-validating mzML parser}
+    gem.description = %Q{A non-validating mzML parser. MzML is a standard data format for representing mass spectrometry data.}
+    gem.email = "angel@delagoya.com"
+    gem.homepage = "http://github.com/delagoya/mzml"
+    gem.authors = ["Angel Pizarro"]
+    gem.add_development_dependency "rspec", ">= 1.2.9"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+    gem.add_dependency  "nokogiri", ">= 1.3.3"
+    
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
+end
+
+require 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :spec => :check_dependencies
+
+task :default => :spec
+
+require 'yard'
+YARD::Rake::YardocTask.new do |yardoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+  yardoc.options = ["--title", "mzml #{version}", "-r", "README.rdoc"] 
+  yardoc.files = ['README*','lib/**/*.rb']
+end

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/lib/mzml.rb

@@ -0,0 +1,228 @@
+require 'nokogiri'
+require 'base64'
+require 'zlib'
+
+#--
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU Library or "Lesser" General Public
+# License (LGPL) as published by the Free Software Foundation;
+# either version 2 of the License, or (at your option) any later
+# version.
+# Author: Angel Pizarro
+# Date: 12/05/2009
+# Copyright: Angel Pizarro, Copyright (c) University of Pennsylvania.  All rights reserved.
+#
+
+# == MzML
+#
+# A non-validating mzML v 1.1.0 parser. Most annotation is left as XML DOM
+# objects. See the Nokogiri::XML::Node and Nokogiri::XML::NodeSet
+# documentation on how to work with these.
+#
+# ===USAGE:
+#
+#     require 'mzml'
+#     mzml =  MzML::Doc.new("test.mzXML")
+
+module MzML
+
+  # An internal module containing useful regular expressions
+  module RGX
+    # The file byte offset of the start of the file index
+    INDEX_OFFSET = /<indexListOffset>(\d+)<\/indexListOffset>/
+    # The start of a either a spectrumList or chromatographList
+    DATA_LIST_START =  /<(spectrum|chromatogram)List\s.*count\=["'](\d+)/m
+    # The start spectrum or chromatogram element
+    DATA_START = /<(spectrum|chromatogram)\s.*id=["']([^'"]+)["']/m
+    # The end spectrum or chromatogram element
+    DATA_END = /(<\/(spectrum|chromatogram)>)/
+  end
+
+  def parse(xml)
+    Nokogiri::XML.parse(xml).root
+  end
+
+  class UnsupportedFileFormat < Exception
+  end
+  class BadIdentifier < Exception
+  end
+
+  class Doc < File
+    attr_reader :index, :fname, :spectrum_count, :chromatogram_count, :node
+
+    def initialize(mz_fname)
+      unless mz_fname =~ /\.mzML$/
+        raise MzML::UnsupportedFileFormat.new  "File extension must be .\"mzML\""
+      end
+      super(mz_fname, "r")
+      @index = parse_index_list
+    end
+
+    def chromatogram(chromatogram_id)
+      if @index[:chromatogram].has_key? chromatogram_id
+        self.seek @index[:chromatogram][chromatogram_id]
+        parse_next
+      else
+        raise MzML::BadIdentifier.new("Invalid ID '#{chromatogram_id}'")
+      end
+    end
+
+    def spectrum(spectrum_id)
+      if @index[:spectrum].has_key? spectrum_id
+        self.seek @index[:spectrum][spectrum_id]
+        return Spectrum.new(parse_next())
+
+      else
+        raise MzML::BadIdentifier.new("Invalid ID '#{spectrum_id}'")
+      end
+    end
+
+    # private
+    # Parses the IndexList
+    def parse_index_list
+      self.seek(self.stat.size - 200)
+      # parse the index offset
+      tmp = self.read
+      tmp  =~  MzML::RGX::INDEX_OFFSET
+      offset = $1
+      # if I didn't match anything, compute the index and return
+      unless (offset)
+        return compute_index_list
+      end
+      @index = {}
+      self.seek(offset.to_i)
+      tmp = Nokogiri::XML.parse(self.read).root
+      tmp.css("index").each do |idx|
+        index_type = idx[:name].to_sym
+        @index[index_type] = {}
+        idx.css("offset").each do |o|
+          @index[index_type][o[:idRef]] = o.text().to_i
+        end
+      end
+      return @index
+    end
+
+    def compute_index_list
+      @index = {}
+      # start at the beginning.
+      self.rewind
+      # fast forward to the first spectrum or chromatograph
+      buffer = ''
+      while !self.eof
+        buffer += self.read(1024)
+        if start_pos = buffer =~ MzML::RGX::DATA_START
+          self.seek start_pos
+          break
+        end
+      end
+      # for each particular entity start to fill in the index
+      buffer = ''
+      rgx_start = /<(spectrum|chromatogram)\s.*id=["']([^"']+)["']/
+      while !self.eof
+        buffer += self.read(1024)
+        if start_pos = buffer =~ rgx_start
+          start_pos = self.pos - buffer.length + start_pos
+          @index[$1.to_sym][$2] = start_pos
+          buffer = ''
+        end
+      end
+      return @index
+    end
+
+    def parse_next
+      buffer = self.read(1024)
+      end_pos = nil
+      while(!self.eof)
+        if end_pos = buffer =~ MzML::RGX::DATA_END
+          buffer = buffer.slice(0..(end_pos + $1.length))
+          break
+        end
+        buffer += self.read(1024)
+      end
+      return Nokogiri::XML.parse(buffer)
+    end
+  end
+
+  class Spectrum
+    attr_accessor :id, :default_array_length, :spot_id, :type,\
+    :charge, :precursor, :base_peak_mz, :base_peak_intensity, :ms_level, \
+    :high_mz, :low_mz, :title, :tic, :polarity, :representation, :mz_node, :intensity_node, \
+    :mz, :intensity, :precursor_list, :scan_list, :retention_time
+    attr_reader :node, :params
+
+    # mz & intensity arrays will be don by proper methods maybe.
+    def initialize(spectrum_node)
+      @node = spectrum_node
+      @params = {}
+      parse_element()
+    end
+
+    protected
+    # This method pulls out all of the annotation from the XML node
+    def parse_element
+      # id
+      @id = @node[:id]
+      @default_array_length = @node[:defaultArrayLength]
+      @spot_id = @node[:spotID]
+      # now reaching into params
+      @params = @node.xpath("cvParam").inject({}) do  |memo,prm|
+        memo[prm[:name]] = prm[:value]
+        memo
+      end
+      @ms_level = @params["ms level"].to_i
+      @low_mz = @params["lowest observed m/z"].to_f if @params.has_key?("lowest observed m/z")
+      @high_mz = @params["highest observed m/z"].to_f if @params.has_key?("highest observed m/z")
+      @tic = @params["total ion current"].to_i if @params.has_key?("total ion current")
+      @base_peak_mz = @params["base peak m/z"].to_i if @params.has_key?("base peak m/z")
+      @base_peak_intensity = @params["base peak intensity"].to_i if @params.has_key?("base peak intensity")
+      # polarity
+      # representation
+      # precursor list
+      if (@node.xpath("precursorList")[0])
+        parse_precursor_list()
+      else
+        @precursor_list = nil
+      end
+      # scan list
+      if (@node.xpath("scanList")[0])
+        @scan_list = parse_scan_list()
+      else
+        @scan_list = nil
+      end
+      # binary data
+      parse_binary_data()
+    end
+
+    def parse_precursor_list
+      @precursor_list = @node.css("precursorList > precursor").each do |p|
+        [p[:spectrumRef], p]
+      end
+    end
+
+    def parse_scan_list
+      @scan_list = @node.xpath("scanList/scan")
+      @retention_time = @node.xpath("scanList/scan/cvParam[@accesion='MS:1000016']")[0]
+    end
+
+    def parse_binary_data
+      @mz_node = @node.xpath("spectrum/binaryDataArrayList/binaryDataArray/cvParam[@accession='MS:1000514']").first.parent
+      data = Base64.decode64(@mz_node.xpath("binary").text)
+      if @mz_node.xpath("cvParam[@accession='MS:1000574']")[0]
+        # need to uncompress the data
+        data = Zlib::Inflate.inflate(data)
+      end
+      # 64-bit floats? default is 32-bit
+      dtype = @mz_node.xpath("cvParam[@accession='MS:1000523']")[0] ? "E*" : "e*"
+      @mz = data.unpack(dtype)
+      @intensity_node = @node.xpath("spectrum/binaryDataArrayList/binaryDataArray/cvParam[@accession='MS:1000515']").first.parent
+      data = Base64.decode64(@intensity_node.xpath("binary").text)
+      if @intensity_node.xpath("cvParam[@accession='MS:1000574']")[0]
+        # need to uncompress the data
+        data = Zlib::Inflate.inflate(data)
+      end
+      # 64-bit floats? default is 32-bit
+      dtype = @intensity_node.xpath("cvParam[@accession='MS:1000523']")[0] ? "E*" : "e*"
+      @intensity = data.unpack(dtype)
+    end
+  end
+end

data/mzml.gemspec

@@ -0,0 +1,62 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{mzml}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Angel Pizarro"]
+  s.date = %q{2009-12-06}
+  s.description = %q{A non-validating mzML parser. MzML is a standard data format for representing mass spectrometry data.}
+  s.email = %q{angel@delagoya.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     ".yardoc",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "lib/mzml.rb",
+     "mzml.gemspec",
+     "spec/mzml_spec.rb",
+     "spec/small.compressed.mzML",
+     "spec/small.mgf",
+     "spec/small.mzML",
+     "spec/spec.opts",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/delagoya/mzml}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.5}
+  s.summary = %q{A non-validating mzML parser}
+  s.test_files = [
+    "spec/mzml_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_runtime_dependency(%q<nokogiri>, [">= 1.3.3"])
+    else
+      s.add_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
+    end
+  else
+    s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
+  end
+end
+

data/spec/mzml_spec.rb

@@ -0,0 +1,60 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe MzML do
+  before(:all) do
+    # set the input file name
+    @file = File.join(File.dirname(__FILE__),  "small.mzML")
+    @compressed = File.join(File.dirname(__FILE__),  "small.compressed.mzML")
+    @mgf = File.join(File.dirname(__FILE__),  "small.mgf")
+  end
+
+  context "Given a valid mzML file" do
+    it "I should be able to open the mzML file" do
+      file = MzML::Doc.new(@file)
+      file.should(be_a_kind_of(MzML::Doc))
+    end
+    it "should read the index" do
+      file = MzML::Doc.new(@file)
+      file.index.should_not be_nil
+    end
+    it "should get the first spectrum" do
+      file = MzML::Doc.new(@file)
+      file.index.should_not be_nil
+    end
+    it "should unmarshall the a 64 byte mz array" do
+      mz = MzML::Doc.new(@file)
+      s = mz.spectrum(mz.index[:spectrum].keys.first)
+      s.mz.should_not be_nil
+    end
+    it "should unmarshall the a 32 byte intensity array" do
+      mz = MzML::Doc.new(@file)
+      s = mz.spectrum(mz.index[:spectrum].keys.first)
+      s.intensity.should_not be_nil
+    end
+
+    it "should be the same mz array as the MGF file" do
+      mgf  = parse_mgf(@mgf)
+      mz = MzML::Doc.new(@file)
+      # grab this same spectrum from the mzML file
+      s = mz.spectrum(mgf.title)
+      i = s.intensity.map {|e| (e * 1000).to_i() / 1000.0}
+      m = s.mz.map {|e| (e * 1000).to_i() / 1000.0}
+      i.join(", ").should be == mgf.intensity.join(", ")
+      m.join(", ").should be == mgf.mz.join(", ")
+    end
+  end
+
+  context "Given a valid mzML file that uses compression" do
+    it "should unmarshall and uncompress the 64 byte mz array" do
+      mz = MzML::Doc.new(@compressed)
+      s = mz.spectrum(mz.index[:spectrum].keys.first)
+      s.mz.should_not be_nil
+    end
+
+    it "should unmarshall and uncompress the 32 byte intensity array" do
+      mz = MzML::Doc.new(@compressed)
+      s = mz.spectrum(mz.index[:spectrum].keys.first)
+      s.intensity.should_not be_nil
+    end
+  end
+end