mzid 0.0.1

data/tests/load_helper.rb

@@ -0,0 +1 @@
+$LOAD_PATH.unshift("#{File.dirname(__FILE__)}/../lib/")

data/tests/test_all.rb

@@ -0,0 +1,6 @@
+require_relative 'test_psm'
+
+require_relative 'test_batch_parser'
+require_relative 'test_streaming_parser'
+require_relative 'test_streaming_parser_lines'
+require_relative 'test_parser_sax'

data/tests/test_batch_parser.rb

@@ -0,0 +1,86 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+
+class TestBatchParser < MiniTest::Test
+  #
+  # test the psm output of a very small mzid file
+  #
+  def test_basic_parser()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::BatchParser.new(infile)
+    p1.each_psm do |spec_id|
+      assert_equal(3591, spec_id.get_spec_num, "unexpected spec num")
+      assert_equal("VVIYDGSYHEVDSSEMAFK", spec_id.get_pep, "unexpected peptide")
+      assert_equal(1.6364497E-26, spec_id.get_spec_prob, "unexpected spectral probability")
+    end
+  end
+  #
+  # test the each_spectrum block
+  #
+  def test_per_spectrum()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::BatchParser.new(infile)
+    p1.each_spectrum do |psm_lst|
+      assert_equal(1, psm_lst.size, "unexpected list size")
+    end
+  end
+  #
+  # test the each_spectrum block on multiple result example
+  #
+  def test_per_spectrum_multiple()
+    infile = "#{File.dirname(__FILE__)}/data/example_2.mzid"
+    p1 = MzID::BatchParser.new(infile)
+    i = 0
+    size_lst = [1,4]
+    num_lst = [3591, 6065]
+    spec_probs = [[1.6364497E-26], [3.9093196E-5, 3.9093196E-5, 3.9093196E-5, 3.9093196E-5]]
+
+    p1.each_spectrum do |psm_lst|
+      #test fo spectrum number
+      assert_equal(size_lst[i], psm_lst.size, "unexpected number of PSMs for spectrum #{num_lst[i]}")
+      # test each PSM of spectrum
+      psm_lst.each_with_index do |psm,j| 
+        assert_equal(num_lst[i], psm.get_spec_num, "unexpected spectrum number for spectrum #{num_lst[i]}")
+        assert_in_epsilon(spec_probs[i][j].to_f, psm.get_spec_prob.to_f, 0.001, "unexpected spectral prob")
+      end
+      i += 1
+    end
+  end
+  #
+  # test parsing of modifications
+  #
+  def test_modifications()
+    infile = "#{File.dirname(__FILE__)}/data/example_mod.mzid"
+    p1 = MzID::BatchParser.new(infile)
+    mod_locs = [nil, [14,17], nil]
+    mod_vals = [nil, [57.021463735,57.021463735], nil]
+    i = 0
+    p1.each_psm do |psm|
+      modh = psm.get_mods
+      if modh.nil? then
+        assert_equal(mod_locs[i], nil, "expected non-nil mod hash")
+      else
+        assert_equal(mod_locs[i], modh.keys, "expected different locations")
+        assert_equal(mod_vals[i], modh.values, "expected different mass deltas")
+      end
+      i += 1
+    end
+  end
+  #
+  # unit test for peptide evidence, checking protein ids
+  #
+  def test_peptide_evidence()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::BatchParser.new(infile)
+    i = 0
+    p1.each_psm do |psm|
+      prot_id_lst = psm.get_pep_ev.map{|pep_ev| pep_ev.get_prot_id.to_s}
+      assert_equal(exp_prot_id_lst[i], prot_id_lst[i], "protein IDs not what expected")
+      i += 1
+    end
+  end
+  
+end

data/tests/test_default_parser.rb

@@ -0,0 +1,72 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+
+class TestDefaultParser < MiniTest::Test
+  #
+  # test the psm output of a very small mzid file
+  #
+  def test_basic_parser()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::Parser.new(infile)
+    p1.each_psm do |spec_id|
+      assert_equal(3591, spec_id.get_spec_num, "unexpected spec num")
+      assert_equal("VVIYDGSYHEVDSSEMAFK", spec_id.get_pep, "unexpected peptide")
+      assert_equal(1.6364497E-26, spec_id.get_spec_prob, "unexpected spectral probability")
+    end
+  end
+  #
+  # test the each_spectrum block
+  #
+  def test_per_spectrum()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::Parser.new(infile)
+    p1.each_spectrum do |psm_lst|
+      assert_equal(1, psm_lst.size, "unexpected list size")
+    end
+  end
+  #
+  # test the each_spectrum block on multiple result example
+  #
+  def test_per_spectrum_multiple()
+    infile = "#{File.dirname(__FILE__)}/data/example_2.mzid"
+    p1 = MzID::Parser.new(infile)
+    i = 0
+    size_lst = [1,4]
+    num_lst = [3591, 6065]
+    spec_probs = [[1.6364497E-26], [3.9093196E-5, 3.9093196E-5, 3.9093196E-5, 3.9093196E-5]]
+
+    p1.each_spectrum do |psm_lst|
+      #test fo spectrum number
+      assert_equal(size_lst[i], psm_lst.size, "unexpected number of PSMs for spectrum #{num_lst[i]}")
+      # test each PSM of spectrum
+      psm_lst.each_with_index do |psm,j| 
+        assert_equal(num_lst[i], psm.get_spec_num, "unexpected spectrum number for spectrum #{num_lst[i]}")
+        assert_in_epsilon(spec_probs[i][j].to_f, psm.get_spec_prob.to_f, 0.001, "unexpected spectral prob")
+      end
+      i += 1
+    end
+  end
+  #
+  # test parsing of modifications
+  #
+  def test_modifications()
+    infile = "#{File.dirname(__FILE__)}/data/example_mod.mzid"
+    p1 = MzID::Parser.new(infile)
+    mod_locs = [nil, [14,17], nil]
+    mod_vals = [nil, [57.021463735,57.021463735], nil]
+    i = 0
+    p1.each_psm do |psm|
+      modh = psm.get_mods
+      if modh.nil? then
+        assert_equal(mod_locs[i], nil, "expected non-nil mod hash")
+      else
+        assert_equal(mod_locs[i], modh.keys, "expected different locations")
+        assert_equal(mod_vals[i], modh.values, "expected different mass deltas")
+      end
+      i += 1
+    end
+  end
+  
+end

data/tests/test_helper.rb

@@ -0,0 +1,8 @@
+# minitest stuff
+require 'rubygems'
+gem 'minitest'
+require 'minitest/autorun'
+
+# minitest-reporters
+require "minitest/reporters"
+Minitest::Reporters.use! Minitest::Reporters::SpecReporter.new

data/tests/test_parser_sax.rb

@@ -0,0 +1,47 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+require 'tempfile'
+
+class TestParserSax < MiniTest::Test   
+  #
+  # test very simple output to csv method
+  #
+  def test_write_to_csv()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::ParserSax.new(infile, nil, false)
+    tmp = Tempfile.new("results")
+    p1.write_to_csv(tmp.path, false)
+    tmp.close
+    # read in output lines
+    lines = IO.readlines(tmp.path)
+    # expected
+    exp_out = ["#spec_num\tpeptide\tspec_prob\tprot_ids\tstart\tend\tnum_prot\n", "3591\tVVIYDGSYHEVDSSEMAFK\t1.6364497e-26\tsp|Q9RXK5|EFG_DEIRA\t573\t591\t1\n"]
+    # test 
+    assert_equal(exp_out, lines, "unexpected output file contents")
+  end
+
+  #
+  # test very simple output to csv method
+  #
+  def test_mods_write_to_csv()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example_mod.mzid"
+    p1 = MzID::ParserSax.new(infile, nil, false)
+    tmp = Tempfile.new("results")
+    p1.write_to_csv(tmp.path)
+    tmp.close
+    # read in output lines
+    lines = IO.readlines(tmp.path)
+    # expected
+    exp_out = ["#spec_num\tpeptide\tspec_prob\tprot_ids\tstart\tend\tnum_prot\tmods\n",
+               "3591\tVVIYDGSYHEVDSSEMAFK\t1.6364497e-26\tsp|Q9RXK5|EFG_DEIRA\t573\t591\t1\t\n",
+               "8578\tRFQIGEVVLEGTGECHPCSR\t3.9070557e-05\ttr|Q9RXN7|Q9RXN7_DEIRA\t132\t151\t1\t15;+57|18;+57\n",
+               "8578\tFFHWEGRERHEFGFFFR\t3.9070557e-05\ttr|Q9RS55|Q9RS55_DEIRA\t99\t115\t1\t\n"]
+    # test 
+    assert_equal(exp_out, lines, "unexpected output file contents")
+  end
+  
+end

data/tests/test_psm.rb

@@ -0,0 +1,15 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+
+class TestPSM < MiniTest::Test
+
+  def test_basic_psm()
+    p1 = MzID::PSM.new(:id => "sp1", :pep => "ACDEF")
+    assert_equal("sp1", p1.get_id, "unexpected ID")
+    assert_equal("ACDEF", p1.get_pep, "unexpected peptide")
+  end
+
+  
+end

data/tests/test_streaming_parser.rb

@@ -0,0 +1,87 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+
+class TestStreamingParser < MiniTest::Test
+  #
+  # test the psm output of a very small mzid file
+  #
+  def test_basic_parser()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParser.new(infile)
+    p1.each_psm do |spec_id|
+      assert_equal(3591, spec_id.get_spec_num, "unexpected spec num")
+      assert_equal("VVIYDGSYHEVDSSEMAFK", spec_id.get_pep, "unexpected peptide")
+      assert_equal(1.6364497E-26, spec_id.get_spec_prob, "unexpected spectral probability")
+    end
+  end
+  #
+  # test the each_spectrum block
+  #
+  def test_per_spectrum()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParser.new(infile)
+    p1.each_spectrum do |psm_lst|
+      assert_equal(1, psm_lst.size, "unexpected list size")
+    end
+  end
+  #
+  # test the each_spectrum block on multiple result example
+  #
+  def test_per_spectrum_multiple()
+    infile = "#{File.dirname(__FILE__)}/data/example_2.mzid"
+    p1 = MzID::StreamingParser.new(infile)
+    i = 0
+    size_lst = [1,4]
+    num_lst = [3591, 6065]
+    spec_probs = [[1.6364497E-26], [3.9093196E-5, 3.9093196E-5, 3.9093196E-5, 3.9093196E-5]]
+
+    p1.each_spectrum do |psm_lst|
+      #test fo spectrum number
+      assert_equal(size_lst[i], psm_lst.size, "unexpected number of PSMs for spectrum #{num_lst[i]}")
+      # test each PSM of spectrum
+      psm_lst.each_with_index do |psm,j| 
+        assert_equal(num_lst[i], psm.get_spec_num, "unexpected spectrum number for spectrum #{num_lst[i]}")
+        assert_in_epsilon(spec_probs[i][j].to_f, psm.get_spec_prob.to_f, 0.001, "unexpected spectral prob")
+      end
+      i += 1
+    end
+  end
+  #
+  # test parsing of modifications
+  #
+  def test_modifications()
+    infile = "#{File.dirname(__FILE__)}/data/example_mod.mzid"
+    p1 = MzID::StreamingParser.new(infile)
+    mod_locs = [nil, [14,17], nil]
+    mod_vals = [nil, [57.021463735,57.021463735], nil]
+    i = 0
+    p1.each_psm do |psm|
+      modh = psm.get_mods
+      if modh.nil? then
+        assert_equal(mod_locs[i], nil, "expected non-nil mod hash")
+      else
+        assert_equal(mod_locs[i], modh.keys, "expected different locations")
+        assert_equal(mod_vals[i], modh.values, "expected different mass deltas")
+      end
+      i += 1
+    end
+  end
+  #
+  # unit test for peptide evidence, checking protein ids
+  #
+  def test_peptide_evidence()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParser.new(infile)
+    i = 0
+    p1.each_psm do |psm|
+      prot_id_lst = psm.get_pep_ev.map{|pep_ev| pep_ev.get_prot_id.to_s} # if use PeptideEvidence object
+      #prot_id_lst = psm.get_pep_ev  # if use simple hash of prot ID
+      assert_equal(exp_prot_id_lst[i], prot_id_lst[i], "protein IDs not what expected")
+      i += 1
+    end    
+  end
+  
+end

data/tests/test_streaming_parser_lines.rb

@@ -0,0 +1,104 @@
+require_relative 'load_helper'
+require_relative 'test_helper'
+
+require 'mzid'
+require 'tempfile'
+
+class TestStreamingParserLines < MiniTest::Test
+  #
+  # test the psm output of a very small mzid file
+  #
+  def test_basic_parser()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParserLines.new(infile)
+    p1.each_psm do |spec_id|
+      assert_equal(3591, spec_id.get_spec_num, "unexpected spec num")
+      assert_equal("VVIYDGSYHEVDSSEMAFK", spec_id.get_pep, "unexpected peptide")
+      assert_equal(1.6364497E-26, spec_id.get_spec_prob, "unexpected spectral probability")
+    end
+  end
+  #
+  # test the each_spectrum block
+  #
+  def test_per_spectrum()
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParserLines.new(infile)
+    p1.each_spectrum do |psm_lst|
+      assert_equal(1, psm_lst.size, "unexpected list size")
+    end
+  end
+  #
+  # test the each_spectrum block on multiple result example
+  #
+  def test_per_spectrum_multiple()
+    infile = "#{File.dirname(__FILE__)}/data/example_2.mzid"
+    p1 = MzID::StreamingParserLines.new(infile)
+    i = 0
+    size_lst = [1,4]
+    num_lst = [3591, 6065]
+    spec_probs = [[1.6364497E-26], [3.9093196E-5, 3.9093196E-5, 3.9093196E-5, 3.9093196E-5]]
+
+    p1.each_spectrum do |psm_lst|
+      #test fo spectrum number
+      assert_equal(size_lst[i], psm_lst.size, "unexpected number of PSMs for spectrum #{num_lst[i]}")
+      # test each PSM of spectrum
+      psm_lst.each_with_index do |psm,j| 
+        assert_equal(num_lst[i], psm.get_spec_num, "unexpected spectrum number for spectrum #{num_lst[i]}")
+        assert_in_epsilon(spec_probs[i][j].to_f, psm.get_spec_prob.to_f, 0.001, "unexpected spectral prob")
+      end
+      i += 1
+    end
+  end  
+  #
+  # unit test for peptide evidence, checking protein ids
+  #
+  def test_peptide_evidence()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParserLines.new(infile)
+    i = 0
+    p1.each_psm do |psm|
+      prot_id_lst = psm.get_pep_ev.map{|pep_ev| p1.get_prot_id(pep_ev.to_sym).to_s} # if use PeptideEvidence object      
+      assert_equal(exp_prot_id_lst[i], prot_id_lst[i], "protein IDs not what expected")
+      i += 1
+    end    
+  end
+  #
+  # test very simple output to csv method
+  #
+  def test_write_to_csv()
+    exp_prot_id_lst = ["sp|Q9RXK5|EFG_DEIRA"]
+    infile = "#{File.dirname(__FILE__)}/data/example.mzid"
+    p1 = MzID::StreamingParserLines.new(infile, 0.0, false, false)
+    tmp = Tempfile.new("results")
+    p1.write_to_csv(tmp.path, nil)
+    tmp.close
+    # read in output lines
+    lines = IO.readlines(tmp.path)
+    # expected
+    exp_out = ["#spec_num\tpeptide\tspec_prob\tprot_ids\tstart\tend\tnum_prot\n", "3591\tVVIYDGSYHEVDSSEMAFK\t1.6364497e-26\tsp|Q9RXK5|EFG_DEIRA\t573\t591\t1\n"]
+    # test 
+    assert_equal(exp_out, lines, "unexpected output file contents")
+  end
+  #
+  # test parsing of modifications
+  #
+  def test_modifications()
+    infile = "#{File.dirname(__FILE__)}/data/example_mod.mzid"
+    p1 = MzID::StreamingParserLines.new(infile)
+    mod_locs = [nil, [14,17], nil]
+    mod_vals = [nil, [57.021463735,57.021463735], nil]
+    i = 0
+    p1.each_psm do |psm|
+      modh = psm.get_mods
+      if modh.nil? then
+        assert_equal(mod_locs[i], nil, "expected non-nil mod hash")
+      else
+        assert_equal(mod_locs[i], modh.keys, "expected different locations")
+        assert_equal(mod_vals[i], modh.values, "expected different mass deltas")
+      end
+      i += 1
+    end
+  end
+  
+end

metadata

@@ -0,0 +1,162 @@
+--- !ruby/object:Gem::Specification
+name: mzid
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Stefano R.B.
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: ox
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: progressbar
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.21'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0.21'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '5.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '5.4'
+- !ruby/object:Gem::Dependency
+  name: minitest-reporters
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+description: A simple gem to parse mzIdentML (mzid) files
+email: sbonisso@ucsd.edu
+executables:
+- convert_mzid_to_csv
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/convert_mzid_to_csv
+- bin/load_helper.rb
+- lib/mzid.rb
+- lib/mzid/base_parser.rb
+- lib/mzid/batch_parser.rb
+- lib/mzid/filtered_streaming_parser.rb
+- lib/mzid/parser_sax.rb
+- lib/mzid/peptide_evidence.rb
+- lib/mzid/psm.rb
+- lib/mzid/streaming_parser.rb
+- lib/mzid/streaming_parser_lines.rb
+- lib/mzid/version.rb
+- tests/data/example.mzid
+- tests/data/example_2.mzid
+- tests/data/example_mod.mzid
+- tests/load_helper.rb
+- tests/test_all.rb
+- tests/test_batch_parser.rb
+- tests/test_default_parser.rb
+- tests/test_helper.rb
+- tests/test_parser_sax.rb
+- tests/test_psm.rb
+- tests/test_streaming_parser.rb
+- tests/test_streaming_parser_lines.rb
+homepage: https://github.com/sbonisso/mzid
+licenses:
+- MIT
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: mzIdentML parser
+test_files:
+- tests/data/example.mzid
+- tests/data/example_2.mzid
+- tests/data/example_mod.mzid
+- tests/load_helper.rb
+- tests/test_all.rb
+- tests/test_batch_parser.rb
+- tests/test_default_parser.rb
+- tests/test_helper.rb
+- tests/test_parser_sax.rb
+- tests/test_psm.rb
+- tests/test_streaming_parser.rb
+- tests/test_streaming_parser_lines.rb