mspire-sequest 0.2.5

data/lib/mspire/sequest.rb

@@ -0,0 +1,6 @@
+
+module Mspire
+  module Sequest
+    VERSION = File.open(File.dirname(__FILE__) + '/../../VERSION') {|io| io.gets.chomp }
+  end
+end

data/script/fasta_ipi_to_ncbi-ish.rb

@@ -0,0 +1,29 @@
+#!/usr/bin/ruby
+
+if ARGV.size == 0
+  puts "usage: #{File.basename(__FILE__)} <file>.fasta ..."
+  puts "outputs: <file>_NCBI.fasta ..."
+  puts ""
+  puts "(Bioworks 3.3.1 [maybe others] does not seem to read an IPI"
+  puts "formatted fasta database header lines.  This will change an" 
+  puts "IPI format to an NCBI style format that Bioworks can read."
+  exit
+end
+
+ARGV.each do |file|
+  base = file.chomp(File.extname(file))
+  outfile = base + '_NCBI' + ".fasta"
+  File.open(outfile, 'w') do |out|
+    IO.foreach(file) do |line|
+      if line =~ /^>/
+        (codes, *description) = line[1..-1].split(" ")
+        description = description.join(" ")
+        code_section = codes.split('|').map {|code| (key, val) = code.split(':') ; "#{key}|#{val}|" }.join
+        out.puts ">#{code_section} #{description}"   
+      else
+        out.print line
+      end
+    end
+  end
+end
+

data/spec/mspire/sequest/params_spec.rb

@@ -0,0 +1,135 @@
+require 'spec_helper'
+
+require 'mspire/sequest/params'
+
+# returns a hash of all params
+def simple_parse(filename)
+  hash = {}
+  data = File.open(filename) do |io| 
+    # this makes it work with ruby 1.9:
+    io.set_encoding("ASCII-8BIT") if io.respond_to?(:set_encoding)
+    io.read 
+  end
+  data.split(/\r?\n/).select {|v| v =~ /^[a-z]/}.each do |line|
+    if line =~ /([^\s]+)\s*=\s*([^;]+)\s*;?/
+      hash[$1.dup] = $2.rstrip
+    end
+  end
+  hash
+end
+
+shared_examples_for 'sequest params' do |params_file, api_hash, backwards_hash|
+
+  subject { Mspire::Sequest::Params.new(params_file) }
+
+  it 'has a method for every parameter in the file' do
+    hash = simple_parse(params_file)
+    hash.each do |k,v|
+      subject.send(k.to_sym).should == v
+    end
+  end
+
+  it 'returns zero length string for params with no information' do
+    subject.second_database_name.should == ""
+    subject.sequence_header_filter.should == ""
+  end
+
+  it 'returns nil for params that do not exist and have no translation' do
+    subject.google_plex.should == nil
+  end
+
+  it 'provides consistent API between versions for important info' do
+    message = capture_stderr do
+      api_hash.each do |k,v|
+        subject.send(k).should == v
+      end
+    end
+  end
+
+  it 'provides some backwards compatibility' do
+    backwards_hash.each do |k,v|
+      subject.send(k).should == v
+    end
+  end
+
+end
+
+describe 'sequest params v 3.1' do
+
+  file = TESTFILES + '/bioworks31.params'
+  api_hash = {
+    :version => '3.1',
+    :enzyme => 'Trypsin',
+    :database => "C:\\Xcalibur\\database\\ecoli_K12.fasta",
+    :enzyme_specificity => [1, 'KR', ''],
+    :precursor_mass_type => "average",
+    :fragment_mass_type => "average",
+    :min_number_termini  => '1',
+  }
+
+  backwards_hash = {
+    :max_num_internal_cleavages => '2',
+    :fragment_ion_tol => '0.0000',
+  }
+
+  it_behaves_like 'sequest params', file, api_hash, backwards_hash
+end
+
+describe 'sequest params v 3.2' do
+  file = TESTFILES + '/bioworks32.params'
+  api_hash = {
+    :version => '3.2',
+    :enzyme => 'Trypsin',
+    :database => "C:\\Xcalibur\\database\\ecoli_K12_ncbi_20060321.fasta",
+    :enzyme_specificity => [1, 'KR', 'P'],
+    :precursor_mass_type => "average",
+    :fragment_mass_type => "average",
+    :min_number_termini  => '2',
+  }
+
+  backwards_hash = {
+    :max_num_internal_cleavages => '2',
+    :fragment_ion_tol => '1.0000',
+  }
+
+  it_behaves_like 'sequest params', file, api_hash, backwards_hash 
+end
+
+describe 'sequest params v 3.3' do
+  file = TESTFILES + '/bioworks33.params'
+  api_hash = {
+    :version => '3.3',
+    :enzyme => 'Trypsin',
+    :database => "C:\\Xcalibur\\database\\yeast.fasta",
+    :enzyme_specificity => [1, 'KR', ''],
+    :precursor_mass_type => "monoisotopic",
+    :fragment_mass_type => "monoisotopic",
+    :min_number_termini  => '2',
+  }
+
+  backwards_hash = {
+    :max_num_internal_cleavages => '2',
+    :fragment_ion_tol => '1.0000',
+  }
+  it_behaves_like 'sequest params', file, api_hash, backwards_hash
+end
+
+describe 'sequest params v 3.2 from srf' do
+  file = TESTFILES + '/7MIX_STD_110802_1.sequest_params_fragment.srf'
+  api_hash = {
+    :version => '3.2',
+    :enzyme => 'Trypsin',
+    :database => "C:\\Xcalibur\\database\\mixed_db_human_ecoli_7prot_unique.fasta",
+    :enzyme_specificity => [1, 'KR', 'P'],
+    :precursor_mass_type => "average",
+    :fragment_mass_type => "average",
+    :min_number_termini  => '2',
+  }
+
+  backwards_hash = {
+    :max_num_internal_cleavages => '2',
+    :fragment_ion_tol => '1.0000',
+  }
+  it_behaves_like 'sequest params', file, api_hash, backwards_hash 
+end
+

data/spec/mspire/sequest/pepxml/modifications_spec.rb

@@ -0,0 +1,50 @@
+require 'spec_helper'
+
+require 'mspire/sequest/params'
+require 'mspire/sequest/pepxml/modifications'
+
+describe 'Mspire::Sequest::Pepxml::Modifications' do
+  before do
+    tf_params = TESTFILES + "/bioworks32.params"
+    @params = Mspire::Sequest::Params.new(tf_params)
+    # The params object here is completely unnecessary for this test, except
+    # that it sets up the mass table
+    @obj = Mspire::Sequest::Pepxml::Modifications.new(@params, "(M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000) ")
+  end
+  it 'creates a mod_symbols_hash' do
+    answ = {[:C, 12.0]=>"^", [:S, 80.0]=>"@", [:M, 29.0]=>"#", [:M, 15.9]=>"*", [:ct, 12.33]=>"[", [:nt, 14.2]=>"]"}
+    @obj.mod_symbols_hash.should == answ
+    ## need more here
+  end
+
+  it 'creates a ModificationInfo object given a special peptide sequence' do
+    mod_string = "(M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000) "
+    @params.diff_search_options = "15.90000 M 29.00000 M 80.00000 S 12.00000 C"
+    @params.term_diff_search_options = "14.20000 12.33000"
+    mod = Mspire::Sequest::Pepxml::Modifications.new(@params, mod_string)
+    ## no mods
+    peptide_nomod = "PEPTIDE"
+    mod.modification_info(peptide_nomod).should be_nil
+    peptide_mod = "]M*EC^S@IDM#M*EMSCM["
+    modinfo = mod.modification_info(peptide_mod)
+
+    xml_string = modinfo.to_xml
+    xml_string.should match( /<mod_aminoacid_mass / )
+    xml_string.should match( /mod_nterm_mass=/ )
+    xml_string.should match( /mod_cterm_mass=/ )
+    xml_string.should match( /modified_peptide=/ )
+
+    modinfo.mod_aminoacid_masses.size.should == 5
+    mod_aa_masses = modinfo.mod_aminoacid_masses
+    # positions are verified, masses are just frozen
+    [1,3,4,7,8].zip([147.09606, 115.1429, 167.0772999, 160.19606, 147.09606], mod_aa_masses) do |pos, mass, obj|
+      obj.position.should == pos
+      obj.mass.should be_within(0.0001).of(mass)
+    end
+    # These values are just frozen and not independently verified yet
+    modinfo.mod_nterm_mass.should be_within(0.0001).of(146.4033)
+    modinfo.mod_cterm_mass.should be_within(0.0001).of(160.5334)
+  end
+
+end
+

data/spec/mspire/sequest/pepxml_spec.rb

@@ -0,0 +1,311 @@
+
+=begin
+require File.expand_path( File.dirname(__FILE__) + '/../../spec_helper' )
+
+require 'spec_id'
+require 'spec_id/sequest/pepxml'
+#require 'mspire/mzxml'
+
+
+NODELETE = false
+
+describe Sequest::PepXML, " created from small bioworks.xml" do
+
+  spec_large do
+    before(:all) do
+      tf_mzxml_path = Tfiles_l + "/yeast_gly_mzXML"
+
+      tf_params = Tfiles + "/bioworks32.params"
+      tf_bioworks_xml = Tfiles + "/bioworks_small.xml"
+      out_path = Tfiles
+      @pepxml_objs = Sequest::PepXML.set_from_bioworks(tf_bioworks_xml, :params => tf_params, :ms_data => tf_mzxml_path, :out_path => out_path)
+    end
+
+    it 'gets some spectrum queries' do
+      @pepxml_objs.each do |obj|
+        (obj.spectrum_queries.size > 2).should be_true
+        (obj.spectrum_queries.first.search_results.first.search_hits.size > 0).should be_true
+      end
+      #@pepxml_objs.each do |pep| puts pep.to_pepxml end
+    end
+  end
+end
+
+
+
+describe Sequest::PepXML, " created from large bioworks.xml" do
+  # assert_equal_by_pairs (really any old array)
+  def assert_equal_pairs(obj, arrs)
+    arrs.each do |arr|
+      #if obj.send(arr[1]) != arr[0]
+      #  puts "HELLO"
+      #  puts "OBJ answer"
+      #  p obj.send(arr[1])
+      #  puts "ar0"
+      #  p arr[0]
+      #  puts "ar1"
+      #  p arr[1]
+      #end
+      if arr[0].is_a? Float
+        obj.send(arr[1]).should be_close(arr[0], 0.0000000001)
+      else
+        obj.send(arr[1]).should == arr[0]
+      end
+    end
+  end
+
+  #swap the first to guys first
+  def assert_equal_pairs_swapped(obj, arrs)
+    arrs.each do |arr|
+      arr[0], arr[1] = arr[1], arr[0] 
+    end
+    assert_equal_pairs(obj, arrs)
+  end
+
+  spec_large do
+    before(:all) do
+      st = Time.new
+      params = Tfiles + "/opd1/sequest.3.2.params"
+      bioworks_xml = Tfiles_l + "/opd1/bioworks.000.oldparams.xml"
+      mzxml_path = Tfiles_l + "/opd1"
+      out_path = Tfiles
+      @pepxml_version = 18
+      @pepxml_objs = Sequest::PepXML.set_from_bioworks_xml(bioworks_xml, params, {:ms_data => mzxml_path, :out_path => out_path, :pepxml_version => @pepxml_version})
+      puts "- takes #{Time.new - st} secs"
+    end
+
+    it 'extracts MSMSPipelineAnalysis' do
+      ######## HMMMMM...
+      Sequest::PepXML.pepxml_version.should == @pepxml_version
+
+      # MSMSPipelineAnalysis
+      po = @pepxml_objs.first
+      msms_pipeline = po.msms_pipeline_analysis
+      msms_pipeline.xmlns.should == 'http://regis-web.systemsbiology.net/pepXML'
+      msms_pipeline.xmlns_xsi.should == 'http://www.w3.org/2001/XMLSchema-instance'
+      msms_pipeline.xsi_schema_location.should == 'http://regis-web.systemsbiology.net/pepXML /tools/bin/TPP/tpp/schema/pepXML_v18.xsd'
+      msms_pipeline.summary_xml.should == '000.xml'
+    end
+
+    it 'extracts MSmSRunSummary' do
+      # MSMSRunSummary
+      rs = @pepxml_objs.first.msms_pipeline_analysis.msms_run_summary
+      rs.base_name.should =~ /\/000/
+      assert_equal_pairs(rs, [ ['ThermoFinnigan', :ms_manufacturer], ['LCQ Deca XP Plus', :ms_model], ['ESI', :ms_ionization], ['Ion Trap', :ms_mass_analyzer], ['UNKNOWN', :ms_detector], ['raw', :raw_data_type], ['.mzXML', :raw_data], ])
+    end
+
+    it 'extracts SampleEnzyme' do
+      # SampleEnzyme
+      se = @pepxml_objs.first.msms_pipeline_analysis.msms_run_summary.sample_enzyme
+      assert_equal_pairs(se, [ ['Trypsin', :name], ['KR', :cut], [nil, :no_cut], ['C', :sense], ])
+    end
+
+    it 'extracts SearchSummary' do
+      # SearchSummary
+      ss = @pepxml_objs.first.msms_pipeline_analysis.msms_run_summary.search_summary
+      ss.is_a?(Sequest::PepXML::SearchSummary).should be_true
+      ss.base_name.should =~ /\/000/
+      ss.peptide_mass_tol.should =~ /1\.500/
+      assert_equal_pairs_swapped(ss, [ # normal attributes
+                                 [:search_engine, "SEQUEST"], [:precursor_mass_type, "average"], [:fragment_mass_type, "average"], [:out_data_type, "out"], [:out_data, ".tgz"], [:search_id, "1"],
+
+                                 # enzymatic_search_constraint
+                                 [:enzyme, 'Trypsin'], [:max_num_internal_cleavages, '2'], [:min_number_termini, '2'],
+
+                                 # parameters
+                                 [:fragment_ion_tol, "1.0000"], [:ion_series, "0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0"], [:max_num_differential_AA_per_mod, "3"], [:nucleotide_reading_frame, "0"], [:num_output_lines, "10"], [:remove_precursor_peak, "0"], [:ion_cutoff_percentage, "0.0000"], [:match_peak_count, "0"], [:match_peak_allowed_error, "1"], [:match_peak_tolerance, "1.0000"], [:protein_mass_filter, "0 0"],
+      ])
+
+    end
+    it 'extracts SearchDatabase' do
+      # SearchDatabase
+      sd = @pepxml_objs.first.msms_pipeline_analysis.msms_run_summary.search_summary.search_database
+      sd.is_a?(Sequest::PepXML::SearchDatabase).should be_true
+      assert_equal_pairs_swapped(sd, [ [:local_path, "C:\\Xcalibur\\database\\ecoli_K12.fasta"], [:seq_type, 'AA'], ])
+    end
+
+    it 'returns SpectrumQueries' do
+      # SpectrumQueries
+      sq = @pepxml_objs.first.msms_pipeline_analysis.msms_run_summary.spectrum_queries
+      spec = sq.first 
+      assert_equal_pairs_swapped(spec, [
+                                 [:spectrum, "000.100.100.1"], [:start_scan, "100"], [:end_scan, "100"],
+                                 #[:precursor_neutral_mass, "1074.5920"], # out2summary
+                                 [:precursor_neutral_mass, 1074.666926], # mine
+                                 [:assumed_charge, 1], [:index, "1"],
+      ])
+      sh = spec.search_results.first.search_hits.first
+      assert_equal_pairs_swapped(sh, [
+                                 # normal attributes
+                                 [:hit_rank, 1], 
+                                 [:peptide, "SIYFRNFK"], 
+                                 [:peptide_prev_aa, "R"], 
+                                 [:peptide_next_aa, "G"], 
+                                 [:protein, "gi|16130084|ref|NP_416651.1|"], 
+                                 [:num_tot_proteins, 1], 
+                                 [:num_matched_ions, 4], 
+                                 [:tot_num_ions, 14],
+                                 #[:calc_neutral_pep_mass, "1074.1920"], # out2summary
+                                 [:calc_neutral_pep_mass, 1074.23261], # mine
+                                 #[:massdiff, "+0.400000"], # out2summary
+                                 [:massdiff, 0.434316000000081],  # mine
+                                 [:num_tol_term, 2], [:num_missed_cleavages, 1], [:is_rejected, 0],
+
+                                 # search_score
+                                 [:xcorr, 0.4], [:deltacn, 0.023], [:deltacnstar, "0"], [:spscore, 78.8], [:sprank, 1],
+      ])
+
+      spec = sq[1]
+      assert_equal_pairs_swapped(spec, [
+                                 [:spectrum, "000.1000.1000.1"], [:start_scan, "1000"], [:end_scan, "1000"], #[:precursor_neutral_mass, "663.1920"], # out2summary
+                                 [:precursor_neutral_mass, 663.206111], # mine
+                                 [:assumed_charge, 1], [:index, "2"],
+      ])
+
+      sh = spec.search_results.first.search_hits.first
+      assert_equal_pairs_swapped(sh, [
+                                 # normal attributes
+                                 [:hit_rank, 1], [:peptide, "ALADFK"], [:peptide_prev_aa, "R"], [:peptide_next_aa, "S"], [:protein, "gi|16128765|ref|NP_415318.1|"], [:num_tot_proteins, 1], [:num_matched_ions, 5], [:tot_num_ions, 10],
+                                 [:num_tol_term, 2], [:num_missed_cleavages, 0], [:is_rejected, 0],
+                                 #[:massdiff, "-0.600000"], # out2summary
+                                 [:massdiff, -0.556499000000031],  # mine
+                                 #[:calc_neutral_pep_mass, 663.7920], # out2summary
+                                 [:calc_neutral_pep_mass, 663.76261], # mine
+
+                                 # search_score
+                                 [:xcorr, 0.965], [:deltacn, 0.132], [:deltacnstar, "0"], [:spscore, 81.1], [:sprank, 1],
+      ])
+
+      spec = sq[9]
+      assert_equal_pairs_swapped(spec, [
+                                 [:spectrum, "000.1008.1008.2"], [:start_scan, "1008"], [:end_scan, "1008"], [:assumed_charge, 2],
+                                 #[:precursor_neutral_mass, "691.0920"], # out2summary
+                                 [:precursor_neutral_mass, 691.150992], # mine
+      ])
+
+      sh = spec.search_results.first.search_hits.first
+      assert_equal_pairs_swapped(sh, [
+                                 # normal attributes
+                                 [:hit_rank, 1], [:peptide, "RLFTR"], [:peptide_prev_aa, "R"], [:peptide_next_aa, "A"], [:protein, "gi|16130457|ref|NP_417027.1|"], [:num_tot_proteins, 1], [:num_matched_ions, 5], [:tot_num_ions, 8], [:num_tol_term, 2], 
+
+                                 #[:num_missed_cleavages, "0"],  # out2summary misses this!
+                                 [:num_missed_cleavages, 1], 
+                                 [:is_rejected, 0],
+                                 #[:calc_neutral_pep_mass, "691.7920"], # out2summary
+                                 [:calc_neutral_pep_mass, 691.82261], # mine
+                                 #[:massdiff, "-0.700000"], # out2summary
+                                 [:massdiff, -0.67161800000008],  # mine
+
+                                 # search_score
+                                 [:xcorr, 0.903], [:deltacn, 0.333], [:deltacnstar, "0"], [:spscore, 172.8], [:sprank, 1],
+      ])
+    end
+
+    it 'can generate correct pepxml file' do
+      
+      ## IF OUR OBJECT IS CORRECT, THEN WE GET THE OUTPUT:
+      string = @pepxml_objs.first.to_pepxml
+      ans_lines = IO.read(Tfiles + "/opd1/000.my_answer.100lines.xml").split("\n")
+      base_name_re = /base_name=".*?files\//o
+      date_re = /date=".*?"/
+      string.split("\n").each_with_index do |line,i|
+        if i > 99 ; break end
+        ans, exp = 
+          if i == 1
+            [line.sub(date_re,''), ans_lines[i].sub(date_re,'')]
+          elsif i == 2 
+            [line.sub(base_name_re,''), ans_lines[i].sub(base_name_re, '').sub(/^\s+/, "\t")]
+          elsif i == 6
+            [line.sub(base_name_re,''), ans_lines[i].sub(base_name_re, '').sub(/^\s+/, "\t\t")]
+          else
+            [line, ans_lines[i]]
+          end
+
+        #ans.split('').zip(exp.split('')) do |l,a|
+        #  if l != a
+        #    puts line
+        #    puts ans_lines[i]
+        #    puts l
+        #    puts a
+        #  end
+        #end
+        if ans != exp
+          puts ans
+          puts exp
+        end
+        ans.should == exp
+        #line.sub(base_name_re,'').should == ans_lines[i].sub(base_name_re,'')
+      end
+    end
+  end
+end
+
+
+describe 'bioworks file with modifications transformed into pepxml' do
+
+  spec_large do
+    before(:all) do
+      modfiles_sequest_dir = Tfiles_l + '/opd1_2runs_2mods/sequest33/'
+      modfiles_data_dir = Tfiles_l + '/opd1_2runs_2mods/data/'
+      @srgfile = modfiles_sequest_dir + 'tmp.srg'
+      @out_path = modfiles_sequest_dir + 'pepxml'
+      modfiles = %w(020 040).map do |file|
+        modfiles_sequest_dir + file + ".srf"
+      end
+      objs = Sequest::PepXML.set_from_bioworks( SRFGroup.new(modfiles).to_srg(@srgfile), {:ms_data => modfiles_data_dir, :out_path => @out_path, :print => true, :backup_db_path => '/project/marcotte/marcotte/ms/database'} )
+      @out_files = %w(020 040).map do |file|
+        @out_path + '/' + file + '.xml'
+      end
+    end
+
+    after(:all) do
+      File.unlink(@srgfile) unless NODELETE
+      FileUtils.rm_r(@out_path)
+      #@out_files.each do |fn|
+      #  File.unlink(fn) unless NODELETE
+      #end
+    end
+
+    # splits string on ' 'and matches the line found by find_line_regexp in
+    # lines
+    def match_modline_pieces(lines, find_line_regexp, string)
+      pieces = string.split(' ').map {|v| /#{Regexp.escape(v)}/ }
+      lines.each do |line|
+        if line =~ find_line_regexp
+          pieces.each do |piece|
+            line.should =~ piece
+          end
+        end
+      end
+    end
+
+    it 'gets modifications right in real run' do
+      @out_files.each do |fn|
+        fn.exist_as_a_file?.should be_true
+        beginning = IO.read(fn) 
+        lines = beginning.split("\n")
+        [
+          [/aminoacid="M"/, '<aminoacid_modification symbol="*" massdiff="+15.9994" aminoacid="M" variable="Y" binary="N" mass="147.192"'],
+
+          [/aminoacid="S"/, '<aminoacid_modification symbol="#" massdiff="+79.9799" aminoacid="S" variable="Y" binary="N" mass="167.0581"'],
+          [/aminoacid="T"/, '<aminoacid_modification symbol="#" massdiff="+79.9799" aminoacid="T" variable="Y" binary="N" mass="181.085"'],
+          [/aminoacid="Y"/, '<aminoacid_modification symbol="#" massdiff="+79.9799" aminoacid="Y" variable="Y" binary="N" mass="243.1559"'],
+          [/parameter name="diff_search_options"/, '<parameter name="diff_search_options" value="15.999400 M 79.979900 STY 0.000000 M 0.000000 X 0.000000 T 0.000000 Y"/>'],
+        ].each do |a,b|
+          match_modline_pieces(lines, a, b)
+        end
+        [
+        '<modification_info modified_peptide="Y#RLGGS#T#K">',
+        '<mod_aminoacid_mass position="1" mass="243.1559"/>',
+        '<mod_aminoacid_mass position="7" mass="167.0581"/>',
+        '</modification_info>',
+        '<mod_aminoacid_mass position="9" mass="181.085"/>'
+        ].each do |line|
+          beginning.should =~ /#{Regexp.escape(line)}/ # "a modification info for a peptide")
+        end
+      end
+    end
+  end
+end
+
+=end

data/spec/mspire/sequest/sqt_spec.rb

@@ -0,0 +1,51 @@
+require 'spec_helper'
+
+require 'mspire/sequest/sqt_spec_helper'
+require 'mspire/sequest/sqt'
+
+describe 'reading a small sqt file' do
+
+  before(:each) do
+    file = TESTFILES + '/small.sqt'
+    @sqt = Mspire::Sequest::Sqt.new(file)
+  end
+
+  it 'can access header entries like a hash' do
+    header = @sqt.header
+    HeaderHash.each do |k,v|
+      header[k].should == v
+    end
+  end
+
+  it 'can access header entries with methods' do
+    header = @sqt.header
+    # for example:
+    header.database.should == HeaderHash['Database']
+    # all working:
+    HeaderHash.each do |k,v|
+      header.send(Mspire::Sequest::Sqt::Header::KeysToAtts[k]).should == v
+    end
+
+  end
+
+  it 'has spectra, matches, and loci' do
+    svt = @sqt.spectra[16]
+    reply = {:first => @sqt.spectra.first, :last => @sqt.spectra.last, :seventeenth => svt, :first_match_17 => svt.matches.first, :last_match_17 => svt.matches.last, :last_match_17_last_loci => svt.matches.last.loci.last}
+    [:first, :last, :seventeenth, :first_match_17, :last_match_17, :last_match_17_last_loci].each do |key|
+      TestSpectra[key].each do |k,v|
+        if v.is_a? Float
+          reply[key].send(k).should be_within(0.0000000001).of(v)
+        else
+          next if key == :last_match_17_last_loci
+          #p k
+          #p v
+          reply[key].send(k).should == v
+        end
+      end
+    end
+    @sqt.spectra[16].matches.first.loci.size.should == 1
+    @sqt.spectra[16].matches.last.loci.size.should == 1
+  end
+
+end
+

data/spec/mspire/sequest/sqt_spec_helper.rb

@@ -0,0 +1,34 @@
+
+
+HeaderHash = {}
+header_doublets = [
+  %w(SQTGenerator	mspire),
+  %w(SQTGeneratorVersion	0.3.1),
+  %w(Database	C:\Xcalibur\database\ecoli_K12_ncbi_20060321.fasta),
+  %w(FragmentMasses	AVG),
+  %w(PrecursorMasses	AVG),
+  ['StartTime', ''],
+  ['Alg-MSModel', 'LCQ Deca XP'],
+  %w(DBLocusCount	4237),
+  %w(Alg-FragMassTol	1.0000),
+  %w(Alg-PreMassTol	25.0000),
+  ['Alg-IonSeries', '0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0'],
+  %w(Alg-PreMassUnits	ppm),
+  ['Alg-Enzyme', 'Trypsin(KR/P) (2)'],
+
+  ['Comment', ['ultra small file created for testing', 'Created from Bioworks .srf file']],
+  ['DynamicMod', ['M*=+15.99940', 'STY#=+79.97990']],
+  ['StaticMod', []],
+].each do |double|
+  HeaderHash[double[0]] = double[1]
+end
+
+TestSpectra = {
+  :first => { :first_scan=>2, :last_scan=>2, :charge=>1, :time_to_process=>0.0, :node=>"TESLA", :mh=>390.92919921875, :total_intensity=>2653.90307617188, :lowest_sp=>0.0, :num_matched_peptides=>0, :matches=>[]},
+  :last => { :first_scan=>27, :last_scan=>27, :charge=>1, :time_to_process=>0.0, :node=>"TESLA", :mh=>393.008056640625, :total_intensity=>2896.16967773438, :lowest_sp=>0.0, :num_matched_peptides=>0, :matches=>[] },
+  :seventeenth => {:first_scan=>23, :last_scan=>23, :charge=>1, :time_to_process=>0.0, :node=>"TESLA", :mh=>1022.10571289062, :total_intensity=>3637.86059570312, :lowest_sp=>0.0, :num_matched_peptides=>41},
+  :first_match_17 => { :rxcorr=>1, :rsp=>5, :mh=>1022.11662242, :deltacn_orig=>0.0, :xcorr=>0.725152492523193, :sp=>73.9527359008789, :ions_matched=>6, :ions_total=>24, :sequence=>"-.MGT#TTM*GVK.L", :manual_validation_status=>"U", :first_scan=>23, :last_scan=>23, :charge=>1, :deltacn=>0.0672458708286285, :aaseq => 'MGTTTMGVK' },
+  :last_match_17 => {:rxcorr=>10, :rsp=>16, :mh=>1022.09807242, :deltacn_orig=>0.398330867290497, :xcorr=>0.436301857233047, :sp=>49.735767364502, :ions_matched=>5, :ions_total=>21, :sequence=>"-.MRT#TSFAK.V", :manual_validation_status=>"U", :first_scan=>23, :last_scan=>23, :charge=>1, :deltacn=>1.1, :aaseq => 'MRTTSFAK'},
+  :last_match_17_last_loci => {:reference =>'gi|16129390|ref|NP_415948.1|', :first_entry =>'gi|16129390|ref|NP_415948.1|', :locus =>'gi|16129390|ref|NP_415948.1|', :description => 'Fake description' }
+}
+