mspire 0.2.4 → 0.3.0

data/test/tc_sequest.rb

@@ -1,336 +0,0 @@
-
-
-
-require 'spec_id'
-require 'spec_id/sequest'
-require 'test/unit'
-require 'spec/mzxml'
-
-
-NODELETE = false
-
-class SequestTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
-    @tf_params = @tfiles + "bioworks32.params"
-    @tf_mzxml_path = @tfiles_l + "yeast_gly_mzXML"
-    @tf_bioworks_xml = @tfiles + "bioworks_small.xml"
-  end
-
-  def Xtest_set_from_bioworks
-    if File.exist? @tfiles_l
-      out_path = '.'
-      pepxml_objs = Sequest::PepXML.set_from_bioworks_xml(@tf_bioworks_xml, @tf_params, {:ms_path => @tf_mzxml_path, :out_path => out_path})
-      pepxml_objs.each do |obj|
-        assert(obj.spectrum_queries.size > 2)
-        assert(obj.spectrum_queries.first.search_results.first.search_hits.size > 0)
-      end
-    else
-      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
-    end
-  end
-
-  # assert_equal_by_pairs (really any old array)
-  def aep(obj, arrs)
-    arrs.each do |arr|
-      assert_equal(arr[0], obj.send(arr[1]), "#{arr[1]}")
-    end
-  end
-
-  #swap the first to guys first
-  def aeps(obj, arrs)
-    arrs.each do |arr|
-      arr[0], arr[1] = arr[1], arr[0] 
-    end
-    aep(obj, arrs)
-  end
-
-  ## turn this off if you are doing lots of tests
-  def Xtest_set_from_bioworks  ## new one for opd1
-    if File.exist? @tfiles_l
-      st = Time.new
-      params = @tfiles + "opd1/sequest.3.2.params"
-      bioworks_xml = @tfiles_l + "opd1/bioworks.000.oldparams.xml"
-      mzxml_path = @tfiles + "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, :sample_enzyme => "trypsin"})
-      puts "TOOK #{Time.new - st}secs"
-      po = pepxml_objs.first
-      assert_equal(pepxml_version, Sequest::PepXML.pepxml_version)
-
-      # MSMSPipelineAnalysis
-      pipe = po.msms_pipeline_analysis
-      aep(pipe, [
-          ['http://regis-web.systemsbiology.net/pepXML', :xmlns],
-          ['http://www.w3.org/2001/XMLSchema-instance', :xmlns_xsi],
-          ['http://regis-web.systemsbiology.net/pepXML /tools/bin/TPP/tpp/schema/pepXML_v18.xsd', :xsi_schema_location],
-          ['000.xml', :summary_xml],
-      ])
-
-      # MSMSRunSummary
-      rs = pipe.msms_run_summary
-      assert_match(/test\/tfiles\/000/, rs.base_name)
-      aep(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], ])
-
-      # SampleEnzyme
-      se = rs.sample_enzyme
-      aep(se, [ ['trypsin', :name], ['KR', :cut], ['P', :no_cut], ['C', :sense], ])
-
-      # SearchSummary
-      ss = rs.search_summary
-      assert_match(/test\/tfiles\/000/, ss.base_name)
-      assert_match(/1\.500/, ss.peptide_mass_tol)
-      aeps(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"],
-      ])
-
-      # SearchDatabase
-      sd = ss.search_database
-      aeps(sd, [ [:local_path, "C:\\Xcalibur\\database\\ecoli_K12.fasta"], [:seq_type, 'AA'], ])
-
-      # SpectrumQueries
-      sq = rs.spectrum_queries
-      spec = sq.first 
-      aeps(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
-      aeps(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, "0.400"], [:deltacn, "0.023"], [:deltacnstar, "0"], [:spscore, "78.8"], [:sprank, "1"],
-      ])
-
-      spec = sq[1]
-      aeps(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
-      aeps(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]
-      aeps(spec, [
-           [:spectrum, "000.1008.1008.2"], [:start_scan, "1008"], [:end_scan, "1008"], [:assumed_charge, "2"], [:index, "10"],
-           #[:precursor_neutral_mass, "691.0920"], # out2summary
-           [:precursor_neutral_mass, "691.150992"], # mine
-      ])
-
-      sh = spec.search_results.first.search_hits.first
-      aeps(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"],
-      ])
-
-      ## IF ARE OBJECT IS CORRECT, THEN WE GET THE OUTPUT:
-      string = po.to_pepxml
-
-      ans_lines = IO.read(@tfiles + "opd1/000.my_answer.100lines.xml").split("\n")
-      string.split("\n").each_with_index do |line,i|
-        base_name_re = /base_name=".*?\/test/o
-        if i > 99 ; break end
-        if i == 1
-          assert_equal(ans_lines[i].sub(/date=".*?"/,''), line.sub(/date=".*?"/,''))
-        elsif i == 2
-          assert_equal(ans_lines[i].sub(base_name_re,''), line.sub(base_name_re,''))
-        else
-          assert_equal(ans_lines[i].sub(base_name_re,''), line.sub(base_name_re,''))
-          #assert_equal(ans_lines[i], line)
-        end
-      end
-    else
-      assert_nil(puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})"))
-    end
-
-      #assert_match(/#{Regexp.escape("")}/, string)
-
-  end
-
- 
-
-  def Xtest_calc_num_tol_term
-    params = Sequest::Params.new(@tf_params)
-    scall = Sequest::PepXML::SearchHit
-    sym = :calc_num_tol_term
-    assert_equal(2, scall.send(sym, params, "K.EPTIDR.E"))
-    assert_equal(1, scall.send(sym, params, "K.PEPTIDR.E"))
-    assert_equal(1, scall.send(sym, params, "F.EEPTIDR.E"))
-    assert_equal(0, scall.send(sym, params, "F.PEPTIDW.R"))
-  end
-
-  def Xtest_calc_num_missed_cleavages
-    params = Sequest::Params.new(@tf_params)
-    scall = Sequest::PepXML::SearchHit
-    sym = :calc_num_missed_cleavages
-    assert_equal(0, scall.send(sym, params, "K.EPTIDR.E"))
-    assert_equal(0, scall.send(sym, params, "K.PEPTIDR.E"))
-    assert_equal(0, scall.send(sym, params, "F.EEPTIDR.E"))
-    assert_equal(0, scall.send(sym, params, "F.PEPTIDW.R"))
-    assert_equal(1, scall.send(sym, params, "F.PEPRTIDW.R"))
-    assert_equal(1, scall.send(sym, params, "F.PEPKTIDW.R"))
-    assert_equal(2, scall.send(sym, params, "F.PKEPRTIDW.R"))
-    assert_equal(3, scall.send(sym, params, "F.PKEPRTIDKW.R"))
-    assert_equal(3, scall.send(sym, params, "F.PKEPRAALKPEERPTIDKW.R"))
-    assert_equal(1, scall.send(sym, params, "K.RTTIDR.E"))
-    assert_equal(2, scall.send(sym, params, "K.RTTIKK.E"))
-  end
-
-
-  def Xtest_sys_ind_basename
-    assert_equal("hello.fasta", Sequest::Params.new._sys_ind_basename("C:\\Xcalibur\\database\\hello.fasta"))
-    assert_equal("hello.fasta", Sequest::Params.new._sys_ind_basename("/work/john/hello.fasta"))
-  end
-
-  def Xtest_modifications
-    obj = Sequest::PepXML::Modifications.new(nil, "(M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000) ")
-    answ = {[:C, 12.0]=>"^", [:S, 80.0]=>"@", [:M, 29.0]=>"#", [:M, 15.9]=>"*", [:ct, 12.33]=>"[", [:nt, 14.2]=>"]"}
-    assert_equal(answ, obj.mod_symbols_hash, "mod_symbols_hash")
-
-    ## need more here
-  end
-
-  def Xtest_modification_info
-    hash = {
-      :mod_nterm_mass => 520.2,
-      :modified_peptide => "MOD*IFI^E&D",
-      :mod_aminoacid_mass => [[3, 150.3], [6, 345.2]],
-    }
-    answ = "<modification_info mod_nterm_mass=\"520.2\" modified_peptide=\"MOD*IFI^E&amp;D\">\n\t<mod_aminoacid_mass position=\"3\" mass=\"150.3\"/>\n\t<mod_aminoacid_mass position=\"6\" mass=\"345.2\"/>\n</modification_info>\n"
-    string = Sequest::PepXML::SearchHit::ModificationInfo.new(hash).to_pepxml
-    assert_match(_re('<modification_info'), answ)
-    assert_match(_re(" mod_nterm_mass=\"520.2\""), answ)
-    assert_match(_re(" modified_peptide=\"MOD*IFI^E&amp;D\""), answ)
-    assert_match(_re("<mod_aminoacid_mass"), answ)
-    assert_match(_re(" position=\"3\""), answ)
-    assert_match(_re(" mass=\"150.3\""), answ)
-    assert_match(_re(" position=\"6\""), answ)
-    assert_match(_re(" mass=\"345.2\""), answ)
-    assert_match(_re("</modification_info>"), answ)
-  end
-
-  def _re(st)
-    /#{Regexp.escape(st)}/
-  end
-
-  def test_modifications
-    params = Sequest::Params.new(@tf_params)
-    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 = Sequest::PepXML::Modifications.new(params, mod_string)
-    ## no mods
-    peptide = "PEPTIDE"
-    assert_equal(nil, mod.modification_info(peptide))
-    peptide = "]M*EC^S@IDM#M*EMSCM["
-    modinfo = mod.modification_info(peptide)
-    assert_equal(peptide, modinfo.modified_peptide)
-    assert_in_delta(146.40054, modinfo.mod_nterm_mass, 0.000001)
-    assert_in_delta(160.52994, modinfo.mod_cterm_mass, 0.000001)
-  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|
-          assert_match(piece, line)
-        end
-      end
-    end
-  end
-
-  def test_modifications_in_run
-    if File.exist? @tfiles_l
-      modfiles_sequest_dir = @tfiles_l + 'opd1_2runs_2mods/sequest/'
-      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'} )
-    %w(020 040).each do |file|
-      fn = out_path + '/' + file + '.xml'
-      assert(File.exist?(fn), "file #{fn} exists")
-      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|
-        assert_match(/#{Regexp.escape(line)}/, beginning, "a modification info for a peptide")
-      end
-      File.unlink(fn) unless NODELETE
-    end
-    else
-      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
-    end
-  end
-end
-

data/test/tc_spec.rb

@@ -1,78 +0,0 @@
-
-require 'test/unit'
-require 'spec/mzxml/parser'
-require 'benchmark'
-
-$SPEED_TEST = false
-
-class SpecTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
-    @tscans = @tfiles + "opd1/twenty_scans.mzXML"
-    @tf_mzxml_path = @tfiles_l + "yeast_gly_mzXML"
-    #@big_file = "/work/john/ISB_Proteomics_18Set/mzXML/sergei_digest_A_full_01.mzXML"
-    @big_file = "../bioworks2prophet/xml/opd00001_test_set/opd00001_prophprepped/000.mzXML"
-  end
-
-  def test_mzxml_path_precursor_mz_by_scan
-    if File.exist? @tfiles_l
-      hash = Spec::MzXML::Parser.new.precursor_mz_by_scan_for_path(@tf_mzxml_path, "*.mzXML")
-      assert_equal(%w(000 020), hash.keys.sort)
-      assert(hash["000"].size > 0)
-      assert(hash["020"].size > 0)
-    else
-      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
-    end
-  end
-
-  def test_mzxml_precursor_mz_by_scan
-    answ = {11=>"1122.119141", 6=>"390.947449", 12=>"444.804504", 7=>"1221.905518", 8=>"1322.036621", 14=>"446.796082", 15=>"1122.041260", 16=>"1421.951416", 18=>"358.676636", 2=>"391.045410", 20=>"1422.277100", 19=>"1460.548340", 3=>"446.009033", 10=>"1322.000732", 4=>"1222.033203"}
-
-    loaded_xmlparser = false
-    $".each do |lib| if lib =~ /xmlparser/ then loaded_xmlparser = true end end
-
-    types = %w(regex rexml)
-    if loaded_xmlparser 
-      types.push("xmlparser") 
-    else
-      puts "'xmlparser' not loaded: SKIPPING 'xmlparser' testing'"
-    end
-    types.unshift(nil)
-    
-    types.each do |ty|
-      arr = Spec::MzXML::Parser.new.precursor_mz_by_scan(@tscans, ty) 
-      assert_hash_equal_arr(answ, arr)
-      # On my linux box these are the speed comparisons:
-      # REXMLStreamParser ~ 28.5 sec
-      # REGEX ~ 3.7 sec 
-      # REGEX without procs??
-      # XMLParser ~0.85 sec
-
-      # Speed test
-      if $SPEED_TEST
-        puts "PARSETYPE = #{ty ? ty : "DEFAULT"}: "
-        puts Benchmark.measure {
-          arr = Spec::MzXML::Parser.new.precursor_mz_by_scan(@big_file, ty ? ty : nil) 
-        }
-      end
-    end
-  end
-
-  def Xtest_mzxml_precursor_mz_and_inten_by_scan
-    arr = Spec::MzXML.precursor_mz_and_inten_by_scan(@tscans) 
-    answ = {11=>["1122.119141", "1188303.000000"], 6=>["390.947449", "6191130.000000"], 12=>["444.804504", "716303.000000"], 7=>["1221.905518", "2245001.000000"], 8=>["1322.036621", "1946525.000000"], 14=>["446.796082", "1472386.000000"], 15=>["1122.041260", "1411827.000000"], 16=>["1421.951416", "1187501.000000"] , 18=>["358.676636", "826186.000000"], 2=>["391.045410", "6986078.000000"], 20=>["1422.277100", "709884.000000"], 19=>["1460.548340", "720317.000000"], 3=>["446.009033", "1531503.000000"], 10=>["1322.000732", "1475536.000000"], 4=>["1222.033203", "1520220.000000"]}
-
-    assert_hash_equal_arr(answ, arr)
-  end
-
-  def assert_hash_equal_arr(hash,arr)
-    hash.each do |k,v|
-      assert_equal(hash[k], arr[k])
-    end
-  end
-end
-
-

data/test/tc_spec_id.rb

@@ -1,201 +0,0 @@
-
-require 'test/unit'
-require 'spec_id'
-
-
-class SpecIDTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
-    @bw = @tfiles + "bioworks_small.xml"
-    @old_prot_proph = @tfiles + 'yeast_gly_small-prot.xml'
-    @prot_proph = @tfiles + 'opd1/000_020_3prots-prot.xml'
-    @srf = @tfiles_l + '7MIX_STD_110802_1.srf'
-  end
-
-  def test_spec_id_creation
-    sp = SpecID.new(@bw)
-    assert_equal(106, sp.prots.size)
-  end
-
-  def test_classify_by_false_flag
-    file = @tfiles + "bioworks_with_INV_small.xml"
-    sp = SpecID.new(file)
-    assert_equal(19, sp.prots.size)
-    (tp, fp) = sp.classify_by_false_flag(:prots, "INV_", true, true)
-    assert_equal(4, fp.size, "num false pos")
-    assert_equal(15, tp.size, "num true pos")
-  end
-
-  
-  def test_precision
-    require 'roc'
-    file = @tfiles + "bioworks_with_INV_small.xml"
-    # 4 INV and 15 non-inv for 19 total prots
-    answ = %w( t t t t t t t t t t F t t t t F t F F )
-    index = 0
-    answ.collect! do |bool|
-      bo = false
-      if bool == 't'; bo = true end
-      index += 1 
-      write_index = index
-      ## in the bioworks_with_INV_small.xml, protein 8 and 9 have the same
-      ## probability as protein 7
-      if write_index == 8 || write_index == 9
-        write_index = 7
-      end
-      [write_index, bo]
-    end
-    roc = ROC.new
-    tp, fp = ROC.new.prep_list(answ)
-    (exp_tp, exp_fp) = roc.tps_and_ppv(tp, fp)
-
-    sp = SpecID.new(file)
-    assert_equal(19, sp.prots.size)
-    tp, fp = sp.rank_and_classify(:prots, proc {|prt| prt.probability }, proc {|prt| if prt.reference =~ /^INV_/ ; false; else; true; end })
-    (tps, ys) = roc.tps_and_ppv(tp, fp)
-    assert_equal(exp_tp, tps)
-    assert_equal(exp_fp, ys)
-    (num_hits, prec) = sp.num_hits_and_ppv_for_prob("INV_", true)
-    # @TODO: assert these guys for consistencies sake:
-    assert_in_delta_arrays([1, 2, 3, 4, 5, 6, 9, 10, 11, 12, 13, 14, 15], tps, 0.0000001)
-    # Consistency check only:
-    assert_in_delta_arrays([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.909090909090909, 0.916666666666667, 0.923076923076923, 0.928571428571429, 0.866666666666667], prec, 0.0000001)
-  end
-
-  def assert_in_delta_arrays(one, two, delta, message=nil)
-    one.each_with_index do |v,i|
-      assert_in_delta(v, two[i], delta, message)
-    end
-  end
-
-  def test_file_type
-    assert_equal('bioworks', SpecID.file_type(@bw))
-    assert_equal('protproph', SpecID.file_type(@prot_proph))
-    assert_equal('srg', SpecID.file_type('whatever.srg'))
-    ## WOULD BE NICE TO GET THIS WORKING, TOO
-    # assert_equal('protproph', SpecID.file_type(@old_prot_proph))
-    if File.exist? @tfiles_l
-      assert File.exist?(@srf), "file #{@srf} is there"
-      assert_equal('srf', SpecID.file_type(@srf))
-    else
-      assert_nil( puts("\n--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
-    end
-  end
-
-  def test_non_standard_aa_removal
-    hash = {"K.PEPTIDE.Z" => "K.PEPTIDE.Z", "K.*M" => "K.M", "aI" => 'I', "YI.&" => "YI.", "EI.!@#\$%^&*(){}[]|\\;:'\"<>,?/EI" => 'EI.EI'}
-    cl = proc {|v| SpecID::Pep.remove_non_amino_acids(v) }
-    hash.each do |k,v|
-      assert_equal(v, cl.call(k))
-    end
-  end
-
-
-
-end
-
-class MyProt ; include SpecID::Prot ; end
-class MyPep ; include SpecID::Pep ; attr_accessor :xcorr end
-
-
-class TestOccamsRazor < Test::Unit::TestCase
-
-  def test_small
-    
-    prots = (0..6).to_a.map do |n|
-      prot = MyProt.new
-      prot.reference = "ref_#{n}"
-      prot
-    end
-
-    peps = (0..12).to_a.map {|v| MyPep.new }
-
-    #           0   1   2   3   4   5   6   7   8   9   10  11    12 
-    aaseqs = %w(AAA BBB CCC ABC AAA BBB CCC ABC DDD EEE FFF EEEEE DDD)
-    xcorrs = [1.0, 2.0, 3.0, 4.0, 1.0, 2.0, 3.0, 4.0, 0.5, 0.6, 0.7, 0.8, 0.5]
-
-    peps.zip(aaseqs, xcorrs) do |pep,aaseq,xcorr|
-      pep.aaseq = aaseq
-      pep.xcorr = xcorr
-    end
-
-    prots[0].peps = peps[0,4]
-    prots[1].peps = [peps[2]]  ## should be missing
-
-    test_prots = prots[0,2]
-    answ = SpecID.occams_razor(test_prots)
-    answ.each do |an|
-      assert( an[0].is_a?(SpecID::Prot), "prots are there")
-    end
-    first = answ.first
-    assert_equal( prots[0], first[0])
-    assert_equal_array_content( prots[0].peps, first[1])
-
-    require 'pp'
-    #pp answ
-
-
-    prots[0].peps = peps[0,4]
-    prots[1].peps = [peps[2]]  ## should be missing
-    prots[2].peps = []  ## should be missing
-
-    answ = SpecID.occams_razor(test_prots, true)
-    #pp answ
-
-
-    #prots[2].peps = [peps[2]]
-    #prots[2].peps.push( peps[3] ) ## should be there since it has 2
-    #prots[3].peps = [peps[3]] ## should be missing
-  end
-
-  def assert_equal_array_content(exp1, ans, message='')
-    exp1.each do |item|
-      assert(ans.include?(item), "finding #{item}: #{message}")
-    end
-  end
-end
-
-
-require 'fasta'
-
-class TestProteinGroups < Test::Unit::TestCase
-
-  def test_small
-    prots = []
-
-    aaseq = ('A'..'Z').to_a.join('')
-    header = "prot1"
-    prots << Fasta::Prot.new(header, aaseq)
-
-    aaseq = ('A'..'Z').to_a.reverse.join('')
-    header = "prot1_reverse"
-    prots << Fasta::Prot.new(header, aaseq)
-
-    aaseq = ('A'..'Z').to_a.join('')
-    header = "prot1_identical"
-    prots << Fasta::Prot.new(header, aaseq)
-
-    aaseq = ('A'..'E').to_a.join('')
-    header = "prot1_short"
-    prots << Fasta::Prot.new(header, aaseq)
-
-    aaseq = ('A'..'E').to_a.reverse.join('')
-    header = "prot1_reverse_short"
-    prots << Fasta::Prot.new(header, aaseq)
-
-    fasta = Fasta.new(prots)
-
-    pep_seqs = %w(ABCD DEFG ABCD DEFG EDCB FEDCB XYZ RANDOM AEABA) 
-
-    arr = SpecID::Pep.protein_groups_by_sequence(pep_seqs, fasta)
-    
-    exp = [[prots[0], prots[2], prots[3]], [prots[0], prots[2]], [prots[0], prots[2], prots[3]], [prots[0],prots[2]], [prots[1], prots[4]], [prots[1]], [prots[0], prots[2]], [], []]
-    
-    assert_equal(exp, arr)
-  end
-
-end
-

data/test/tc_spec_id_xml.rb

@@ -1,36 +0,0 @@
-require 'test/unit'
-require 'spec_id'
-require 'ostruct'
-
-class Bob
-  include SpecIDXML
-  def initialize(first, second)
-    @first = first ; @second = second 
-  end
-end
-
-
-class SpecIDXMLTest < Test::Unit::TestCase
-  include SpecIDXML
-
-  def initialize(*args)
-    super(*args)
-  end
-
-  def test_short_element_xml_from_instance_vars
-    obj = Bob.new(1, 2) 
-    st = obj.short_element_xml_from_instance_vars("bob")
-    assert_match(/second="2"/, st)
-    assert_match(/first="1"/, st)
-    assert_match(/^<bob /, st)
-    assert_match(/>$/, st)
-  end
-
-  def test_escape_special_chars
-    assert_equal("&amp;&gt;&lt;&quot;&apos;" , escape_special_chars("&><\"'"))
-    assert_equal("PE&amp;PT&gt;I&lt;D&quot;E&apos;", escape_special_chars("PE&PT>I<D\"E'"))
-  end
-
-end
-  
-