mspire 0.2.4 → 0.3.0

data/test/tc_fasta_shaker.rb

@@ -1,149 +0,0 @@
-
-require 'test/unit'
-require 'fasta'
-require File.dirname(__FILE__) + '/load_bin_path.rb'
-
-Filestring = ">gi|P1
-AMKRGAN
->gi|P2
-CRGATKKTAGRPMEK
->gi|P3
-PEPTIDE
-"
-
-Rev = ">gi|P1
-NAGRKMA
->gi|P2
-KEMPRGATKKTAGRC
->gi|P3
-EDITPEP
-"
-
-RevTryptic = ">gi|P1
-MAKRNAG
->gi|P2
-CRTAGKKEMPRGATK
->gi|P3
-EDITPEP
-"
-
-ShuffTryptic = ">gi|P1
-MAKRNAG
->gi|P2
-CRTAGKKEMPRGATK
->gi|P3
-EDITPEP
-"
-
-
-
-class TestBasic < Test::Unit::TestCase
-
-  def setup
-    testdir = File.dirname(__FILE__)
-    libdir = testdir + '/../lib'
-    bindir = testdir +  '/../bin'
-    progname = "fasta_shaker.rb"
-    @cmd = "ruby -I #{libdir} #{bindir}/#{progname} "
-    @tfiles = testdir + '/tfiles/'
-    @tmpfile = @tfiles + "littlefasta.trash.fasta"
-    File.open(@tmpfile, "w") {|fh| fh.print Filestring }
-    @f = @tfiles + "trash.fasta"
-  end
-
-  def teardown
-    File.unlink @tmpfile if File.exist? @tmpfile
-    File.unlink @f if File.exist? @f
-  end
-
-  def Xtest_reverse
-    cmd = @cmd + "reverse #{@tmpfile} -o #{@f}"
-    system cmd
-    assert_equal(Rev, fastap(@f).to_s)
-  end
-
-  def Xtest_reverse_tryptic
-    cmd = @cmd + "reverse #{@tmpfile} -o #{@f} --tryptic_peptides"
-    system cmd
-    assert_equal(RevTryptic, fastap(@f).to_s)
-  end
-
-  def test_shuff_tryptic
-    cmd = @cmd + "shuffle #{@tmpfile} -o #{@f} --tryptic_peptides"
-
-    system cmd
-    lns = fastap(@f).to_s.split("\n")
-    assert_equal('KR', lns[1][2..3])
-    assert_equal('R', lns[3][1..1])
-    assert_equal('CRGATKKTAGRPMEK'.size, lns[3].size, "sequence is same size")
-    assert_not_equal('CRGATKKTAGRPMEK', lns[3], "sequence is randomised from original [remote chance of failure] rerun to make sure")
-  end
-
-  def Xtest_shuffle
-    cmd = @cmd + "shuffle #{@tmpfile} -o #{@f}"
-    system cmd
-    clines = strlns(Filestring)
-    lns = fastalns(@f)
-    lns.each_with_index do |line,i| 
-      assert_equal(clines[i].size, line.size, "same size lines: A: <<#{clines[i]}>> B: <<#{line}>>")
-    end
-    assert_equal('CRGATKKTAGRPMEK'.size, lns[3].size, "sequence is same size")
-    assert_not_equal('CRGATKKTAGRPMEK', lns[3], "sequence is randomised from original [remote chance of failure] rerun to make sure")
-  end
-
-  def Xtest_cat
-    cmd = @cmd + "reverse #{@tmpfile} -c -o #{@f}"
-    `#{cmd}`  ## suppress warning
-    lns = fastalns(@f)
-    assert_equal(strlns(Filestring), lns[0..5], "first part equal")      
-    assert_equal(strlns(Rev), lns[6..-1], "second part equal")      
-  end
-
-  def Xtest_fraction
-    cmd = @cmd + "reverse #{@tmpfile} -f 2.6 -o #{@f}"
-    `#{cmd}`
-    assert_equal(8, fastap(@f).size)
-
-    cmd = @cmd + "shuffle #{@tmpfile} -f 2.0 -c -p MINE_ -o #{@f}"
-    `#{cmd}`
-    assert_equal(9, fastap(@f).size)
-    fp = fastap(@f)
-    fp[0..2].each do |prt|
-      assert_match(/^>/, prt.header, "prefix matches")
-    end
-    fp[3..5].each do |prt|
-      assert_match(/^>MINE_f0_/, prt.header, "prefix matches")
-    end
-    fp[6..8].each do |prt|
-      assert_match(/^>MINE_f1_/, prt.header, "prefix matches")
-    end
-    #cmd = @cmd + "reverse #{@tmpfile} -c -f 2.0 -o #{@f}"
-  end
-
-  def Xtest_prefix
-    cmd = @cmd + "reverse #{@tmpfile} -p SILLY_ -o #{@f}"
-    `#{cmd}`
-    fp = fastap(@f)
-    fp.each do |prt|
-      assert_match(/^>SILLY_.+/, prt.header)
-    end
-  end
-
-
-  private
-  def strlns(str)
-    str.split("\n")
-  end
-
-  def fastalns(fn)
-    assert(File.exist?(fn), "FILE: #{fn} exists")
-    IO.read(fn).split("\n")
-  end
-
-  # returns the fasta object proteins
-  def fastap(fn)
-    assert(File.exist?(fn), "FILE: #{fn} exists")
-    Fasta.new.read_file(fn).prots
-  end
-
-end

data/test/tc_filter.rb

@@ -1,203 +0,0 @@
-
-require 'test/unit'
-require 'spec_id/filter'
-require 'spec_id/srf'
-require 'set_from_hash'
-require File.dirname(__FILE__) + '/test_helper'
-
-$VERBOSE = false
-
-
-class TestFilter < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
-    @small_inv = @tfiles + 'bioworks_with_INV_small.xml'
-    @small = @tfiles + 'bioworks_small.xml'
-    ## SRF:
-    @zero_srf = @tfiles_l + 'opd1_cat_inv/000.srf'
-    @twenty_srf = @tfiles_l + 'opd1_cat_inv/020.srf'
-    @zero_srg = @tfiles_l + 'bioworks_000.srg'
-    @both_srg = @tfiles_l + 'bioworks_both.srg'
-    ## FASTA:
-    @opd1_fasta = @tfiles_l + 'opd1_cat_inv/ecoli_K12_ncbi_20060321.fasta'
-    @opd1_correct_fasta = @tfiles_l + 'opd1_cat_inv/correct_fictitious_314.fasta'
-    if File.exist? @tfiles_l
-      File.open(@zero_srg, 'w') {|fh| fh.puts( File.expand_path(@zero_srf) ) }
-      File.open(@both_srg, 'w') {|fh| fh.puts( File.expand_path(@zero_srf) ); fh.puts( File.expand_path(@twenty_srf) ) }
-    end
-  end
-
-  def test_protein_fppr
-    peps_per_prot = [4,4,3,2,2]
-    (num, mean_fppr, std_num, std_fppr) = SpecID::Filter.new.protein_fppr(peps_per_prot, 1, 10)
-    assert_equal(0, mean_fppr, "no prots completely wrong")    
-    assert_equal(0, std_fppr, "no prots completely wrong")    
-    (num, mean_fppr, std_num, std_fppr) = SpecID::Filter.new.protein_fppr(peps_per_prot, 14, 10)
-    assert_equal(4.0/5, mean_fppr, "only one prot right")    
-    assert_equal(0.0, std_fppr, "only one prot right")    
-  end
-
-  def test_filter_sequest
-    hashes = [
-      {:xcorr => 1.2, :deltacn => 0.1, :ppm => 40, :charge => 2},
-      {:xcorr => 1.3, :deltacn => 0.1, :ppm => 50, :charge => 3},
-      {:xcorr => 1.4, :deltacn => 0.1, :ppm => 50, :charge => 1},
-      {:xcorr => 1.5, :deltacn => 1.1, :ppm => 20, :charge => 2},
-      {:xcorr => 1.3, :deltacn => 0.1, :ppm => 20, :charge => 2},
-      {:xcorr => 1.3, :deltacn => 0.1, :ppm => 40, :charge => 2},
-    ]
-    peps = hashes.map do |hash|
-      pep = SRF::OUT::Pep.new.set_from_hash(hash) 
-    end
-    sp = GenericSpecID.new.set_from_hash({:peps => peps})
-    before_size = sp.peps.size
-    assert_filter([1.2, 1.2, 1.2, 0.1, 50], sp, 5, "all passing")
-    assert_filter([1.6, 1.6, 1.6, 0.1, 50], sp, 0, "xcorrs too high")
-    assert_filter([1.6, 1.0, 1.0, 0.1, 50], sp, 4, "one xcorr too high")
-    assert_filter([1.0, 1.6, 1.0, 0.1, 50], sp, 2, "one xcorr too high")
-    assert_filter([1.0, 1.0, 1.6, 0.1, 50], sp, 4, "one xcorr too high")
-    assert_filter([1.2, 1.2, 1.2, 0.2, 50], sp, 0, "high deltacn")
-
-    ## with deltcnstars:
-    assert_filter([1.2, 1.2, 1.2, 0.1, 50], sp, 6, "all passing", true)
-    assert_filter([1.2, 1.2, 1.2, 0.2, 50], sp, 1, "high deltacn", true)
-    assert_filter([1.0, 1.0, 1.6, 0.1, 50], sp, 5, "one xcorr too high", true)
-  end
-
-  def assert_filter(filter_args, spec_id, expected_passing, message, include_deltcn=false)
-    npeps = spec_id.filter_sequest(filter_args, include_deltcn)
-    assert_equal(expected_passing, npeps.size, message)
-  end
-
-  def test_passing_proteins
-    hash_prots = (0..7).map do |n|
-      SpecID::GenericProt.new.set_from_hash({:reference => "prot_"+n.to_s, :peps => []})
-    end
-    arr_prots = (0..7).map do |n|
-      SRF::OUT::Prot.new.set_from_hash({:reference => "prot_"+n.to_s, :peps => []})
-    end
-    [hash_prots, arr_prots].each do |prots|
-
-      hashes = [
-        {:aaseq => 'PEP0', :xcorr => 1.2, :deltacn => 0.1, :ppm => 40, :charge => 2, :prots => [prots[0],prots[1]]},
-        {:aaseq => 'PEP1', :xcorr => 1.3, :deltacn => 0.1, :ppm => 50, :charge => 3, :prots => [prots[1],prots[2]]},
-        {:aaseq => 'PEP2', :xcorr => 1.4, :deltacn => 0.1, :ppm => 50, :charge => 1, :prots => [prots[3]]},
-        {:aaseq => 'PEP3', :xcorr => 1.5, :deltacn => 1.1, :ppm => 20, :charge => 2, :prots => [prots[4]]},
-        {:aaseq => 'PEP4', :xcorr => 1.3, :deltacn => 0.1, :ppm => 20, :charge => 2, :prots => [prots[0]]},
-        {:aaseq => 'PEP5', :xcorr => 1.3, :deltacn => 0.1, :ppm => 40, :charge => 2, :prots => prots[1,2]},
-      ]
-
-      peps = hashes.map do |hash|
-        SRF::OUT::Pep.new.set_from_hash(hash) 
-      end
-
-
-      prts = SpecID.passing_proteins(peps)
-      exp = (0..4).map do |n|
-      "prot_" + n.to_s
-      end
-      refs = prts.map { |v| v.reference }.sort
-      assert_equal(exp, refs)
-
-
-      prts = SpecID.passing_proteins(peps, :update)
-      prot_0_before = prts.select {|v| v.reference == 'prot_0'}.first
-      assert_protein_match(prts, 'prot_0', %w(PEP0 PEP4))
-      assert_protein_match(prts, 'prot_1', %w(PEP0 PEP1 PEP5))
-      assert_protein_match(prts, 'prot_2', %w(PEP1 PEP5))
-      assert_protein_match(prts, 'prot_3', %w(PEP2))
-      assert_protein_match(prts, 'prot_4', %w(PEP3))
-      srt_ref = prts.map {|v| v.reference}.sort
-      assert_equal(%w(prot_0 prot_1 prot_2 prot_3 prot_4), srt_ref, "just the right number of prots")
-      prot_0 = prts.select {|v| v.reference == 'prot_0'}.first
-      assert_equal(prot_0_before.__id__, prot_0.__id__, "proteins are identical")
-
-
-      prot_0_before = prts.select {|v| v.reference == 'prot_0'}.first.__id__
-
-      prts = SpecID.passing_proteins(peps, :new)
-      assert_protein_match(prts, 'prot_0', %w(PEP0 PEP4))
-      assert_protein_match(prts, 'prot_1', %w(PEP0 PEP1 PEP5))
-      assert_protein_match(prts, 'prot_2', %w(PEP1 PEP5))
-      assert_protein_match(prts, 'prot_3', %w(PEP2))
-      assert_protein_match(prts, 'prot_4', %w(PEP3))
-      srt_ref = prts.map {|v| v.reference}.sort
-      assert_equal(%w(prot_0 prot_1 prot_2 prot_3 prot_4), srt_ref, "just the right number of prots")
-      prot_0 = prts.select {|v| v.reference == 'prot_0'}.first
-      assert_not_equal(prot_0_before, prot_0.__id__, "proteins are not identical")
-
-    end
-  end
-
-  def assert_protein_match(prts, ref, pepseqs, message='') 
-    prt = prts.select{|v| v.reference == ref }.first
-    sorted_prt_peps_aaseqs = prt.peps.map {|v| v.aaseq }.sort 
-    sorted_pepseqs = pepseqs.sort
-    assert_equal(pepseqs, sorted_prt_peps_aaseqs, message)
-  end
-
-  def test_usage
-    output = capture_stdout {
-      SpecID::Filter.run_from_argv([])
-    }
-    assert_match('usage:', output)
-  end
-
-  def test_basic_bioworks_xml
-
-    output = capture_stdout {
-      SpecID::Filter.run_from_argv([@small].push( *(%w(-1 1.0 -2 1.0 -3 1.0 -c 0.1 --ppm 1000))) )
-    }
-    ## FROZEN:
-    assert_match(/pep_hits\s+4/, output)
-    assert_match(/uniq_aa_hits\s+4/, output)
-    assert_match(/prot_hits\s+4/, output)
-    
-
-    output = capture_stdout {
-      SpecID::Filter.run_from_argv([@small_inv].push( *(%w(-1 1.0 -2 1.0 -3 1.0 -c 0.1 --ppm 1000 -f INV_))) )
-    }
-    #puts ""
-    #puts output
-    ## FROZEN:
-    assert_match(/pep_hits\s+151/, output)
-    assert_match(/uniq_aa_hits\s+75/, output)
-    assert_match(/prot_hits\s+13/, output)
-  end
-  
-  def test_srf
-    if File.exist? @tfiles_l
-      ## dcy
-      output = capture_stdout {
-        SpecID::Filter.run_from_argv([@zero_srg].push( *(%w(-1 1.0 -2 1.0 -3 1.0 -c 0.1 --ppm 1000 -f INV_))) )
-      }
-      ## FROZEN:
-      #puts ""
-      #puts output
-      assert_match(/pep_hits\s+2111\s+107\.2/, output)
-      assert_match(/uniq_aa_hits\s+2034\s+106\.6/, output)
-      assert_match(/prot_hits\s+1454\s+100\.0/, output)
-
-      ## cys tps fps COMBINED
-      # tps are fictitious!
-      output = capture_stdout {
-        # that's the background freq for ecoli that this file's from
-        SpecID::Filter.run_from_argv([@zero_srg].push( *(%w(-1 1.0 -2 1.0 -3 1.0 -c 0.1 --ppm 1000 --occams_razor --cys 0.0115866200193321 --t).push(@opd1_correct_fasta))))
-      }
-      #puts ""
-      #puts output
-      ## FROZEN:
-      assert_match(/num\s+tps%\s+cys%/, output, "header")
-      assert_match(/pep_hits\s+4374\s+9\d\.\d.*\s+83\.7/, output)
-      assert_match(/uniq_aa_hits\s+4203\s+9\d\.\d.*\s+82\.8/, output)
-      assert_match(/prot_hits\s+2986\s+9\d\..*\s+7\d\./, output)
-      assert_match(/occams.*\s+2986\s+8\d\..*\s+7\d\./, output)
-    else
-      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})" ))
-    end
-  end
-
-end

data/test/tc_filter_peps.rb

@@ -1,46 +0,0 @@
-
-
-require 'test/unit'
-
-class TestFilter < Test::Unit::TestCase
-  ROOT_DIR = File.join(File.dirname(__FILE__), '..')
-
-  def test_filter_results
-    @tfiles = File.dirname(File.expand_path(__FILE__)) + '/tfiles/'
-    @bfile = @tfiles + "bioworks_with_SHUFF_small.xml"
-    
-    cmd_core = "ruby -I #{File.join(ROOT_DIR, 'lib')} #{File.join(ROOT_DIR, 'script', 'filter-peps.rb')} "
-    #puts `#{cmd_core}`
-    cmd = cmd_core + "SHUFF_ #{@bfile}"
-    output = `#{cmd}`
-    
-    freeze = %{FILENAME\tPepProts\tScanChargeBest\tScanChargeTop10\tScanBest\tScanTop10\tSeqChargeBest\tSeqChargeTop10
-TP: #{@tfiles}bioworks_with_SHUFF_small.xml\t3\t3\t3\t3\t3\t3\t3
-FP: #{@tfiles}bioworks_with_SHUFF_small.xml\t3\t3\t3\t3\t3\t2\t3
-DIFF: #{@tfiles}bioworks_with_SHUFF_small.xml\t0\t0\t0\t0\t0\t1\t0
-}
-    assert_equal(freeze, output)
-
-
-
-
-    cmd = cmd_core + "SHUFF_ #{@bfile} -1 1.0 -2 2.0 -3 3.0"
-    output = `#{cmd}`
-    
-    freeze = %{FILENAME\tPepProts\tScanChargeBest\tScanChargeTop10\tScanBest\tScanTop10\tSeqChargeBest\tSeqChargeTop10
-TP: #{@tfiles}bioworks_with_SHUFF_small.xml\t3\t3\t3\t3\t3\t3\t3
-FP: #{@tfiles}bioworks_with_SHUFF_small.xml\t4\t4\t4\t4\t4\t3\t4
-DIFF: #{@tfiles}bioworks_with_SHUFF_small.xml\t-1\t-1\t-1\t-1\t-1\t0\t-1
-}
-    assert_equal(freeze, output)
-
-
-
-  end
-
-
-
-
-
-
-end

data/test/tc_gi.rb

@@ -1,17 +0,0 @@
-
-require 'test/unit'
-require 'gi'
-
-
-class Gi2AnnotTest < Test::Unit::TestCase
-  ROOT_DIR = File.join(File.dirname(__FILE__), '..')
-
-  def test_single_query
-    annot = GI.gi2annot([836805])
-    if annot
-      assert_equal('proteosome component PRE4 [Saccharomyces cerevisiae]', annot.first)
-    else
-      assert_nil( puts("SKIPPING gi test (no internet connection available)") )
-    end
-  end
-end

data/test/tc_id_class_anal.rb

@@ -1,70 +0,0 @@
-
-require 'test/unit'
-require File.dirname(File.expand_path(__FILE__)) + '/load_bin_path'
-
-
-class IDClassAnalTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tf_bioworks_esmall_xml = @tfiles + "bioworks_with_INV_small.xml" 
-    @tf_bioworks_small_xml = @tfiles + "bioworks_small.xml"
-    @tf_bioworks_shuff = @tfiles + "bioworks_with_SHUFF_small.xml"
-    @tf_proph_inv = @tfiles + "opd1/opd1_cat_inv_small-prot.xml"
-    @cmd = "ruby -I#{File.join(File.dirname(__FILE__), "..", "lib")} -S id_class_anal.rb "
-  end
-
-  def test_usage
-    assert_match(/usage:/, `#{@cmd}`)
-  end
-
-  def test_proph_basic
-    output = `#{@cmd} -p INV_ #{@tf_proph_inv}`
-    fps = [1.00, 1.00, 0.97]
-    tps = [1.00, 1.00, 0.98, 0.97, 0.97, 0.97, 0.97]
-    #File.open("tmp.csv","w") do |fh| fh.print output end
-    assert 1
-  end
-
-  def test_basic
-    output = `#{@cmd} -p INV_ #{@tf_bioworks_esmall_xml}`
-    exp = [
-      [1, 1.0, 0.0],
-      [2, 1.0, 0.0],
-      [3, 1.0, 0.0],
-      [4, 1.0, 0.0],
-      [5, 1.0, 0.0],
-      [6, 1.0, 0.0],
-      [9, 1.0, 0.0],
-      [10, 1.0, 0.0],
-      [11, 0.909090909090909],
-      [12, 0.916666666666667],
-      [13, 0.923076923076923],
-      [14, 0.928571428571429],
-      [15, 0.866666666666667],
-    ]
-    outarr = output.split($/)
-    exp.each_with_index do |line,i|
-      outfloats = outarr[i+1].split("\t").collect {|v| v.to_f }
-      line.each_with_index do |v,j|
-        assert_in_delta(v, outfloats[j], 0.00000000000000001)
-      end
-    end
-  end
-
-  def test_multiple_output
-    myplot = 'class_anal.toplot'
-    output = `#{@cmd} -j -p INV_,SHUFF_ #{@tf_bioworks_esmall_xml} #{@tf_bioworks_shuff}`
-    assert(output.size > 10) ## @TODO: BETTER HERE
-    assert(File.exist?(myplot), "file #{myplot} exists")
-    File.unlink myplot
-  end
-
-  def test_jtplot_output
-    myplot = 'class_anal.toplot'
-    output = `#{@cmd} -p INV_ -j #{@tf_bioworks_esmall_xml}`
-    assert(File.exist?(myplot), "file #{myplot} exists")
-    File.unlink myplot
-  end
-end

data/test/tc_id_precision.rb

@@ -1,89 +0,0 @@
-
-require 'test/unit'
-require File.dirname(File.expand_path(__FILE__)) + '/load_bin_path'
-
-class IDPrecisionTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tf_bioworks_inv_xml = @tfiles + "bioworks_with_INV_small.xml" 
-    @tf_bioworks_shuff = @tfiles + "bioworks_with_SHUFF_small.xml"
-    @cmd = "ruby -I#{File.join(File.dirname(__FILE__), "..", "lib")} -S id_precision.rb "
-  end
-
-  def test_usage
-    #puts "RUNNING: #{@cmd}"
-    assert_match(/usage:/, `#{@cmd}`)
-  end
-
-  ## freeze the output
-  def test_basic
-    cmd = "#{@cmd} INV_ #{@tf_bioworks_inv_xml}"
-    #puts "RUNNING: #{cmd}"
-    reply = `#{cmd}`
-    string =<<END
-#  NH = number of hits
-#  TP = true positives
-#  FP = false positives
-#  PR = precision = TP/(TP+FP)
-PepProts: NH,PepProts: PR,SeqCharge: NH,SeqCharge: PR,Scan(TopHit): NH,Scan(TopHit): PR,Scan(Top10): NH,Scan(Top10): PR,ScanCharge(TopHit): NH,ScanCharge(TopHit): PR,ScanCharge(Top10): NH,ScanCharge(Top10): PR
-75, 1.0, 37, 1.0, 75, 1.0, 75, 1.0, 75, 1.0, 75, 1.0
-95, 1.0, 49, 1.0, 95, 1.0, 95, 1.0, 95, 1.0, 95, 1.0
-155, 1.0, 67, 1.0, 123, 1.0, 155, 1.0, 125, 1.0, 155, 1.0
-186, 1.0, 85, 1.0, 154, 1.0, 186, 1.0, 156, 1.0, 186, 1.0
-196, 1.0, 90, 1.0, 161, 1.0, 196, 1.0, 163, 1.0, 196, 1.0
-214, 1.0, 94, 1.0, 168, 1.0, 214, 1.0, 170, 1.0, 214, 1.0
-215, 1.0, 95, 1.0, 169, 1.0, 215, 1.0, 171, 1.0, 215, 1.0
-217, 0.995391705069124, 97, 0.989690721649485, 171, 0.994152046783626, 217, 0.995391705069124, 173, 0.994219653179191, 217, 0.995391705069124
-219, 0.995433789954338, 99, 0.98989898989899, 172, 0.994186046511628, 219, 0.995433789954338, 175, 0.994285714285714, 219, 0.995433789954338
-227, 0.995594713656388, 106, 0.990566037735849, 180, 0.994444444444444, 227, 0.995594713656388, 183, 0.994535519125683, 227, 0.995594713656388
-228, 0.995614035087719, 107, 0.990654205607477, 181, 0.994475138121547, 228, 0.995614035087719, 184, 0.994565217391304, 228, 0.995614035087719
-229, 0.991266375545852, 108, 0.981481481481482, 182, 0.989010989010989, 229, 0.991266375545852, 185, 0.989189189189189, 229, 0.991266375545852
-END
-
-    # This was the result we were getting before first hashing on protein
-    # sequences and doing uniqe peptide hits.  It is very similar ( but not
-    # exactly the same) to what we are doing now).  Must have something to do
-    # with the way things are hashed out.
-    before_doing_uniq_peptides=<<END
-#  NH = number of hits
-#  TP = true positives
-#  FP = false positives
-#  PR = precision = TP/(TP+FP)
-PepProts: NH,PepProts: PR,SeqCharge: NH,SeqCharge: PR,Scan(TopHit): NH,Scan(TopHit): PR,Scan(Top10): NH,Scan(Top10): PR,ScanCharge(TopHit): NH,ScanCharge(TopHit): PR,ScanCharge(Top10): NH,ScanCharge(Top10): PR
-75, 1.0, 37, 1.0, 75, 1.0, 75, 1.0, 75, 1.0, 75, 1.0
-95, 1.0, 49, 1.0, 95, 1.0, 95, 1.0, 95, 1.0, 95, 1.0
-125, 1.0, 67, 1.0, 123, 1.0, 125, 1.0, 125, 1.0, 125, 1.0
-155, 1.0, 85, 1.0, 154, 1.0, 155, 1.0, 156, 1.0, 155, 1.0
-186, 1.0, 90, 1.0, 161, 1.0, 186, 1.0, 163, 1.0, 186, 1.0
-193, 1.0, 94, 1.0, 168, 1.0, 193, 1.0, 170, 1.0, 193, 1.0
-204, 1.0, 95, 1.0, 169, 1.0, 204, 1.0, 171, 1.0, 204, 1.0
-212, 1.0, 97, 0.989690721649485, 171, 0.994152046783626, 212, 1.0, 173, 0.994219653179191, 212, 1.0
-214, 0.995327102803738, 99, 0.98989898989899, 172, 0.994186046511628, 214, 0.995327102803738, 175, 0.994285714285714, 214, 0.995327102803738
-216, 0.99537037037037, 106, 0.990566037735849, 180, 0.994444444444444, 216, 0.99537037037037, 183, 0.994535519125683, 216, 0.99537037037037
-227, 0.995594713656388, 107, 0.990654205607477, 181, 0.994475138121547, 227, 0.995594713656388, 184, 0.994565217391304, 227, 0.995594713656388
-228, 0.995614035087719, 108, 0.981481481481482, 182, 0.989010989010989, 228, 0.995614035087719, 185, 0.989189189189189, 228, 0.995614035087719
-229, 0.991266375545852, , , , , 229, 0.991266375545852, , , 229, 0.991266375545852
-END
-    assert_equal(string, reply)
-  end
-
-  def test_basic_with_area
-    cmd = "#{@cmd} INV_ #{@tf_bioworks_inv_xml} -a"
-    #puts "RUNNING: #{cmd}"
-    reply = `#{cmd}`
-    # This is what we were getting before hashing for uniqe peptides
-    # It is very similar (but not identical to previous output)
-    string =<<END
-Filename PepProts SeqCharge Scan(TopHit) Scan(Top10) ScanCharge(TopHit) ScanCharge(Top10)
-./test/tfiles/bioworks_with_INV_small.xml 228.925377117814 107.877585995136 181.929045912105 228.925377117814 184.924437525838 228.925377117814
-END
-
-    string =<<NEWEND
-Filename PepProts SeqCharge Scan(TopHit) Scan(Top10) ScanCharge(TopHit) ScanCharge(Top10)
-./test/tfiles/bioworks_with_INV_small.xml 228.939375794224 107.877585995136 181.929045912105 228.939375794224 184.924437525838 228.939375794224
-NEWEND
-    assert_equal(string, reply, "area under the curve")
-  end
-end

data/test/tc_msrun.rb

@@ -1,88 +0,0 @@
-
-require 'test/unit'
-require 'spec/msrun'
-require 'spec/mzxml/parser'
-
-
-class MSRunTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @ti_file = @tfiles + "020a.mzXML.timeIndex"
-    @mzxml_file = @tfiles + "opd1/twenty_scans.mzXML"
-  end
-
-  def test_precursor_mz_by_scan
-    answer = [nil, nil, "391.045410", "446.009033", "1222.033203", nil, "390.947449", "1221.905518", "1322.036621", nil, "1322.000732", "1122.119141", "444.804504", nil, "446.796082", "1122.041260", "1421.951416", nil, "358.676636", "1460.548340", "1422.277100"]
-    array = Spec::MSRun.precursor_mz_by_scan(@mzxml_file)
-    assert_equal(answer, array)
-  end
-
-  def test_basename_noext
-    obj = Spec::MSRunIndex.new
-    {'path/to/file.mzXML' => 'file', 'other/path/file1.mzXML.timeIndex' => 'file1', 'path2/path3/file2.timeIndex' => 'file2', 'other/path/file3.weird' => 'file3', '/path/file4.ext1.ext2'=> 'file4.ext1'}.each do |k,v|
-      obj.basename_noext = k
-      assert_equal(v, obj.basename_noext)
-    end
-  end
-
-  def test_msrun_index_from_file
-    guy = Spec::MSRunIndex.new(@ti_file) 
-    sbn =  guy.scans_by_num
-    s1 = sbn[1]
-    s2 = sbn[2]
-    sl = sbn[-1]
-    assert [1, 1, 600.020000], [s1.num, s1.ms_level, s1.time]
-    assert [2, 2, 601.280000], [s2.num, s2.ms_level, s2.time]
-    assert [3496, 2, 4802.130000], [sl.num, sl.ms_level, sl.time]
-  end
-
-  def test_msrun_index_from_mzXML
-    exp = [
-      "1 1 0.44",
-      "2 2 1.9 391.045410 6986078.0",
-      "2 3 2.75 446.009033 1531503.0",
-      "2 4 3.64 1222.033203 1520220.0",
-      "1 5 5.15",
-      "2 6 6.5 390.947449 6191130.0",
-      "2 7 7.47 1221.905518 2245001.0",
-      "2 8 9.14 1322.036621 1946525.0",
-      "1 9 10.69",
-      "2 10 12.0 1322.000732 1475536.0",
-      "2 11 13.66 1122.119141 1188303.0",
-      "2 12 15.37 444.804504 716303.0",
-      "1 13 16.4",
-      "2 14 17.77 446.796082 1472386.0",
-      "2 15 18.77 1122.041260 1411827.0",
-      "2 16 20.65 1421.951416 1187501.0",
-      "1 17 22.37",
-      "2 18 23.74 358.676636 826186.0",
-      "2 19 25.23 1460.548340 720317.0",
-      "2 20 27.05 1422.277100 709884.0",
-    ]
-    %w(xmlparser rexml).each do |parser|
-      scans = Spec::MzXML::Parser.new.scans_by_num(@mzxml_file, parser)
-      obj = Spec::MSRunIndex.new
-      obj.scans_by_num = scans
-      assert_equal(Spec::MSRunIndex, obj.class)
-      obj.scans_by_num.each_with_index do |scan,i|
-        next if i == 0
-        assert_equal(Spec::Scan, scan.class)
-        assert_equal_values(exp[i-1], scan.to_index_file_string)
-      end
-    end
-  end
-
-  # takes two space delimited strings
-  # and asks if they are the same (as floats)
-  def assert_equal_values(string1, string2)
-    arr1 = string1.split(" ")
-    arr2 = string2.split(" ")
-    arr1.each_with_index do |val,i|
-      assert_equal(val.to_f, arr2[i].to_f)
-    end
-  end
-
-end
-