mspire 0.1.7 → 0.2.0

data/test/tc_filter.rb

@@ -0,0 +1,203 @@
+
+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_gi.rb

@@ -7,14 +7,11 @@ class Gi2AnnotTest < Test::Unit::TestCase
   ROOT_DIR = File.join(File.dirname(__FILE__), '..')
 
   def test_single_query
-    #begin
-      annot = GI.gi2annot([16130548]).first
-    #rescue 
-      puts "SKIPPING gi2annot test since no internet connection available:"
-      puts "#{$!}"
-      assert true
-    #else
-      assert_equal('CP4-57 prophage; RNase LS [Escherichia coli K12]'+"\n", annot)
-    #end
+    annot = GI.gi2annot([16130548])
+    if annot
+      assert_equal('CP4-57 prophage; RNase LS [Escherichia coli K12]', annot.first)
+    else
+      assert_nil( puts("SKIPPING gi test (no internet connection available)") )
+    end
   end
 end

data/test/tc_id_precision.rb

@@ -30,6 +30,30 @@ class IDPrecisionTest < Test::Unit::TestCase
 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
@@ -49,10 +73,17 @@ END
     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_mzxml.rb

@@ -1,7 +1,6 @@
 require 'test/unit'
 require 'spec/mzxml/parser'
 
-
 class SpecMzXML < Test::Unit::TestCase
   def initialize(arg)
     super(arg)
@@ -49,23 +48,24 @@ class SpecMzXML < Test::Unit::TestCase
       sr_raw = @tfiles + 'smallraw.RAW'
       sr_noext = @tfiles + 'smallraw'
       sr_mzxml = @tfiles + 'smallraw.mzXML'
-      ob = Spec::MzXML::Parser.new 
+      klass = Spec::MzXML
       # given raw
-      file = ob.file_to_mzxml(sr_raw)
+      file = klass.file_to_mzxml(sr_raw)
       file_to_mzxml_assert(file)
       # given mzXML 
-      file = ob.file_to_mzxml(sr_mzxml)
+      file = klass.file_to_mzxml(sr_mzxml)
       file_to_mzxml_assert(file)
       File.unlink(sr_mzxml)
       # given basename (and no mzXML)
-      file = ob.file_to_mzxml(sr_noext)
+      file = klass.file_to_mzxml(sr_noext)
       file_to_mzxml_assert(file)
       # given basename (and mzXML)
-      file = ob.file_to_mzxml(sr_noext)
+      file = klass.file_to_mzxml(sr_noext)
       file_to_mzxml_assert(file)
       File.unlink(sr_mzxml)
     else
       puts "SKIPPING tests requiring 't2x' to convert RAW to mzXML"
+      puts "(look in the archive folder of the gem for t2x binary for linux)"
     end
   end
     
@@ -84,3 +84,5 @@ class SpecMzXML < Test::Unit::TestCase
   end
 
 end
+
+

data/test/tc_peptide_parent_times.rb

@@ -9,7 +9,8 @@ class PeptideParentTimesTest < Test::Unit::TestCase
   end
 
   def test_blank
-    puts "NOT RUNNING ANY TESTS FOR PEPTIDE_PARENT_TIMES RIGHT NOW"
+    ## need to finish this guy up:
+    puts "\nSKIPPING: tests for peptide_parent_times"
   end
 
   def Xtest_run

data/test/tc_precision.rb

@@ -3,7 +3,7 @@ require 'test/unit'
 require File.dirname(File.expand_path(__FILE__)) + '/load_bin_path'
 
 
-class PrecisionTest < Test::Unit::TestCase
+class PrecTest < Test::Unit::TestCase
   ROOT_DIR = File.join(File.dirname(__FILE__), "..")
 
   def initialize(arg)

data/test/tc_proph.rb

@@ -16,8 +16,8 @@ class ProphTest < Test::Unit::TestCase
 
   def test_parse_protxml_file
     file = @tfiles + 'opd1/000_020_3prots-prot.xml'
-    #obj = SpecID::Proph::ProtSummary.new
-    obj = SpecID::Proph::ProtSummary.new(file)
+    #obj = Proph::ProtSummary.new
+    obj = Proph::ProtSummary.new(file)
     assert_equal(3, obj.prot_groups.size)
     assert_equal("1.00", obj.prot_groups.first.probability)
     assert_equal("0.98", obj.prot_groups[2].probability)
@@ -38,7 +38,7 @@ class ProphTest < Test::Unit::TestCase
 
 
   def Xtest_filter_by_min_pep_prob
-    obj = SpecID::Proph::Pep::Parser.new
+    obj = Proph::Pep::Parser.new
     new_file = "tfiles/tmp.xml"
     assert_match(/peptideprophet_result probability="0.[0-5]/, IO.read(@pepproph_xml))
     obj.filter_by_min_pep_prob(@pepproph_xml, new_file, 0.50)
@@ -48,7 +48,7 @@ class ProphTest < Test::Unit::TestCase
   end
 
   def Xtest_uniq_by_seqcharge
-    cls = SpecID::Proph::Pep
+    cls = Proph::Pep
     p1 = cls.new({ :charge => '2', :sequence => 'PEPTIDE' })
     p2 = cls.new({ :charge => '3', :sequence => 'PEPTIDE' })
     p3 = cls.new({ :charge => '2', :sequence => 'PEPTIDE' })
@@ -91,7 +91,7 @@ class ProphTest < Test::Unit::TestCase
     s1 = Spec::Scan.new(1,2,0.10, 300.2, i1, p1)
     s2 = Spec::Scan.new(2,2,0.20, 301.1, i2, p2)
     s3 = Spec::Scan.new(3,2,0.30, 302.0, i3, p3)
-    scan = SpecID::Proph::Pep.new({:scans => [s1,s2,s3]}).arithmetic_avg_scan_by_parent_time
+    scan = Proph::Pep.new({:scans => [s1,s2,s3]}).arithmetic_avg_scan_by_parent_time
     tot_inten = i1 + i2 + i3
     tm = ( t1 * (i1/tot_inten) + t2 * (i2/tot_inten) + t3 * (i3/tot_inten) )
     {:ms_level => 2, :prec_inten => 130115.0/3, :num => nil, :prec_mz => 301.1.to_f, :time => tm }.each do |k,v|

data/test/tc_protein_summary.rb

@@ -1,6 +1,7 @@
 
 require 'test/unit'
-require File.dirname(File.expand_path(__FILE__)) + '/load_bin_path'
+require 'spec_id/protein_summary'
+require File.dirname(__FILE__) + '/test_helper'
 
 
 
@@ -20,16 +21,29 @@ class ProphProtSummaryTest < Test::Unit::TestCase
     @tf_proph_cat_inv_summary_html = @tfiles + 'opd1/opd1_cat_inv_small-prot.summary.html'
     @tf_proph_cat_inv_summary_png = @tfiles + 'opd1/opd1_cat_inv_small-prot.summary.png'
     @tf_peptide_count = @tfiles + "peptide_counts.tmp.txt"
-    @cmd = "ruby -I#{File.join(File.dirname(__FILE__), "..", "lib")} -S protein_summary.rb "
   end
 
+  def runit(string_or_args)
+    args = if string_or_args.is_a? String
+             string_or_args.split(/\s+/)
+           else
+             string_or_args
+           end
+    ProteinSummary.new.create_from_command_line_args(args) 
+  end
+
+ 
   def test_usage
-    assert_match(/usage:/, `#{@cmd}`)
+    output = capture_stdout {
+      runit('')
+    }
+    assert_match(/usage:/, output)
   end
 
-  def Xtest_proph_basic
+  def test_proph_basic
     if File.exist? @tfiles_l
-      print `#{@cmd} -c 5.0 #{@tf_proph}`
+      runit "-c 5.0 #{@tf_proph}"
+      ProteinSummary.new.create_from_command_line_args([@tf_proph, '-c', '5.0'])
       assert(File.exist?(@tf_summary), "file #{@tf_summary} exists")
       string = IO.read(@tf_summary)
       assert_match(/gi\|16132176\|ref\|NP_418775\.1\|/, string)
@@ -41,7 +55,7 @@ class ProphProtSummaryTest < Test::Unit::TestCase
   end
 
   def test_bioworks_basic
-    print `#{@cmd} #{@tf_bioworks_small}`
+    runit "#{@tf_bioworks_small}"
     assert(File.exist?(@tf_bioworks_small_summary_html), "file #{@tf_bioworks_small_summary_html} exists")
     File.unlink @tf_bioworks_small_summary_html unless NODELETE
 
@@ -49,23 +63,32 @@ class ProphProtSummaryTest < Test::Unit::TestCase
   end
 
   def test_bioworks_with_precision
-    `#{@cmd} -f #{@tf_bioworks_small} #{@tf_bioworks_small} --precision`
-    assert_match('TP : 106', IO.read(@tf_bioworks_small_summary_html))
-    assert_match(/False Positive Rate.*: 0.500/, IO.read(@tf_bioworks_small_summary_html))
+    ## Could reimplement a separate file approach?
+    #reply = `#{@cmd} -f #{@tf_bioworks_small} #{@tf_bioworks_small} --precision`
+    runit "#{@tf_bioworks_small} --precision"
+    assert_match(/# hits.*106/m, IO.read(@tf_bioworks_small_summary_html))
+    #assert_match(/False Positive Rate.*: 0.500/, IO.read(@tf_bioworks_small_summary_html))
+    #assert_match(/False Positive Rate.*: 0.500/, IO.read(@tf_bioworks_small_summary_html))
     assert(File.exist?(@tf_bioworks_small_summary_html), "file #{@tf_bioworks_small_summary_html} exists")
     File.unlink @tf_bioworks_small_summary_html unless NODELETE
   end
 
-  def Xtest_proph_with_precision
+  def test_proph_with_precision
     #puts @cmd
-    print `#{@cmd} #{@tf_proph_cat_inv} -f INV_ --precision`
+    runit "#{@tf_proph_cat_inv} -f INV_ --precision"
+    html =  IO.read(@tf_proph_cat_inv_summary_html)
+    assert_match(/# hits/, html, "in #{@tf_proph_cat_inv_summary_html}")
+    assert_match(/2.*0\.0000/m, html, "in #{@tf_proph_cat_inv_summary_html}")
+    assert_match(/3.*0\.3333/m, html, "in #{@tf_proph_cat_inv_summary_html}")
+    assert_match(/7.*0\.5714/m, html, "in #{@tf_proph_cat_inv_summary_html}")
+
     File.unlink @tf_proph_cat_inv_summary_html unless NODELETE
     File.unlink @tf_proph_cat_inv_summary_png unless NODELETE
   end
 
-  def Xtest_peptide_count
+  def test_peptide_count
     if File.exist? @tfiles_l
-      print `#{@cmd} -c 5.0 #{@tf_proph} --peptide_count #{@tf_peptide_count}`
+      runit "-c 5.0 #{@tf_proph} --peptide_count #{@tf_peptide_count}"
       assert(File.exist?(@tf_peptide_count), "file #{@tf_peptide_count} exists")
       file = IO.read(@tf_peptide_count)
       assert_match("gi|16132176|ref|NP_418775.1|\t2", file)

data/test/tc_sequest.rb

@@ -4,8 +4,10 @@
 require 'spec_id'
 require 'spec_id/sequest'
 require 'test/unit'
+require 'spec/mzxml'
 
 
+NODELETE = false
 
 class SequestTest < Test::Unit::TestCase
 
@@ -18,10 +20,10 @@ class SequestTest < Test::Unit::TestCase
     @tf_bioworks_xml = @tfiles + "bioworks_small.xml"
   end
 
-  def test_set_from_bioworks
+  def Xtest_set_from_bioworks
     if File.exist? @tfiles_l
       out_path = '.'
-      pepxml_objs = SpecID::Sequest::PepXML.set_from_bioworks(@tf_params, @tf_bioworks_xml, @tf_mzxml_path, 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)
@@ -55,10 +57,10 @@ class SequestTest < Test::Unit::TestCase
       mzxml_path = @tfiles + "opd1"
       out_path = @tfiles
       pepxml_version = 18
-      pepxml_objs = SpecID::Sequest::PepXML.set_from_bioworks(params, bioworks_xml, mzxml_path, out_path, pepxml_version, "trypsin")
+      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, SpecID::Sequest::PepXML.pepxml_version)
+      assert_equal(pepxml_version, Sequest::PepXML.pepxml_version)
 
       # MSMSPipelineAnalysis
       pipe = po.msms_pipeline_analysis
@@ -197,9 +199,9 @@ class SequestTest < Test::Unit::TestCase
 
  
 
-  def test_calc_num_tol_term
-    params = SpecID::Sequest::Params.new(@tf_params)
-    scall = SpecID::Sequest::PepXML::SearchHit
+  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"))
@@ -207,9 +209,9 @@ class SequestTest < Test::Unit::TestCase
     assert_equal(0, scall.send(sym, params, "F.PEPTIDW.R"))
   end
 
-  def test_calc_num_missed_cleavages
-    params = SpecID::Sequest::Params.new(@tf_params)
-    scall = SpecID::Sequest::PepXML::SearchHit
+  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"))
@@ -225,35 +227,27 @@ class SequestTest < Test::Unit::TestCase
   end
 
 
-  def test_sys_ind_basename
-    assert_equal("hello.fasta", SpecID::Sequest::Params.new._sys_ind_basename("C:\\Xcalibur\\database\\hello.fasta"))
-    assert_equal("hello.fasta", SpecID::Sequest::Params.new._sys_ind_basename("/work/john/hello.fasta"))
+  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 test_modifications
-    obj = SpecID::Sequest::PepXML::Modifications.new(nil, "(M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000) ")
+  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 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::Sequest::PepXML::SearchHit.remove_non_amino_acids(v) }
-    hash.each do |k,v|
-      assert_equal(v, cl.call(k))
-    end
-  end
-
-  def test_modification_info
+  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 = SpecID::Sequest::PepXML::SearchHit::ModificationInfo.new(hash).to_pepxml
+    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)
@@ -270,22 +264,73 @@ class SequestTest < Test::Unit::TestCase
   end
 
   def test_modifications
-    params = SpecID::Sequest::Params.new(@tf_params)
+    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"
-    assert 1
-=begin
-    mod = SpecID::Sequest::PepXML::Modifications(params, mod_string)
-SpecID::Sequest::PepXML::Modifications
-    peptide = "PEPTIDE"
+    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["
-    p mod.modification_info(peptide)
-=end
+    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