mspire 0.3.1 → 0.3.9

data/specs/spec_helper.rb

@@ -3,12 +3,14 @@ gem 'rspec'
 
 # a global flag that lets me know what format we're dealing with for output
 $specdoc = false
-ObjectSpace.each_object do |obj|
-  case obj
-  when Spec::Runner::Formatter::SpecdocFormatter
-    $specdoc = true
-  end
-end
+## something changed between version 1.0.6?? and 1.1.1 in rspec so that
+#Spec::Runner is no longer an object being created...
+#ObjectSpace.each_object do |obj|
+#  case obj
+#  when Spec::Runner::Formatter::SpecdocFormatter
+#    $specdoc = true
+#  end
+#end
 
 # Set up some global testing variables:
 #silent {
@@ -109,9 +111,9 @@ require SPEC_DIR + '/load_bin_path'
 class String
   #alias_method :exist?, exist_as_a_file?
   #alias_method exist_as_a_file?, exist?
-  def exist?
-    File.exist? self
-  end
+  #def exist?
+  #  File.exist? self
+  #end
   def exist_as_a_file?
     File.exist? self
   end

data/specs/spec_id/bioworks_spec.rb

@@ -37,7 +37,8 @@ describe Bioworks, 'set from an xml file' do
     tmpfile = Tfiles + "/tf_bioworks_to_excel.tmp"
     bio = Bioworks.new(tf_bioworks_to_excel)
     bio.to_excel(tmpfile)
-    File.should exist(tmpfile)
+    tmpfile.exist_as_a_file?.should be_true
+    #File.should exist_as_a_file(tmpfile)
     exp = _arr_of_arrs(tf_bioworks_to_excel_actual)
     act = _arr_of_arrs(tmpfile)
     exp.each_index do |i|

data/specs/spec_id/precision/filter_spec.rb

@@ -103,7 +103,7 @@ describe 'filtering on small bioworks file with inverse prots' do
     @regexp = /^INV_/o
     @file = Tfiles + '/bioworks_with_INV_small.xml'
     @spec_id = SpecID.new(@file)
-    vals = [Validator::Decoy.new(@regexp)]
+    vals = [Validator::Decoy.new(:constraint => @regexp)]
     @opts = {:sequest => {:xcorr1 => 1.0, :xcorr2 => 1.0, :xcorr3 => 1.0, :deltacn => 0.1, :ppm => 1000.0, :include_deltacnstar=> false}, :validators => vals}
   end
 
@@ -121,7 +121,7 @@ describe 'filtering on small bioworks file with inverse prots' do
     # this does a minimal test to see if this functions properly
     # (not for accuracy, which is done in validator_spec)
     ## WITH FASTA FILE:
-    val1 = Validator::AA.new('C').set_frequency(Fasta.new(Tfiles + '/small.fasta'))
+    val1 = Validator::AAEst.new('C').set_frequency(Fasta.new(Tfiles + '/small.fasta').prots)
     @opts[:validators] << val1   # obviously this guy is not his
     ans1 = SpecID::Precision::Filter.new.filter_and_validate(@spec_id, @opts)
     peps = ans1[:pephits]
@@ -131,7 +131,7 @@ describe 'filtering on small bioworks file with inverse prots' do
 
     ## WITH A CYSTEINE BACKGROUND:
     background_cys = 0.0172
-    val3 = Validator::AA.new('C', :background => background_cys).set_frequency(Fasta.new(Tfiles + '/small.fasta'))
+    val3 = Validator::AAEst.new('C', :background => background_cys).set_frequency(Fasta.new(Tfiles + '/small.fasta').prots)
     @opts[:validators][1] = val3
     ans3 = SpecID::Precision::Filter.new.filter_and_validate(@spec_id, @opts)
     peps = ans3[:pephits]
@@ -156,8 +156,8 @@ describe 'filtering on a real srf file' do
       
       regexp = /FAKINGIT_OUT/
       opts[:decoy] = regexp
-      decoy_val = Validator::Decoy.new(regexp) # this is not real, just to test
-      cys_val = Validator::AA.new('C').set_frequency(Fasta.new(fasta_file))
+      decoy_val = Validator::Decoy.new(:constraint => regexp) # this is not real, just to test
+      cys_val = Validator::AAEst.new('C').set_frequency(Fasta.new(fasta_file).prots)
       tmm_val = Validator::Transmem::Protein.new(tmm_file, :min_num_tms => 1, :soluble_fraction => true, :correct_wins => true, :no_include_tm_peps => false, :background => 0.0).set_false_to_total_ratio( Digestor.digest( Fasta.new(fasta_file), Sequest::Params.new(sequest_file) ) )
       opts[:validators] = [decoy_val, cys_val, tmm_val]
       ans = SpecID::Precision::Filter.new.filter_and_validate(spec_id, opts)

data/specs/spec_id/precision/prob_spec.rb

@@ -41,71 +41,4 @@ describe 'finding precision Proph::Prot::Pep objects' do
 end
 
 
-=begin
-  it 'gets precision with all validators (including probability and decoy)' do
-    ## create some decoy peptides!
-    @spec_id.peps.sort_by {|pep| pep.probability }[100..-1].each_with_index do |pep,i|
-      if i % 3 == 0
-        pep.prots.each {|prot| prot.protein_name = 'DECOY_' + prot.protein_name }
-      end
-    end
-    # check which ones are ACTUALLY normal and decoy
-    (decoy, normal) = @spec_id.peps.partition do |pep|
-      pep.prots.all? {|prot| prot.protein_name =~ /^DECOY_/}
-    end
-    num_decoy = decoy.size
-    num_normal = normal.size
-  end
-
-prob_spec_helper = File.expand_path( File.dirname(__FILE__) + '/prob_spec_helper' )
-
-# this does a minimal test to see if this functions properly
-# (not for accuracy, which is done in validator_spec)
-## WITH FASTA FILE:
-base_dir = Tfiles_l + '/opd1_2runs_2mods/sequest'
-fasta_file = base_dir + '/ecoli_K12_ncbi_20060321.fasta'
-params_file = base_dir + '/ecoli.params'
-bias_file = base_dir + '/ecoli_K12_ncbi_20060321.bias.fasta'
-toppred_file = base_dir + '/ecoli_K12_ncbi_20060321.toppred.xml'
-
-fasta_file.should exist
-
-prob = Validator::Probability.new
-badaa_freq = Validator::AA.new('C', :frequency => 0.0115866200193321)
-badaa_dig = Validator::AA.new('C')
-bias = Validator::Bias.new(Fasta.new(bias_file))
-transmem = Validator::Transmem::Protein.new(toppred_file)
-decoy = Validator::Decoy.new(/^DECOY_/)
-
-turn_on_digestion = true
-if turn_on_digestion
-  # digestion based validators need this set!
-  digested_peps = Digestor.digest(Fasta.new(fasta_file), Sequest::Params.new(params_file))
-  [badaa_dig, bias, transmem].each do |val|
-    val.set_false_to_total_ratio(digested_peps)
-  end
-end
-transmem.transmem_status_hash = transmem.create_transmem_status_hash(@spec_id.peps)
-val_list = [decoy, badaa_freq, badaa_dig, prob, bias, transmem]
-
-opts = { :validators => val_list }
-
-
-hash = SpecID::Precision::Prob.new.precision_vs_num_hits(@spec_id, opts)
-#puts "OUTPUT: "
-#puts hash.to_yaml
-
-
-# frozen
-e_hash = ProbMSHelper::Answer2
-# hash[:pephits_precision].size.should == e_hash[:pephits_precision].size
-# other data types are tested above, just testing validators
-hash[:pephits_precision].zip( e_hash[:pephits_precision] ) do |val_hash, val_hash_e|
-  val_hash[:values].size.should == num_normal
-  #val_hash[:validator].should == val_hash_e[:validator]
-  val_hash[:values].zip(val_hash_e[:values]) {|v,e| v.should be_close(e, 0.000000001)}
-end
-    end
-end
 
-=end

data/specs/spec_id/proph/pep_summary_spec.rb

@@ -13,7 +13,7 @@ ToCheck = {
 }
 
 
-describe Proph::PepSummary, "reading a .xml file" do
+describe Proph::PepSummary, "reading a small .xml file" do
   before(:each) do
     file = Tfiles + '/opd1_2runs_2mods/interact-opd1_mods__small.xml'
     @obj = Proph::PepSummary.new(file)
@@ -23,15 +23,25 @@ describe Proph::PepSummary, "reading a .xml file" do
     lambda { Proph::PepSummary.new(Tfiles + '/opd1/000.tpp_2.9.2.first10.xml')}.should raise_error(ArgumentError)
   end
 
-  it 'has spectrum queries' do
-    @obj.spectrum_queries.size.should == 18
+  it 'has msms_run_summary objects with spectrum_queries' do
+    @obj.msms_run_summaries.size.should == 1
+    sqs = @obj.msms_run_summaries.first.spectrum_queries
+    sqs.size.should == 18
 
     [:first, :last].each do |mth|
       ToCheck[:spectrum_query][mth].each do |k,v|
-        @obj.spectrum_queries.send(mth).send(k).should == v
+        if v.is_a? Float
+          sqs.send(mth).send(k).should be_close(v, 0.0000000001)
+        else
+          sqs.send(mth).send(k).should == v
+        end
       end
       ToCheck[:search_hit][mth].each do |k,v|
-        @obj.spectrum_queries.send(mth).search_results.first.search_hits.first.send(k).should == v
+        if v.is_a? Float
+          sqs.send(mth).search_results.first.search_hits.first.send(k).should be_close(v, 0.0000000001)
+        else
+          sqs.send(mth).search_results.first.search_hits.first.send(k).should == v
+        end
       end
     end
   end
@@ -44,7 +54,11 @@ describe Proph::PepSummary, "reading a .xml file" do
 
     [:first, :last].each do |mth|
       ToCheck[:search_hit][mth].each do |k,v|
-        @obj.peps.send(mth).send(k).should == v
+        if v.is_a? Float
+          @obj.peps.send(mth).send(k).should be_close(v, 0.0000000001)
+        else
+          @obj.peps.send(mth).send(k).should == v
+        end
       end
     end
 
@@ -52,92 +66,33 @@ describe Proph::PepSummary, "reading a .xml file" do
 
 end
 
-####################################################
-# OTHER TESTS NOT IMPLEMENTED (do we need these??)
-####################################################
-
-=begin
-
-require 'test/unit'
-require 'spec_id'
-require 'ms/scan'
-
-class ProphTest < Test::Unit::TestCase
-
-  def initialize(arg)
-    super(arg)
-    @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @pepproph_xml = @tfiles + 'pepproph_small.xml'
-  end
-
-  def Xtest_filter_by_min_pep_prob
-    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)
-    assert_no_match(/peptideprophet_result probability="0.[0-5]/, IO.read(new_file))
-    assert_match(/<peptideprophet_result[^>]*probability="0.[6-9][^>]*>/, IO.read(new_file))
-    File.unlink new_file
-  end
-
-  def Xtest_uniq_by_seqcharge
-    cls = Proph::Pep
-    p1 = cls.new({ :charge => '2', :sequence => 'PEPTIDE' })
-    p2 = cls.new({ :charge => '3', :sequence => 'PEPTIDE' })
-    p3 = cls.new({ :charge => '2', :sequence => 'PEPTIDE' })
-    p4 = cls.new({ :charge => '2', :sequence => 'APEPTIDE' })
-    p5 = cls.new({ :charge => '2', :sequence => 'APEPTIDE' })
-    un_peps = cls.uniq_by_seqcharge([p1,p2,p3,p4,p5])
-    ## WHY ISn't that working? below!
-    ##assert_equal([p1,p2,p4].to_set, un_peps.to_set)
-    assert(equal_sets([p1,p2,p4], un_peps))
-  end
-
-  def Xequal_sets(arr1, arr2)
-    c1 = arr1.dup
-    c2 = arr2.dup
-    arr1.each do |c|
-      arr2.each do |d|
-        if c == d
-          c1.delete c
-          c2.delete d
-        end
-      end
+describe Proph::PepSummary, 'reading a large .xml file' do 
+  spec_large do 
+    before(:all) do 
+      file = Tfiles_l + '/opd1_2runs_2mods/prophet/interact-opd1_mods.xml'
+      @obj = Proph::PepSummary.new(file) 
     end
-    if (c1.size == c2.size) && (c1.size == 0)
-      true
-    else
-      false
+
+    it 'has peps of class Proph::PepSummary::Pep' do
+      @obj.peps.first.class.to_s.should == 'Proph::PepSummary::Pep'
+      @obj.peps.size.should == 1643
     end
-  end
 
-  def Xtest_arithmetic_avg_scan_by_parent_time
-    i1 = 100015.0
-    i2 = 30000.0
-    i3 = 100.0
-    t1 = 0.13
-    t2 = 0.23
-    t3 = 0.33
-    p1 = MS::Scan.new(1,1, t1)
-    p2 = MS::Scan.new(2,1, t2)
-    p3 = MS::Scan.new(3,1, t3)
-    s1 = MS::Scan.new(1,2,0.10, 300.2, i1, p1)
-    s2 = MS::Scan.new(2,2,0.20, 301.1, i2, p2)
-    s3 = MS::Scan.new(3,2,0.30, 302.0, i3, p3)
-    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|
-      if k == :prec_mz  # not sure why this is bugging out, but..
-        assert_equal(v.to_s, scan.send(k).to_s)
-      else
-        assert_equal(v, scan.send(k))
-      end
+    it 'contains peps that respond_to :aaseq' do
+      @obj.peps.first.should respond_to(:aaseq)
     end
 
+    it 'has prots (also callable from peps)' do
+      (@obj.prots.size > 0).should be_true
+      @obj.peps.all? {|v| v.prots.size > 0 }.should be_true 
+      peps_with_prots = @obj.peps.select {|v| v.prots.size > 1 }
+      # frozen:
+      peps_with_prots.first.prots.size.should == 3
+      peps_with_prots.first.prots.first.name.should == "gi|16128676|ref|NP_415229.1|"
+      peps_with_prots.first.prots.first.protein_descr.should == "RhsC protein in RhsC element [Escherichia coli K12]"
+      peps_with_prots.first.prots.first.reference.should == "gi|16128676|ref|NP_415229.1| RhsC protein in RhsC element [Escherichia coli K12]"
+      peps_with_prots.first.prots.last.protein_descr.should == "RhsA protein in RhsA element [Escherichia coli K12]"
+    end
   end
-
-
 end
 
-=end

data/specs/spec_id/protein_summary_spec.rb

@@ -18,7 +18,7 @@ xdescribe ProteinSummary do
   spec_large do
     it 'does basic summary on prophet file' do
       runit "-c 5.0 #{@tf_proph}"
-      @tf_summary.should exist
+      @tf_summary.exist_as_a_file?.should be_true
       string = IO.read(@tf_summary)
       string.should =~ /gi\|16132176\|ref\|NP_418775\.1\|/
       string.should =~ /16132176/
@@ -28,7 +28,7 @@ xdescribe ProteinSummary do
 
   it 'does basic summary on bioworks.xml file' do
     runit "#{@tf_bioworks_small}"
-    @tf_bioworks_small_summary_html.should exist
+    @tf_bioworks_small_summary_html.exist_as_a_file?.should be_true
     File.unlink @tf_bioworks_small_summary_html unless @no_delete
     # @TODO: need to freeze the output here
   end
@@ -40,7 +40,7 @@ xdescribe ProteinSummary do
     runit "#{@tf_bioworks_small} --precision"
     IO.read(@tf_bioworks_small_summary_html).should =~ /# hits.*106/m
     # should add more tests here...
-    @tf_bioworks_small_summary_html.should exist
+    @tf_bioworks_small_summary_html.exist_as_a_file?.should be_true
     File.unlink @tf_bioworks_small_summary_html unless @no_delete
   end
 
@@ -59,7 +59,7 @@ xdescribe ProteinSummary do
   spec_large do
     it 'gives correct peptide counts' do
       runit "-c 5.0 #{@tf_proph} --peptide_count #{@tf_peptide_count}"
-      @tf_peptide_count.should exist
+      @tf_peptide_count.exist_as_a_file?.should be_true
       file = IO.read(@tf_peptide_count)
       file.should include("gi|16132176|ref|NP_418775.1|\t2")
       file.should include("gi|16131996|ref|NP_418595.1|\t1")

data/specs/spec_id/sequest/pepxml_spec.rb

@@ -8,84 +8,6 @@ require 'spec_id/sequest/pepxml'
 
 NODELETE = false
 
-describe Sequest::PepXML::SearchHit, 'making enzyme calculations on sequences' do
-
-  before(:each) do
-    @tf_params_fullKRP = Tfiles + "/bioworks32.params"
-    # The enzyme is: 1 KR P
-    @tf_params_justKR = Tfiles + "/bioworks33.params"
-  end
-
-  it 'calculates the number of tolerant termini' do
-    exp = [{
-      # full KR/P
-      'K.EPTIDR.E' => 2,
-      'K.PEPTIDR.E' => 1,
-      'F.EEPTIDR.E' => 1,
-      'F.PEPTIDW.R' => 0,
-    },
-    {
-      # just KR
-      'K.EPTIDR.E' => 2,
-      'K.PEPTIDR.E' => 2,
-      'F.EEPTIDR.E' => 1,
-      'F.PEPTIDW.R' => 0,
-    }
-    ]
-    scall = Sequest::PepXML::SearchHit
-    sym = :calc_num_tol_term
-    params_ar = [Sequest::Params.new(@tf_params_fullKRP), Sequest::Params.new(@tf_params_justKR)]
-    params_ar.zip(exp) do |params,hash|
-      hash.each do |seq, val|
-        scall.send(sym, params, seq).should == val
-      end
-    end
-  end
-
-  it 'calculates number of missed cleavages' do
-    exp = [{
-    "K.EPTIDR.E" => 0,
-    "K.PEPTIDR.E" => 0,
-    "F.EEPTIDR.E" => 0,
-    "F.PEPTIDW.R" => 0,
-    "F.PERPTIDW.R" => 0,
-    "F.PEPKPTIDW.R" => 0,
-    "F.PEPKTIDW.R" => 1,
-    "K.RTTIDR.E" => 1,
-    "K.RTTIKK.E" => 2,
-    "F.PKEPRTIDW.R" => 2,
-    "F.PKEPRTIDKP.R" => 2,
-    "F.PKEPRAALKPEERPTIDKW.R" => 3,
-    },
-    {
-    "K.EPTIDR.E" => 0,
-    "K.PEPTIDR.E" => 0,
-    "F.EEPTIDR.E" => 0,
-    "F.PEPTIDW.R" => 0,
-    "F.PERPTIDW.R" => 1,
-    "F.PEPKPTIDW.R" => 1,
-    "F.PEPKTIDW.R" => 1,
-    "K.RTTIDR.E" => 1,
-    "K.RTTIKK.E" => 2,
-    "F.PKEPRTIDW.R" => 2,
-    "F.PKEPRTIDKP.R" => 3,
-    "F.PKEPRAALKPEERPTIDKW.R" => 5,
-    }
-    ]
-
-    params_ar = [Sequest::Params.new(@tf_params_fullKRP), Sequest::Params.new(@tf_params_justKR)] 
-    scall = Sequest::PepXML::SearchHit
-    sym = :calc_num_missed_cleavages
-    #params_ar[1] = params_ar[0]
-    params_ar.zip(exp) do |params, hash|
-      hash.each do |seq, val|
-        scall.send(sym, params, seq).should == val
-      end
-    end
-  end
-
-end
-
 describe Sequest::PepXML, " created from small bioworks.xml" do
 
   spec_large do
@@ -423,7 +345,7 @@ describe 'bioworks file with modifications transformed into pepxml' do
 
     it 'gets modifications right in real run' do
       @out_files.each do |fn|
-        fn.should exist
+        fn.exist_as_a_file?.should be_true
         beginning = IO.read(fn) 
         lines = beginning.split("\n")
         [