mspire 0.4.9 → 0.5.0

data/specs/spec_helper.rb

@@ -1,135 +0,0 @@
-gem 'rspec'
-
-
-# a global flag that lets me know what format we're dealing with for output
-$specdoc = false
-## 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 {
-  ROOT_DIR = File.dirname(__FILE__) + '/..'
-  SPEC_DIR = File.dirname(__FILE__)
-
-  Tfiles = File.dirname(__FILE__) + '/../test_files'
-  Tfiles_l = File.dirname(__FILE__) + '/../test_files_large'
-  Tfiles_large = Tfiles_l
-#}
-
-# this variable is for large files!
-if ENV['SPEC_LARGE']
-  $spec_large = true
-else
-  #[NOTE: NOT testing with large test files]"
-  # ** run with env var: SPEC_LARGE and ensure tfiles_large dir"
-  $spec_large = false
-end
-
-def spec_large(&block)
-  if $spec_large
-    block.call
-  else
-    # Requires SPEC_LARGE=true and tfiles_large dir for testing large test files
-    it 'SKIPPING (not testing large files)' do
-    end
-  end
-end
-
-# returns all output to stdout as a string
-# will respond to is_a? File -> false is_a? IO true even though it is really a
-# file
-def capture_stdout(&block)
-  capture_file = Tfiles + '/capture_stdout.tmp'
-  def capture_file.is_a?(klass)
-    case klass.to_s
-    when 'IO'
-      true
-    when 'File'
-      false
-    else
-      false
-    end
-  end
-  $stdout = File.open(capture_file, 'w')
-  block.call
-  $stdout.close
-  $stdout = STDOUT
-  string = IO.read(capture_file)
-  File.unlink capture_file
-  string
-end
-
-require 'ostruct'
-# class for using a ruby-ish initializer
-class MyOpenStruct < OpenStruct
-  def initialize(*args) 
-    super(*args)
-    if block_given?
-      yield(self)
-    end
-  end
-end
-
-
-def xdescribe(*args)
-  puts "describe: #{args.join(' ')}"
-  puts "**SKIPPING**"
-end
-
-def Xdescribe(*args)
-  xdescribe(*args)
-end
-
-def xit(*args)
-  puts "\n- SKIPPING: #{args.join(' ')}"
-end
-
-def it_should(*args)
-  string = "- WRITE TEST: #{args.join(' ')}"
-  if $specdoc
-    puts(string)
-  else
-    puts("\n" + string)
-  end
-end
-
-def silent(&block)
-  tmp = $VERBOSE ; $VERBOSE = nil
-  block.call
-  $VERBOSE = tmp
-end
-
-
-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_as_a_file?
-    File.exist? self
-  end
-end
-
-describe "a cmdline program", :shared => true do
-  before(:all) do
-    testdir = File.dirname(__FILE__)
-    libdir = testdir + '/../lib'
-    bindir = testdir +  '/../bin'
-    @cmd = "ruby -I #{libdir} #{bindir}/#{@progname} "
-  end
-
-  it 'gives usage when called with no args' do
-    reply = `#{@cmd}`
-    reply.should =~ /usage/i
-  end
-
-end

data/specs/spec_id/aa_freqs_spec.rb

@@ -1,52 +0,0 @@
-require File.expand_path( File.dirname(__FILE__) + '/../spec_helper'
 )
-require 'spec_id/aa_freqs'
-
-
-
-describe SpecID::AAFreqs, "given a small fasta file" do
-  before(:all) do
-    @sf = Tfiles + "/small.fasta"
-    @fobj = Fasta.new(@sf)
-    @obj = SpecID::AAFreqs.new(@fobj)
-  end
-
-  it 'calculates AA freqs properly' do
-    expect = {:I=>0.0628918621937819, :S=>0.0539719475147049, :D=>0.0526145691939758, :Z=>0.0, :L=>0.102772929998061, :T=>0.0491888048607071, :E=>0.0609527503070261, :O=>0.0, :C=>0.0157714433456144, :K=>0.0471850559110594, :U=>0.0, :Q=>0.0382651412319824, :W=>0.0137030573330748, :A=>0.101997285243359, :M=>0.0294745006786892, :J=>0.0, :G=>0.0811195139292871, :Y=>0.0254670027793937, :X=>0.0, :F=>0.0418201796910348, :R=>0.0546829552065154, :V=>0.0702604873634542, :H=>0.0213302307543145, :B=>0.0, :N=>0.03471010277293, :P=>0.0418201796910348}
-    aaf =  @obj.aafreqs
-    expect.each do |k,v|
-      #aaf.key?(k).should be_true
-      aaf.should have_key(k)
-      aaf[k].should be_close(v, 0.00000001)
-    end
-    sum = 0.0
-    aaf.values.each do |v|
-      sum += v
-    end
-    sum.should be_close(1.0, 0.0000000000001)
-  end
-
-  it 'gets actual and expected nums for at least 1 amino acid' do
-    peptide_aaseqs = @fobj.prots.map do |prot|
-      prot.aaseq[0..12]
-    end
-    peptide_aaseqs.size.should == 50
-    (ac,ex) = @obj.actual_and_expected_number(peptide_aaseqs, :C, 1)
-    ac.should == 9
-    ex.should be_close(9.33530631238985, 0.0000000001)
-  end
-end
-
-describe SpecID::AAFreqs, "with class methods" do
-  it 'creates a probability of length lookup table' do
-    expecting = [0.0, 0.01, 0.0199, 0.029701, 0.0394039900000001]
-    SpecID::AAFreqs.probability_of_length_table(0.01, 4).zip(expecting) do |answ, exp|
-      answ.should be_close(exp, 0.0000000001)
-    end
-    expecting = [0.0, 0.2, 0.36, 0.488, 0.5904]
-    SpecID::AAFreqs.probability_of_length_table(0.2, 4).zip(expecting) do |answ, exp|
-      answ.should be_close(exp, 0.0000000001)
-    end
-  end
-end
-
-

data/specs/spec_id/bioworks_spec.rb

@@ -1,148 +0,0 @@
-require File.expand_path( File.dirname(__FILE__) + '/../spec_helper' )
-
-require 'spec_id'
-require 'spec_id/bioworks'
-#require 'benchmark'
-
-describe Bioworks, 'set from an xml file' do
-  # NEED TO DEBUG THIS PROB!
-  it 'can set one with labeled proteins' do
-    file = Tfiles + "/bioworks_with_INV_small.xml"
-    obj = Bioworks.new(file)
-    obj.prots.size.should == 19
-    file = Tfiles + '/bioworks_small.xml'
-    obj = Bioworks.new(file)
-    obj.prots.size.should == 106
-  end
-
-  it 'can parse an xml file NOT derived from multi-concensus' do
-    tf_bioworks_single_xml_small = Tfiles + '/bioworks_single_run_small.xml'
-    obj = Bioworks.new(tf_bioworks_single_xml_small)
-    gfn = '5prot_mix_michrom_20fmol_200pmol'
-    origfilename = '5prot_mix_michrom_20fmol_200pmol.RAW'
-    origfilepath = 'C:\Xcalibur\sequest'
-    obj.global_filename.should == gfn
-    obj.origfilename.should == origfilename
-    obj.origfilepath.should == origfilepath
-    obj.prots.size.should == 7
-    obj.prots.first.peps.first.base_name.should ==  gfn
-    obj.prots.first.peps.first.file.should ==  "152"
-    obj.prots.first.peps.first.charge.should == 2
-    # @TODO: add more tests here
-  end
-
-  it 'can output in excel format (**semi-verified right now)' do
-    tf_bioworks_to_excel = Tfiles + '/tf_bioworks2excel.bioXML'
-    tf_bioworks_to_excel_actual = Tfiles + '/tf_bioworks2excel.txt.actual'
-    tmpfile = Tfiles + "/tf_bioworks_to_excel.tmp"
-    bio = Bioworks.new(tf_bioworks_to_excel)
-    bio.to_excel(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|
-      break if i == 23 ## this is where the ordering becomes arbitrary between guys with the same scans, but different filenames
-      _assert_equal_pieces(exp[i], act[i], exp[i][0] =~ /\d/)
-    end
-
-    File.unlink tmpfile
-  end
-
-  # prot is boolean if this is a protein line!
-  def _assert_equal_pieces(exp, act, prot)
-    # equal as floats (by delta)
-    exp.each_index do |i|
-      if i == 5  # both prots and peps
-        act[i].to_f.should be_close(exp[i].to_f, 0.1)
-      elsif i == 3 && !prot
-        act[i].to_f.should be_close(exp[i].to_f, 0.01)
-      elsif i == 6 && !prot
-        act[i].to_f.should be_close(exp[i].to_f, 0.01)
-      elsif i == 9 && prot
-        ## NEED TO GET THESE BACK (for consistency):
-        #act[i].split(" ")[0].should =~ exp[i].split(" ")[0]
-      else
-        ## NEED TO GET THESE BACK (for consistency):
-        #act[i].should == exp[i]
-      end
-    end
-  end
-
-  # takes a bioworks excel (in txt format) and outputs an arr of arrs
-  def _arr_of_arrs(file)
-    IO.readlines(file).collect do |line|
-      line.chomp!
-      line.split("\t")
-    end
-  end
-
-  it 'can return unique peptides and proteins by sequence+charge (private)' do
-    cnt = 0
-    answer = [%w(2 PEPTIDE), %w(3 PEPTIDE), %w(3 PEPY), %w(2 PEPY)]
-    exp_peps = answer.collect! do |arr|
-      pep = Bioworks::Pep.new
-      pep.charge = arr[0]
-      pep.sequence = arr[1]
-      pep
-    end
-    exp_prots = [[0,2],[1,4,5],[3],[6]].collect do |arr|
-      arr.collect do |num|
-        prot = Bioworks::Prot.new
-        prot.reference = "#{num}"
-        prot
-      end
-    end
-    exp_peps = exp_peps.zip(exp_prots)
-    exp_peps.collect! do |both|
-      both[0].prots = [both[1]]
-      both[0]
-    end
-
-    peptides = [%w(2 PEPTIDE), %w(3 PEPTIDE), %w(2 PEPTIDE), %w(3 PEPY), %w(3 PEPTIDE), %w(3 PEPTIDE), %w(2 PEPY)].collect do |arr|
-      pep = Bioworks::Pep.new
-      pep.charge = arr[0]
-      pep.sequence = arr[1]
-      pep.prots = [Bioworks::Prot.new]
-      pep.prots.first.reference = "#{cnt}"
-      cnt += 1
-      pep
-    end
-    peptides, proteins = Bioworks.new._uniq_peps_by_sequence_charge(peptides)
-    proteins.size.should == peptides.size
-    exp_peps.each_with_index do |pep, i|
-      peptides[i].charge.should == pep.charge
-      peptides[i].sequence.should == pep.sequence
-    end
-
-    exp_prots.each_index do |i|
-      exp_prots[i].each_index do |j|
-        proteins[i][j].reference.should == exp_prots[i][j].reference
-      end
-    end
-  end
-
-end
-
-describe Bioworks::Pep do
-  it 'can be initialized from a hash' do
-    hash = {:sequence => 0, :mass => 1, :deltamass => 2, :charge => 3, :xcorr => 4, :deltacn => 5, :sp => 6, :rsp => 7, :ions => 8, :count => 9, :tic => 10, :prots => 11, :base_name => 12, :first_scan => 13, :last_scan => 14, :peptide_probability => 15, :file => 16, :_num_prots => 17, :_first_prot => 18}
-    pep = Bioworks::Pep.new(hash)
-    hash.each do |k,v|
-      pep.send(k).should == v
-    end
-  end
-
-  it 'correctly extracts file information' do
-    pep = Bioworks::Pep.new
-    testing = ['005a, 1131', '005b, 1131 - 1133', '1131', '1131 - 1133']
-    answers = [%w(005a 1131 1131), %w(005b 1131 1133), [nil, '1131', '1131'], [nil, '1131', '1133']]
-    testing.zip(answers) do |ar|
-      ans = pep.class.extract_file_info(ar[0])
-      ans.join(" ").should == ar[1].join(" ") 
-    end
-  end
-
-end
-
-

data/specs/spec_id/digestor_spec.rb

@@ -1,75 +0,0 @@
-require 'set'
-
-require File.expand_path( File.dirname(__FILE__) + '/../spec_helper' )
-require 'spec_id/digestor'
-require 'spec_id/sequest/params'
-require 'fasta'
-
-
-describe 'selecting peptides based on size' do
-  before(:each) do 
-    # (M+H)+ PEPTIDE
-    # http://db.systemsbiology.net:8080/proteomicsToolkit/FragIonServlet.html
-    mono = { 
-      'AACK' => 392.19681,
-      'PEPTIDE' => 800.36783, 
-      'TTTYW' => 671.72767,
-      'AGGGGGGLKNADEEEP' => 1457.65088,
-      'IMNDR' => 648.31396
-      
-    }
-    avg = {
-      'AACK' => 392.49375,
-      'PEPTIDE' => 800.84071,
-      'TTTYW' => 671.30411,
-      'AGGGGGGLKNADEEEP' => 1458.48147,
-      'IMNDR' => 648.75518,  #  648.76,  thermo
-    }
-    @pepseqs = [%w(AACK PEPTIDE TTTYW), %w(AGGGGGGLKNADEEEP IMNDR)]
-    # basically the protein sequence ONLY matters if the peptide is n or c
-    # terminal and there is an n or c terminal modification for ONLY the
-    # protein.
-    @protseqs = %w(LLLLAACKLLLLLLLPEPTIDELLLLLLTTTYWLLL LLLLAGGGGGGLKNADEEEPLLLLLLIMNDRLLL)
-  end
-
-  it 'is sensitive to mono/avg' do
-    h_plus = false
-
-    expect = [%w(PEPTIDE TTTYW), %w(IMNDR)]
-    masses_hash = Mass::MONO
-    answ = Digestor.new.limit_sizes(@protseqs, @pepseqs, 400.0, 800.38, masses_hash, h_plus)
-    answ.to_set.should == expect.to_set
-    masses_hash = Mass::AVG
-    expect = [%w(TTTYW), %w(IMNDR)]
-    answ = Digestor.new.limit_sizes(@protseqs, @pepseqs, 400.0, 800.38, masses_hash, h_plus)
-    answ.to_set.should == expect.to_set
-  end
-
-  it 'is sensitive to static mass changes' do
-    expect_before = [%w(PEPTIDE TTTYW), %w(IMNDR)]
-    h_plus = false
-    masses_hash = Mass::MONO
-    answ = Digestor.new.limit_sizes(@protseqs, @pepseqs, 400.0, 800.38, Mass::MONO, h_plus)
-    answ.to_set.should == expect_before.to_set
-
-    static = {:C => 20.0}
-    expect_after = [%w(AACK PEPTIDE TTTYW), %w(IMNDR)]
-    masses_hash = Mass::MONO.dup
-    masses_hash[:C] = masses_hash[:C] + 20.0
-    answ = Digestor.new.limit_sizes(@protseqs, @pepseqs, 400.0, 800.38, masses_hash, h_plus)
-    #answ.to_set.should == expect_before.to_set
-    answ.to_set.should == expect_after.to_set
-  end
-
-  it 'returns peptides linked to their proteins given fasta and params' do
-    fasta_obj = Fasta.new(Tfiles + '/small.fasta')
-    params_obj = Sequest::Params.new(Tfiles + '/bioworks32.params')
-    peps = Digestor.digest(fasta_obj, params_obj)
-    peps.first.is_a?(SpecID::Pep).should be_true
-    # frozen
-    peps.size.should == 2843
-    # frozen
-    peps.select {|v| v.prots.size > 1 }.size.should == 10
-  end
-  
-end

data/specs/spec_id/precision/filter/cmdline_spec.rb

@@ -1,20 +0,0 @@
-require File.expand_path( File.dirname(__FILE__) + '/../../../spec_helper' )
-
-require 'spec_id/precision/filter'
-
-describe SpecID::Precision::Filter::CmdlineParser, 'getting all command line options correct' do
-
-  before(:all) do
-    @bioworks_file = Tfiles + '/bioworks_small.xml'
-  end
-
-  it_should 'gets all defaults correct with nothing passed in' do
-    (spec_id_obj, options, option_parser) = SpecID::Precision::Filter::CmdlineParser.new.parse([@bioworks_file])
-    p options
-  end
-
-  it_should 'gets all passed in params correct' do
-  end
-
-end
-

data/specs/spec_id/precision/filter/output_spec.rb

@@ -1,31 +0,0 @@
-require File.expand_path( File.dirname(__FILE__) + '/../../../spec_helper' )
-require 'spec_id/precision/filter'
-require 'spec_id/precision/filter/output'
-
-describe 'transforming hash with symbols into strings' do
-  it 'works' do
-    hash = {:one=>2, :this=>{:one=>"string", 3=>{:four=>5}}}
-    new_hash = SpecID::Precision::Output.symbol_keys_to_string(hash)
-    new_hash.should == {'one'=>2, 'this'=>{'one'=>"string", 3=>{'four'=>5}}}
-  end
-end
-
-describe 'outputs' do
-  before(:each) do
-    @file = Tfiles + '/bioworks_with_INV_small.xml'
-    @opts = {}
-  end
-
-  it 'makes a table' do
-    my_file = Tfiles + '/filtering_tmp.tmp'
-    File.unlink my_file if File.exist? my_file
-    @opts[:output] = [[:text_table, my_file]]
-    SpecID::Precision::Filter.new.filter_and_validate(SpecID.new(@file), @opts)  
-    #reply = capture_stdout {
-    #  SpecID::Precision::Filter.new.filter_and_validate(SpecID.new(@file), @opts)  
-    #}
-    # frozen
-    IO.read(my_file) =~ /138/
-    File.unlink my_file if File.exist? my_file
-  end
-end