ms-sequest 0.0.11 → 0.0.12

data/spec/ms/sequest/srf/sqt_spec.rb

@@ -0,0 +1,142 @@
+require File.expand_path( File.dirname(__FILE__) + '/../../../spec_helper' )
+
+require 'ms/sequest/srf'
+require 'ms/sequest/srf/sqt'
+
+SpecHelperHeaderHash = {
+  'SQTGenerator' => 'mspire: ms-sequest',
+  'SQTGeneratorVersion' => String,
+  'Database' => 'C:\\Xcalibur\\database\\ecoli_K12_ncbi_20060321.fasta',
+  'FragmentMasses' => 'AVG',
+  'PrecursorMasses' => 'AVG',
+  'StartTime' => nil, 
+  'Alg-MSModel' => 'LCQ Deca XP',
+  'Alg-PreMassUnits' => 'amu',
+  'DBLocusCount' => '4237',
+  'Alg-FragMassTol' => '1.0000',
+  'Alg-PreMassTol' => '1.4000',
+  'Alg-IonSeries' => '0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0',
+  'Alg-Enzyme' => 'Trypsin(KR/P) (2)',
+  'Comment' => ['Created from Bioworks .srf file'],
+  'DynamicMod' => ['STY*=+79.97990', 'M#=+14.02660'],
+}
+
+ExpasyStaticMods = ['C=160.1901','Cterm=10.1230','E=161.4455']
+MoleculesStaticMods = ["C=160.1942", "Cterm=10.1230", "E=161.44398"]
+SpecHelperHeaderHash['StaticMod'] = MoleculesStaticMods 
+
+
+  SpecHelperOtherLines =<<END
+S	2	2	1	0.0	VELA	391.04541015625	3021.5419921875	0.0	0
+S	3	3	1	0.0	VELA	446.009033203125	1743.96911621094	0.0	122
+M	1	1	445.5769264522	0.0	0.245620265603065	16.6666660308838	1	6	R.SNSK.S	U
+L	gi|16128266|ref|NP_414815.1|
+END
+
+SpecHelperOtherLinesEnd =<<END
+L	gi|90111093|ref|NP_414704.4|
+M	10	17	1298.5350544522	0.235343858599663	0.823222815990448	151.717300415039	12	54	K.LQKIITNSY*K	U
+L	gi|90111124|ref|NP_414904.2|
+END
+
+describe 'converting a large srf to sqt' do
+
+  @file = Ms::TESTDATA + '/sequest/opd1_static_diff_mods/000.srf'
+  @output = Ms::TESTDATA + '/sequest/opd1_static_diff_mods/000.sqt.tmp'
+  @srf = Ms::Sequest::Srf.new(@file)
+  @original_db_filename = @srf.header.db_filename
+
+  def del(file)
+    if File.exist?(file)
+      File.unlink(file)
+    end
+  end
+
+  # returns true or false
+  def header_hash_match(header_lines, hash)
+    header_lines.all? do |line|
+      (h, k, v) = line.chomp.split("\t")
+      if hash[k].is_a? Array
+        if hash[k].include?(v) 
+          true
+        else
+          puts "FAILED: "
+          p k
+          p v
+          p hash[k]
+          false
+        end
+      elsif hash[k] == String
+        v.is_a?(String)
+      else
+        if v == hash[k]
+          true
+        else
+          puts "FAILED: "
+          p k
+          p v
+          p hash[k]
+          false
+        end
+      end
+    end
+  end
+
+  it 'converts without bothering with the database' do
+    @srf.to_sqt(@output)
+    ok File.exist?(@output)
+    lines = File.readlines(@output)
+    lines.size.is 80910
+    header_lines = lines.grep(/^H/)
+    ok(header_lines.size > 10)
+    ok header_hash_match(header_lines, SpecHelperHeaderHash)
+    other_lines = lines.grep(/^[^H]/)
+    other_lines[0,4].join('').is SpecHelperOtherLines
+    other_lines[-3,3].join('').is SpecHelperOtherLinesEnd
+    del(@output)
+  end
+
+  it 'warns if the db path is incorrect and we want to update db info' do
+    # requires some knowledge of how the database file is extracted
+    # internally
+    wacky_path = '/not/a/real/path/wacky.fasta'
+    @srf.header.db_filename = wacky_path
+    my_error_string = ''
+    StringIO.open(my_error_string, 'w') do |strio|
+      $stderr = strio
+      @srf.to_sqt(@output, :db_info => true)
+    end
+    ok my_error_string.include?(wacky_path)
+    @srf.header.db_filename = @original_db_filename
+    $stderr = STDERR
+    ok File.exists?(@output)
+    IO.readlines(@output).size.is 80910
+    del(@output)
+  end
+  it 'can get db info with correct path' do
+    @srf.to_sqt(@output, :db_info => true, :new_db_path => Ms::TESTDATA + '/sequest/opd1_2runs_2mods/sequest33')
+    ok File.exist?(@output)
+    lines = IO.readlines(@output)
+    has_md5 = lines.any? do |line|
+      line =~ /DBMD5Sum\s+202b1d95e91f2da30191174a7f13a04e/
+    end
+    ok has_md5
+
+    has_seq_len = lines.any? do |line|
+      # frozen
+      line =~ /DBSeqLength\s+1342842/
+    end
+    ok has_seq_len
+    lines.size.is 80912
+    del(@output)
+  end
+  it 'can update the Database' do
+    @srf.to_sqt(@output, :new_db_path => Ms::TESTDATA + '/sequest/opd1_2runs_2mods/sequest33', :update_db_path => true)
+    regexp = Regexp.new("Database\t/.*/opd1_2runs_2mods/sequest33/ecoli_K12_ncbi_20060321.fasta")
+    updated_db = IO.readlines(@output).any? do |line|
+      line =~ regexp
+    end
+    ok updated_db
+    del(@output)
+  end
+end

data/spec/ms/sequest/srf_spec.rb

@@ -0,0 +1,182 @@
+require File.expand_path( File.dirname(__FILE__) + '/../../spec_helper' )
+require File.expand_path( File.dirname(__FILE__) + '/srf_spec_helper' )
+
+require 'ms/sequest/srf'
+
+require 'fileutils'
+
+include SRFHelper
+
+class Hash
+  def object_match(obj)
+    self.all? do |k,v|
+      k = k.to_sym
+      retval = 
+        if k == :peaks or k == :hits or k == :prots
+          obj.send(k).size == v
+        elsif v.class == Float
+          delta = 
+            if k == :ppm ; 0.0001          
+            else ; 0.0000001          
+            end
+          (v - obj.send(k)).abs <= delta
+        else
+          obj.send(k) == v
+        end
+      if retval == false
+        puts "BAD KEY: #{k}"
+        puts "need: #{v}"
+        puts "got: #{obj.send(k)}"
+      end
+      retval
+    end
+  end
+end
+
+
+shared 'an srf reader' do
+
+  it 'retrieves correct header info' do
+    ok @header.object_match(@srf_obj.header)
+    ok @dta_gen.object_match(@srf_obj.header.dta_gen)
+  end
+
+  # a few more dta params could be added in here:
+  it 'retrieves correct dta files' do
+    ok @dta_files_first.object_match(@srf_obj.dta_files.first)
+    ok @dta_files_last.object_match(@srf_obj.dta_files.last)
+  end
+
+  # given an array of out_file objects, returns the first set of hits
+  def get_first_peps(out_files)
+    out_files.each do |outf|
+      if outf.num_hits > 0
+        return outf.hits
+      end
+    end
+    return nil
+  end
+
+  it 'retrieves correct out files' do
+    ok @out_files_first.object_match(@srf_obj.out_files.first)
+    ok @out_files_last.object_match(@srf_obj.out_files.last)
+    # first available peptide hit
+    ok @out_files_first_pep.object_match(get_first_peps(@srf_obj.out_files).first)
+    # last available peptide hit
+    ok @out_files_last_pep.object_match(get_first_peps(@srf_obj.out_files.reverse).last)
+  end
+
+  it 'retrieves correct params' do
+    ok @params.object_match(@srf_obj.params)
+  end
+
+  # TODO:
+  #it_should 'retrieve probabilities if available'
+end
+
+# TODO:, we should try to get some tests with sf values present!
+
+
+Expected_hash_keys = %w(header dta_gen dta_files_first dta_files_last out_files_first out_files_last out_files_first_pep out_files_last_pep params)
+
+To_run = {
+  '3.2' => {:hash => File_32, :file => '/opd1_2runs_2mods/sequest32/020.srf'},
+  '3.3' => {:hash => File_33, :file => '/opd1_2runs_2mods/sequest33/020.srf'},
+  '3.3.1' => {:hash => File_331, :file => '/opd1_2runs_2mods/sequest331/020.srf'},
+}
+
+# I had these nicely combined under RSpec, but this is not as obvious a task
+# under minispec given the corrupted include behavior...
+
+describe 'reading srf with duplicate refs v3.2' do
+
+  info = To_run['3.2']
+  @file = Ms::TESTDATA + '/sequest' + info[:file]
+  @srf_obj = Ms::Sequest::Srf.new(@file)
+  Expected_hash_keys.each do |c|
+    instance_variable_set("@#{c}", info[:hash][c.to_sym])
+  end
+
+  behaves_like 'an srf reader'
+end
+
+describe 'reading srf with duplicate refs v3.3' do
+  info = To_run['3.3']
+  @file = Ms::TESTDATA + '/sequest' + info[:file]
+  @srf_obj = Ms::Sequest::Srf.new(@file)
+  Expected_hash_keys.each do |c|
+    instance_variable_set("@#{c}", info[:hash][c.to_sym])
+  end
+
+  behaves_like 'an srf reader'
+end
+
+describe 'reading srf with duplicate refs v3.3.1' do
+  info = To_run['3.3.1']
+  @file = Ms::TESTDATA + '/sequest' + info[:file]
+  @srf_obj = Ms::Sequest::Srf.new(@file)
+  Expected_hash_keys.each do |c|
+    instance_variable_set("@#{c}", info[:hash][c.to_sym])
+  end
+  behaves_like 'an srf reader'
+end
+
+#class SRFReadingACorruptedFile < MiniTest::Spec
+
+#  it 'reads a file from an aborted run w/o failing, but gives warning msg' do
+#    srf_file = TESTFILES + '/corrupted_900.srf'
+#    message = capture_stderr do
+#      srf_obj = Ms::Sequest::Srf.new(srf_file) 
+#      srf_obj.base_name.is '900'
+#      srf_obj.params.is nil
+#      header = srf_obj.header
+#      header.db_filename.is "C:\\Xcalibur\\database\\sf_hs_44_36f_longesttrpt.fasta.hdr"
+#      header.enzyme.is 'Enzyme:Trypsin(KR) (2)'
+#      dta_gen = header.dta_gen
+#      dta_gen.start_time.must_be_close_to(1.39999997615814, 0.00000000001)
+#      srf_obj.dta_files.is []
+#      srf_obj.out_files.is []
+#    end
+#    message.must_match(/no SEQUEST/i)
+#  end
+#end
+
+#class SRFGroupCreatingAnSrg < MiniTest::Spec
+  #it 'creates one given some non-existing, relative filenames' do 
+    ### TEST SRG GROUPING:
+    #filenames = %w(my/lucky/filename /another/filename)
+    #@srg = SRFGroup.new
+    #@srg.filenames = filenames
+    #srg_file = TESTFILES + '/tmp_srg_file.srg'
+    #begin
+      #@srg.to_srg(srg_file)
+      #ok File.exist?(srg_file)
+    #ensure
+      #File.unlink(srg_file)
+    #end
+  #end
+#end
+
+
+## @TODO: this test needs to be created for a small mock dataset!!
+#describe SRF, 'creating dta files' do
+  #spec_large do 
+    #before(:all) do
+      #file = Tfiles_l + '/opd1_2runs_2mods/sequest33/020.srf'
+      #@srf = SRF.new(file)
+    #end
+
+    #it 'creates dta files' do
+      #@srf.to_dta
+      #ok File.exist?('020')
+      #ok File.directory?('020')
+      #ok File.exist?('020/020.3366.3366.2.dta')
+      #lines = IO.readlines('020/020.3366.3366.2.dta', "\r\n")
+      #lines.first.is "1113.106493 2\r\n"
+      #lines[1].is "164.5659 4817\r\n"
+      
+      #FileUtils.rm_rf '020'
+    #end
+  #end
+
+#end

data/spec/ms/sequest/srf_spec_helper.rb

@@ -0,0 +1,172 @@
+
+class Hash
+  def dup_hash
+    new_hash = {}
+    self.each do |k,v|
+      new_val = if v.is_a?(Fixnum) || v.is_a?(Symbol) ||v.is_a?(Float)
+                  v
+                else
+                  v.dup
+                end
+      new_hash[k] = new_val
+    end
+    new_hash
+  end
+end
+
+
+
+module SRFHelper
+
+  
+  File_32 = {
+    :header => 
+    {
+      :params_filename=>"C:\\Xcalibur\\sequest\\john\\opd1_2runs_2mods\\ecoli.params",
+      :raw_filename=>"C:\\Xcalibur\\data\\john\\opd00001\\020.RAW", 
+      :modifications=>"(M* +15.99940) (STY# +79.97990)",
+      :sequest_log_filename=>"C:\\Xcalibur\\sequest\\john\\opd1_2runs_2mods\\020_sequest.log",
+      :ion_series=>"ion series nABY ABCDVWXYZ: 0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0",
+      :db_filename=>"C:\\Xcalibur\\database\\ecoli_K12_ncbi_20060321.fasta",
+      :enzyme=>"Enzyme:Trypsin(KR/P) (2)",
+      :version=>"3.2",
+      :model=>"LCQ Deca XP",
+      :dta_log_filename=>"C:\\Xcalibur\\sequest\\john\\opd1_2runs_2mods\\020_dta.log"
+    },
+    :dta_gen => {
+      :min_group_count => 1,
+      :start_time => 1.5,
+      :start_mass => 300.0,
+      :end_scan => 3620,
+      :group_scan => 1,
+      :start_scan => 1,
+      :num_dta_files => 3747,
+      :min_ion_threshold => 15,
+      :end_mass => 4500.0,
+    },
+    :dta_files_first => {
+
+      :mh=>390.92919921875,
+      :dta_tic=>9041311.0,
+      :num_peaks=>48,
+      :charge=>1,
+      :ms_level=>2,
+      :total_num_possible_charge_states=>0,
+    },
+    :dta_files_last => {
+      :dta_tic=>842424.0,
+      :mh=>357.041198730469,
+      :num_peaks=>78,
+      :ms_level=>2,
+      :charge=>1,
+      :total_num_possible_charge_states=>0,
+    },
+    :out_files_first => {
+      :num_hits => 0,
+      :computer => 'VELA',
+      :date_time => '05/06/2008, 02:08 PM,',
+      :hits => 0,
+    },
+    :out_files_last => {
+      :num_hits => 0,
+      :computer => 'VELA',
+      :date_time => '05/06/2008, 02:11 PM,',
+      :hits => 0,
+    },
+    :out_files_first_pep => {
+      :aaseq=>"YRLGGSTK",
+      :sequence=>"R.Y#RLGGS#T#K.K",
+      :mh=>1121.9390244522,
+      :deltacn_orig=>0.0,
+      :sp=>29.8529319763184,
+      :sf=>0.0,
+      :xcorr=>0.123464643955231,
+      :id=>2104,
+      :rsp=>1,
+      :ions_matched=>5,
+      :ions_total=>35,
+      :prots=>1,
+      :deltamass=>-0.00579976654989878,
+      :ppm=>5.16938660859491,
+      :base_name=>"020",
+      :first_scan=>3,
+      :last_scan=>3,
+      :charge=>1,
+      :deltacn=>0.795928299427032,
+      :base_name=>"020",
+    },
+    :out_files_last_pep => 
+    {
+      :aaseq=>"LLPGTARTMRR",
+      :sequence=>"R.LLPGTARTMRR.M",
+      :mh=>1272.5493424522,
+      :deltacn_orig=>0.835508584976196,
+      :deltacn=>1.1,
+      :sp=>57.9885787963867,
+      :sf=>0.0,
+      :xcorr=>0.109200321137905,
+      :id=>1361,
+      :rsp=>11,
+      :ions_matched=>6,
+      :ions_total=>40,
+      :prots=>1,
+      :deltamass=>0.00243330985608736,
+      :ppm=>1.91215729542523,
+      :base_name=>"020",
+      :first_scan=>3619,
+      :last_scan=>3619,
+      :charge=>3,
+      :deltacn=>1.1,
+      :base_name=>"020",
+    },
+
+    :params => {
+        "add_O_Ornithine"=>"0.0000", "add_F_Phenylalanine"=>"0.0000", "add_A_Alanine"=>"0.0000", "add_C_Cysteine"=>"0.0000", "add_Y_Tyrosine"=>"0.0000", "add_X_LorI"=>"0.0000", "add_J_user_amino_acid"=>"0.0000", "add_Cterm_peptide"=>"0.0000", "add_S_Serine"=>"0.0000", "add_Nterm_protein"=>"0.0000", "add_D_Aspartic_Acid"=>"0.0000", "add_Q_Glutamine"=>"0.0000", "add_K_Lysine"=>"0.0000", "add_R_Arginine"=>"0.0000", "add_W_Tryptophan"=>"0.0000", "add_Nterm_peptide"=>"0.0000", "add_H_Histidine"=>"0.0000", "add_L_Leucine"=>"0.0000", "add_I_Isoleucine"=>"0.0000", "add_N_Asparagine"=>"0.0000", "add_B_avg_NandD"=>"0.0000", "add_Z_avg_QandE"=>"0.0000", "add_E_Glutamic_Acid"=>"0.0000", "add_G_Glycine"=>"0.0000", "add_P_Proline"=>"0.0000", "add_M_Methionine"=>"0.0000", "add_Cterm_protein"=>"0.0000", "add_V_Valine"=>"0.0000", "add_T_Threonine"=>"0.0000", "add_U_user_amino_acid"=>"0.0000", "match_peak_tolerance"=>"1.0000", "match_peak_allowed_error"=>"1", "normalize_xcorr"=>"0", "nucleotide_reading_frame"=>"0", "num_results"=>"250", "sequence_header_filter"=>"", "diff_search_options"=>"15.999400 M 79.979900 STY 0.000000 M 0.000000 X 0.000000 T 0.000000 Y", "partial_sequence"=>"", "max_num_internal_cleavage_sites"=>"2", "search_engine"=>"SEQUEST", "print_duplicate_references"=>"40", "ion_series"=>"0 1 1 0.0 1.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0", "remove_precursor_peak"=>"0", "num_output_lines"=>"10", "second_database_name"=>"", "first_database_name"=>"C:\\Xcalibur\\database\\ecoli_K12_ncbi_20060321.fasta", "peptide_mass_tolerance"=>"25.0000", "digest_mass_range"=>"600.0 3500.0", "enzyme_info"=>"Trypsin(KR/P) 1 1 KR P", "show_fragment_ions"=>"0", "protein_mass_filter"=>"0 0", "term_diff_search_options"=>"0.000000 0.000000", "num_description_lines"=>"5", "fragment_ion_tolerance"=>"1.0000", "peptide_mass_units"=>"2", "mass_type_parent"=>"0", "match_peak_count"=>"0", "max_num_differential_per_peptide"=>"3", "ion_cutoff_percentage"=>"0.0000", "mass_type_fragment"=>"0"
+    }
+  }
+
+  File_33 = {}
+  File_32.each do |k,v|
+    File_33[k] = v.dup_hash
+  end
+
+  ## Bioworks 3.3 (srf version 3.3)
+  File_33[:header][:raw_filename] = "C:\\Xcalibur\\data\\john\\021112-EcoliSol37-1\\020.RAW"
+  File_33[:header][:version] = "3.3"
+
+  File_33[:out_files_first][:computer] = 'TESLA'
+  File_33[:out_files_first][:date_time] = '04/24/2007, 10:41 AM,'
+  File_33[:out_files_last][:computer] = 'TESLA'
+  File_33[:out_files_last][:date_time] = '04/24/2007, 10:42 AM,'
+
+  File_33[:out_files_first_pep][:sp] = 29.8535556793213
+  File_33[:out_files_last_pep][:sp] = 57.987476348877
+  File_33[:out_files_first_pep][:sf] = 0.0
+  File_33[:out_files_last_pep][:sf] = 0.0
+  File_33[:out_files_last_pep][:rsp] = 10
+  File_33[:out_files_last_pep][:deltacn_orig] = 0.835624694824219
+
+
+  ## Bioworks 3.3.1 (srf version 3.5)
+  File_331 = {}
+
+
+  File_33.each do |k,v|
+    File_331[k] = v.dup_hash
+  end
+
+  File_331[:params] = File_33[:params].dup_hash
+
+  adjust_keys = File_331[:params].keys.select {|k| k =~ /^add/ }.push(*%w(ion_cutoff_percentage peptide_mass_tolerance match_peak_tolerance fragment_ion_tolerance) )
+  adjust_keys.each do |key|
+    File_331[:params][key] = File_331[:params][key] << "0"
+  end
+
+  File_331[:header][:raw_filename] = "C:\\Xcalibur\\data\\john\\opd1_2runs_2mods\\020.RAW"
+  File_331[:header][:version] = "3.5"
+  File_331[:out_files_first][:date_time] = '05/06/2008, 03:31 PM,'
+  File_331[:out_files_last][:date_time] = '05/06/2008, 03:32 PM,'
+
+end
+
+