mspire 0.1.5 → 0.1.7

data/test/tc_srf.rb

@@ -0,0 +1,216 @@
+
+require 'test/unit'
+require 'spec_id/srf'
+
+
+module ToMatch
+  Header = {
+    :db_filename => "C:\\Xcalibur\\database\\mixed_db_human_ecoli_7prot_unique.fasta",
+    :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",
+    :sequest_log_filename => "C:\\Xcalibur\\sequest\\john\\db_quest\\alone_new\\sash7\\7MIX_STD_110802_1_sequest.log",
+    :raw_filename => "C:\\Xcalibur\\data\\john\\sashimi7\\7MIX_STD_110802_1.RAW",
+    :enzyme => "Enzyme:Trypsin(KR/P) (2)",
+    :params_filename => "C:\\Xcalibur\\sequest\\john\\db_quest\\alone_new\\sash7\\sash7.params",
+    :modifications => "",
+    :version => "3.2",
+    :dta_log_filename => "C:\\Xcalibur\\sequest\\john\\db_quest\\alone_new\\sash7\\7MIX_STD_110802_1_dta.log",
+    :model => "LCQ Deca XP",
+  }
+  ## DTA Gen
+  Dta_gen = {
+    :group_scan => 1,
+    :start_time => 1.39999997615814,
+    :start_scan => 1,
+    :num_dta_files => 6952,
+    :min_ion_threshold => 15, 
+    :end_mass => 4500.0,
+    :min_group_count => 1,
+    :start_mass => 400.0,
+    :end_scan => 7161,
+  }
+  
+  Dta_files_first = {
+    :mh => 1221.88989257812,
+    :dta_tic => 7703132.0,
+    :num_peaks => 74,
+    :charge => 1,
+    :ms_level => 2,
+    :total_num_possible_charge_states => 0,
+    :peaks => "\346\214\271C\000p|F\340\016\335C\000D\fG\022l\335C\000\3604F\020\205\337C\000D~F\260\256\340C\000\020\347E\220\023\343C\000\220&F\020R\352C\000\244\313F\246\237\353C\000\360\032E\206\223\004D\000\204\030F\260\177\005D\000\346\220F \316\005D\000`\222F<\001\006D\000\356\217Fd\213\010D\000\336\tGr\314\vD\000\034}F\262\006\rD\000\026\221F\f\202!D\000\340\274E\302u#D\000\030\036Fl\275#D\000U\035G\254~&D\200\370\022H\364\315&D\000\346bGT\365&D\000\000\000@\300s5D\000`\307ET\2008D\000\3175G\310{:D\200\307\251G\230\311:D\000`5F\000\214<D\000\000\270E\254\301<D\000\340\024FX\264=D\000\270\021F\204\204?D\000\226\006H\356\256?D\000\000\000@\300\023@D\000\005\002Gb~BD\200\256\350G\032\312BD\000zAG\034\316CD\000\350\254E8\314DD\000\270\310E\316\020ED\000\010\254E\026\005QD\000\240\267E\250tSD\000tEFB\200VD\200\342\235G\374\247VD\000$\023F\000\206XD\200K\245G\242\303XD\000\343xG\270\201YD\000\214\325F\304\365ZD\0008\225FZF[D\000\230RF\232~[D@\r\201Hl\307[D\000L\031Hv\001\\D\000\3540Fx\201^D`\222\275H\f\305^D\000wZG\006\023oD\000\360\217E\354\205oD\200\335-H\350zrD\000\224,GFXtD\000\364\223F\222\201tD\200\221\341H\024\304tD\000)\034H\314\354tD\000\000\200@\022}wD\200\001\205I\274\274wD\000\t\210H\260\344wD\000\000pA\004\370yD\000@\203Eh\272\205D\2006\214Gh\336\205D\000\026\235Fb,\210D\200\177 H\\@\210D\240,\355Il`\210D\200\022\026I\320\202\210D\000 \336Fx\227\210D\000\000\200?\334{\212D\000<\252F4>\222D\000\264\213F\302\321\223D\000H\354Ed\275\230D\000-\fHv\332\230D@\313\tH\374\367\230D\000?\aG",
+  }
+  Dta_files_last = {
+    :mh => 2604.8360326775,
+    :dta_tic => 31977.0,
+    :num_peaks => 17,
+    :charge => 3,
+    :ms_level => 2,
+    :total_num_possible_charge_states => 0,
+    :peaks => "4\n\216C\000`\305D\254\205\303C\000@;D\354\321\nD\000 \275D\232\243'D\000\020iE\350\2302D\000`\245D\f\3164D\000p@E\314JID\000\300\213D\264\002PD\000\260\016E\252\213[D\0000\eE\340NoD\000@\177D0\371xD\000@:Dd\f\205D\000\000yD\200\261\215D\000@\371D\210N\221D\000`\274D\034N\256D\000\020\032EN\372\266D\000\000\aD\356\223\322D\000\250\227E"
+  }
+
+  Out_files_first = {
+    :num_hits => 10,
+    :charge => 1,
+    :computer => "VELA",
+    :date_time => "11/17/2006, 04:13 PM,",
+  }
+
+  Out_files_first_hit = {
+    :mh => 1220.5128044522,
+    :deltacn => 0.0,
+    :sp => 96.5815887451172,
+    :xcorr => 1.08377742767334,
+    :id => 224,
+    :rsp => 13,
+    :ions_matched => 8,
+    :ions_total => 20,
+    :peptide => "K.LCPHLTLLPGR.F",
+    :reference => "gi|1786425|gb|AAC73335.1| damage-inducible protein P; putative tRNA synthetase",
+  }
+
+  Out_files_last = {
+    :num_hits => 10, 
+    :charge => 1,
+    :computer => "VELA",
+    :date_time => "11/17/2006, 04:25 PM," ,
+  }
+  Out_files_last_first_hit = {
+    :mh => 2605.9368784522,
+    :deltacn => 0.0,
+    :sp => 76.7447052001953,
+    :xcorr => 0.915680646896362,
+    :id => 13562,
+    :rsp => 4,
+    :ions_matched => 10,
+    :ions_total => 84,
+    :peptide => "K.HLEINPNHPIVETLRQKAETHK.N",
+    :reference => "gi|30149327|ref|XP_293672.2| similar to ebiP7687 [Homo sapiens]",
+  }
+  Out_files_last_last_hit = {
+    :mh => 2604.9025174522,
+    :deltacn => 0.307604849338531,
+    :sp => 26.1511478424072,
+    :xcorr => 0.634012818336487,
+    :id => 8105,
+    :rsp => 165,
+    :ions_matched => 6,
+    :ions_total => 84,
+    :peptide => "R.EAFLVNSDLTLRAQLTEFRDHK.L",
+    :reference => "gi|5453830|ref|NP_006181.1| origin recognition complex, subunit 2-like; origin"
+  }
+  Sequest_params = {
+     "add_F_Phenylalanine"=>"0.0000",
+     "add_O_Ornithine"=>"0.0000",
+     "add_Y_Tyrosine"=>"0.0000",
+     "add_C_Cysteine"=>"0.0000",
+     "add_A_Alanine"=>"0.0000",
+     "add_J_user_amino_acid"=>"0.0000",
+     "add_X_LorI"=>"0.0000",
+     "add_S_Serine"=>"0.0000",
+     "add_Cterm_peptide"=>"0.0000",
+     "add_Q_Glutamine"=>"0.0000",
+     "add_D_Aspartic_Acid"=>"0.0000",
+     "add_Nterm_protein"=>"0.0000",
+     "add_W_Tryptophan"=>"0.0000",
+     "add_R_Arginine"=>"0.0000",
+     "add_K_Lysine"=>"0.0000",
+     "add_H_Histidine"=>"0.0000",
+     "add_Nterm_peptide"=>"0.0000",
+     "add_E_Glutamic_Acid"=>"0.0000",
+     "add_Z_avg_QandE"=>"0.0000",
+     "add_B_avg_NandD"=>"0.0000",
+     "add_N_Asparagine"=>"0.0000",
+     "add_I_Isoleucine"=>"0.0000",
+     "add_L_Leucine"=>"0.0000",
+     "add_M_Methionine"=>"0.0000",
+     "add_P_Proline"=>"0.0000",
+     "add_G_Glycine"=>"0.0000",
+     "add_U_user_amino_acid"=>"0.0000",
+     "add_T_Threonine"=>"0.0000",
+     "add_V_Valine"=>"0.0000",
+     "add_Cterm_protein"=>"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"=>"0.000000 S 0.000000 C 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\\mixed_db_human_ecoli_7prot_unique.fasta",
+     "peptide_mass_tolerance"=>"1.4000",
+     "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"=>"0",
+     "mass_type_parent"=>"0",
+     "match_peak_count"=>"0",
+     "max_num_differential_per_peptide"=>"1",
+     "ion_cutoff_percentage"=>"0.0000",
+     "mass_type_fragment"=>"0"
+  }
+
+end
+
+class TestSRF < Test::Unit::TestCase
+  include ToMatch
+  def initialize(arg)
+    super(arg)
+    @tfiles = File.dirname(__FILE__) + '/tfiles/'
+    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
+    @tf_srf = @tfiles_l + "7MIX_STD_110802_1.srf"
+  end
+
+  def test_basic
+    start = Time.now
+    obj = SRF.new(@tf_srf)
+    puts "TOOK: #{Time.now - start} secs"
+    ## Verify that we have everything and it is as we expect (not exhaustive)
+    head = obj.header
+    dtgen = head.dta_gen
+    ## HEADER
+    hash_match(Header, head)
+    hash_match(Dta_gen, dtgen)
+    ## DTA_FILES
+    hash_match(Dta_files_first, obj.dta_files.first)
+    hash_match(Dta_files_last, obj.dta_files.last)
+    ## OUT_FILES
+    hash_match(Out_files_first, obj.out_files.first)
+    hash_match(Out_files_first_hit, obj.out_files.first.hits.first)
+    hash_match(Out_files_last_first_hit, obj.out_files.last.hits.first)
+    hash_match(Out_files_last_last_hit, obj.out_files.last.hits.last)
+    ## SEQUEST_PARAMS
+    hash_match(Sequest_params, obj.params)
+    ## INDEX
+    assert_equal([7161, 7161, 3], obj.index.last)
+    assert_equal([2, 2, 1], obj.index.first)
+
+    assert_equal(obj.index.size, obj.dta_files.size)
+    assert_equal(obj.out_files.size, obj.dta_files.size)
+  end
+
+  def hash_match(hash, obj)
+    hash.each do |k,v|
+      if v.is_a? Float
+        delta = v/100000
+        assert_in_delta( obj.send(k.to_sym), v, delta, "param: #{k}")
+      else
+        assert_equal(obj.send(k.to_sym), v, "param: #{k}")
+      end
+    end
+  end
+
+end
+
+

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.9.0
 specification_version: 1
 name: mspire
 version: !ruby/object:Gem::Version 
-  version: 0.1.5
-date: 2007-02-08 00:00:00 -06:00
+  version: 0.1.7
+date: 2007-03-27 00:00:00 -05:00
 summary: Mass Spectrometry Proteomics Objects, Scripts, and Executables
 require_paths: 
 - lib
@@ -32,15 +32,18 @@ files:
 - lib/spec_id
 - lib/align
 - lib/spec
-- lib/spec_id.rb
-- lib/fasta.rb
 - lib/sample_enzyme.rb
-- lib/align.rb
+- lib/fasta.rb
 - lib/roc.rb
+- lib/spec_id.rb
+- lib/gi.rb
+- lib/align.rb
+- lib/spec_id/srf.rb
 - lib/spec_id/bioworks.rb
 - lib/spec_id/proph.rb
 - lib/spec_id/sequest.rb
-- lib/spec_id/false_positive_rate.rb
+- lib/spec_id/precision.rb
+- lib/spec_id/aa_freqs.rb
 - lib/align/chams.rb
 - lib/spec/mzxml
 - lib/spec/mzdata
@@ -54,6 +57,8 @@ files:
 - README
 - Rakefile
 - LICENSE
+- changelog.txt
+- release_notes.txt
 - bin/fasta_cat_mod.rb
 - bin/fasta_mod.rb
 - bin/gi2annot.rb
@@ -63,45 +68,53 @@ files:
 - bin/bioworks2sequestXML_gui.rb
 - bin/bioworks2excel.rb
 - bin/pepproph_filter.rb
+- bin/filter_spec_id.rb
 - bin/bioworks_to_pepxml.rb
+- bin/mzxml_to_lmat.rb
 - bin/protxml2prots_peps.rb
-- bin/false_positive_rate.rb
 - bin/id_precision.rb
-- bin/mzxml_to_lmat.rb
 - bin/id_class_anal.rb
-- bin/filter_spec_id.rb
-- script/create_little_pepxml.rb
+- bin/precision.rb
+- bin/fasta_shaker.rb
+- script/prep_dir.rb
+- script/msvis.rb
+- script/gen_database_searching.rb
 - script/mzXML2timeIndex.rb
 - script/tpp_installer.rb
-- script/msvis.rb
+- script/create_little_pepxml.rb
 - script/histogram_probs.rb
-- script/prep_dir.rb
 - script/top_hit_per_scan.rb
 - script/filter-peps.rb
-- script/gen_database_searching.rb
 - script/simple_protein_digestion.rb
+- script/genuine_tps_and_probs.rb
+- script/estimate_fpr_by_cysteine.rb
+- script/find_cysteine_background.rb
 test_files: 
-- test/tc_false_positive_rate.rb
+- test/tc_srf.rb
 - test/tc_proph.rb
 - test/tc_sequest.rb
-- test/tc_spec.rb
 - test/tc_align.rb
+- test/tc_spec.rb
+- test/tc_aa_freqs.rb
 - test/tc_protein_summary.rb
 - test/tc_fasta.rb
 - test/tc_bioworks.rb
-- test/tc_msrun.rb
 - test/tc_peptide_parent_times.rb
+- test/tc_msrun.rb
 - test/tc_spec_id.rb
 - test/tc_mzxml.rb
 - test/tc_id_precision.rb
 - test/tc_id_class_anal.rb
 - test/tc_filter_peps.rb
-- test/tc_gi2annot.rb
+- test/tc_precision.rb
 - test/tc_roc.rb
 - test/tc_scan.rb
-- test/tc_bioworks_to_pepxml.rb
 - test/tc_mzxml_to_lmat.rb
+- test/tc_bioworks_to_pepxml.rb
 - test/tc_sample_enzyme.rb
+- test/tc_fasta_shaker.rb
+- test/tc_gi.rb
+- test/tc_spec_id_xml.rb
 rdoc_options: 
 - --main
 - README
@@ -121,13 +134,14 @@ executables:
 - bioworks2sequestXML_gui.rb
 - bioworks2excel.rb
 - pepproph_filter.rb
+- filter_spec_id.rb
 - bioworks_to_pepxml.rb
+- mzxml_to_lmat.rb
 - protxml2prots_peps.rb
-- false_positive_rate.rb
 - id_precision.rb
-- mzxml_to_lmat.rb
 - id_class_anal.rb
-- filter_spec_id.rb
+- precision.rb
+- fasta_shaker.rb
 extensions: []
 
 requirements: