mspire 0.1.7 → 0.2.0

data/test/tc_spec_id.rb

@@ -8,11 +8,14 @@ class SpecIDTest < Test::Unit::TestCase
   def initialize(arg)
     super(arg)
     @tfiles = File.dirname(__FILE__) + '/tfiles/'
+    @tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
     @bw = @tfiles + "bioworks_small.xml"
+    @old_prot_proph = @tfiles + 'yeast_gly_small-prot.xml'
+    @prot_proph = @tfiles + 'opd1/000_020_3prots-prot.xml'
+    @srf = @tfiles_l + '7MIX_STD_110802_1.srf'
   end
 
   def test_spec_id_creation
-    sp = SpecID.new
     sp = SpecID.new(@bw)
     assert_equal(106, sp.prots.size)
   end
@@ -45,20 +48,21 @@ class SpecIDTest < Test::Unit::TestCase
       end
       [write_index, bo]
     end
+    roc = ROC.new
     tp, fp = ROC.new.prep_list(answ)
-    (exp_tp, exp_fp) = ROC.new.by_tps(:fpr2, tp, fp)
+    (exp_tp, exp_fp) = roc.tps_and_ppv(tp, fp)
 
     sp = SpecID.new(file)
     assert_equal(19, sp.prots.size)
     tp, fp = sp.rank_and_classify(:prots, proc {|prt| prt.probability }, proc {|prt| if prt.reference =~ /^INV_/ ; false; else; true; end })
-    tps, ys = sp.by_tps(:fpr2, tp, fp)
+    (tps, ys) = roc.tps_and_ppv(tp, fp)
     assert_equal(exp_tp, tps)
     assert_equal(exp_fp, ys)
-    tps, prec, fpr = sp.tps_and_precision_and_fpr2_times2_for_prob("INV_")
+    (num_hits, prec) = sp.num_hits_and_ppv_for_prob("INV_")
     # @TODO: assert these guys for consistencies sake:
     assert_in_delta_arrays([1, 2, 3, 4, 5, 6, 9, 10, 11, 12, 13, 14, 15], tps, 0.0000001)
-    assert_in_delta_arrays([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.916666666666667, 0.923076923076923, 0.928571428571429, 0.933333333333333, 0.882352941176471], prec, 0.0000001)
-    assert_in_delta_arrays([0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.166666666666667, 0.153846153846154, 0.142857142857143, 0.133333333333333, 0.235294117647059], fpr, 0.0000001)
+    # Consistency check only:
+    assert_in_delta_arrays([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 0.909090909090909, 0.916666666666667, 0.923076923076923, 0.928571428571429, 0.866666666666667], prec, 0.0000001)
   end
 
   def assert_in_delta_arrays(one, two, delta, message=nil)
@@ -66,5 +70,123 @@ class SpecIDTest < Test::Unit::TestCase
       assert_in_delta(v, two[i], delta, message)
     end
   end
+
+  def test_file_type
+    assert_equal('bioworks', SpecID.file_type(@bw))
+    assert_equal('protproph', SpecID.file_type(@prot_proph))
+    assert_equal('srg', SpecID.file_type('whatever.srg'))
+    ## WOULD BE NICE TO GET THIS WORKING, TOO
+    # assert_equal('protproph', SpecID.file_type(@old_prot_proph))
+    if File.exist? @tfiles_l
+      assert File.exist?(@srf), "file #{@srf} is there"
+      assert_equal('srf', SpecID.file_type(@srf))
+    else
+      assert_nil( puts("\n--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
+    end
+  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::Pep.remove_non_amino_acids(v) }
+    hash.each do |k,v|
+      assert_equal(v, cl.call(k))
+    end
+  end
+
+
+
+end
+
+class MyProt ; include SpecID::Prot ; end
+class MyPep ; include SpecID::Pep ; attr_accessor :xcorr end
+
+
+class TestOccamsRazor < Test::Unit::TestCase
+
+  def test_small
+    
+    prots = (0..6).to_a.map do |n|
+      prot = MyProt.new
+      prot.reference = "ref_#{n}"
+      prot
+    end
+
+    peps = (0..12).to_a.map {|v| MyPep.new }
+
+    #           0   1   2   3   4   5   6   7   8   9   10  11    12 
+    aaseqs = %w(AAA BBB CCC ABC AAA BBB CCC ABC DDD EEE FFF EEEEE DDD)
+    xcorrs = [1.0, 2.0, 3.0, 4.0, 1.0, 2.0, 3.0, 4.0, 0.5, 0.6, 0.7, 0.8, 0.5]
+
+    peps.zip(aaseqs, xcorrs) do |pep,aaseq,xcorr|
+      pep.aaseq = aaseq
+      pep.xcorr = xcorr
+    end
+
+    prots[0].peps = peps[0,4]
+    prots[1].peps = [peps[2]]  ## should be missing
+
+    test_prots = prots[0,2]
+    require 'pp'
+    answ = SpecID.occams_razor(test_prots)
+    answ.each do |an|
+      assert( an[0].is_a?(SpecID::Prot), "prots are there")
+    end
+    first = answ.first
+    assert_equal( prots[0], first[0])
+    assert_equal_array_content( prots[0].peps, first[1])
+
+
+
+    #prots[2].peps = [peps[2]]
+    #prots[2].peps.push( peps[3] ) ## should be there since it has 2
+    #prots[3].peps = [peps[3]] ## should be missing
+  end
+
+  def assert_equal_array_content(exp1, ans, message='')
+    exp1.each do |item|
+      assert(ans.include?(item), "finding #{item}: #{message}")
+    end
+  end
+end
+
+
+require 'fasta'
+
+class TestProteinGroups < Test::Unit::TestCase
+
+  def test_small
+    prots = []
+
+    aaseq = ('A'..'Z').to_a.join('')
+    header = "prot1"
+    prots << Fasta::Prot.new(header, aaseq)
+
+    aaseq = ('A'..'Z').to_a.reverse.join('')
+    header = "prot1_reverse"
+    prots << Fasta::Prot.new(header, aaseq)
+
+    aaseq = ('A'..'Z').to_a.join('')
+    header = "prot1_identical"
+    prots << Fasta::Prot.new(header, aaseq)
+
+    aaseq = ('A'..'E').to_a.join('')
+    header = "prot1_short"
+    prots << Fasta::Prot.new(header, aaseq)
+
+    aaseq = ('A'..'E').to_a.reverse.join('')
+    header = "prot1_reverse_short"
+    prots << Fasta::Prot.new(header, aaseq)
+
+    fasta = Fasta.new(prots)
+
+    pep_seqs = %w(ABCD DEFG ABCD DEFG EDCB FEDCB XYZ RANDOM AEABA) 
+
+    arr = SpecID::Pep.protein_groups_by_sequence(pep_seqs, fasta)
+    
+    exp = [[prots[0], prots[2], prots[3]], [prots[0], prots[2]], [prots[0], prots[2], prots[3]], [prots[0],prots[2]], [prots[1], prots[4]], [prots[1]], [prots[0], prots[2]], [], []]
+    
+    assert_equal(exp, arr)
+  end
+
 end
 

data/test/tc_srf.rb

@@ -50,53 +50,70 @@ module ToMatch
 
   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,
+    :deltacn => 0.071944423019886, ## this is the modified version
     :sp => 96.5815887451172,
     :xcorr => 1.08377742767334,
     :id => 224,
     :rsp => 13,
     :ions_matched => 8,
     :ions_total => 20,
-    :peptide => "K.LCPHLTLLPGR.F",
+    :sequence => "K.LCPHLTLLPGR.F",
+    :aaseq => "LCPHLTLLPGR",
     :reference => "gi|1786425|gb|AAC73335.1| damage-inducible protein P; putative tRNA synthetase",
+    :first_scan => 2,
+    :last_scan => 2,
+    :base_name => '7MIX_STD_110802_1',
+    :charge => 1,
   }
 
   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,
+    :deltacn => 0.03921128064394,
     :sp => 76.7447052001953,
     :xcorr => 0.915680646896362,
     :id => 13562,
     :rsp => 4,
     :ions_matched => 10,
     :ions_total => 84,
-    :peptide => "K.HLEINPNHPIVETLRQKAETHK.N",
+    :sequence => "K.HLEINPNHPIVETLRQKAETHK.N",
+    :aaseq => "HLEINPNHPIVETLRQKAETHK",
     :reference => "gi|30149327|ref|XP_293672.2| similar to ebiP7687 [Homo sapiens]",
+    :first_scan => 7161,
+    :last_scan => 7161,
+    :base_name => '7MIX_STD_110802_1',
+    :deltamass => 2605.9368784522 - 2604.8360326775,
+    :ppm => ((1.0e6 * (2605.9368784522 - 2604.8360326775)) / 2604.8360326775).abs,
+    :charge => 3,
   }
   Out_files_last_last_hit = {
     :mh => 2604.9025174522,
-    :deltacn => 0.307604849338531,
+    :deltacn => 1.1,
     :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"
+    :sequence => "R.EAFLVNSDLTLRAQLTEFRDHK.L",
+    :aaseq => "EAFLVNSDLTLRAQLTEFRDHK",
+    :reference => "gi|5453830|ref|NP_006181.1| origin recognition complex, subunit 2-like; origin",
+    :first_scan => 7161,
+    :last_scan => 7161,
+    :base_name => '7MIX_STD_110802_1',
+    :deltamass =>  2604.9025174522 - 2604.8360326775,
+    :ppm => ((1.0e6 * (2604.9025174522 - 2604.8360326775)) / 2604.8360326775).abs,
+    :charge => 3,
   }
   Sequest_params = {
      "add_F_Phenylalanine"=>"0.0000",
@@ -163,50 +180,79 @@ module ToMatch
 
 end
 
+tfiles = File.dirname(__FILE__) + '/tfiles/'
+tfiles_l = File.dirname(__FILE__) + '/tfiles_large/'
+tf_srf = tfiles_l + "7MIX_STD_110802_1.srf"
+tf_srf_inv = tfiles_l + "7MIX_STD_110802_1_INV.srf"
+if File.exist? tfiles_l
+  start = Time.now
+  $group = SRFGroup.new([tf_srf, tf_srf_inv]) 
+  $srf = $group.srfs.first
+  puts "Time to read and compile two SRF: #{Time.now - start} secs"
+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"
+    @srg_file = @tfiles + "tmp_bioworks.srg"
+
+    @srf = $srf
+    @group = $group
+
   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)
+    if File.exist? @tfiles_l
+      ## Verify that we have everything and it is as we expect (not exhaustive)
+      head = @srf.header
+      dtgen = head.dta_gen
+      ## HEADER
+      hash_match(Header, head)
+      hash_match(Dta_gen, dtgen)
+      ## DTA_FILES
+      hash_match(Dta_files_first, @srf.dta_files.first)
+      hash_match(Dta_files_last, @srf.dta_files.last)
+      ## OUT_FILES
+      hash_match(Out_files_first, @srf.out_files.first)
+      hash_match(Out_files_first_hit, @srf.out_files.first.hits.first)
+      hash_match(Out_files_last_first_hit, @srf.out_files.last.hits.first)
+      hash_match(Out_files_last_last_hit, @srf.out_files.last.hits.last)
+      ## SEQUEST_PARAMS
+      hash_match(Sequest_params, @srf.params)
+      ## INDEX
+      assert_equal([7161, 7161, 3], @srf.index.last)
+      assert_equal([2, 2, 1], @srf.index.first)
+
+      assert_equal(@srf.index.size, @srf.dta_files.size)
+      assert_equal(@srf.out_files.size, @srf.dta_files.size)
+    else
+      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
+    end
+  end
+
+  def test_srg
+    if File.exist? @tfiles_l
+      @group.to_srg(@srg_file)
+      assert(File.exist?(@srg_file), "file exists: " + @srg_file )
+    else
+      assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
+    end
   end
 
-  def hash_match(hash, obj)
+  ## treats reference special
+  def hash_match(hash, srf)
     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}")
+        assert_in_delta(v, srf.send(k.to_sym), delta, "param: #{k}")
+      elsif k == :reference
+        assert_equal(v[0,38], srf.prots.first.reference)
       else
-        assert_equal(obj.send(k.to_sym), v, "param: #{k}")
+        assert_equal(v, srf.send(k.to_sym), "param: #{k}")
       end
     end
   end

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.0
+rubygems_version: 0.9.2
 specification_version: 1
 name: mspire
 version: !ruby/object:Gem::Version 
-  version: 0.1.7
-date: 2007-03-27 00:00:00 -05:00
+  version: 0.2.0
+date: 2007-04-25 00:00:00 -05:00
 summary: Mass Spectrometry Proteomics Objects, Scripts, and Executables
 require_paths: 
 - lib
@@ -29,28 +29,32 @@ post_install_message:
 authors: 
 - John Prince
 files: 
-- lib/spec_id
+- lib/spec_id.rb
 - lib/align
+- lib/spec_id_xml.rb
+- lib/spec_id
+- lib/toppred.rb
+- lib/align.rb
 - lib/spec
-- lib/sample_enzyme.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/roc.rb
+- lib/sample_enzyme.rb
+- lib/align/chams.rb
 - lib/spec_id/sequest.rb
+- lib/spec_id/filter.rb
+- lib/spec_id/bioworks.rb
+- lib/spec_id/srf.rb
 - lib/spec_id/precision.rb
+- lib/spec_id/protein_summary.rb
 - lib/spec_id/aa_freqs.rb
-- lib/align/chams.rb
-- lib/spec/mzxml
-- lib/spec/mzdata
+- lib/spec_id/proph.rb
 - lib/spec/msrun.rb
 - lib/spec/scan.rb
-- lib/spec/mzxml.rb
+- lib/spec/mzxml
 - lib/spec/mzdata.rb
+- lib/spec/mzdata
+- lib/spec/mzxml.rb
 - lib/spec/mzxml/parser.rb
 - lib/spec/mzdata/parser.rb
 - INSTALL
@@ -59,62 +63,62 @@ files:
 - LICENSE
 - changelog.txt
 - release_notes.txt
-- bin/fasta_cat_mod.rb
-- bin/fasta_mod.rb
-- bin/gi2annot.rb
-- bin/protein_summary.rb
-- bin/raw2mzXML.rb
-- bin/fasta_cat.rb
 - bin/bioworks2sequestXML_gui.rb
-- bin/bioworks2excel.rb
+- bin/srf_group.rb
 - bin/pepproph_filter.rb
-- bin/filter_spec_id.rb
-- bin/bioworks_to_pepxml.rb
-- bin/mzxml_to_lmat.rb
+- bin/filter.rb
 - bin/protxml2prots_peps.rb
-- bin/id_precision.rb
+- bin/raw_to_mzXML.rb
+- bin/gi2annot.rb
 - bin/id_class_anal.rb
 - bin/precision.rb
+- bin/id_precision.rb
+- bin/protein_summary.rb
+- bin/bioworks_to_pepxml.rb
+- bin/bioworks2excel.rb
+- bin/mzxml_to_lmat.rb
 - bin/fasta_shaker.rb
+- bin/find_aa_freq.rb
 - script/prep_dir.rb
+- script/degenerate_peptides.rb
+- script/histogram_probs.rb
+- script/simple_protein_digestion.rb
+- script/top_hit_per_scan.rb
 - script/msvis.rb
-- script/gen_database_searching.rb
 - script/mzXML2timeIndex.rb
 - script/tpp_installer.rb
-- script/create_little_pepxml.rb
-- script/histogram_probs.rb
-- script/top_hit_per_scan.rb
 - script/filter-peps.rb
-- script/simple_protein_digestion.rb
-- script/genuine_tps_and_probs.rb
 - script/estimate_fpr_by_cysteine.rb
+- script/genuine_tps_and_probs.rb
+- script/create_little_pepxml.rb
 - script/find_cysteine_background.rb
 test_files: 
-- test/tc_srf.rb
-- test/tc_proph.rb
-- test/tc_sequest.rb
-- test/tc_align.rb
-- test/tc_spec.rb
-- test/tc_aa_freqs.rb
-- test/tc_protein_summary.rb
+- test/tc_spec_id_xml.rb
+- test/tc_mzxml_to_lmat.rb
+- test/tc_id_class_anal.rb
+- test/tc_gi.rb
 - test/tc_fasta.rb
-- test/tc_bioworks.rb
 - test/tc_peptide_parent_times.rb
-- test/tc_msrun.rb
 - test/tc_spec_id.rb
+- test/tc_roc.rb
 - test/tc_mzxml.rb
+- test/tc_sample_enzyme.rb
+- test/tc_srf.rb
+- test/tc_bioworks.rb
+- test/tc_spec.rb
+- test/tc_bioworks_to_pepxml.rb
+- test/tc_scan.rb
+- test/tc_sequest.rb
+- test/tc_fasta_shaker.rb
 - test/tc_id_precision.rb
-- test/tc_id_class_anal.rb
+- test/tc_msrun.rb
+- test/tc_protein_summary.rb
 - test/tc_filter_peps.rb
+- test/tc_filter.rb
+- test/tc_aa_freqs.rb
+- test/tc_proph.rb
+- test/tc_align.rb
 - test/tc_precision.rb
-- test/tc_roc.rb
-- test/tc_scan.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
@@ -125,29 +129,30 @@ extra_rdoc_files:
 - INSTALL
 - LICENSE
 executables: 
-- fasta_cat_mod.rb
-- fasta_mod.rb
-- gi2annot.rb
-- protein_summary.rb
-- raw2mzXML.rb
-- fasta_cat.rb
 - bioworks2sequestXML_gui.rb
-- bioworks2excel.rb
+- srf_group.rb
 - pepproph_filter.rb
-- filter_spec_id.rb
-- bioworks_to_pepxml.rb
-- mzxml_to_lmat.rb
+- filter.rb
 - protxml2prots_peps.rb
-- id_precision.rb
+- raw_to_mzXML.rb
+- gi2annot.rb
 - id_class_anal.rb
 - precision.rb
+- id_precision.rb
+- protein_summary.rb
+- bioworks_to_pepxml.rb
+- bioworks2excel.rb
+- mzxml_to_lmat.rb
 - fasta_shaker.rb
+- find_aa_freq.rb
 extensions: []
 
 requirements: 
 - "\"xmlparser\" is the prefered xml parser right now.  REXML and regular expressions are used as fallback in some routines."
 - some plotting functions will not be available without the "gnuplot" gem (and underlying gnuplot binary)
-- the "t2x" binary to convert .RAW files to mzXML is expected in some applications
+- the "t2x" binary (in archive) or readw.exe is required to convert .RAW files to mzXML in some applications
+- "\"rake\" is useful for development"
+- "\"webgen (with gems redcloth and bluecloth) is necessary to build web pages"
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: libjtp

data/bin/fasta_cat.rb

@@ -1,39 +0,0 @@
-#!/usr/bin/ruby
-
-require 'fasta'
-require 'getoptlong'
-
-connector = Fasta::FILE_CONNECTOR
-
-# Get the prefix option:
-opts = GetoptLong.new(
-  [ "-p",    "--prefixes",        GetoptLong::REQUIRED_ARGUMENT]
-)
-
-opt_hash = {}
-opts.each do |opt, arg|
-  opt_hash[opt] = arg
-end
-
-prefix_array = nil
-if opt_hash.key?('-p')
-  prefix_array = opt_hash['-p'].split(',')
-end
-
-# Usage info:
-if ARGV.size < 2
-  puts "
-  usage: #{File.basename(__FILE__)} [-p=prefix1,prefix2,...] <file1>.fasta <file2>.fasta ...
-
-  Concatenates the files together with '#{connector}' (the file extension will
-  be the extension of the first file).
-
-  -p    prefixes protein headers with the corresponding value in the comma
-  separated list.
-  "
-  exit
-end
-
-files = ARGV.to_a
-outfile = Fasta.cat_and_prefix(files, prefix_array, connector)
-puts "OUTFILE: #{outfile}"

data/bin/fasta_cat_mod.rb

@@ -1,59 +0,0 @@
-#!/usr/bin/ruby
-
-require 'fasta'
-require 'optparse'
-
-hash = {
-  'shuffle' => {
-    'method' => :aaseq_shuffle!,
-    'protein_header_prefix' => Fasta::SHUFF_PREFIX,
-    'file_postfix' => Fasta::CAT_SHUFF_FILE_POSTFIX,
-  },
-  'invert' => {
-    'method' => :aaseq_invert!,
-    'protein_header_prefix' => Fasta::INV_PREFIX,
-    'file_postfix' => Fasta::CAT_INV_FILE_POSTFIX,
-  },
-}
-
-opt = {}
-OptionParser.new do |opts|
-  opts.on("-f", "--fraction FLOAT", "fraction") {|v| opt['f'] = v }
-end.parse!
-
-
-if ARGV.size < 2
-  puts "
-  usage: #{File.basename(__FILE__)} [-f <fraction>] <method> <file>.fasta ...
-
-  The AA seq's of (a fraction of) proteins will be modified according to
-  <method> and concatenated to the end of the normal proteins.  Each modified
-  protein's header takes on a header prefix after the '>'.  Each file takes on
-  a postfix (before the extension).
-
-  METHOD      PROT_PREFIX     FILE_POSTFIX
-  shuffle     #{hash['shuffle']['protein_header_prefix']}          #{hash['shuffle']['file_postfix']}
-  invert      #{hash['invert']['protein_header_prefix']}            #{hash['invert']['file_postfix']}
-  "
-  exit
-end
-
-method = ARGV.shift
-opt_h = nil
-if hash.key? method
-  opth = hash[method]
-else
-  abort "invalid method! choose: #{hash.keys.join(", ")}"
-end
-
-fraction = 1; if opt.key?('f') then fraction = opt['f'] end
-
-specific_method = opth['method']
-file_postfix = opth['file_postfix']
-protein_header_prefix = opth['protein_header_prefix']
-#puts [file, specific_method, fraction, file_postfix, protein_header_prefix].join("*")
-
-ARGV.each do |file|
-  outfile = Fasta.modify_fraction_and_cat_to_file(file, specific_method, fraction, file_postfix, protein_header_prefix)
-  puts "OUTPUT: #{outfile}"
-end