mspire 0.1.7 → 0.2.0

data/lib/spec_id_xml.rb

@@ -0,0 +1,101 @@
+
+# I would prefer to call this SpecID::XML, but I keep getting an error:
+# /home/john/Proteomics/msprot/lib/spec_id/bioworks.rb:412: warning: toplevel
+# constant XML referenced by SpecID::XML' This works around that for now.
+# Any major xml elements should return a newline at the end for simple
+# concatenation into a file
+module SpecIDXML
+
+  Special_chrs_hash = {
+    '"' => '"',
+    '&' => '&',
+    "'" => ''',
+    '<' => '&lt;',
+    '>' => '&gt;',
+  }
+
+  # substitutes special xml chars
+  def escape_special_chars(string)
+    string.split('').map do |char|
+      if Special_chrs_hash.key? char ; Special_chrs_hash[char] 
+        # if x = Special_chrs_hash[char] ; x  # <-- that's slightly slower
+      else ; char end
+    end.join
+  end
+
+  $DEPTH = 0
+
+  def tabs
+    # this is ugly
+    string = ""
+    $DEPTH.times { string << "\t" }
+    string
+  end
+
+
+  def param_xml(symbol)
+    tabs + '<parameter name="' + "#{symbol}" + '" value="' + "#{send(symbol)}" + '"/>'
+  end
+
+  def params_xml(*symbol_list)
+    symbol_list.collect { |sy|
+      param_xml(sy)
+    }.join("\n") + "\n"
+  end
+
+  def short_element_xml(element, att_list)
+    "#{tabs}<#{element} #{attrs_xml(att_list)}/>\n"
+  end
+
+  def short_element_xml_and_att_string(element, att_string)
+    "#{tabs}<#{element} #{att_string}/>\n"
+  end
+
+  # requires that obj have attribute '@xml_element_name'
+  # displays all *instance_variables* (does not call methods!)
+  def short_element_xml_from_instance_vars(element_name)
+    string = instance_variables.map{|v| "#{v[1..-1]}=\"#{instance_variable_get(v)}\"" }.join(' ')
+    "#{tabs}<#{element_name} #{string}/>\n"
+  end
+
+  # takes an element as a symbol and returns the 
+  def element_xml_no_atts(element)
+    start = "#{tabs}<#{element}>\n"
+    $DEPTH += 1
+    if block_given? ; middle = yield else ; middle = '' end
+    $DEPTH -= 1
+    start + middle + "#{tabs}</#{element}>\n"
+  end
+
+  # takes an element as a symbol and returns the 
+  def element_xml(element, att_list)
+
+    start = "#{tabs}<#{element} #{attrs_xml(att_list)}>\n"
+    $DEPTH += 1
+    if block_given? ; middle = yield else ; middle = '' end
+    $DEPTH -= 1
+    start + middle + "#{tabs}</#{element}>\n"
+  end
+
+  # element as symbol and att_string as attributes
+  # takes a block of whatever
+  def element_xml_and_att_string(element, att_string)
+    start = "#{tabs}<#{element} #{att_string}>\n"
+    $DEPTH += 1
+    if block_given? ; middle = yield else ; middle = '' end
+    $DEPTH -= 1
+    start + middle + "#{tabs}</#{element}>\n"
+  end
+
+  def attr_xml(symbol)
+    "#{symbol}=\"#{send(symbol)}\""
+  end
+
+  def attrs_xml(list_of_symbols)
+    list_of_symbols.collect {|sy|
+      attr_xml(sy)
+    }.join(" ")
+  end
+
+end
+

data/lib/toppred.rb

@@ -0,0 +1,18 @@
+
+# reader for the http://bioweb.pasteur.fr/seqanal/interfaces/toppred.html
+# output
+class TopPred
+  
+  attr_accessor :hmmmm
+
+  def initialize(toppred_out_file=nil)
+    if toppred_out_file
+      from_file(toppred_out_file)
+    end
+  end
+
+  def from_file(toppred_out_file)
+  end
+
+end
+

data/script/degenerate_peptides.rb

@@ -0,0 +1,47 @@
+#!/usr/bin/ruby -w
+
+require 'fasta'
+require 'sample_enzyme'
+
+if ARGV.size < 3
+  puts "usage: #{File.basename(__FILE__)} min_peptide_length missed_cleavages <file>.fasta ..."
+  puts "       returns <file>.min_pep_length_<#>.missed_cleavages_<#>.degenerate_peptides.csv"
+  abort
+end
+
+
+
+min_peptide_length = ARGV.shift.to_i
+missed_cleavages = ARGV.shift.to_i
+
+ARGV.each do |file|
+  hash = {}
+
+  if file !~ /\.fasta/
+    abort "must be a fasta file with extension fasta"
+  end
+  new_filename = file.sub(/\.fasta$/, '')
+  new_filename << ".min_pep_length_#{min_peptide_length}.missed_cleavages_#{missed_cleavages}.degenerate_peptides.csv"
+  peptides = []
+  Fasta.new.read_file(file).prots.each do |prot|
+
+
+    SampleEnzyme.tryptic(prot.aaseq, missed_cleavages).each do |aaseq|
+      if aaseq.size >= min_peptide_length
+        hash[aaseq] ||= []
+        hash[aaseq].push( prot.header.sub(/^>/,'') )
+      end
+    end
+    #fh.puts( prot.header.split(/\s+/).first.sub(/^>/,'') + "\t" + SampleEnzyme.tryptic(prot.aaseq, missed_cleavages).join(" ") )
+  end
+
+  File.open(new_filename, "w") do |fh|
+    hash.keys.sort_by {|pep| hash[pep].size }.reverse.each do |pep|
+      fh.puts( [pep, *(hash[pep])].join("\t") )
+    end     
+  end
+end
+
+
+
+

data/script/filter-peps.rb

@@ -123,14 +123,18 @@ puts csv_headers.join(DELIMITER)
 files.each_with_index do |file,i|
 
   obj = SpecID.new(file)
+  obj.peps = obj.pep_prots
+
+
   obj.peps.each do |pep|
     pep.charge = pep.charge.to_i
     pep.xcorr = pep.xcorr.to_f
     pep.deltacn = pep.deltacn.to_f
   end
+  
 
   re_prefix = /^#{Regexp.escape(prefixes[i])}/
-  prc = proc {|it| it.prot.reference =~ re_prefix }
+  prc = proc {|it| it.prots.first.reference =~ re_prefix }
   #(match, nomatch) = obj.classify(:peps, prc)
   (fp, tp) = obj.classify(:peps, prc)
 

data/test/tc_align.rb

@@ -64,7 +64,7 @@ class AlignTest < Test::Unit::TestCase
     expx2 = [-10,-9,-8,-7,-6,-5,-4,-3,-2,-1,1,2,3,4,5,6,7,8,9]
     expy2 = [-10,-9,-8,-7,-6,-5,-4,-3,-2,-1,1,2,3,4,5,6,7,8,9]
 
-    pcls = SpecID::Proph::Pep
+    pcls = Proph::Pep
     scls = Spec::Scan
 
     pep_groups = [x,y].collect do |arr|

data/test/tc_bioworks.rb

@@ -19,33 +19,34 @@ class BioworksTest < Test::Unit::TestCase
   end
 
   def test_bioworks_pep
-    hash = {:sequence => 0, :mass => 1, :deltamass => 2, :charge => 3, :xcorr => 4, :deltacn => 5, :sp => 6, :rsp => 7, :ions => 8, :count => 9, :tic => 10, :prot => 11, :base_name => 12, :first_scan => 13, :last_scan => 14, :peptide_probability => 15, :file => 16, :_num_prots => 17, :_first_prot => 18}
-    pep = SpecID::Bioworks::Pep.new(hash)
+    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|
       assert_equal(v, pep.send(k))
     end
   end
 
+
   # NEED TO DEBUG THIS PROB!
   def test_xml_parsing
-    obj = SpecID::Bioworks.new(@tf_bioworks_xml_really_small)
+    obj = Bioworks.new(@tf_bioworks_xml_really_small)
     assert_equal(19, obj.prots.size)
-    #obj = SpecID::Bioworks.new(@tf_bioworks_xml_small)
+    #obj = Bioworks.new(@tf_bioworks_xml_small)
     #assert_equal(106, obj.prots.size)
   end
 
   def Xtest_xml_parsing_speed
     if File.exist? @tfiles_l
-    #puts Benchmark.bm {|b|
-      obj = SpecID::Bioworks.new(@tf_bioworks_xml)
-    #}
+      #puts Benchmark.bm {|b|
+      obj = Bioworks.new(@tf_bioworks_xml)
+      #}
     else
       assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
     end
   end
 
   def test_xml_parsing_bioworks_single
-    obj = SpecID::Bioworks.new(@tf_bioworks_single_xml_small)
+    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'
@@ -61,17 +62,17 @@ class BioworksTest < Test::Unit::TestCase
 
   def test_to_excel
     tmpfile = @tfiles + "tf_bioworks_to_excel.tmp"
-    bio = SpecID::Bioworks.new(@tf_bioworks_to_excel)
+    bio = Bioworks.new(@tf_bioworks_to_excel)
     bio.to_excel tmpfile
     assert( File.exist?(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/)
+      _assert_equal_pieces(exp[i], act[i], exp[i][0] =~ /\d/)
     end
-      
-    File.unlink tmpfile
+
+    #File.unlink tmpfile
   end
 
   # prot is boolean if this is a protein line!
@@ -85,13 +86,15 @@ class BioworksTest < Test::Unit::TestCase
       elsif i == 6 && !prot
         assert_in_delta(exp[i].to_f, act[i].to_f, 0.01)
       elsif i == 9 && prot
+        ## NEED TO GET THESE BACK (for consistency):
         assert_match(exp[i].split(" ")[0], act[i].split(" ")[0])
       else
+        ## NEED TO GET THESE BACK (for consistency):
         assert_equal(exp[i], act[i], "#{i} index")
       end
     end
   end
-  
+
 
   # takes a bioworks excel (in txt format) and outputs an arr of arrs
   def _arr_of_arrs(file)
@@ -105,34 +108,34 @@ class BioworksTest < Test::Unit::TestCase
     cnt = 0
     answer = [%w(2 PEPTIDE), %w(3 PEPTIDE), %w(3 PEPY), %w(2 PEPY)]
     exp_peps = answer.collect! do |arr|
-      pep = SpecID::Bioworks::Pep.new
+      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 = SpecID::Bioworks::Prot.new
+        prot = Bioworks::Prot.new
         prot.reference = "#{num}"
         prot
       end
     end
     exp_peps = exp_peps.zip(exp_prots)
     exp_peps.collect! do |both|
-      both[0].prot = both[1]
+      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 = SpecID::Bioworks::Pep.new
+      pep = Bioworks::Pep.new
       pep.charge = arr[0]
       pep.sequence = arr[1]
-      pep.prot = SpecID::Bioworks::Prot.new
-      pep.prot.reference = "#{cnt}"
+      pep.prots = [Bioworks::Prot.new]
+      pep.prots.first.reference = "#{cnt}"
       cnt += 1
       pep
     end
-    peptides, proteins = SpecID::Bioworks.new._uniq_peps_by_sequence_charge(peptides)
+    peptides, proteins = Bioworks.new._uniq_peps_by_sequence_charge(peptides)
     assert_equal(peptides.size, proteins.size)
     exp_peps.each_with_index do |pep, i|
       assert_equal(pep.charge, peptides[i].charge)
@@ -147,7 +150,7 @@ class BioworksTest < Test::Unit::TestCase
   end
 
   def test_extract_file_info
-    pep = SpecID::Bioworks::Pep.new
+    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|

data/test/tc_bioworks_to_pepxml.rb

@@ -3,6 +3,22 @@ require 'test/unit'
 require File.dirname(File.expand_path(__FILE__)) + '/load_bin_path'
 require 'fileutils'
 
+tmp = $VERBOSE
+$VERBOSE = 5
+
+$XML_SANITY_LINES = ['<sample_enzyme name="trypsin">', '<specificity cut="KR" no_cut="P" sense="C"/>', '<parameter name="diff_search_options" value="0.000000 S 0.000000 C 0.000000 M 0.000000 X 0.000000 T 0.000000 Y"/>']
+
+$XML_SANITY_MATCHES = [/<spectrum_query spectrum="0\d0.\d+.\d+.[123]" start_scan="\d+" end_scan="\d+" precursor_neutral_mass="[\d\.]+" assumed_charge="[123]" index="\d+">/,
+  /	<search_hit hit_rank="\d" peptide="[\w\-\.]+" peptide_prev_aa="." peptide_next_aa="." protein=".*" num_tot_proteins="\d+" num_matched_ions="\d+" tot_num_ions="\d+" calc_neutral_pep_mass="[\d\.]+" massdiff="[\+\-][\d\.]+" num_tol_term="\d" num_missed_cleavages="\d" is_rejected="[01]">/, 
+  /<search_score name="xcorr" value="[\d\.]+"\/>/,
+  /<search_score name="deltacn" value="[\d\.]+"\/>/, 
+  /<search_score name="deltacnstar" value="[01]"\/>/, 
+  /<search_score name="spscore" value="[\d\.]+"\/>/, 
+  /<search_score name="sprank" value="\d+"\/>/,
+]
+
+
+
 
 class BioworksToPepXMLTest < Test::Unit::TestCase
 
@@ -13,7 +29,7 @@ class BioworksToPepXMLTest < Test::Unit::TestCase
     @tf_mzxml_path = @tfiles_l + "yeast_gly_mzXML"
     @tf_bioworks_xml = @tfiles + "bioworks_small.xml"
     @tf_params = @tfiles + "bioworks32.params"
-    @no_delete = false
+    @no_delete = true
     @out_path = @tfiles + 'pepxml/'
     @cmd = "ruby -I#{File.join(File.dirname(__FILE__), "..", "lib")} -S bioworks_to_pepxml.rb "
   end
@@ -23,8 +39,9 @@ class BioworksToPepXMLTest < Test::Unit::TestCase
   end
 
   def _basic(cmd, prc)
-    puts "Performing: #{cmd}"
-    puts `#{cmd}`
+    puts "Performing: #{cmd}" if $VERBOSE
+    reply = `#{cmd}`
+    puts reply if $VERBOSE
     %w(000 020).each do |file|
       ffile = @out_path + file + ".xml"
       prc.call(ffile)
@@ -33,11 +50,25 @@ class BioworksToPepXMLTest < Test::Unit::TestCase
 
   def test_basic
     if File.exist? @tfiles_l
-      cmd = "#{@cmd} -p #{@tf_params} -o #{@out_path} #{@tf_bioworks_xml} -m #{@tf_mzxml_path} -d /work/special/path"
+      cmd = "#{@cmd} -p #{@tf_params} -o #{@out_path} #{@tf_bioworks_xml} -m #{@tf_mzxml_path} -d /work/special/path --copy_mzxml"
+      ## FILES EXIST:
       prc = proc {|file| 
         assert(File.exist?(file), "#{file} exists")
+        beginning = IO.readlines(file)[0,50].join("\n")
+        $XML_SANITY_LINES.each do |line|
+          assert(beginning.include?(line), "xml includes line: #{line}")
+        end
+        $XML_SANITY_MATCHES.each do |match|
+          assert_match(match, beginning, "matches")
+        end
       }
       _basic(cmd, prc)
+      ## COPY MZXML:
+      %w(000 020).each do |file|
+        mzxml_file = File.join(@out_path, "#{file}.mzXML")
+        assert(File.exist?( mzxml_file ), "file: #{mzxml_file} exists")
+      end
+      ## CLEANUP:
       unless @no_delete then FileUtils.rm_rf(@out_path) end
     else
       assert_nil( puts("--SKIPPING TEST-- (missing dir: #{@tfiles_l})") )
@@ -60,3 +91,5 @@ class BioworksToPepXMLTest < Test::Unit::TestCase
     end
   end
 end
+
+$VERBOSE = tmp

data/test/tc_fasta.rb

@@ -26,7 +26,6 @@ class FastaTest < Test::Unit::TestCase
     @inv_ext = Fasta::INV_FILE_POSTFIX
 
     @tfiles = File.dirname(__FILE__) + '/tfiles/'
-    @tmpfile = @tfiles + "tmp.tmp"
     @base_cmd = "ruby -I #{File.join(File.dirname(__FILE__), "..", "lib")} -S "
     @fasta_mod_cmd = @base_cmd + "fasta_mod.rb "
     @fasta_cat_mod_cmd = @base_cmd + "fasta_cat_mod.rb "
@@ -41,6 +40,7 @@ class FastaTest < Test::Unit::TestCase
 
   def test_read_file
     obj = Fasta.new.read_file(@sf)
+    @tmpfile = @tfiles + "tmp.tmp"
     obj.write_file(@tmpfile)
     assert_not_equal_file_content(@tmpfile, @sf)
     obj2 = Fasta.new.read_file(@tmpfile)
@@ -74,6 +74,7 @@ class FastaTest < Test::Unit::TestCase
     assert('f1__f2.ext1', Fasta.cat_filenames(['f1.ext1', 'f2.ext2'], '__'))
   end
 
+=begin
   def test_mod
     ## Testing shuffle:
     `#{@fasta_mod_cmd + 'shuffle ' + @sf}`
@@ -105,6 +106,7 @@ class FastaTest < Test::Unit::TestCase
     assert_equal(ob1.prots.size, IO.read(@sf_invert).scan(/>_HELLO_/).size)
     File.unlink(@sf_invert)
   end
+=end
 
   def test_gi
     gis = ['>gi|7427923|pir||PHRBG glycogen phosphorylase (EC 2.4.1.1), muscle - rabbit', '>sp|lollygag|helloyou', '>only has one bar | and thats it', 'notme|me|nome', '>lots|an|lots|of|bars|heehee']

data/test/tc_fasta_shaker.rb

@@ -1,6 +1,7 @@
 
 require 'test/unit'
 require 'fasta'
+require File.dirname(__FILE__) + '/load_bin_path.rb'
 
 Filestring = ">gi|P1
 AMKRGAN
@@ -55,13 +56,13 @@ class TestBasic < Test::Unit::TestCase
     File.unlink @f if File.exist? @f
   end
 
-  def test_reverse
+  def Xtest_reverse
     cmd = @cmd + "reverse #{@tmpfile} -o #{@f}"
     system cmd
     assert_equal(Rev, fastap(@f).to_s)
   end
 
-  def test_reverse_tryptic
+  def Xtest_reverse_tryptic
     cmd = @cmd + "reverse #{@tmpfile} -o #{@f} --tryptic_peptides"
     system cmd
     assert_equal(RevTryptic, fastap(@f).to_s)
@@ -69,6 +70,7 @@ class TestBasic < Test::Unit::TestCase
 
   def test_shuff_tryptic
     cmd = @cmd + "shuffle #{@tmpfile} -o #{@f} --tryptic_peptides"
+
     system cmd
     lns = fastap(@f).to_s.split("\n")
     assert_equal('KR', lns[1][2..3])
@@ -77,7 +79,7 @@ class TestBasic < Test::Unit::TestCase
     assert_not_equal('CRGATKKTAGRPMEK', lns[3], "sequence is randomised from original [remote chance of failure] rerun to make sure")
   end
 
-  def test_shuffle
+  def Xtest_shuffle
     cmd = @cmd + "shuffle #{@tmpfile} -o #{@f}"
     system cmd
     clines = strlns(Filestring)
@@ -89,7 +91,7 @@ class TestBasic < Test::Unit::TestCase
     assert_not_equal('CRGATKKTAGRPMEK', lns[3], "sequence is randomised from original [remote chance of failure] rerun to make sure")
   end
 
-  def test_cat
+  def Xtest_cat
     cmd = @cmd + "reverse #{@tmpfile} -c -o #{@f}"
     `#{cmd}`  ## suppress warning
     lns = fastalns(@f)
@@ -97,7 +99,7 @@ class TestBasic < Test::Unit::TestCase
     assert_equal(strlns(Rev), lns[6..-1], "second part equal")      
   end
 
-  def test_fraction
+  def Xtest_fraction
     cmd = @cmd + "reverse #{@tmpfile} -f 2.6 -o #{@f}"
     `#{cmd}`
     assert_equal(8, fastap(@f).size)
@@ -118,7 +120,7 @@ class TestBasic < Test::Unit::TestCase
     #cmd = @cmd + "reverse #{@tmpfile} -c -f 2.0 -o #{@f}"
   end
 
-  def test_prefix
+  def Xtest_prefix
     cmd = @cmd + "reverse #{@tmpfile} -p SILLY_ -o #{@f}"
     `#{cmd}`
     fp = fastap(@f)