ms-ident 0.0.2

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/Gemfile

@@ -0,0 +1,31 @@
+source "http://rubygems.org"
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+gem 'nokogiri'
+gem 'ms-core', ">= 0.0.12"
+gem 'andand'
+
+dev_gems = {
+    "spec-more" => ">= 0.0.4",
+    "bundler" => "~> 1.0.0",
+    "jeweler" => "~> 1.5.2",
+    "rcov" => ">= 0",
+}
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  dev_gems.each do |name,version_string|
+    gem name, version_string
+  end
+end
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development_large do
+  dev_gems.each do |name,version_string|
+    gem name, version_string
+  end
+  gem "ms-testdata", ">= 0.1.1"
+end

data/Gemfile.lock

@@ -0,0 +1,32 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    andand (1.3.1)
+    bacon (1.1.0)
+    bio (1.4.1)
+    git (1.2.5)
+    jeweler (1.5.2)
+      bundler (~> 1.0.0)
+      git (>= 1.2.5)
+      rake
+    ms-core (0.0.12)
+      bio (>= 1.4.1)
+    ms-testdata (0.1.1)
+    nokogiri (1.4.4)
+    rake (0.8.7)
+    rcov (0.9.9)
+    spec-more (0.0.4)
+      bacon
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  andand
+  bundler (~> 1.0.0)
+  jeweler (~> 1.5.2)
+  ms-core (>= 0.0.12)
+  ms-testdata (>= 0.1.1)
+  nokogiri
+  rcov
+  spec-more (>= 0.0.4)

data/LICENSE

@@ -0,0 +1,61 @@
+Work on pepxml is from the original mspire library, whose license is
+duplicated here:
+===============================================================================
+Copyright (c) 2006, The University of Texas at Austin("U.T. Austin"). All
+rights reserved.  
+
+Software by John T. Prince under the direction of Edward M. Marcotte.
+
+By using this software the USER indicates that he or she has read, understood
+and will comply with the following:
+
+U. T. Austin hereby grants USER permission to use, copy, modify, merge,
+publish, distribute, sublicense, and/or sell copies of this software and its
+documentation for any purpose and without fee, provided that a full copy of
+this notice is included with the software and its documentation.
+
+Title to copyright this software and its associated documentation shall at all
+times remain with U. T. Austin. No right is granted to use in advertising,
+publicity or otherwise any trademark, service mark, or the name of U. T.
+Austin.
+
+This software and any associated documentation are provided "as is," and U. T.
+AUSTIN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESSED OR IMPLIED, INCLUDING
+THOSE OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, OR THAT USE OF
+THE SOFTWARE, MODIFICATIONS, OR ASSOCIATED DOCUMENTATION WILL NOT INFRINGE ANY
+PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER INTELLECTUAL PROPERTY RIGHTS OF A
+THIRD PARTY. U. T. Austin, The University of Texas System, its Regents,
+officers, and employees shall not be liable under any circumstances for any
+direct, indirect, special, incidental, or consequential damages with respect
+to any claim by USER or any third party on account of or arising from the use,
+or inability to use, this software or its associated documentation, even if U.
+T. Austin has been advised of the possibility of those damages.
+
+Submit software operation questions to: Edward M. Marcotte, Department of
+Chemistry and Biochemistry, U. T. Austin, Austin, Texas 78712.
+===============================================================================
+
+The rest of the work (and modifications) are licensed here:
+===============================================================================
+Copyright (c) 2011 Brigham Young University
+Author: John T. Prince
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+===============================================================================

data/README.rdoc

@@ -0,0 +1,97 @@
+= ms-ident
+
+Working with mass spectrometry based peptide/protein identifications.  Includes support for building pepxml files.
+
+Planned support for mzIdentML and reading pepxml.
+
+== Synposis
+
+=== Generating a pepxml file
+
+This example shows a very block oriented way of constructing a pepxml.
+Objects or empty data structures are passed into blocks for subcategories to
+use.  Because there are a lot of attributes to manage, most objects accept upon 
+initialization or later with 'merge!'
+
+    pepxml = Pepxml.new do |msms_pipeline_analysis|
+      msms_pipeline_analysis.merge!(:summary_xml => "020.xml") do |msms_run_summary|
+        # prep the sample enzyme and search_summary
+        msms_run_summary.merge!(
+          :base_name => '/home/jtprince/dev/mspire/020', 
+          :ms_manufacturer => 'Thermo', 
+          :ms_model => 'LTQ Orbitrap', 
+          :ms_ionization => 'ESI', 
+          :ms_mass_analyzer => 'Ion Trap', 
+          :ms_detector => 'UNKNOWN'
+        ) do |sample_enzyme, search_summary, spectrum_queries|
+          sample_enzyme.merge!(:name=>'Trypsin',:cut=>'KR',:no_cut=>'P',:sense=>'C')
+          search_summary.merge!(
+            :base_name=>'/path/to/file/020',
+            :search_engine => 'SEQUEST',
+            :precursor_mass_type =>'monoisotopic',
+            :fragment_mass_type => 'average'
+          ) do |search_database, enzymatic_search_constraint, modifications, parameters|
+            search_database.merge!(:local_path => '/path/to/db.fasta', :seq_type => 'AA') # note seq_type == type
+            enzymatic_search_constraint.merge!(
+              :enzyme => 'Trypsin', 
+              :max_num_internal_cleavages => 2,
+              :min_number_termini => 2
+            )
+            modifications << Pepxml::AminoacidModification.new(
+              :aminoacid => 'M', :massdiff => 15.9994, :mass => Ms::Mass::AA::MONO['M']+15.9994,
+              :variable => 'Y', :symbol => '*')
+              # invented, for example, a protein terminating mod
+            modifications << Pepxml::TerminalModification.new( 
+              :terminus => 'c', :massdiff => 23.3333, :mass => Ms::Mass::MONO['oh'] + 23.3333, 
+              :variable => 'Y', :symbol => '[', :protein_terminus => 'c', 
+              :description => 'leave protein_terminus off if not protein mod'
+            )
+            modifications << Pepxml::TerminalModification.new( 
+              :terminus => 'c', :massdiff => 25.42322, :mass => Ms::Mass::MONO['h+'] + 25.42322, 
+              :variable => 'N', :symbol => ']', :description => 'example: c term mod'
+            )
+            parameters.merge!( 
+                              :fragment_ion_tolerance => 1.0000, 
+                              :digest_mass_range => '600.0 3500.0', 
+                              :enzyme_info => 'Trypsin(KR/P) 1 1 KR P', # etc.... 
+                             )
+          end
+          spectrum_query1 = Pepxml::SpectrumQuery.new(
+            :spectrum  => '020.3.3.1', :start_scan => 3, :end_scan => 3, 
+            :precursor_neutral_mass => 1120.93743421875, :assumed_charge => 1
+          ) do |search_results|
+            search_result1 = Pepxml::SearchResult.new do |search_hits|
+              modpositions = [[1, 243.1559], [6, 167.0581], [7,181.085]].map do |pair|  
+                Pepxml::SearchHit::ModificationInfo::ModAminoacidMass.new(*pair)
+              end
+              # order(modified_peptide, mod_aminoacid_masses, :mod_nterm_mass, :mod_cterm_mass)
+              # or can be set by hash
+              mod_info = Pepxml::SearchHit::ModificationInfo.new('Y#RLGGS#T#K', modpositions)
+              search_hit1 = Pepxml::SearchHit.new( 
+                :hit_rank=>1, :peptide=>'YRLGGSTK', :peptide_prev_aa => "R", :peptide_next_aa => "K",
+                :protein => "gi|16130113|ref|NP_416680.1|", :num_tot_proteins => 1, :num_matched_ions => 5,
+                :tot_num_ions => 35, :calc_neutral_pep_mass => 1120.93163442, :massdiff => 0.00579979875010395,
+                :num_tol_term => 2, :num_missed_cleavages => 1, :is_rejected => 0, 
+                :modification_info => mod_info) do |search_scores|
+                  search_scores.merge!(:xcorr => 0.12346, :deltacn => 0.7959, :deltacnstar => 0, 
+                                     :spscore => 29.85, :sprank => 1)
+                end
+              search_hits << search_hit1
+            end
+            search_results << search_result1
+          end
+          spectrum_queries << spectrum_query1
+        end
+      end
+    end
+    puts pepxml.to_xml
+
+The block is optional in initalization or with merge!  You can just as easily
+set the needed attributes directly. 
+
+    msms_run_summary.new(:search_summary => my_search_summary, :spectrum_queries => spec_queries)
+    msms_run_summary.sample_enzyme = sample_enzyme_object
+
+== Copyright
+
+see LICENSE

data/Rakefile

@@ -0,0 +1,54 @@
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "ms-ident"
+  gem.homepage = "http://github.com/jtprince/ms-ident"
+  gem.license = "MIT"
+  gem.summary = %Q{mspire library for working with mzIdentML and pepxml}
+  gem.description = %Q{mspire library for working with mzIdentML and pepxml}
+  gem.email = "jtprince@gmail.com"
+  gem.authors = ["John T. Prince"]
+  gem.rubyforge_project = 'mspire'
+  # Include your dependencies below. Runtime dependencies are required when using your gem,
+  # and development dependencies are only needed for development (ie running rake tasks, tests, etc)
+  #  gem.add_runtime_dependency 'jabber4r', '> 0.1'
+  #  gem.add_development_dependency 'rspec', '> 1.2.3'
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+require 'rcov/rcovtask'
+Rcov::RcovTask.new do |spec|
+  spec.libs << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
+end
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "ms-ident #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.2

data/lib/merge.rb

@@ -0,0 +1,7 @@
+module Merge
+  # allows objects to be set from a hash
+  def merge!(hash={}, &block)
+    hash.each {|k,v| send("#{k}=",v) }
+    block.call(block_arg) if block
+  end
+end

data/lib/ms/ident/pepxml/modifications/sequest.rb

@@ -0,0 +1,237 @@
+require 'ms/ident/pepxml/modifications'
+require 'ms/ident/pepxml/search_hit/modification_info'
+
+module Ms ; end
+module Ms::Ident ; end
+class Ms::Ident::Pepxml ; end
+
+module Ms::Ident::Pepxml::Modifications 
+  # Handles modifications for sequest style searches
+  class Sequest
+    include Ms::Ident::Pepxml::Modifications 
+
+    # a hash of all differential modifications present by aa_one_letter_symbol
+    # and special_symbol. This is NOT the mass difference but the total mass {
+    # 'M*' => 155.5, 'S@' => 190.3 }.  NOTE: Since the termini are dependent on
+    # the amino acid sequence, they are give the *differential* mass.  The
+    # termini are given the special symbol as in sequest e.g. '[' => 12.22, #
+    # cterminus    ']' => 14.55 # nterminus
+    attr_accessor :masses_by_diff_mod_hash
+    # a hash, key is [AA_one_letter_symbol.to_sym, difference.to_f]
+    # values are the special_symbols
+    attr_accessor :mod_symbols_hash
+
+    # sequest params object
+    attr_accessor :params
+
+
+    # The modification symbols string looks like this:
+    # (M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000)
+    # ct is cterminal peptide (differential)
+    # nt is nterminal peptide (differential)
+    # the C is just cysteine
+    # will set_modifications and masses_by_diff_mod hash
+    def initialize(params=nil, modification_symbols_string='')
+      @params = params
+      if @params
+        set_modifications(params, modification_symbols_string)
+      end
+    end
+
+    # set the masses_by_diff_mod and mod_symbols_hash from 
+    def set_hashes(modification_symbols_string)
+
+      @mod_symbols_hash = {}
+      @masses_by_diff_mod = {}
+      if (modification_symbols_string == nil || modification_symbols_string == '')
+        return nil
+      end
+      table = @params.mass_table
+      modification_symbols_string.split(/\)\s+\(/).each do |mod|
+        if md = mod.match(/\(?(\w+)(.) (.[\d\.]+)\)?/)
+          if md[1] == 'ct' || md[1] == 'nt' 
+            mass_diff = md[3].to_f
+            @masses_by_diff_mod[md[2]] = mass_diff
+            @mod_symbols_hash[[md[1].to_sym, mass_diff]] = md[2].dup
+          else
+            symbol_string = md[2].dup 
+            mass_diff = md[3].to_f
+            md[1].split('').each do |aa|
+              aa_as_sym = aa.to_sym
+              @masses_by_diff_mod[aa+symbol_string] = mass_diff + table[aa_as_sym]
+              @mod_symbols_hash[[aa_as_sym, mass_diff]] = symbol_string
+            end
+          end
+        end
+      end
+    end
+
+    # given a bare peptide (no end pieces) returns a ModificationInfo object
+    # e.g. given "]PEPT*IDE", NOT 'K.PEPTIDE.R'
+    # if there are no modifications, returns nil
+    def modification_info(peptide)
+      if @masses_by_diff_mod.size == 0
+        return nil
+      end
+      hash = {}
+      hash[:modified_peptide] = peptide.dup
+      hsh = @masses_by_diff_mod  
+      table = @params.mass_table
+      h = table[:h]  # this? or h_plus ??
+      oh = table[:o] + h
+      ## only the termini can match a single char
+      if hsh.key? peptide[0,1]
+        # AA + H + differential_mod
+        hash[:mod_nterm_mass] = table[peptide[1,1].to_sym] + h + hsh[peptide[0,1]]
+        peptide = peptide[1...(peptide.size)]
+      end
+      if hsh.key? peptide[(peptide.size-1),1]
+        # AA + OH + differential_mod
+        hash[:mod_cterm_mass] = table[peptide[(peptide.size-2),1].to_sym] + oh + hsh[peptide[-1,1]]
+        peptide.slice!( 0..-2 )
+        peptide = peptide[0...(peptide.size-1)]
+      end
+      mod_array = []
+      (0...peptide.size).each do |i|
+        if hsh.key? peptide[i,2]
+          mod_array << Ms::Ident::Pepxml::SearchHit::ModificationInfo::ModAminoacidMass.new([ i+1 , hsh[peptide[i,2]] ])
+        end
+      end
+      if mod_array.size > 0
+        hash[:mod_aminoacid_masses] = mod_array
+      end
+      if hash.size > 1  # if there is more than just the modified peptide there
+        Ms::Ident::Pepxml::SearchHit::ModificationInfo.new(hash)
+        #Ms::Ident::Pepxml::SearchHit::ModificationInfo.new(hash.values_at(:modified_peptide, :mod_aminoacid_masses, :mod_nterm_mass, :mod_cterm_mass)
+      else
+        nil
+      end
+    end
+
+    # returns an array of static mod objects and static terminal mod objects
+    def create_static_mods(params)
+
+      ####################################
+      ## static mods
+      ####################################
+
+      static_mods = [] # [[one_letter_amino_acid.to_sym, add_amount.to_f], ...]
+      static_terminal_mods = [] # e.g. [add_Cterm_peptide, amount.to_f]
+
+      params.mods.each do |k,v|
+        v_to_f = v.to_f
+        if v_to_f != 0.0
+          if k =~ /add_(\w)_/
+            static_mods << [$1.to_sym, v_to_f]
+          else
+            static_terminal_mods << [k, v_to_f]
+          end
+        end
+      end
+      aa_hash = params.mass_table
+
+      ## Create the static_mods objects
+      static_mods.map! do |mod|
+        hash = {
+          :aminoacid => mod[0].to_s,
+          :massdiff => mod[1],
+          :mass => aa_hash[mod[0]] + mod[1],
+          :variable => 'N',
+          :binary => 'Y',
+        } 
+        Ms::Ident::Pepxml::AminoacidModification.new(hash)
+      end
+
+      ## Create the static_terminal_mods objects
+      static_terminal_mods.map! do |mod|
+        terminus = if mod[0] =~ /Cterm/ ; 'c'
+                   else                 ; 'n' # only two possible termini
+                   end
+        protein_terminus = case mod[0] 
+                           when /Nterm_protein/ ; 'n'
+                           when /Cterm_protein/ ; 'c'
+                           else nil
+                           end
+
+        # create the hash                            
+        hash = {
+          :terminus => terminus,
+          :massdiff => mod[1],
+          :variable => 'N',
+          :description => mod[0],
+        }
+        hash[:protein_terminus] = protein_terminus if protein_terminus
+        Ms::Ident::Pepxml::TerminalModification.new(hash)
+      end
+      [static_mods, static_terminal_mods]
+    end
+
+    # 1. sets aminoacid_modifications and terminal_modifications from a sequest params object
+    # 2. sets @params
+    # 3. sets @masses_by_diff_mod
+    def set_modifications(params, modification_symbols_string)
+      @params = params
+
+      set_hashes(modification_symbols_string)
+      (static_mods, static_terminal_mods) = create_static_mods(params)
+
+      aa_hash = params.mass_table
+      #################################
+      # Variable Mods:
+      #################################
+      arr = params.diff_search_options.rstrip.split(/\s+/)
+      # [aa.to_sym, diff.to_f]
+      variable_mods = []
+      (0...arr.size).step(2) do |i|
+        if arr[i].to_f != 0.0
+          variable_mods << [arr[i+1], arr[i].to_f]
+        end
+      end
+      mod_objects = []
+      variable_mods.each do |mod|
+        mod[0].split('').each do |aa|
+          hash = {
+
+            :aminoacid => aa,
+            :massdiff => mod[1],
+            :mass => aa_hash[aa.to_sym] + mod[1],
+            :variable => 'Y',
+            :binary => 'N',
+            :symbol => @mod_symbols_hash[[aa.to_sym, mod[1]]],
+          }
+          mod_objects << Ms::Ident::Pepxml::AminoacidModification.new(hash)
+        end
+      end
+      variable_mods = mod_objects
+      #################################
+      # TERMINAL Variable Mods:
+      #################################
+      # These are always peptide, not protein termini (for sequest)
+      (nterm_diff, cterm_diff) = params.term_diff_search_options.rstrip.split(/\s+/).map{|v| v.to_f }
+
+      to_add = []
+      if nterm_diff != 0.0
+        to_add << ['n',nterm_diff.to_plus_minus_string, @mod_symbols_hash[:nt, nterm_diff]]
+      end
+      if cterm_diff != 0.0
+        to_add << ['c', cterm_diff.to_plus_minus_string, @mod_symbols_hash[:ct, cterm_diff]]
+      end
+
+      variable_terminal_mods = to_add.map do |term, mssdiff, symb|
+        hash = {
+          :terminus => term,
+          :massdiff => mssdiff,
+          :variable => 'Y',
+          :symbol => symb,
+        }
+        Ms::Ident::Pepxml::TerminalModification.new(hash)
+      end
+
+      #########################
+      # COLLECT THEM
+      #########################
+      @aminoacid_modifications = static_mods + variable_mods
+      @terminal_modifications = static_terminal_mods + variable_terminal_mods
+    end
+  end
+

data/lib/ms/ident/pepxml/modifications.rb

@@ -0,0 +1,94 @@
+require 'merge'
+require 'nokogiri'
+
+module Ms ; end
+module Ms::Ident ; end
+class Ms::Ident::Pepxml ; end
+
+# holds a list of AminoacidModification and TerminalModification objects.
+class Ms::Ident::Pepxml::Modifications < Array
+  ## Generates the pepxml for static and differential amino acid mods based on
+  ## sequest object
+  def to_xml(builder=nil)
+    xmlb = builder || Nokogiri::XML::Builder.new
+    self.each {|mod| mod.to_xml(xmlb) }
+    builder || xmlb.doc.root.to_xml
+  end
+end
+
+# Modified aminoacid, static or variable
+# unless otherwise stated, all attributes can be anything
+class Ms::Ident::Pepxml::AminoacidModification
+  include Merge
+  # The amino acid (one letter code)
+  attr_accessor :aminoacid
+  # Mass difference with respect to unmodified aminoacid, as a Float
+  attr_accessor :massdiff
+  # Mass of modified aminoacid, Float
+  attr_accessor :mass
+  # Y if both modified and unmodified aminoacid could be present in the
+  # dataset, N if only modified aminoacid can be present
+  attr_accessor :variable
+  # whether modification can reside only at protein terminus (specified 'n',
+  # 'c', or 'nc')
+  attr_accessor :peptide_terminus
+  # Symbol used by search engine to designate this modification
+  attr_accessor :symbol
+  # 'Y' if each peptide must have only modified or unmodified aminoacid, 'N' if a
+  # peptide may contain both modified and unmodified aminoacid
+  attr_accessor :binary
+
+  def initialize(hash={})
+    merge!(hash)
+  end
+
+  # returns the builder or an xml string if no builder supplied
+  def to_xml(builder=nil)
+    xmlb = builder || Nokogiri::XML::Builder.new
+    # note massdiff: must begin with either + (nonnegative) or - [e.g.
+    # +1.05446 or -2.3342] consider Numeric#to_plus_minus_string in
+    # Ms::Ident::Pepxml
+    attrs = [:aminoacid, :massdiff, :mass, :variable, :peptide_terminus, :symbol, :binary].map {|at| v=send(at) ; [at,v] if v }.compact
+    hash = Hash[attrs]
+    hash[:massdiff] = hash[:massdiff].to_plus_minus_string
+    xmlb.aminoacid_modification(hash)
+    builder || xmlb.doc.root.to_xml
+  end
+end
+
+# Modified aminoacid, static or variable
+class Ms::Ident::Pepxml::TerminalModification
+  include Merge
+  # n for N-terminus, c for C-terminus
+  attr_accessor :terminus
+  # Mass difference with respect to unmodified terminus
+  attr_accessor :massdiff
+  # Mass of modified terminus
+  attr_accessor :mass
+  # Y if both modified and unmodified terminus could be present in the
+  # dataset, N if only modified terminus can be present
+  attr_accessor :variable
+  # MSial symbol used by search engine to designate this modification
+  attr_accessor :symbol
+  # whether modification can reside only at protein terminus (specified n or
+  # c)
+  attr_accessor :protein_terminus
+  attr_accessor :description
+
+  def initialize(hash={})
+    hash.each {|k,v| send("#{k}=", v) }
+  end
+
+  # returns the builder or an xml string if no builder supplied
+  def to_xml(builder=nil)
+    xmlb = builder || Nokogiri::XML::Builder.new
+    #short_element_xml_from_instance_vars("terminal_modification")
+   attrs = [:terminus, :massdiff, :mass, :variable, :protein_terminus, :description].map {|at| v=send(at) ; [at,v] if v }
+   hash = Hash[attrs] 
+    hash[:massdiff] = hash[:massdiff].to_plus_minus_string
+    xmlb.terminal_modification(hash)
+    builder || xmlb.doc.root.to_xml
+  end
+end
+
+