mspire 0.3.1 → 0.3.9

data/lib/spec_id/precision/prob/output.rb

@@ -1,4 +1,4 @@
-
+require 'yaml'
 require 'spec_id/precision/output'
 require 'table'
 require 'matrix'
@@ -12,12 +12,18 @@ class SpecID::Precision::Prob::Output
   # returns array of data arrays and parallel labels
   def to_cols_and_labels(answer_hash)
     col_labels = %w(count probability peptide)
+    col_labels[1] = 'q_values' if answer_hash.key?(:q_values)
 
     cols = []
     cols << answer_hash[:count]
-    cols << answer_hash[:probabilities]
+    if answer_hash.key?(:q_values)
+      cols << answer_hash[:q_values]
+    else
+      cols << answer_hash[:probabilities]
+    end
     cols << answer_hash[:aaseqs]
 
+
     # if there is a single modified peptide, we'll include the column
     if answer_hash.key?(:modified_peptides)
       cols << answer_hash[:modified_peptides]

data/lib/spec_id/proph/pep_summary.rb

@@ -1,7 +1,6 @@
 
 require 'array_class'
-puts "REQUIRING"
-puts( require 'spec_id/sequest/pepxml' )
+require 'spec_id/sequest/pepxml'
 require 'spec_id/parser/proph'
 
 module Sequest ; end
@@ -13,10 +12,12 @@ module SpecID ; end
 module SpecID::Prot ; end
 module SpecID::Pep ; end
 
+
+
 module Proph
 
-  class PepSummary < Sequest::PepXML::MSMSRunSummary
-    # MSMSRunSummary is a SpecID object!
+  class PepSummary
+    include SpecID
 
     Filetype_and_version_re_new = /version="PeptideProphet v([\d\.]+) /
 
@@ -25,7 +26,7 @@ module Proph
     # the protein groups
     # currently these are just xml nodes returned!
     attr_accessor :peptideprophet_summary
-    attr_accessor :spectrum_queries
+    attr_accessor :msms_run_summaries
     attr_accessor :version
 
     def hi_prob_best ; true end
@@ -51,24 +52,26 @@ module Proph
     end
 
     def initialize(file=nil)
-      @prots = nil
       if file
         @version = get_version(file)
-        #@prot_groups = ProtSummary::Parser.new.parse_file(file)
-        SpecID::Parser::PepProph.new(:spec_id).parse(file, :spec_id => self)
+        spec_id = SpecID::Parser::PepProph.new(:spec_id).parse(file, :spec_id => self)
       end
     end
   end
 
+  # this is a SpecID::Pep (by interface: not including stuff yet)
   class PepSummary::Pep < Sequest::PepXML::SearchHit
-    %w(probability fval ntt nmc massd).each do |guy|
+
+    # aaseq is defined in SearchHit
+    
+    %w(probability fval ntt nmc massd prots).each do |guy|
       self.add_member(guy) 
     end
 
     # returns self
-    def from_pepxml_node(node, spec_query)
-      super(node, spec_query)
-      #pp_n = node.find_first('descendant::peptideprophet_result')
+    def from_pepxml_node(node)
+      super(node)
+
       an_res = node.find_first('child::analysis_result')
       pp_n = an_res.find_first('child::peptideprophet_result')
       self.probability = pp_n['probability'].to_f
@@ -87,6 +90,16 @@ module Proph
       self
     end
   end
+
+  ::Proph::PepSummary::Prot = ArrayClass.new(%w(name protein_descr peps))
+
+  class PepSummary::Prot
+    def first_entry ; self[0] end ## name
+    def reference ; self[0] + ' ' + self[1] end
+  end
+
 end
 
 
+
+

data/lib/spec_id/sequest.rb

@@ -1,5 +1,33 @@
 require 'spec_id/sequest/params'
+require 'hash_by'
+require 'sort_by_attributes.rb'
 
 module Sequest
+
+  # returns one array of peptide hits:  indexes hits based on index_by, takes
+  # the uniq ones and then sorts the group by sort_by (compatible with
+  # sort_by_attributes) then slices from first_index to last_index
+  # (inclusive).
+  def self.other_hits(peps, first_index=1, last_index=9, index_by=[:base_name, :first_scan, :charge], sort_by=[:xcorr, {:down => :xcorr}])
+    all_hits = []
+    peps.hash_by(*index_by).each do |scan_key, peps_per_scan|
+      if peps_per_scan.size >= (first_index + 1)
+        all_hits.push( *(peps_per_scan.uniq.sort_by_attributes(*sort_by)[first_index..last_index]) )
+      end
+    end
+    all_hits.compact
+  end
+
+  def self.other_hits_sorted_by_xcorr(peps, first_index, last_index, index_by=[:base_name, :first_scan, :charge])
+    all_hits = []
+    peps.hash_by(*index_by).each do |scan_key, peps_per_scan|
+      if peps_per_scan.size >= (first_index + 1)
+        all_hits.push( *(peps_per_scan.uniq.sort_by {|x| x.xcorr }.reverse[first_index..last_index]) )
+      end
+    end
+    all_hits.compact
+
+  end
+
 end
 

data/lib/spec_id/sequest/pepxml.rb

@@ -155,25 +155,6 @@ class Sequest::PepXML::MSMSRunSummary
     @ms_detector = node['msDetector']
     @raw_data_type = node['raw_data_type']
     @raw_data = node['raw_data']
-
-    sample_enzyme_n = node.find_first("child::sample_enzyme")
-    @sample_enzyme = SampleEnzyme.from_pepxml_node(sample_enzyme_n)
-
-    search_summary_n = sample_enzyme_n.find_first("following-sibling::search_summary")
-    spectrum_queries = search_summary_n.find("following-sibling::spectrum_query")
-    @spectrum_queries = spectrum_queries.map do |sq_n|
-      Sequest::PepXML::SpectrumQuery.from_pepxml_node(sq_n, self) 
-    end
-
-    ## NOTE: this is currently just the xml node!!!! TODO: wrap everything up
-    #into a better search summary object (to eventually depracate the params object)
-    @search_summary = node  ## in future call SearchSummary.from_pepxml_node
-    @peps = [] 
-    @spectrum_queries.each do |sq|
-      sq.search_results.each do |sr|
-        @peps.push( *(sr.search_hits) )
-      end
-    end
     self
   end
 end
@@ -353,7 +334,13 @@ Default_Options = {
     search_summary = Sequest::PepXML::SearchSummary.new( params, modifications_string, search_summary_options)
 
     # create the sample enzyme from the params object:
-    opts[:sample_enzyme] = params.sample_enzyme
+    sample_enzyme_obj = 
+      if opts[:sample_enzyme]
+        opts[:sample_enzyme]
+      else
+        params.sample_enzyme
+      end
+    opts[:sample_enzyme] = sample_enzyme_obj
 
     ## Create the pepxml obj and top level objects
     pepxml_obj = Sequest::PepXML.new(ppxml_version, params) 
@@ -390,36 +377,20 @@ Default_Options = {
     out_files = srf.out_files
     spectrum_queries_arr = Array.new(srf.dta_files.size)
     files_with_hits_index = 0  ## will end up being 1 indexed
-    srf.dta_files.each_with_index do |dta_file,i|
-      next if out_files[i].num_hits == 0
-      files_with_hits_index += 1
-
-      # We don't need to sort the hits by xcorr since it comes pre-sorted in
-      # srf files!
-      #arr = hits.sort_by{|v| v.xcorr }
-
-      # Get proper deltacn and deltacnstar
-      # under new srf, deltacn is already corrected for what prophet wants,
-      # deltacn_orig is how to access the old one
-      # Prophet deltacn is not the same as the native Sequest deltacn
-      # It is the deltacn of the second best hit!
-
-      hits = out_files[i].hits
-      top_hit = hits[0]
-      second_hit = hits[1]
-      deltacnstar =
-        if second_hit ; '0'
-        else ; '1'
-        end
-
-      ## mass calculations:
-      precursor_neutral_mass = dta_file.mh - h_plus
-      calc_neutral_pep_mass = top_hit[0] - h_plus
 
-      (start_scan, end_scan, charge) = srf_index[i]
+    deltacn_orig = opts[:deltacn_orig]
+    deltacn_index = 
+      if deltacn_orig ; 20
+      else 19
+      end
 
+    srf.dta_files.each_with_index do |dta_file,dta_i|
+      next if out_files[dta_i].num_hits == 0
+      files_with_hits_index += 1
 
+      precursor_neutral_mass = dta_file.mh - h_plus
 
+      (start_scan, end_scan, charge) = srf_index[dta_i]
       sq_hash = {
         :spectrum => [bn_noext, start_scan, end_scan, charge].join('.'),
         :start_scan => start_scan,
@@ -432,39 +403,70 @@ Default_Options = {
 
       spectrum_query = Sequest::PepXML::SpectrumQuery.new(sq_hash)
 
-      sequence = top_hit.sequence
-
-      #  NEED TO MODIFY SPLIT SEQUENCE TO DO MODS!
-      ## THIS IS ALL INNER LOOP, so we make every effort at speed here:
-      (prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(sequence)
-      # 0=mh 1=deltacn 2=sp 3=xcorr 4=id 5=num_other_loci 6=rsp 7=ions_matched 8=ions_total 9=sequence 10=prots 11=deltamass 12=ppm 13=aaseq 14=base_name 15=first_scan 16=last_scan 17=charge 18=srf 19=deltacn
-
-      sh_hash = {
-        :hit_rank => 1,
-        :peptide => pepseq,
-        :peptide_prev_aa => prevaa,
-        :peptide_next_aa => nextaa,
-        :protein => top_hit[10].first.reference.split(" ").first, 
-        :num_tot_proteins => top_hit[10].size,
-        :num_matched_ions => top_hit[7],
-        :tot_num_ions => top_hit[8],
-        :calc_neutral_pep_mass => calc_neutral_pep_mass,
-        :massdiff => precursor_neutral_mass - calc_neutral_pep_mass, 
-        :num_tol_term => Sequest::PepXML::SearchHit.calc_num_tol_term(params, sequence),
-        :num_missed_cleavages => Sequest::PepXML::SearchHit.calc_num_missed_cleavages(params, sequence),
-        :is_rejected => 0,
-        # These are search score attributes:
-        :xcorr => top_hit[3],
-        :deltacn => top_hit[19],
-        :deltacnstar => deltacnstar,
-        :spscore => top_hit[2],
-        :sprank => top_hit[6],
-        :modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(sequence)[1]),
-      }
-      search_hit = Sequest::PepXML::SearchHit.new(sh_hash) # there can be multiple hits
+
+      hits = out_files[dta_i].hits
+
+      search_hits = 
+        if opts[:all_hits]
+          Array.new(out_files[dta_i].num_hits)  # all hits
+        else
+          Array.new(1)  # top hit only
+        end
+
+      (0...(search_hits.size)).each do |hit_i|
+        hit = hits[hit_i]
+        # under the modified deltacn schema (like bioworks)
+        # Get proper deltacn and deltacnstar
+        # under new srf, deltacn is already corrected for what prophet wants,
+        # deltacn_orig_updated is how to access the old one
+        # Prophet deltacn is not the same as the native Sequest deltacn
+        # It is the deltacn of the second best hit!
+
+        ## mass calculations:
+        calc_neutral_pep_mass = hit[0] - h_plus
+
+
+        sequence = hit.sequence
+
+        #  NEED TO MODIFY SPLIT SEQUENCE TO DO MODS!
+        ## THIS IS ALL INNER LOOP, so we make every effort at speed here:
+        (prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(sequence)
+        # 0=mh 1=deltacn_orig 2=sp 3=xcorr 4=id 5=num_other_loci 6=rsp 7=ions_matched 8=ions_total 9=sequence 10=prots 11=deltamass 12=ppm 13=aaseq 14=base_name 15=first_scan 16=last_scan 17=charge 18=srf 19=deltacn 20=deltacn_orig_updated
+
+        sh_hash = {
+          :hit_rank => hit_i+1,
+          :peptide => pepseq,
+          :peptide_prev_aa => prevaa,
+          :peptide_next_aa => nextaa,
+          :protein => hit[10].first.reference.split(" ").first, 
+          :num_tot_proteins => hit[10].size,
+          :num_matched_ions => hit[7],
+          :tot_num_ions => hit[8],
+          :calc_neutral_pep_mass => calc_neutral_pep_mass,
+          :massdiff => precursor_neutral_mass - calc_neutral_pep_mass, 
+          :num_tol_term => sample_enzyme_obj.num_tol_term(sequence),
+          :num_missed_cleavages => sample_enzyme_obj.num_missed_cleavages(pepseq),
+          :is_rejected => 0,
+          # These are search score attributes:
+          :xcorr => hit[3],
+          :deltacn => hit[deltacn_index],
+          :spscore => hit[2],
+          :sprank => hit[6],
+          :modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(sequence)[1]),
+        }
+        unless deltacn_orig
+          sh_hash[:deltacnstar] = 
+            if hits[hit_i+1].nil?  # no next hit? then its deltacnstar == 1
+            '1'
+            else
+            '0'
+            end
+        end
+        search_hits[hit_i] = Sequest::PepXML::SearchHit.new(sh_hash) # there can be multiple hits
+      end
 
       search_result = Sequest::PepXML::SearchResult.new
-      search_result.search_hits = [search_hit]
+      search_result.search_hits = search_hits
       spectrum_query.search_results = [search_result]
       spectrum_queries_arr[files_with_hits_index] = spectrum_query
     end
@@ -473,56 +475,61 @@ Default_Options = {
     pipeline.msms_run_summary.spectrum_queries = spectrum_queries_arr 
     pepxml_obj.base_name = pipeline.msms_run_summary.base_name
     pipeline.msms_run_summary.spectrum_queries =  spectrum_queries_arr 
-  
+
     pepxml_obj
   end
 
   # takes an .srg or bioworks.xml file
   # if possible, ensures that an mzXML file is present for each pepxml file
   # :print => true, will print files
+  # NOTES: num_tol_term and num_missing_cleavages are both calculated from the
+  # sample_enzyme.  Thus, a No_Enzyme search may still pass in a
+  # :sample_enzyme option to get these calculated.
   def self.set_from_bioworks(bioworks_file, opts={})
     opts = Default_Options.merge(opts)
     ## Create the out_path directory if necessary
 
-    unless File.exist? opts[:out_path]
-      FileUtils.mkpath(opts[:out_path])
-    end
-    unless File.directory? opts[:out_path]
-      abort "#{opts[:out_path]} must be a directory!"
-    end
-    
-    spec_id = SpecID.new(bioworks_file)
-    pepxml_objs = 
-    if spec_id.is_a? Bioworks
-      abort("must have opts[:params] set!") unless opts[:params]
-      set_from_bioworks_xml(bioworks_file, opts[:params], opts)
-    elsif spec_id.is_a? SRFGroup
-      spec_id.srfs.map do |srf|
-        new_from_srf(srf, opts) 
+      unless File.exist? opts[:out_path]
+        FileUtils.mkpath(opts[:out_path])
       end
-    else
-      abort "invalid object"
-    end
-    
-    if opts[:print]
-      pepxml_objs.each do |obj|
-        obj.to_pepxml(obj.base_name + ".xml")
+      unless File.directory? opts[:out_path]
+        abort "#{opts[:out_path]} must be a directory!"
+      end
+
+      spec_id = SpecID.new(bioworks_file)
+      pepxml_objs = 
+        if spec_id.is_a? Bioworks
+          abort("must have opts[:params] set!") unless opts[:params]
+          set_from_bioworks_xml(bioworks_file, opts[:params], opts)
+        elsif spec_id.is_a? SRFGroup
+          spec_id.srfs.map do |srf|
+            new_from_srf(srf, opts) 
+          end
+        else
+          abort "invalid object"
+        end
+
+      if opts[:print]
+        pepxml_objs.each do |obj|
+          obj.to_pepxml(obj.base_name + ".xml")
+        end
       end
+      pepxml_objs
     end
-    pepxml_objs
-  end
 
 
-  # Takes bioworks 3.2/3.3 xml output (with no filters)
-  # Returns a list of PepXML objects
-  # params = sequest.params file
-  # bioworks = bioworks.xml exported multi-consensus view file
-  # pepxml_version = 0 for tpp 1.2.3
-  # pepxml_version = 18 for tpp 2.8.2, 2.8.3, 2.9.2
+    # Takes bioworks 3.2/3.3 xml output (with no filters)
+    # Returns a list of PepXML objects
+    # params = sequest.params file
+    # bioworks = bioworks.xml exported multi-consensus view file
+    # pepxml_version = 0 for tpp 1.2.3
+    # pepxml_version = 18 for tpp 2.8.2, 2.8.3, 2.9.2
   def self.set_from_bioworks_xml(bioworks, params, opts={})
     opts = Default_Options.merge(opts)
     pepxml_version, ms_manufacturer, ms_model, ms_ionization, ms_mass_analyzer, ms_detector, raw_data_type, raw_data, out_data_type, out_data, ms_data, out_path = opts.values_at(:pepxml_version, :ms_manufacturer, :ms_model, :ms_ionization, :ms_mass_analyzer, :ms_detector, :raw_data_type, :raw_data, :out_data_type, :out_data, :ms_data, :out_path)
 
+
+
     unless out_path
       out_path = '.'
     end
@@ -545,6 +552,13 @@ Default_Options = {
     else                           ; abort "Don't recognize #{bioworks} as object or string!"
     end
 
+    sample_enzyme_obj = 
+      if opts[:sample_enzyme]
+        opts[:sample_enzyme]
+      else
+        params.sample_enzyme
+      end
+
     #puts "bioworks.peps.size: #{bioworks.peps.size}"; #puts "bioworks.prots.size: #{bioworks.prots.size}"; #puts "Bioworks.version: #{bioworks.version}"
 
     ## TURN THIS ON IF YOU THINK YOU MIGHT NOT BE GETTING PEPTIDES from
@@ -589,7 +603,7 @@ Default_Options = {
           :ms_detector => ms_detector,
           :raw_data_type => raw_data_type,
           :raw_data => raw_data,
-          :sample_enzyme => params.sample_enzyme,
+          :sample_enzyme => sample_enzyme_obj, # usually, params.sample_enzyme,
           :search_summary => search_summary,
         }) 
         pipeline.msms_run_summary = msms_run_summary
@@ -626,10 +640,11 @@ Default_Options = {
       end
 
 
-      spectrum_queries_ar = pep_arr.hash_by(:first_scan, :last_scan, :charge).collect do |key,arr|
+      spectrum_queries_ar = pep_arr.hash_by(:first_scan, :last_scan, :charge).map do |key,arr|
 
 
         # Sort_by_rank and take the top hit (to mimick out2summary):
+
         arr = arr.sort_by {|pep| pep.xcorr.to_f } # ascending
         top_pep = arr.pop
         second_hit = arr.last # needed for deltacnstar
@@ -643,7 +658,7 @@ Default_Options = {
         end
 
         calc_neutral_pep_mass = (top_pep.mass.to_f - pepxml_obj.h_plus)
-        
+
         # deltacn & star:
         # (NOTE: OLD?? out2summary wants the deltacn of the 2nd best hit.)
         if second_hit 
@@ -685,8 +700,8 @@ Default_Options = {
           :tot_num_ions => tot_num_ions,
           :calc_neutral_pep_mass => calc_neutral_pep_mass,
           :massdiff => precursor_neutral_mass - calc_neutral_pep_mass,
-          :num_tol_term => Sequest::PepXML::SearchHit.calc_num_tol_term(params, top_pep.sequence),
-          :num_missed_cleavages => Sequest::PepXML::SearchHit.calc_num_missed_cleavages(params, top_pep.sequence),
+          :num_tol_term => sample_enzyme_obj.num_tol_term(top_pep.sequence),
+          :num_missed_cleavages => sample_enzyme_obj.num_missed_cleavages(pepseq),
           :is_rejected => 0,
           # These are search score attributes:
           :xcorr => top_pep.xcorr,
@@ -697,7 +712,7 @@ Default_Options = {
           :modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(top_pep.sequence)[1]),
           :spectrum_query => spec_query,
         })
-        search_result.search_hits = [search_hit]   # there can be multiple search hits
+        search_result.search_hits = [search_hit] # there can be multiple search hits
         spec_query.search_results = [search_result]  # can be multiple search_results
         spec_query
       end
@@ -766,9 +781,8 @@ class Sequest::PepXML::SearchResult
   attr_accessor :search_hits
 
   # if block given, then search_hits set to return value
-  def initialize
-    if block_given? ; @search_hits = yield
-    else ; @search_hits = [] end
+  def initialize(search_hits = [])
+    @search_hits = search_hits
   end
 
   def to_pepxml
@@ -777,17 +791,6 @@ class Sequest::PepXML::SearchResult
     end
   end
 
-  def self.from_pepxml_node(node, spec_query)
-    self.new.from_pepxml_node(node, spec_query)
-  end
-
-  def from_pepxml_node(node, spec_query, msmsrun_obj)
-    sh_klass = msmsrun_obj.search_hit_class
-    @search_hits = node.children.map do |sh_n|
-      sh_klass.from_pepxml_node(sh_n, spec_query)
-    end
-    self
-  end
 end
 
 class Sequest::PepXML::SearchSummary
@@ -820,7 +823,11 @@ class Sequest::PepXML::SearchSummary
   def to_pepxml
     element_xml(:search_summary, [:base_name, :search_engine, :precursor_mass_type, :fragment_mass_type, :out_data_type, :out_data, :search_id]) do
       search_database.to_pepxml +
-        short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini]) +
+        if @params.enzyme =~ /^No_Enzyme/
+          ''
+        else
+          short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini])
+        end +
         @modifications.to_pepxml +
         Sequest::PepXML::Parameters.new(@params).to_pepxml
     end
@@ -1216,21 +1223,17 @@ class Sequest::PepXML::SpectrumQuery
     end
   end
 
-  def self.from_pepxml_node(node, msmsrun_obj)
-    self.new.from_pepxml_node(node, msmsrun_obj)
+  def self.from_pepxml_node(node)
+    self.new.from_pepxml_node(node)
   end
 
-  def from_pepxml_node(node, msmsrun_obj)
+  def from_pepxml_node(node)
     self[0] = node['spectrum']
     self[1] = node['start_scan'].to_i
     self[2] = node['end_scan'].to_i
     self[3] = node['precursor_neutral_mass'].to_f
     self[4] = node['index'].to_i
     self[5] = node['assumed_charge'].to_i
-    self[6] = node.children.map do |v|   
-      sh = Sequest::PepXML::SearchResult.new
-      sh.from_pepxml_node(v, self, msmsrun_obj)
-    end
     self
   end
 
@@ -1299,6 +1302,8 @@ class Sequest::PepXML::SearchHit
 
   Non_standard_amino_acid_char_re = /[^A-Z\.\-]/
 
+  def aaseq ; self[1] end
+  def aaseq=(arg) ; self[1] = arg end
 
   # These are all search_score elements:
 
@@ -1321,44 +1326,6 @@ class Sequest::PepXML::SearchHit
     "#<SearchHit #{var}>"
   end
 
-  # requires Params object and full sequence (with heads and tails)
-  def self.calc_num_missed_cleavages(params, sequence)
-    num_missed = 0
-    offset, split_after, except_before = params.enzyme_specificity
-    first, middle, last = SpecID::Pep.split_sequence(sequence)
-    to_regexp = "[#{split_after}]"
-    if except_before.size > 0
-      to_regexp << "[^#{except_before}]"
-    end
-    regexp = /#{to_regexp}/
-    arr = middle.scan(regexp)
-    num = arr.size
-    if middle[-1,1] =~ regexp
-      # if the regexp is a single letter (exceptions) and the last letter
-      # matches, then it will count when it is not a missed cleavage
-      # we can correct for this and get the right answer
-      num -= 1
-    else
-      num
-    end
-  end
-
-  # requires Params object and full sequence (with heads and tails)
-  def self.calc_num_tol_term(params, sequence)
-    num_tol = 0
-    offset, split_after, except_before = params.enzyme_specificity
-    first, middle, last = SpecID::Pep.split_sequence(sequence)
-    last_of_middle = middle[-1,1]
-    first_of_middle = middle[0,1]
-    if ( split_after.include?(first) && !except_before.include?(first_of_middle) ) || first == '-'
-      num_tol += 1
-    end
-    if split_after.include?(last_of_middle) && !except_before.include?(last) || last == '-'
-      num_tol += 1
-    end
-    num_tol
-  end
-
   # Takes ions in the form XX/YY and returns [XX.to_i, YY.to_i]
   def self.split_ions(ions)
     ions.split("/").map {|ion| ion.to_i }
@@ -1392,11 +1359,7 @@ class Sequest::PepXML::SearchHit
     end
   end
 
-  def self.from_pepxml_node(node, spec_query)
-    self.new.from_pepxml_node(node, spec_query)
-  end
-
-  def from_pepxml_node(node, spec_query)
+  def from_pepxml_node(node)
     self[0] = node['hit_rank'].to_i
     self[1] = node['peptide']
     self[2] = node['peptide_prev_aa']
@@ -1410,24 +1373,6 @@ class Sequest::PepXML::SearchHit
     self[10] = node['num_tol_term'].to_i
     self[11] = node['num_missed_cleavages'].to_i
     self[12] = node['is_rejected'].to_i
-    if modinfo_node = node.find_first("child::modification_info")
-      self[18] = Sequest::PepXML::SearchHit::ModificationInfo.from_pepxml_node(modinfo_node)
-    end
-    node.find("child::search_score").each do |ss_n|
-      case ss_n['name']
-      when 'deltacnstar'
-        self[13] = ss_n['value'].to_i
-      when 'xcorr'
-        self[14] = ss_n['value'].to_f
-      when 'deltacn'
-        self[15] = ss_n['value'].to_f
-      when 'spscore'
-        self[16] = ss_n['value'].to_f
-      when 'sprank'
-        self[17] = ss_n['value'].to_i
-      end
-    end
-    self[19] = spec_query
     self
   end