protk 1.1.0.pre → 1.1.0

data/README.md

@@ -4,11 +4,7 @@
 ***
 ## What is it?
 
-Protk is a wrapper for various proteomics tools. Initially it focusses on MS/MS database search and validation.
-
-## Why do we need a wrapper around these tools
-
-The aim of protk is present a consistent interface to numerous proteomics tools that is as uniform as possible. Protk also provides built-in support for managing protein databases. 
+Protk is a wrapper for various proteomics tools. It aims to present a consistent interface to a wide variety of tools and provides support for managing protein databases. 
 
 ***
 
@@ -16,27 +12,33 @@ The aim of protk is present a consistent interface to numerous proteomics tools
 
 ## Basic Installation
  
-1. Install rvm
-curl -L https://get.rvm.io | bash -s stable
+Protk depends on ruby 1.9.  The recommended way to install ruby and manage ruby gems is with rvm. Install rvm using this command.
+    
+    curl -L https://get.rvm.io | bash -s stable
+
+Next install ruby and protk's dependencies
 
 On OSX
-- rvm install 1.9.3 --with-gcc=clang
-- rvm use 1.9.3
-- gem install protk
-- protk_setup.rb all
+
+    rvm install 1.9.3 --with-gcc=clang
+    rvm use 1.9.3
+    gem install protk
+    protk_setup.rb all
 
 On Linux
-- rvm install 1.9.3
-- rvm use 1.9.3
-- gem install protk
-- sudo protk_setup.rb system_dependencies
-- protk_setup all
+    
+    rvm install 1.9.3
+    rvm use 1.9.3
+    gem install protk
+    sudo protk_setup.rb system_dependencies
+    protk_setup all
 
 
 ## Sequence databases
 
-After running the setup.sh script you should run manage_db.rb to install specific sequence databases for use by the search engines. Protk comes with several predefined database configurations. For example, to install a database consisting of human entries from Swissprot plus known contaminants use the following command;
+After running the setup.sh script you should run manage_db.rb to install specific sequence databases for use by the search engines. Protk comes with several predefined database configurations. For example, to install a database consisting of human entries from Swissprot plus known contaminants use the following commands;
 
+    manage_db.rb add crap
     manage_db.rb add sphuman
 
 You should now be able to run database searches, specifying this database by using the -d sphuman flag.  Every month or so swissprot will release a new database version. You can keep your database up to date using;

data/bin/annotate_ids.rb

@@ -1,6 +1,6 @@
 #!/usr/bin/env ruby
 #
-# This file is part of MSLIMS
+# This file is part of Protk
 # Created by Ira Cooke 21/7/2011
 #
 # Takes an input file with a list of identified proteins and creates a table with swissprot/uniprot database details in various columns for each protein in the input file.

data/bin/asapratio.rb

@@ -0,0 +1,27 @@
+#!/usr/bin/env ruby
+#
+# Created by John Chilton
+#
+# Run ASAPRatio against protein prophet results.
+#
+#
+
+require 'protk/constants'
+require 'protk/protxml'
+require 'protk/galaxy_util'
+
+for_galaxy = GalaxyUtil.for_galaxy?
+
+protxml_path = ARGV.shift
+
+if for_galaxy
+  protxml_path = GalaxyUtil.stage_protxml(protxml_path)
+end
+
+protxml = ProtXML.new(protxml_path)
+pepxml_path = protxml.find_pep_xml()
+
+genv=Constants.new
+
+command="#{genv.asapratiopeptideparser} '#{pepxml_path}' #{ARGV.join(" ")} ; #{genv.asapratioproteinparser} '#{protxml_path}'; #{genv.asaprationpvalueparser} '#{protxml_path}' "
+%x[#{command}]

data/bin/file_convert.rb

@@ -126,14 +126,14 @@ basedir=Pathname.new(filename).dirname.to_s #Where we run the tool
 
 if ( convert_tool.maldi )
   #For MALDI we know the charge is 1 so set it explicitly. Sometimes it is missing from the data
-  runner.run_local("cd #{basedir}; #{genv.tpp_root}/msconvert #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
+  runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
 else
   if ( has_charge_information(filename) )
-    runner.run_local("cd #{basedir}; #{genv.tpp_root}/msconvert #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.<ChargeState>\" --#{convert_tool.output_format} -o #{output_dir}")
+    runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.<ChargeState>\" --#{convert_tool.output_format} -o #{output_dir}")
   else
     # If input file is missing charges the best we can do is just assign charge=1. Search engines can choose to ignore this value anyway.
     #    
-    runner.run_local("cd #{basedir}; #{genv.tpp_root}/msconvert #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
+    runner.run_local("cd #{basedir}; #{genv.msconvert} #{input_relative_filename} --filter \"titleMaker <RunId>.<ScanNumber>.<ScanNumber>.1\" --#{convert_tool.output_format} -o #{output_dir}")
   end
 end
 

data/bin/libra.rb

@@ -0,0 +1,70 @@
+#!/usr/bin/env ruby
+#
+# Created by John Chilton
+#
+# Run libra quantification against protein prophet results.
+#
+#
+
+require 'protk/constants'
+require 'protk/protxml'
+require 'protk/galaxy_util'
+require 'optparse'
+
+for_galaxy = GalaxyUtil.for_galaxy?
+
+protxml_path = ARGV.shift
+
+if for_galaxy
+  protxml_path = GalaxyUtil.stage_protxml(protxml_path)
+end
+
+protxml = ProtXML.new(protxml_path)
+pepxml_path = protxml.find_pep_xml()
+
+genv=Constants.new
+
+option_parser=OptionParser.new()
+
+reagents = []
+mass_tolerance = "0.2"
+option_parser.on( '--mass-tolerance TOL',"Specifies the mass tolerance (window libra will search for the most intense m/z value in)." ) do |tol|
+  mass_tolerance = tol
+end
+
+option_parser.on( '--reagent MZ', "Specify a reagent (via m/z values).") do |reagent|
+  reagents << reagent
+end
+
+minimum_threshold_string = ""
+option_parser.on( '--minimum-threshold THRESH', "Minimum threshhold intensity (not required).") do |thresh|
+  minimum_threshold_string = "<minimumThreshhold value=\"#{thresh}\"/>"
+end
+
+option_parser.parse!
+
+
+reagent_strings = reagents.map do |reagent|
+  "<reagent mz=\"#{reagent}\" />"
+end
+reagents_string = reagent_strings.join(" ")
+
+isotopic_contributions = ""
+
+condition_contents = "<SUMmOnCondition description=\"libra_galaxy_run\">
+  <fragmentMasses>
+    #{reagents_string}
+  </fragmentMasses>
+  #{isotopic_contributions}
+  <massTolerance value=\"#{mass_tolerance}\"/>
+  <centroiding type=\"2\" iterations=\"1\"/>
+  <normalization type=\"4\"/>
+  <targetMs level=\"2\"/>
+  <output type=\"1\"/>
+  <quantitationFile name=\"quantitation.tsv\"/>
+  #{minimum_threshold_string}
+</SUMmOnCondition>"
+File.open("condition.xml", "w") { |f| f.write(condition_contents) }
+print condition_contents
+command="#{genv.librapeptideparser} '#{pepxml_path}' -ccondition.xml; #{genv.libraproteinratioparser} '#{protxml_path}' -c#{condition_file}"
+%x[#{command}]

data/bin/msgfplus_search.rb

@@ -9,11 +9,15 @@ $VERBOSE=nil
 require 'protk/constants'
 require 'protk/command_runner'
 require 'protk/search_tool'
+require 'protk/galaxy_stager'
+require 'protk/galaxy_util'
 
+for_galaxy = GalaxyUtil.for_galaxy
+input_stager = nil
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
-search_tool=SearchTool.new({:msms_search=>true,:background=>false,:glyco=>true,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
+search_tool=SearchTool.new({:msms_search=>true,:background=>false,:glyco=>false,:database=>true,:explicit_output=>true,:over_write=>true,:msms_search_detailed_options=>true})
 search_tool.option_parser.banner = "Run an MSGFPlus msms search on a set of msms spectrum input files.\n\nUsage: msgfplus_search.rb [options] file1.mzML file2.mzML ..."
 search_tool.options.output_suffix="_msgfplus"
 
@@ -92,16 +96,26 @@ ARGV.each do |filename|
   if ( search_tool.explicit_output!=nil)
     output_path=search_tool.explicit_output
   else
-    output_path="#{search_tool.output_base_path(filename.chomp)}.mzid"
+    output_path="#{search_tool.output_base_path(filename.chomp)}.pepXML"
   end
-  
+
+
   # (*.mzML, *.mzXML, *.mgf, *.ms2, *.pkl or *_dta.txt)
   # Get the input file extension
   ext = Pathname.new(filename).extname
+  input_path="#{search_tool.input_base_path(filename.chomp)}#{ext}"
 
+  mzid_output_path="#{search_tool.input_base_path(filename.chomp)}.mzid"
+
+
+  if for_galaxy
+    original_input_file = input_path
+    original_input_path = Pathname.new("#{original_input_file}")
+    input_stager = GalaxyStager.new("#{original_input_file}", :extension => '.mzML')
+    input_path = input_stager.staged_path
+  end
 
 
-  input_path="#{search_tool.input_base_path(filename.chomp)}#{ext}"
 
   # Only proceed if the output file is not present or we have opted to over-write it
   #
@@ -109,11 +123,10 @@ ARGV.each do |filename|
   
     # The basic command
     #
-    cmd= "java -Xmx#{search_tool.java_mem} -jar #{msgf_bin} -d #{current_db} -s #{input_path} -o #{output_path} "
-
+    cmd= "java -Xmx#{search_tool.java_mem} -jar #{msgf_bin} -d #{current_db} -s #{input_path} -o #{mzid_output_path} "
     #Missed cleavages
     #
-    throw "Maximum value for missed cleavages is 2" if ( search_tool.missed_cleavages > 2)
+    throw "Maximum value for missed cleavages is 2" if ( search_tool.missed_cleavages.to_i > 2)
     cmd << " -ntt #{search_tool.missed_cleavages}"
 
     # Precursor tolerance
@@ -121,8 +134,7 @@ ARGV.each do |filename|
     cmd << " -t #{search_tool.precursor_tol}#{search_tool.precursor_tolu}"
     
     # Instrument type
-    #
-    cmd << " -inst 2"
+    cmd << " -inst #{search_tool.instrument}"
     
 #    cmd << " -m 4"
 
@@ -134,55 +146,49 @@ ARGV.each do |filename|
   #      cmd << " -e #{search_tool.enzyme}"
   #    end
 
-  mods_path="#{search_tool.input_base_path(filename.chomp)}.msgfplus_mods.txt"
-  mods_file=File.open(mods_path,'w+')
+  mods_file_content = ""
 
     # Variable Modifications
     #
     if ( search_tool.var_mods !="" && !search_tool.var_mods =~/None/) # Checking for none is to cope with galaxy input
-      var_mods = search_tool.var_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject {|e| e.empty? }.join(",")
+      var_mods = search_tool.var_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject {|e| e.empty? }.join("\n")
       if ( var_mods !="" )
-        cmd << " -mv #{var_mods}"
-      end
-    else 
-      # Add options related to peptide modifications
-      #
-      if ( search_tool.glyco )
-        cmd << " -mv 119 "
+        mods_file_content << "#{var_mods}\n"
       end
     end
 
   # Fixed modifications
   #
     if ( search_tool.fix_mods !="" && !search_tool.fix_mods=~/None/)
-      fix_mods = search_tool.fix_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject { |e| e.empty? }.join(",")
+      fix_mods = search_tool.fix_mods.split(",").collect { |mod| mod.lstrip.rstrip }.reject { |e| e.empty? }.join("\n")
       if ( fix_mods !="")
-        cmd << " -mf #{fix_mods}"    
+        mods_file_content << "#{fix_mods}"    
       end
-    else
-      if ( search_tool.has_modifications )
-        cmd << " -mf "
-        if ( search_tool.carbamidomethyl )
-          cmd<<"3 "
-        end
-
-        if ( search_tool.methionine_oxidation )
-          cmd<<"1 "
-        end
+    end
 
-      end
+    if ( mods_file_content != "")
+      mods_path="#{search_tool.input_base_path(filename.chomp)}.msgfplus_mods.txt"
+      mods_file=File.open(mods_path,'w+')
+      mods_file.write "NumMods=2\n#{mods_file_content}"
+      mods_file.close
+      cmd << " -mod #{mods_path}"
     end
     
-    # Up to here we've formulated the omssa command. The rest is cleanup
+    # As a final part of the command we convert to pepxml
+    cmd << "; #{genv.idconvert} #{mzid_output_path} --pepXML -o #{Pathname.new(mzid_output_path).dirname}"
+
+    #Then copy the pepxml to the final output path
+    cmd << "; cp #{mzid_output_path.chomp('.mzid')}.pepXML #{output_path}"
+
+    # Up to here we've formulated the command. The rest is cleanup
     p "Running:#{cmd}"
     
     # Run the search
     #
     job_params= {:jobid => search_tool.jobid_from_filename(filename) }
-    job_params[:queue]="lowmem"
-    job_params[:vmem]="900mb"    
     search_tool.run(cmd,genv,job_params)
 
+    input_stager.restore_references(output_path)
 
   else
     genv.log("Skipping search on existing file #{output_path}",:warn)       

data/bin/omssa_search.rb

@@ -10,7 +10,9 @@ $VERBOSE=nil
 require 'protk/constants'
 require 'protk/command_runner'
 require 'protk/search_tool'
+require 'protk/galaxy_util'
 
+for_galaxy = GalaxyUtil.for_galaxy?
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
@@ -33,6 +35,10 @@ search_tool.option_parser.on(  '--intensity-cut-off co', 'Peak intensity cut-off
   search_tool.options.intensity_cut_off=co
 end
 
+search_tool.options.galaxy_index_dir=nil
+search_tool.option_parser.on( '--galaxy-index-dir dir', 'Specify galaxy index directory, will search for mods file there.' ) do |dir|
+  search_tool.options.galaxy_index_dir=dir
+end
 
 search_tool.option_parser.parse!
 
@@ -45,9 +51,14 @@ genv=Constants.new
 rt_correct_bin="#{File.dirname(__FILE__)}/correct_omssa_retention_times.rb"
 repair_script_bin="#{File.dirname(__FILE__)}/repair_run_summary.rb"
 
+make_blastdb_cmd=""
+
 case 
 when Pathname.new(search_tool.database).exist? # It's an explicitly named db
   current_db=Pathname.new(search_tool.database).realpath.to_s
+  if(not FileTest.exists?("#{current_db}.phr"))
+    make_blastdb_cmd << "#{@genv.makeblastdb} -dbtype prot -parse_seqids -in #{current_db}; "
+  end
 else
   current_db=search_tool.current_database :fasta
 end
@@ -85,12 +96,29 @@ ARGV.each do |filename|
   
     # The basic command
     #
-    cmd= "#{genv.omssacl} -d #{current_db} -fm #{input_path} -op #{output_path} -w"
+    cmd = "#{make_blastdb_cmd} #{genv.omssacl} -d #{current_db} -fm #{input_path} -op #{output_path} -w"
 
     #Missed cleavages
     #
     cmd << " -v #{search_tool.missed_cleavages}"
 
+    # If this is for Galaxy and a data directory has been specified
+    # look for a common unimod.xml file.
+    if for_galaxy
+      galaxy_index_dir = search_tool.galaxy_index_dir
+      if galaxy_index_dir
+        galaxy_mods = File.join(galaxy_index_dir, "mods.xml")
+        if( FileTest.exists?(galaxy_mods) )      
+          cmd << " -mx #{galaxy_mods}"
+        end
+        galaxy_usermods = File.join(galaxy_index_dir, "usermods.xml")
+        if( FileTest.exists?(galaxy_usermods) )
+          cmd << " -mux #{galaxy_usermods}"
+        end
+      end
+    end
+
+
     # Precursor tolerance
     #
     if ( search_tool.precursor_tolu=="ppm")
@@ -202,4 +230,8 @@ ARGV.each do |filename|
     genv.log("Skipping search on existing file #{output_path}",:warn)       
   end
 
+  # Reset this.  We only want to index the database at most once
+  #
+  make_blastdb_cmd=""
+
 end

data/bin/peptide_prophet.rb

@@ -82,6 +82,15 @@ prophet_tool.option_parser.on( '-F', '--one-ata-time', 'Create a separate pproph
   prophet_tool.options.one_ata_time = true
 end
 
+prophet_tool.options.decoy_prefix="decoy"
+prophet_tool.option_parser.on( '--decoy-prefix prefix', 'Prefix for decoy sequences') do |prefix|
+  prophet_tool.options.decoy_prefix = prefix
+end  
+
+prophet_tool.options.override_database=nil
+prophet_tool.option_parser.on( '--override-database database', 'Manually specify database') do |database|
+  prophet_tool.options.override_database = database
+end
 
 prophet_tool.option_parser.parse!
 
@@ -99,7 +108,11 @@ ARGV.each {|file_name|
   name=file_name.chomp
   
   engine=prophet_tool.extract_engine(name)
-  db_path=prophet_tool.extract_db(name)
+  if prophet_tool.override_database
+    db_path = prophet_tool.override_database
+  else
+    db_path=prophet_tool.extract_db(name)
+  end
   
   
   file_info[name]={:engine=>engine , :database=>db_path } 
@@ -130,7 +143,7 @@ end
 
 def generate_command(genv,prophet_tool,inputs,output,database,engine)
   
-  cmd="#{genv.xinteract} -N#{output}  -l7 -eT -D#{database} "
+  cmd="#{genv.xinteract} -N#{output}  -l7 -eT -D'#{database}' "
 
   if prophet_tool.glyco 
     cmd << " -Og "
@@ -189,9 +202,9 @@ def generate_command(genv,prophet_tool,inputs,output,database,engine)
   end
 
   if engine=="omssa" || engine=="phenyx"
-    cmd << "-Op -P -ddecoy "
+    cmd << " -Op -P -d#{prophet_tool.decoy_prefix} "
   else
-    cmd << "-ddecoy "
+    cmd << " -d#{prophet_tool.decoy_prefix} "
   end
   
   

data/bin/pepxml_to_table.rb

@@ -34,10 +34,20 @@ output_fh=File.new("#{output_file}",'w')
 
 output_fh.write "protein\tpeptide\tassumed_charge\tcalc_neutral_pep_mass\tneutral_mass\tretention_time\tstart_scan\tend_scan\tsearch_engine\tpeptideprophet_prob\tinterprophet_prob\n"
 
+XML::Error.set_handler(&XML::Error::QUIET_HANDLER)
+
 pepxml_parser=XML::Parser.file("#{input_file}")
-pepxml_doc=pepxml_parser.parse
 
-spectrum_queries=pepxml_doc.find('//xmlns:spectrum_query','xmlns:http://regis-web.systemsbiology.net/pepXML')
+pepxml_ns_prefix="xmlns:"
+pepxml_ns="xmlns:http://regis-web.systemsbiology.net/pepXML"
+ pepxml_doc=pepxml_parser.parse
+if not pepxml_doc.root.namespaces.default
+  pepxml_ns_prefix=""
+  pepxml_ns=nil
+end
+
+
+spectrum_queries=pepxml_doc.find("//#{pepxml_ns_prefix}spectrum_query", pepxml_ns)
 
 spectrum_queries.each do |query| 
 
@@ -45,7 +55,7 @@ spectrum_queries.each do |query|
   neutral_mass=query.attributes['precursor_neutral_mass']
   assumed_charge=query.attributes['assumed_charge']
 
-  top_search_hit=query.find('./xmlns:search_result/xmlns:search_hit','xmlns:http://regis-web.systemsbiology.net/pepXML')[0]
+  top_search_hit=query.find("./#{pepxml_ns_prefix}search_result/#{pepxml_ns_prefix}search_hit",pepxml_ns)[0]
   peptide=top_search_hit.attributes['peptide']
   protein=top_search_hit.attributes['protein']
   calc_neutral_pep_mass=top_search_hit.attributes['calc_neutral_pep_mass']
@@ -53,7 +63,7 @@ spectrum_queries.each do |query|
   end_scan=query.attributes['end_scan']
 
   search_engine=""
-  search_score_names=top_search_hit.find('./xmlns:search_score/@name','xmlns:http://regis-web.systemsbiology.net/pepXML').collect {|s| s.to_s}
+  search_score_names=top_search_hit.find("./#{pepxml_ns_prefix}search_score/@name",pepxml_ns).collect {|s| s.to_s}
 
   if ( search_score_names.length==2 && search_score_names.grep(/^name.*=.*pvalue/))
     search_engine="omssa" 
@@ -63,9 +73,10 @@ spectrum_queries.each do |query|
     search_engine="x!tandem"
   end
 
-  pp_result=top_search_hit.find('./xmlns:analysis_result/xmlns:peptideprophet_result/@probability','xmlns:http://regis-web.systemsbiology.net/pepXML')
-  ip_result=top_search_hit.find('./xmlns:analysis_result/xmlns:interprophet_result/@probability','xmlns:http://regis-web.systemsbiology.net/pepXML')
   
+  pp_result=top_search_hit.find("./#{pepxml_ns_prefix}analysis_result/#{pepxml_ns_prefix}peptideprophet_result/@probability",pepxml_ns)
+  ip_result=top_search_hit.find("./#{pepxml_ns_prefix}analysis_result/#{pepxml_ns_prefix}interprophet_result/@probability",pepxml_ns)
+
   peptide_prophet_prob=""
   interprophet_prob=""
   peptide_prophet_prob=pp_result[0].value if ( pp_result.length>0 )

data/bin/protein_prophet.rb

@@ -13,7 +13,7 @@ require 'protk/prophet_tool'
 require 'protk/galaxy_stager'
 require 'protk/galaxy_util'
 
-for_galaxy = GalaxyUtil.for_galaxy
+for_galaxy = GalaxyUtil.for_galaxy?
 
 if for_galaxy
   # Stage files for galaxy

data/bin/tandem_search.rb

@@ -41,6 +41,47 @@ search_tool.option_parser.on( '-K', '--keep-params-files', 'Keep X!Tandem parame
   search_tool.options.keep_params_files = true
 end
 
+# In case want pepXML, but still want tandem output also.
+search_tool.options.tandem_output=nil
+search_tool.option_parser.on( '--tandem-output tandem_output', 'Keep X! Tandem Output') do |tandem_output|
+  search_tool.options.tandem_output=tandem_output
+end
+
+search_tool.options.thresholds_type = 'isb_kscore'
+search_tool.option_parser.on( '--thresholds-type thresholds_type', 'Threshold Type (tandem_default, isb_native, isb_kscore, scaffold)' ) do |thresholds_type|
+  search_tool.options.thresholds_type = thresholds_type
+end
+
+search_tool.options.algorithm = "kscore"
+search_tool.option_parser.on( '--algorithm algorithm', "Scoring algorithm (kscore or native)" ) do |algorithm|
+  search_tool.options.algorithm = algorithm
+end
+
+search_tool.options.cleavage_semi = false
+search_tool.option_parser.on( '--cleavage-semi' ) do 
+  search_tool.options.cleavage_semi = true
+end
+
+search_tool.options.n_terminal_mod_mass=nil
+search_tool.option_parser.on('--n-terminal-mod-mass mass') do |mass|
+    search_tool.options.n_terminal_mod_mass = mass
+end
+
+search_tool.options.c_terminal_mod_mass=nil
+search_tool.option_parser.on('--c-terminal-mod-mass mass') do |mass|
+    search_tool.options.c_terminal_mod_mass = mass
+end
+
+search_tool.options.cleavage_n_terminal_mod_mass=nil
+search_tool.option_parser.on('--cleavage-n-terminal-mod-mass mass') do |mass|
+    search_tool.options.cleavage_n_terminal_mod_mass = mass
+end
+
+search_tool.options.cleavage_c_terminal_mod_mass=nil
+search_tool.option_parser.on('--cleavage-c-terminal-mod-mass mass') do |mass|
+    search_tool.options.cleavage_c_terminal_mod_mass = mass
+end
+
 search_tool.option_parser.parse!
 
 
@@ -60,8 +101,6 @@ else
 end
 
 
-
-
 # Parse options from a parameter file (if provided), or from the default parameter file
 #
 params_parser=XML::Parser.file(tandem_params)
@@ -100,7 +139,7 @@ def generate_parameter_doc(std_params,output_path,input_path,taxo_path,current_d
   #
   scoring_notes=std_params.find('/bioml/note[@type="input" and @label="list path, default parameters"]')
   throw "Exactly one list path, default parameters note is required in the parameter file" unless scoring_notes.length==1
-  scoring_notes[0].content="#{genv.tpp_root}/bin/isb_default_input_kscore.xml"
+  scoring_notes[0].content="#{genv.tpp_root}/bin/isb_default_input_#{search_tool.algorithm}.xml"
 
   # Taxonomy and Database
   #  
@@ -264,8 +303,13 @@ ARGV.each do |filename|
     # pepXML conversion and repair
     #
     unless search_tool.no_pepxml
-      repair_script="#{File.dirname(__FILE__)}/repair_run_summary.rb"      
-      cmd << "; #{genv.tandem2xml} #{output_path} #{pepxml_path}; #{repair_script} #{pepxml_path}; rm #{output_path}"
+      repair_script="#{File.dirname(__FILE__)}/repair_run_summary.rb"
+      cmd << "; #{genv.tandem2xml} #{output_path} #{pepxml_path}; #{repair_script} #{pepxml_path}"
+      if search_tool.tandem_output 
+        cmd << "; cp #{output_path} #{search_tool.tandem_output}"
+      else
+        cmd << "; rm #{output_path}"
+      end
     end
 
     # Add a cleanup command unless the user wants to keep params files