protk 1.3.1.pre3 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7d5d14d3a6fdd45c7ac3be6f122a9a30dd5e3823
-  data.tar.gz: c77c6b6a83386426ad8a727866f0c0ca8a0c42b5
+  metadata.gz: 22d2c990e46bf29f08cbf00dc2ecd9a759fae457
+  data.tar.gz: 09dd0159d8b564d9d297a987c74e13833fabbc24
 SHA512:
-  metadata.gz: 62ddf0c0d8b42a12a34a0f81b866b823a85af7a8cb7908ea6080604fcc64e9fb8c3ad24eb3f7aa8ef6ffc8333d004d778e563fab4e152d054a2dca266c9d0287
-  data.tar.gz: 19bfc66be4caace10de8c4c602a9ff9ed9d397db2f836b60351350ecade6abf9f046de53b2b717ac1a49e483f470a15337cecb27f6b654b8bd9b51d09bb65c62
+  metadata.gz: 2b08c1086187da5755e4b0d98dcfebcff80893eb291e09291ea3853fa848ade7f464f83fc97a8fe362d2b9a96e915e2aa1945ddd6e0f39ada32d1a747a0c7d73
+  data.tar.gz: 767b474d9f0b890342f783bff0e8633434542cf151d34f239f9ed52dab43a1909b683fa285b25954af54856d68493ab67e4776d152830bc938e62a932c63e9b3

data/README.md

@@ -12,7 +12,7 @@ Protk is a suite of tools for proteomics. It aims to present a simple and consis
 - Tandem MS search with X!Tandem, Mascot, OMSSA and MS-GF+
 - Peptide and Protein inference with Peptide Prophet, iProphet and Protein Prophet
 - Conversion of pepXML or protXML to tabulular format
-
+- Proteogenomics (mapping peptides to genomic coordinates)
 
 ## Installation
  
@@ -41,6 +41,7 @@ Protk consists of a suite of small ruby programs.  After installing the protk ru
 - `protxml_to_table.rb` Convert protXML to tabular format
 - `make_decoy.rb` Generate semi-random decoy sequences
 - `sixframe.rb` Generate six-frame translations of DNA sequences
+- `protxml_to_gff.rb` Map peptides to genomic coordinates
 - `protk_setup.rb` Install third party dependencies
 - `manage_db.rb` Manage protein databases
 
@@ -52,7 +53,7 @@ Protk includes a setup tool to install various third party proteomics tools such
     protk_setup.rb tpp omssa blast msgfplus pwiz
 ```
 
-By default protk will install tools and databases into `.protk` in your home directory.  If this is not desirable you can change the protk root default by setting the environment variable `PROTK_INSTALL_DIR`. If you prefer to install the tools yourself protk will find them provided they are included in your `$PATH`. Those executables will be used as a fallback if nothing is available under the `.protk` installation directory.  A common source of errors when running the protk_setup script is missing dependencies. The setup script has been tested on ubuntu 12 with the following dependencies installed;
+By default protk will install tools and databases into `.protk` in your home directory.  If this is not desirable you can change the protk root default by setting the environment variable `PROTK_INSTALL_DIR`. If you prefer to install the tools yourself protk will find them, provided they are included in your `$PATH`. Those executables will be used as a fallback if nothing is available under the `.protk` installation directory.  A common source of errors when running the protk_setup script is missing dependencies. The setup script has been tested on ubuntu 12 with the following dependencies installed;
 
 ```
 	apt-get install build-essential autoconf automake git-core mercurial subversion pkg-config libc6-dev curl libxml2-dev openjdk-6-jre libbz2-dev libgd2-noxpm-dev unzip
@@ -98,13 +99,13 @@ Many protk tools have equivalent galaxy wrappers available on the [galaxy toolsh
 
 4.  Install protk in an isolated gemset using rvm.
 
-	This sets up an isolated environment where only a specific version of protk is available.  We name the environment according to the protk intermediate version numer (1.3 in this example). Minor bugfixes will be released as 1.3.x and can be installed without updating the toolshed wrappers
+	This sets up an isolated environment where only a specific version of protk is available.  We name the environment according to the protk intermediate version numer (1.4 in this example). Minor bugfixes will be released as 1.4.x and can be installed without updating the toolshed wrappers
 
 	```bash
 		rvm 2.1
-		rvm gemset create protk1.3
-		rvm use 2.1@protk1.3
-		gem install protk -v '~>1.3'
+		rvm gemset create protk1.4
+		rvm use 2.1@protk1.4
+		gem install protk -v '~>1.4'
 	```
 
 5. Configure Galaxy's tool dependency directory.
@@ -118,32 +119,33 @@ Many protk tools have equivalent galaxy wrappers available on the [galaxy toolsh
 
 6.  Create a tool dependency that sets up protk in the environment created by rvm
 
-	In this example we create the environment for protk `1.3.0` as this was the version installed in step 4 above.
+	In this example we create the environment for protk `1.4` as this was the version installed in step 4 above.
 
 	```bash
 		cd <tool_dependency_dir>
 		mkdir protk
 		cd protk
-		mkdir 1.3
-		ln -s 1.3 default
-		rvmenv=`rvm env --path 2.1@protk1.3`
-		echo ". $rvmenv" > 1.3/env.sh
+		mkdir 1.4
+		ln -s 1.4 default
+		rvm use 2.1@protk1.4
+		rvmenv=`rvm env --path 2.1@protk1.4`
+		echo ". $rvmenv" > 1.4/env.sh
 	```
 
 7. Keep things up to date
 
-	When new versions of galaxy tools are released they may change the version of protk that is required.  Check the release notes on the tool to see what is needed.  For example, if upgrading to version 1.4.0 you would do the following;
+	When new versions of galaxy tools are released they may change the version of protk that is required.  Check the release notes on the tool to see what is needed.  For example, if upgrading to version 1.5 you would do the following;
 
 	```bash
 		rvm 2.1
-		rvm gemset create protk1.4
-		rvm use 2.1@protk1.4
-		gem install protk -v '~>1.4'
+		rvm gemset create protk1.5
+		rvm use 2.1@protk1.5
+		gem install protk -v '~>1.5'
 		cd <tool_dependency_dir>/protk/
-		mkdir 1.4
-		rvmenv=`rvm env --path 2.1@protk1.4`
-		echo ". $rvmenv" > 1.4/env.sh
-		ln -s 1.4 default
+		mkdir 1.5
+		rvmenv=`rvm env --path 2.1@protk1.5`
+		echo ". $rvmenv" > 1.5/env.sh
+		ln -s 1.5 default
 	```
 
 

data/bin/add_retention_times.rb

@@ -15,7 +15,7 @@ include LibXML
 
 # Environment with global constants
 #
-genv=Constants.new
+genv=Constants.instance
 
 tool=Tool.new([:over_write,:explicit_output])
 tool.option_parser.banner = "Look up retention times in a raw file and \

data/bin/interprophet.rb

@@ -19,6 +19,8 @@ for_galaxy = GalaxyUtil.for_galaxy?
 prophet_tool=ProphetTool.new([
   :explicit_output,
   :over_write,
+  :probability_threshold,
+  :threads,
   :prefix])
 
 prophet_tool.option_parser.banner = "Run InterProphet on a set of pep.xml input files.\n\nUsage: interprophet.rb [options] file1.pep.xml file2.pep.xml ..."
@@ -30,13 +32,13 @@ prophet_tool.add_boolean_option(:no_nrs,false,['--no-nrs', 'Don\'t use NRS (Numb
 prophet_tool.add_boolean_option(:no_nse,false,['--no-nse', 'Don\'t use NSE (Number of Sibling Experiments) in Model'])
 prophet_tool.add_boolean_option(:no_nsi,false,["--no-nsi",'Don\'t use NSE (Number of Sibling Ions) in Model'])
 prophet_tool.add_boolean_option(:no_nsm,false,["--no-nsm",'Don\'t use NSE (Number of Sibling Modifications) in Model'])
-prophet_tool.add_value_option(:min_prob,"",["--minprob mp","Minimum probability cutoff "])
+# prophet_tool.add_value_option(:min_prob,"",["--minprob mp","Minimum probability cutoff "])
 
 exit unless prophet_tool.check_options(true)
 
 
 # Obtain a global environment object
-genv=Constants.new
+genv=Constants.instance
 
 inputs = ARGV.collect {|file_name| 
   file_name.chomp
@@ -51,20 +53,23 @@ end
 if ( !Pathname.new(output_file).exist? || prophet_tool.over_write )
 
   cmd="InterProphetParser "
-
+  cmd<<"THREADS=#{prophet_tool.threads.to_i}" if prophet_tool.threads.to_i > 0
   cmd<<"NONSS " if prophet_tool.options.no_nss
   cmd<<"NONRS " if prophet_tool.options.no_nrs
   cmd<<"NONSE " if prophet_tool.options.no_nse
   cmd<<"NONSI " if prophet_tool.options.no_nsi
   cmd<<"NONSM " if prophet_tool.options.no_nsm
 
-  cmd << " MINPROB=#{prophet_tool.min_prob}" if ( prophet_tool.min_prob !="" )
+
+  cmd << " MINPROB=#{prophet_tool.probability_threshold}" if ( prophet_tool.probability_threshold !="" )
 
   if for_galaxy
     inputs = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
   end
 
-  cmd << " #{inputs.join(" ")} #{output_file}"
+  input_files = inputs.collect { |e| e.staged_path }
+
+  cmd << " #{input_files.join(" ")} #{output_file}"
 
   genv.log("Running #{cmd}",:info)
 
@@ -72,6 +77,12 @@ if ( !Pathname.new(output_file).exist? || prophet_tool.over_write )
   #
   code = prophet_tool.run(cmd,genv)
   throw "Command failed with exit code #{code}" unless code==0
+
+  if for_galaxy
+    inputs.each do |ip_stager|
+      ip_stager.restore_references(output_file)
+    end
+  end
     
 else
   genv.log("Interprophet output file #{output_file} already exists. Run with -r option to replace",:warn)   

data/bin/make_decoy.rb

@@ -40,7 +40,7 @@ end
 
 output_file = tool.explicit_output if tool.explicit_output!=nil
 
-genv=Constants.new()
+genv=Constants.instance()
 
 decoys_tmp_file = Pathname.new(Tempfile.new("random").path).basename.to_s;
 

data/bin/manage_db.rb

@@ -35,7 +35,7 @@ if ( dbname!=nil)
   throw "Database name should contain no spaces" if ( dbname=~/\s/)
 end
 
-genv=Constants.new()
+genv=Constants.instance()
 
 
 case command

data/bin/mascot_search.rb

@@ -110,7 +110,7 @@ end
 
 # Environment with global constants
 #
-$genv=Constants.new
+$genv=Constants.instance
 
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
@@ -188,7 +188,7 @@ else
     #site = RestClient::Resource.new(mascot_cgi, timeout=300)
     #search_response=site['/nph-mascot.exe?1'].post , postdict, {:cookies=>cookie}
 
-    search_response=RestClient::Request.execute(:method => :post, :url => "#{mascot_cgi}/nph-mascot.exe?1", :payload => postdict,:headers=>{:cookies=>cookie},:timeout => search_tool.options.timeout, :open_timeout => 10)
+    search_response=RestClient::Request.execute(:method => :post, :url => "#{mascot_cgi}/nph-mascot.exe?1", :payload => postdict,:headers=>{:cookies=>cookie},:timeout => search_tool.options.timeout.to_i, :open_timeout => 10)
 
 
     #search_response=RestClient.post "#{mascot_cgi}/nph-mascot.exe?1", postdict, {:cookies=>cookie}

data/bin/mascot_to_pepxml.rb

@@ -13,7 +13,7 @@ require 'protk/mascot_util'
 
 # Environment with global constants
 #
-genv=Constants.new
+genv=Constants.instance
 
 tool=SearchTool.new([
   :database,

data/bin/msgfplus_search.rb

@@ -60,7 +60,7 @@ exit unless search_tool.check_options(true)
 
 # Environment with global constants
 #
-genv=Constants.new
+genv=Constants.instance
 
 # Set search engine specific parameters on the SearchTool object
 #
@@ -81,17 +81,21 @@ db_info=search_tool.database_info
 
 database_path=db_info.path
 
-# Database must have fasta extension
-if Pathname.new(database_path).extname.to_s.downcase != ".fasta"
-  File.symlink(database_path,"#{database_path}.fasta") unless File.exists?("#{database_path}.fasta")
-  # make_msgfdb_cmd << "ln -s #{database_path} #{database_path}.fasta;"
-  database_path="#{database_path}.fasta"
-  database_path
+database_stager=nil
+
+if for_galaxy || Pathname.new(database_path).extname.to_s.downcase != ".fasta"
+  database_stager = GalaxyUtil.stage_fasta(database_path)
+  database_path = database_stager.staged_path
+# # Database must have fasta extension
+# if 
+#   File.symlink(database_path,"#{database_path}.fasta") unless File.exists?("#{database_path}.fasta")
+#   # make_msgfdb_cmd << "ln -s #{database_path} #{database_path}.fasta;"
+#   database_path="#{database_path}.fasta"
 end
 
 # Database must be indexed
 unless FileTest.exists?("#{database_path}.canno")
-  dbdir = Pathname.new(database_path).dirname.to_s
+  # dbdir = Pathname.new(database_path).dirname.to_s
   tdavalue=search_tool.decoy_search ? 1 : 0;
   make_msgfdb_cmd << "java -Xmx3500M -cp #{genv.msgfplusjar} edu.ucsd.msjava.msdbsearch.BuildSA -d #{database_path} -tda #{tdavalue}; "
 end
@@ -210,8 +214,17 @@ ARGV.each do |filename|
       cmd << ";ruby -pi.bak -e \"gsub('post=\\\"?','post=\\\"X')\" #{mzid_output_path}"
       cmd << ";ruby -pi.bak -e \"gsub('pre=\\\"?','pre=\\\"X')\" #{mzid_output_path}"
       cmd << ";idconvert #{mzid_output_path} --pepXML -o #{Pathname.new(mzid_output_path).dirname}" 
+
+ 
+      pepxml_output_path = "#{mzid_output_path.chomp('.mzid')}.pepXML"
+
+      # Fix the msms_run_summary base_name attribute
+      #
+      if for_galaxy
+        cmd << ";ruby -pi.bak -e \"gsub(/ base_name=[^ ]+/,' base_name=\\\"#{original_input_file}\\\"')\" #{pepxml_output_path}"
+      end
       #Then copy the pepxml to the final output path
-      cmd << "; mv #{mzid_output_path.chomp('.mzid')}.pepXML #{output_path}"
+      cmd << "; mv #{pepxml_output_path} #{output_path}"
     else
       cmd << "; mv #{mzid_output_path} #{output_path}"
     end
@@ -228,6 +241,10 @@ ARGV.each do |filename|
     input_stager.restore_references(output_path)
   end
 
+  unless database_stager.nil?
+    database_stager.restore_references(output_path)
+  end
+
   else
     genv.log("Skipping search on existing file #{output_path}",:warn)       
   end

data/bin/omssa_search.rb

@@ -48,7 +48,7 @@ exit unless search_tool.check_options(true)
 
 # Environment with global constants
 #
-genv=Constants.new
+genv=Constants.instance
 
 # Set search engine specific parameters on the SearchTool object
 #

data/bin/peptide_prophet.rb

@@ -11,6 +11,7 @@ require 'protk/constants'
 require 'protk/command_runner'
 require 'protk/prophet_tool'
 require 'protk/galaxy_util'
+require 'protk/pepxml'
 
 for_galaxy = GalaxyUtil.for_galaxy?
 input_stager = nil
@@ -23,7 +24,9 @@ prophet_tool=ProphetTool.new([
   :over_write,
   :maldi,
   :prefix,
-  :database])
+  :database,
+  :threads,
+  :probability_threshold])
 prophet_tool.option_parser.banner = "Run PeptideProphet on a set of pep.xml input files.\n\nUsage: peptide_prophet.rb [options] file1.pep.xml file2.pep.xml ..."
 @output_suffix="_pproph"
 prophet_tool.options.database=nil
@@ -49,39 +52,64 @@ exit unless prophet_tool.check_options(true)
 throw "When --output and -F options are set only one file at a time can be run" if  ( ARGV.length> 1 ) && ( prophet_tool.explicit_output!=nil ) && (prophet_tool.one_ata_time!=nil)
 
 # Obtain a global environment object
-genv=Constants.new
+genv=Constants.instance
 
 input_stagers=[]
 inputs=ARGV.collect { |file_name| file_name.chomp}
 if for_galaxy
-  input_stagers = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
+
+  # Force a copy since we need to edit it temporarily
+  input_stagers = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip,:force_copy => true) }
+
+  # For each pepxml we will also have some raw files that need staging.
+  # And for each raw file we need to replace references to it in the pep.xml with the staged path
+  #
+  input_stagers.each do |pepxml_stager|
+    staged_pepxml_path = pepxml_stager.staged_path
+    raw_inputs = PepXML.new(staged_pepxml_path).find_runs()
+
+    raw_inputs.each_pair do |base_name,atts|
+      extension = atts[:type]=="" ? "" : ".#{atts[:type]}"
+
+      raw_input_stager = GalaxyStager.new(base_name, :extension => extension)
+
+      GalaxyStager.replace_references(staged_pepxml_path,base_name,raw_input_stager.staged_base_path)
+    end
+  end
+
   inputs=input_stagers.collect { |sg| sg.staged_path }
 end
 
 # Interrogate all the input files to obtain the database and search engine from them
 #
-genv.log("Determining search engine and database used to create input files ...",:info)
+genv.log("Determining search engine, database and digestion enzyme for input files ...",:info)
 file_info={}
 inputs.each {|file_name| 
   name=file_name.chomp
   
-  engine=prophet_tool.extract_engine(name)
+  throw "Missing input file #{file_name}" unless File.exist?(file_name)
+
+  file_pepxml = PepXML.new(name)
+
+  engine=file_pepxml.extract_engine()
   if prophet_tool.database
     db_path = prophet_tool.database_info.path
   else
-    db_path=prophet_tool.extract_db(name)
+    db_path=file_pepxml.extract_db()
     throw "Unable to find database #{db_path} used for searching. Specify database path using -d option" unless File.exist?(db_path)
   end
+
+  enzyme = file_pepxml.extract_enzyme() 
   
-  
-  file_info[name]={:engine=>engine , :database=>db_path } 
+  file_info[name]={:engine=>engine , :database=>db_path, :enzyme=>enzyme } 
 }
 
-# Check that all searches were performed with the same engine and database
+# Check that all searches were performed with the same engine, database and enzyme
 #
 #
 engine=nil
 database=nil
+enzyme=nil
 inputs=file_info.collect do |info|
   if ( engine==nil)
     engine=info[1][:engine]
@@ -89,7 +117,11 @@ inputs=file_info.collect do |info|
   if ( database==nil)
     database=info[1][:database]
   end
-  throw "All files to be analyzed must have been searched with the same database and search engine" unless (info[1][:engine]==engine) && (info[1][:database])
+  if ( enzyme==nil)
+    enzyme=info[1][:enzyme]
+  end
+
+  throw "All files to be analyzed must have been searched with the same database and search engine" unless (info[1][:engine]==engine) && (info[1][:database]) && (info[1][:enzyme]==enzyme)
 
   retname=  info[0]
   # if ( info[0]=~/\.dat$/)
@@ -100,13 +132,21 @@ inputs=file_info.collect do |info|
 
 end
 
-def generate_command(genv,prophet_tool,inputs,output,database,engine)
+def generate_command(genv,prophet_tool,inputs,output,database,engine,enzyme)
   
-  cmd="xinteract -N#{output}  -l7 -eT -D'#{database}' "
+  enzyme_code = ProphetTool.xinteract_code_for_enzyme(enzyme)
+
+  throw "Unrecognized enzyme #{enzyme}" if enzyme_code.nil?
+
+  cmd="xinteract -N#{output}  -l7 -e#{enzyme_code} -D'#{database}' "
 
   # Do not produce png plots
   cmd << " -Ot "
 
+  if prophet_tool.threads
+    cmd << " -THREADS=#{prophet_tool.threads}"
+  end
+
   if prophet_tool.glyco 
     cmd << " -Og "
   end
@@ -166,14 +206,11 @@ def generate_command(genv,prophet_tool,inputs,output,database,engine)
   end
 
   unless prophet_tool.no_decoys
-
-    if engine=="omssa" || engine=="phenyx"
-      cmd << " -Op -P -d#{prophet_tool.decoy_prefix} "
-    else
-      cmd << " -d#{prophet_tool.decoy_prefix} "
-    end
+      cmd << " -d#{prophet_tool.decoy_prefix} -Od "
   end  
   
+  cmd << " -p#{prophet_tool.probability_threshold}"
+
   if ( inputs.class==Array)
     cmd << " #{inputs.join(" ")}"  
   else
@@ -199,7 +236,7 @@ if ( prophet_tool.one_ata_time )
   inputs.each do |input|
     output_file_name=Tool.default_output_path(input,".pep.xml",prophet_tool.output_prefix,@output_suffix)
     
-    cmd=generate_command(genv,prophet_tool,input,output_file_name,database,engine)
+    cmd=generate_command(genv,prophet_tool,input,output_file_name,database,engine,enzyme)
     run_peptide_prophet(genv,prophet_tool,cmd,output_file_name,engine)        
   end
 
@@ -211,7 +248,7 @@ else
     output_file_name=prophet_tool.explicit_output
   end
 
-  cmd=generate_command(genv,prophet_tool,inputs,output_file_name,database,engine)
+  cmd=generate_command(genv,prophet_tool,inputs,output_file_name,database,engine,enzyme)
   run_peptide_prophet(genv,prophet_tool,cmd,output_file_name,engine)
   
 end