protk 1.2.1 → 1.2.2

data/lib/protk/tool.rb

@@ -49,7 +49,7 @@ class Tool
   # Creates an empty options object to hold commandline options
   # Also creates an option_parser with default options common to all tools
   #
-  def initialize(option_support={:help=>true})
+  def initialize(option_support=[])
     @jobid_prefix = "x"
     @options = OpenStruct.new
     options.library = []
@@ -59,8 +59,8 @@ class Tool
     options.verbose = false
     
     @option_parser=OptionParser.new do |opts|
-      
-      if ( option_support[:prefix_suffix]==true)
+
+      if ( option_support.include? :prefix_suffix)
       
         @options.output_prefix = ""
         opts.on( '-b', '--output-prefix pref', 'A string to prepend to the name of output files' ) do |prefix|
@@ -74,14 +74,14 @@ class Tool
         
       end
       
-      if ( option_support[:explicit_output]==true)
+      if ( option_support.include? :explicit_output )
         @options.explicit_output = nil
         opts.on( '-o', '--output out', 'An explicitly named output file.' ) do |out|
           @options.explicit_output = out
         end
       end
          
-      if ( option_support[:over_write]==true)
+      if ( option_support.include? :over_write)
             
         @options.over_write=false
         opts.on( '-r', '--replace-output', 'Dont skip analyses for which the output file already exists' ) do  
@@ -90,7 +90,7 @@ class Tool
         
       end
 
-      if ( option_support[:background]==true)
+      if ( option_support.include? :background)
 
         @options.background = false
         opts.on( '-z', '--background', 'Run jobs in the background using pbs' ) do  
@@ -99,12 +99,10 @@ class Tool
         
       end
       
-      if ( option_support[:help]==true)
        
-        opts.on( '-h', '--help', 'Display this screen' ) do
-          puts opts
-          exit
-        end
+      opts.on( '-h', '--help', 'Display this screen' ) do
+        puts opts
+        exit
       end
        
     end
@@ -133,7 +131,23 @@ class Tool
    end
 
 
-
+   def check_options(mandatory=[])
+    # Checking for required options
+    begin
+      self.option_parser.parse!
+      missing = mandatory.select{ |param| self.send(param).nil? }
+      if not missing.empty?                                            
+        puts "Missing options: #{missing.join(', ')}"                  
+        puts self.option_parser                                                  
+        return false                                                        
+      end                                                              
+    rescue OptionParser::InvalidOption, OptionParser::MissingArgument      
+      puts $!.to_s                                                           
+      puts tool.option_parser                                              
+      return false                                                         
+    end
+    return true
+   end
 
    # Create a full base path (without extension) representing the input file for this analysis
    # Optionally provide the extension to be removed (if not provided it will be inferred)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.2.1
+  version: 1.2.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-03-05 00:00:00.000000000 Z
+date: 2013-06-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ftools
@@ -123,6 +123,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: 2.3.3
+- !ruby/object:Gem::Dependency
+  name: mascot-dat
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 0.3.1
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -151,7 +167,6 @@ executables:
 - mascot_search.rb
 - omssa_search.rb
 - msgfplus_search.rb
-- big_search.rb
 - mascot_to_pepxml.rb
 - file_convert.rb
 - make_decoy.rb
@@ -171,13 +186,11 @@ executables:
 - gffmerge.rb
 - sixframe.rb
 - uniprot_annotation.rb
+- protxml_to_table.rb
 extensions:
 - ext/protk/extconf.rb
 extra_rdoc_files: []
 files:
-- lib/convert_util.rb
-- lib/pepxml.rb
-- lib/protk/big_search_tool.rb
 - lib/protk/bio_sptr_extensions.rb
 - lib/protk/biotools_excel_converter.rb
 - lib/protk/command_runner.rb
@@ -206,12 +219,10 @@ files:
 - lib/protk/uniprot_mapper.rb
 - lib/protk/xtandem_defaults.rb
 - lib/protk.rb
-- lib/protk/big_search_rakefile.rake
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/setup_rakefile.rake
 - bin/annotate_ids.rb
 - bin/asapratio.rb
-- bin/big_search.rb
 - bin/correct_omssa_retention_times.rb
 - bin/feature_finder.rb
 - bin/file_convert.rb
@@ -221,6 +232,7 @@ files:
 - bin/libra.rb
 - bin/make_decoy.rb
 - bin/manage_db.rb
+- bin/mascot2xml.rb
 - bin/mascot_search.rb
 - bin/mascot_to_pepxml.rb
 - bin/msgfplus_search.rb
@@ -229,10 +241,10 @@ files:
 - bin/pepxml_to_table.rb
 - bin/protein_prophet.rb
 - bin/protk_setup.rb
+- bin/protxml_to_table.rb
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
 - bin/tandem_search.rb
-- bin/template_search.rb
 - bin/toppas_pipeline.rb
 - bin/unimod_to_loc.rb
 - bin/uniprot_annotation.rb
@@ -247,6 +259,7 @@ files:
 - lib/protk/data/FeatureFinderCentroided.ini
 - lib/protk/data/FeatureFinderIsotopeWavelet.ini
 - lib/protk/data/galaxyenv.sh
+- lib/protk/data/pepxml_mascot_template.xml
 - lib/protk/data/predefined_db.crap.yaml
 - lib/protk/data/predefined_db.sphuman.yaml
 - lib/protk/data/predefined_db.swissprot_annotation.yaml
@@ -287,3 +300,4 @@ signing_key:
 specification_version: 3
 summary: Proteomics Toolkit
 test_files: []
+has_rdoc: 

data/bin/big_search.rb

@@ -1,41 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 14/12/2010
-#
-# Runs an MS/MS search using multiple search engines on multiple files in parallel
-# Merges results using interprophet to produce a single output file
-#
-# This tool assumes that datasets are from an ESI-QUAD-TOF instrument
-#
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/search_tool'
-require 'protk/big_search_tool'
-require 'rest_client'
-require 'rake'
-
-# Environment with global constants
-#
-genv=Constants.new
-
-# Setup specific command-line options for this tool. Other options are inherited from SearchTool
-#
-search_tool=SearchTool.new({:msms_search=>true,:background=>false,:database=>true,:over_write=>true,:glyco=>true,:explicit_output=>true})
-search_tool.jobid_prefix="b"
-
-search_tool.option_parser.banner = "Run a multi-search engine search on a set of input files.\n\nUsage: big_search.rb [options] file1.mzML file2.mzML ..."
-search_tool.options.output_suffix="_multisearch"
-
-
-search_tool.options.ncpu=1
-search_tool.option_parser.on( '-N', '--ncpu n', 'Split tasks into n separate processes if possible' ) do |n| 
-  search_tool.options.ncpu=n
-end
-
-search_tool.option_parser.parse!
-
-bgsrch = BigSearchTool.new
-
-
-p bgsrch.run ["hi", "howdy"]

data/bin/template_search.rb

@@ -1,144 +0,0 @@
-#!/usr/bin/env ruby
-#
-# This file is part of protk
-# Created by Ira Cooke 14/12/2010
-#
-# Runs an MS/MS search using the MSGFPlus search engine
-#
-require 'protk/search_tool'
-
-
-# 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.option_parser.banner = "Run an msms search on a set of msms spectrum input files.\n\nUsage: template_search.rb [options] file1.mzML file2.mzML ..."
-search_tool.options.output_suffix="_template"
-
-search_tool.options.custom_option="default"
-search_tool.option_parser.on('--custom-opt value','Custom option relevant to this tool only (Default default)') do |val|
-  search_tool.options.custom_option=val
-end
-  
-search_tool.option_parser.parse!
-
-# Set search engine specific parameters on the SearchTool object
-#
-msgf_bin="#{genv.msgf_bin}/MSGFPlus.jar"
-
-case 
-when Pathname.new(search_tool.database).exist? # It's an explicitly named db
-  current_db=Pathname.new(search_tool.database).realpath.to_s
-else
-  current_db=search_tool.current_database :fasta
-end
-
-fragment_tol = search_tool.fragment_tol
-precursor_tol = search_tool.precursor_tol
-
-
-throw "When --output is set only one file at a time can be run" if  ( ARGV.length> 1 ) && ( search_tool.explicit_output!=nil ) 
-
-# Run the search engine on each input file
-#
-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"
-  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}"
-
-  # Only proceed if the output file is not present or we have opted to over-write it
-  #
-  if ( search_tool.over_write || !Pathname.new(output_path).exist? )
-  
-    # The basic command
-    #
-    cmd= "java -Xmx#{search_tool.java_mem} -jar #{msgf_bin} -d #{current_db} -s #{input_path} -o #{output_path} "
-
-    #Missed cleavages
-    #
-    throw "Maximum value for missed cleavages is 2" if ( search_tool.missed_cleavages > 2)
-    cmd << " -ntt #{search_tool.missed_cleavages}"
-
-    # Precursor tolerance
-    #
-    cmd << " -t #{search_tool.precursor_tol}#{search_tool.precursor_tolu}"
-    
-    # Instrument type
-    #
-    cmd << " -inst 2"
-    
-#    cmd << " -m 4"
-
-    cmd << " -addFeatures 1"
-
-    # Enzyme
-    #
-  #    if ( search_tool.enzyme!="Trypsin")
-  #      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+')
-
-    # 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(",")
-      if ( var_mods !="" )
-        cmd << " -mv #{var_mods}"
-      end
-    else 
-      # Add options related to peptide modifications
-      #
-      if ( search_tool.glyco )
-        cmd << " -mv 119 "
-      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(",")
-      if ( fix_mods !="")
-        cmd << " -mf #{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
-    
-    # Up to here we've formulated the omssa 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)
-
-
-  else
-    genv.log("Skipping search on existing file #{output_path}",:warn)       
-  end
-
-end

data/lib/convert_util.rb

@@ -1,27 +0,0 @@
-require 'libxml'
-require 'constants'
-
-class ConvertUtil
-
-  def self.ensure_mzml_indexed(run_file)
-    if unindexed_mzml?(run_file)
-      index_mzml(run_file)
-    end
-  end
-
-  def self.index_mzml(mzml_file)
-    Dir.mktmpdir do |tmpdir|
-      genv=Constants.new
-      %x["#{genv.tpp_bin}/msconvert -o #{tmpdir} #{mzml_file}"]
-      indexed_file = Dir["#{tmpdir}/*"][0]
-      FileUtils.mv(indexed_file, mzml_file)
-    end
-  end
-  
-  def self.unindexed_mzml?(mzml_file)
-    reader = LibXML::XML::Reader.file(mzml_file)
-    reader.read
-    reader.name == "mzML"
-  end
-
-end

data/lib/pepxml.rb

@@ -1,22 +0,0 @@
-require 'rubygems'
-require 'rexml/document'
-require 'rexml/xpath'
-
-class PepXML
-  def initialize(file_name)
-    @doc=REXML::Document.new(File.new(file_name))
-  end
-
-  def find_runs() 
-    runs = {}
-    REXML::XPath.each(@doc,"//msms_run_summary") do |summary|
-      base_name = summary.attributes["base_name"]
-      if not runs.has_key?(base_name)
-        runs[base_name] = {:base_name => summary.attributes["base_name"],
-                           :type => summary.attributes["raw_data"]}
-      end
-    end
-    runs
-  end
-  
-end

data/lib/protk/big_search_rakefile.rake

@@ -1,16 +0,0 @@
-require 'protk/constants'
-
-$genv=Constants.new()
-
-ARGV.each do |fname| 
-
-	file fname do
-		puts fname
-	end
-
-	multitask :run => fname
-
-end
-
-
-task :default => :run

data/lib/protk/big_search_tool.rb

@@ -1,23 +0,0 @@
-# create rake dependencies
-# run rakefile
-#
-require 'optparse'
-require 'pathname'
-require 'protk/tool'
-require 'protk/command_runner'
-require 'pp'
-require 'rake'
-
-class BigSearchTool < Tool
-
-  def run input_files
-	command = "rake -f #{rakefile_path} #{input_files.join(" ")}"
-	runner=CommandRunner.new(Constants.new)
-    runner.run_local(command)
-  end
-
-  def rakefile_path
-    "#{File.dirname(__FILE__)}/big_search_rakefile.rake"
-  end
-
-end