protk 1.2.6.pre5 → 1.3.0.pre1

data/lib/protk/tool.rb

@@ -18,7 +18,9 @@ class Tool
   
   # The option parser used to parse command-line options. 
   #
-  attr :option_parser, false
+  attr :option_parser
+
+  attr :options_defined_by_user
 
   # Prefix for background jobs
   # x = X!Tandem, o=OMSSA, p="Phenyx", m="Mascot"
@@ -32,6 +34,14 @@ class Tool
     @jobid_prefix=p
   end
 
+  def supported_options
+    os_hash=@options.to_h
+    # Remove entries entirely related to internal use
+    internal_keys=[:library, :inplace, :encoding, :transfer_type, :verbose]
+    os_hash.delete_if { |key,val| internal_keys.include? key }
+    os_hash
+  end
+
   # Provides direct access to options through methods of the same name
   #
   def method_missing(meth, *args, &block)
@@ -43,9 +53,23 @@ class Tool
   end
   
   
+  def add_value_option(symbol,default_value,opts)
+    @options[symbol]=default_value
+    @option_parser.on(*opts) do |val|
+      @options[symbol]=val
+      @options_defined_by_user[symbol]=opts
+    end
+  end
   
-  
-  
+  def add_boolean_option(symbol,default_value,opts)
+    @options[symbol]=default_value
+    @option_parser.on(*opts) do 
+      @options[symbol]=!default_value
+      @options_defined_by_user[symbol]=opts
+    end
+  end
+
+
   # Creates an empty options object to hold commandline options
   # Also creates an option_parser with default options common to all tools
   #
@@ -58,80 +82,66 @@ class Tool
     options.transfer_type = :auto
     options.verbose = false
     
-    @option_parser=OptionParser.new do |opts|
-
-      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|
-          @options.output_prefix = prefix
-        end
-
-        @options.output_suffix = ""
-        opts.on( '-e', '--output-suffix suff', 'A string to append to the name of output files' ) do |suffix|
-          @options.output_suffix = suffix
-        end
-        
-      end
-      
-      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.include? :over_write)
-            
-        @options.over_write=false
-        opts.on( '-r', '--replace-output', 'Dont skip analyses for which the output file already exists' ) do  
-          @options.over_write = true
-        end
-        
-      end
+    @options_defined_by_user={}
 
-      if ( option_support.include? :background)
+    @option_parser=OptionParser.new do |opts|      
 
-        @options.background = false
-        opts.on( '-z', '--background', 'Run jobs in the background using pbs' ) do  
-          @options.background = true
-        end
-        
-      end
-      
-       
       opts.on( '-h', '--help', 'Display this screen' ) do
         puts opts
         exit
       end
-       
     end
-    
-  end
-  
 
+    if ( option_support.include? :prefix)
+      add_value_option(:output_prefix,"",['-b','--output-prefix pref', 'A string to prepend to the name of output files'])
+    end
 
+    if ( option_support.include? :over_write)
+      add_boolean_option(:over_write,false,['-r', '--replace-output', 'Dont skip analyses for which the output file already exists'])        
+    end
 
+    if ( option_support.include? :explicit_output )
+      add_value_option(:explicit_output,nil,['-o', '--output out', 'An explicitly named output file.'])
+    end
 
-   # Create and return a full base path (without extension) representing the output file for this analysis
-   # Optionally provide the extension to be removed (if not provided it will be inferred)
-   #
-   def output_base_path(output_file,ext=nil)
-
-     output_path=Pathname.new(output_file)
-     throw "Error: Output directory #{output_path.dirname} does not exist" unless output_path.dirname.exist?
-     dir=output_path.dirname.realpath.to_s
-     basename=output_path.basename.to_s
-     if ( ext==nil)
-       ext=output_path.extname    
-     end
-     base_name=basename.gsub(/#{ext}$/,"")
-
-     "#{dir}/#{@options.output_prefix}#{base_name}#{@options.output_suffix}"
+    if ( option_support.include? :threads )
+      add_value_option(:threads,1,['-n','--threads num','Number of processing threads to use. Set to 0 to autodetect an appropriate value'])
+    end
+
+  end
+
+
+   def self.extension_from_filename(filename)
+    ext=""
+    case filename.chomp
+    when /\.pep\.xml/
+      ext=".pep.xml"
+    when /\.prot\.xml/
+      ext=".prot.xml"
+    else
+      ext=Pathname.new(filename.chomp).extname
+    end
+    ext
    end
 
+  def self.default_output_path(input_path,newext,prefix,suffix)
+    path=""
+    input_path=input_path[0] if (input_path.instance_of?(Array) && input_path.length==1)
+    if input_path.instance_of?(Array)
+      dir=Pathname.new(input_path[0]).dirname.realpath.to_s
+      basename="collected_outputs"
+      path="#{dir}/#{prefix}#{basename}#{suffix}#{newext}"
+    else
+      dir=Pathname.new(input_path).dirname.realpath.to_s
+      basename=Pathname.new(input_path).basename.to_s
+      oldext=Tool.extension_from_filename(input_path)
+      basename=basename.gsub(/#{oldext}$/,"")
+      path="#{dir}/#{prefix}#{basename}#{suffix}#{newext}"
+    end
+    path
+   end
 
-   def check_options(mandatory=[])
+   def check_options(require_input_file=false,mandatory=[])
     # Checking for required options
     begin
       self.option_parser.parse!
@@ -143,54 +153,25 @@ class Tool
       end                                                              
     rescue OptionParser::InvalidOption, OptionParser::MissingArgument      
       puts $!.to_s                                                           
-      puts tool.option_parser                                              
+      puts self.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)
-   #
-   def input_base_path(input_file,ext=nil)
-     input_path=Pathname.new(input_file)
-     throw "Error: Input directory #{input_path.dirname} does not exist" unless input_path.dirname.exist?
-     dir=input_path.dirname.realpath.to_s
-     if ( ext==nil)
-       ext=input_path.extname    
-     end
-     base_name=input_path.basename.to_s.gsub(/#{ext}$/,"")
-     "#{dir}/#{base_name}"
-   end
-   
-   
+    if ( require_input_file && ARGV[0].nil? )
+      puts "You must supply an input file"
+      puts self.option_parser 
+      return false
+    end
+
+    return true
+   end   
    
    # Run the search tool using the given command string and global environment
    #
-   def run(cmd,genv,job_params=nil,jobscript_path=nil,autodelete=true)
-     if ( @options.background )
-       throw "Error: Background option was selected but this host does not support background jobs" unless genv.has_pbs
-       # Send this job off to be run in a batch queuer
-       
-       cmd_runner=CommandRunner.new(genv)
-       
- 
-       
-       cmd_runner.run_batch(cmd,job_params,jobscript_path,autodelete)
-       
-     else 
-       cmd_runner=CommandRunner.new(genv)
-       cmd_runner.run_local(cmd)
-     end
+   def run(cmd,genv,autodelete=true)
+    cmd_runner=CommandRunner.new(genv)
+    cmd_runner.run_local(cmd)
    end
    
-   def jobid_from_filename(filename)
-      jobid="protk"
-      jobnum_match=filename.match(/(.{1,10})\.d/)
-      if (jobnum_match!=nil)
-        jobid="#{self.jobid_prefix}#{jobnum_match[1]}"
-      end
-      return jobid
-    end
   
 end

data/lib/protk.rb

@@ -1,19 +1,14 @@
 require 'protk/tool.rb'
 require 'protk/swissprot_database.rb'
-require 'protk/spreadsheet_extensions.rb'
 require 'protk/search_tool.rb'
 require 'protk/protxml.rb'
-require 'protk/protein_annotator.rb'
 require 'protk/prophet_tool.rb'
-require 'protk/plasmodb.rb'
 require 'protk/omssa_util.rb'
 require 'protk/mascot_util.rb'
 require 'protk/manage_db_tool.rb'
 require 'protk/galaxy_util.rb'
 require 'protk/galaxy_stager.rb'
-require 'protk/eupathdb_gene_information_table.rb'
 require 'protk/constants.rb'
 require 'protk/command_runner.rb'
-require 'protk/biotools_excel_converter.rb'
 require 'protk/bio_sptr_extensions.rb'
-require 'protk/galaxy_stager.rb'
+require 'protk/galaxy_stager.rb'

metadata

@@ -1,35 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.2.6.pre5
+  version: 1.3.0.pre1
 platform: ruby
 authors:
 - Ira Cooke
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-10-28 00:00:00.000000000 Z
+date: 2014-06-24 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: ftools
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '0.0'
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.0.0
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: '0.0'
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.0.0
 - !ruby/object:Gem::Dependency
   name: open4
   requirement: !ruby/object:Gem::Requirement
@@ -110,26 +90,6 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: 3.2.5
-- !ruby/object:Gem::Dependency
-  name: spreadsheet
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 0.7.4
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.7.4
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 0.7.4
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.7.4
 - !ruby/object:Gem::Dependency
   name: libxml-ruby
   requirement: !ruby/object:Gem::Requirement
@@ -151,112 +111,79 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 2.7.0
 - !ruby/object:Gem::Dependency
-  name: mascot-dat
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.3.1
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.3.1
-  type: :runtime
+        version: '3.0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 0.3.1
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 0.3.1
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: bio-blastxmlparser
+  name: rspec-mocks
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.1.1
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 1.1.1
-  type: :runtime
+        version: '3.0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 1.1.1
-    - - '>='
-      - !ruby/object:Gem::Version
-        version: 1.1.1
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: rake-compiler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.5'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '2.5'
+        version: '0'
 description: A bunch of tools for proteomics
 email: iracooke@gmail.com
 executables:
 - protk_setup.rb
 - manage_db.rb
-- asapratio.rb
-- libra.rb
-- xpress.rb
 - tandem_search.rb
 - mascot_search.rb
 - omssa_search.rb
 - msgfplus_search.rb
 - mascot_to_pepxml.rb
-- file_convert.rb
+- tandem_to_pepxml.rb
 - make_decoy.rb
-- correct_omssa_retention_times.rb
 - repair_run_summary.rb
 - add_retention_times.rb
 - peptide_prophet.rb
 - interprophet.rb
 - protein_prophet.rb
 - pepxml_to_table.rb
-- xls_to_table.rb
-- annotate_ids.rb
 - unimod_to_loc.rb
-- generate_omssa_loc.rb
 - uniprot_mapper.rb
-- feature_finder.rb
-- toppas_pipeline.rb
-- gffmerge.rb
 - sixframe.rb
 - augustus_to_proteindb.rb
 - protxml_to_gff.rb
-- uniprot_annotation.rb
 - protxml_to_table.rb
-- blastxml_to_table.rb
 extensions:
-- ext/protk/decoymaker/extconf.rb
+- ext/decoymaker/extconf.rb
 extra_rdoc_files: []
 files:
 - README.md
 - bin/add_retention_times.rb
-- bin/annotate_ids.rb
-- bin/asapratio.rb
 - bin/augustus_to_proteindb.rb
-- bin/blastxml_to_table.rb
-- bin/correct_omssa_retention_times.rb
-- bin/feature_finder.rb
-- bin/file_convert.rb
-- bin/generate_omssa_loc.rb
-- bin/gffmerge.rb
 - bin/interprophet.rb
-- bin/libra.rb
 - bin/make_decoy.rb
 - bin/manage_db.rb
 - bin/mascot_search.rb
@@ -272,18 +199,13 @@ files:
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
 - bin/tandem_search.rb
-- bin/toppas_pipeline.rb
+- bin/tandem_to_pepxml.rb
 - bin/unimod_to_loc.rb
-- bin/uniprot_annotation.rb
 - bin/uniprot_mapper.rb
-- bin/xls_to_table.rb
-- bin/xpress.rb
-- ext/protk/decoymaker/decoymaker.c
-- ext/protk/decoymaker/extconf.rb
-- ext/protk/simplealign/extconf.rb
+- ext/decoymaker/decoymaker.c
+- ext/decoymaker/extconf.rb
 - lib/protk.rb
 - lib/protk/bio_sptr_extensions.rb
-- lib/protk/biotools_excel_converter.rb
 - lib/protk/command_runner.rb
 - lib/protk/constants.rb
 - lib/protk/convert_util.rb
@@ -299,6 +221,9 @@ files:
 - lib/protk/data/predefined_db.sphuman.yaml
 - lib/protk/data/predefined_db.swissprot_annotation.yaml
 - lib/protk/data/predefined_db.swissprot_fasta_annotation.yaml
+- lib/protk/data/tandem_gpm_defaults.xml
+- lib/protk/data/tandem_isb_kscore_defaults.xml
+- lib/protk/data/tandem_isb_native_defaults.xml
 - lib/protk/data/tandem_params.xml
 - lib/protk/data/taxonomy_template.xml
 - lib/protk/data/unimod.xml
@@ -306,11 +231,9 @@ files:
 - lib/protk/data/uniprot_accessions_table.txt
 - lib/protk/data/uniprot_input_accessions.loc
 - lib/protk/data/yum_packages.yaml
-- lib/protk/eupathdb_gene_information_table.rb
 - lib/protk/fastadb.rb
 - lib/protk/galaxy_stager.rb
 - lib/protk/galaxy_util.rb
-- lib/protk/gapped_aligner.rb
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/manage_db_tool.rb
 - lib/protk/mascot_util.rb
@@ -319,22 +242,20 @@ files:
 - lib/protk/pepxml.rb
 - lib/protk/plasmodb.rb
 - lib/protk/prophet_tool.rb
-- lib/protk/protein_annotator.rb
 - lib/protk/protxml.rb
+- lib/protk/protxml_to_gff_tool.rb
 - lib/protk/randomize.rb
 - lib/protk/search_tool.rb
 - lib/protk/setup_rakefile.rake
 - lib/protk/setup_tool.rb
-- lib/protk/spreadsheet_extensions.rb
 - lib/protk/swissprot_database.rb
+- lib/protk/tandem_search_tool.rb
 - lib/protk/tool.rb
 - lib/protk/uniprot_mapper.rb
-- lib/protk/xtandem_defaults.rb
 homepage: http://rubygems.org/gems/protk
 licenses: []
 metadata: {}
-post_install_message: Now run protk_setup.rb to install third party tools and manage_db.rb
-  to install databases.
+post_install_message: Now run protk_setup.rb to install third party tools
 rdoc_options: []
 require_paths:
 - lib

data/bin/annotate_ids.rb

@@ -1,59 +0,0 @@
-#!/usr/bin/env ruby
-#
-# 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.
-#
-#
-require 'protk/constants'
-require 'protk/command_runner'
-require 'protk/prophet_tool'
-require 'protk/protein_annotator'
-
-
-
-# Setup specific command-line options for this tool. Other options are inherited from Tool
-#
-id_tool=ProphetTool.new([:explicit_output,:over_write,:prefix_suffix])
-id_tool.option_parser.banner = "Run ID annotation on a prot.xml input file.\n\nUsage: annotate_ids.rb [options] file1.prot.xml"
-id_tool.options.output_prefix="annotated_"
-
-
-id_tool.options.input_format=nil
-id_tool.option_parser.on( '-I', '--input-format format', 'Format of input file' ) do |format| 
-  id_tool.options.input_format = format
-end
-
-exit unless id_tool.check_options
-
-# Obtain a global environment object
-genv=Constants.new
-
-input_file=ARGV[0]
-
-database_file=id_tool.extract_db(input_file)
-
-output_file=nil
-
-if ( id_tool.explicit_output==nil)
-  output_file="#{id_tool.output_prefix}#{input_file}#{id_tool.output_suffix}.xls"
-else
-  output_file=id_tool.explicit_output
-end
-
-converter=ProteinAnnotator.new
-
-begin
-  outpath=Pathname.new(output_file)
-        
-  if ( id_tool.over_write || !outpath.exist? )
-    converter.convert(input_file,output_file,id_tool.input_format)
-  else
-    p "Output file #{output_file} already exists"
-  end
-
-rescue Exception
-  p "Couldn't convert #{input_file}"
-  raise
-end

data/bin/asapratio.rb

@@ -1,27 +0,0 @@
-#!/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}]