ms-xcalibur 0.1.0 → 0.2.0

data/History

@@ -0,0 +1,8 @@
+== 0.2.0 / 2009-03-31
+
+Updated release to use latest tap.  Removed
+raw_to_mgf task as it can be performed using
+existing tasks.
+
+* removed RawToMgf
+* updated tasks

data/MIT-LICENSE

@@ -1,21 +1,19 @@
-Copyright (c) 2006-2008, Regents of the University of Colorado.
-Developer:: Simon Chiang, Biomolecular Structure Program, Hansen Lab
-Support:: CU Denver School of Medicine Deans Academic Enrichment Fund
+Copyright (c) 2009, Regents of the University of Colorado.
 
-Permission is hereby granted, free of charge, to any person obtaining a copy of this
-software and associated documentation files (the "Software"), to deal in the Software
-without restriction, including without limitation the rights to use, copy, modify, merge,
-publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons
-to whom the Software is furnished to do so, subject to the following conditions:
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in all copies or
-substantial portions of the Software.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
-HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
-WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-OTHER DEALINGS IN THE SOFTWARE.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README

@@ -8,6 +8,14 @@ An {Mspire}[http://mspire.rubyforge.org] library supporting {Xcalibur}[http://ww
 * Github[http://github.com/bahuvrihi/ms-xcalibur/tree/master]
 * {Google Group}[http://groups.google.com/group/mspire-forum]
 
+== Usage
+
+Currently the primary use of Ms-Xcalibur is to convert RAW files to dta files.  Use this workflow to do so:
+
+  % tap run -- raw_to_dta RAW_FILE --:s dta_to_mgf > MGF_FILE
+
+The extract_msn.exe tool provided by Xcalibur/BioWorks must already be installed.
+
 == Installation
 
 Ms-Xcalibur is available as a gem on RubyForge[http://rubyforge.org/projects/mspire].  Use:
@@ -16,7 +24,7 @@ Ms-Xcalibur is available as a gem on RubyForge[http://rubyforge.org/projects/msp
 
 == Info 
 
-Copyright (c) 2006-2008, Regents of the University of Colorado.
+Copyright (c) 2009, Regents of the University of Colorado.
 Developer:: {Simon Chiang}[http://bahuvrihi.wordpress.com], {Biomolecular Structure Program}[http://biomol.uchsc.edu/], {Hansen Lab}[http://hsc-proteomics.uchsc.edu/hansenlab/] 
 Support:: CU Denver School of Medicine Deans Academic Enrichment Fund
 Licence:: {MIT-Style}[link:files/MIT-LICENSE.html]

data/lib/ms/xcalibur/convert/dta_to_mgf.rb

@@ -3,9 +3,20 @@ require 'constants'
 module Ms
   module Xcalibur
     module Convert
+      
       # :startdoc::manifest convert dta files to mgf format
-      # Converts a set of .dta files (Sequest format) into an .mgf (Mascot format) 
-      # file.  The conversion is straightforward.  
+      #
+      # Converts a set of dta files (Sequest format) into an mgf (Mascot format) 
+      # file.  By default the mgf file is printed to $stdout, so redirection is
+      # a good way to save the results.
+      #
+      #   % tap run -- dta_to_mgf ... > results.mgf
+      #
+      # Alternatively, specify the output file using the output configuration.
+      #
+      # === Conversion
+      #
+      # The dta -> mgf conversion is straightforward:
       #
       # dta format:
       #   [input_file.dta]
@@ -36,26 +47,17 @@ module Ms
 
         # Returns the unrounded mass of a proton (H - e) as calculated
         # from the {constants}[bioactive.rubyforge.org/constants] gem.
-        config :proton_mass, Element['H'].mass - Particle['Electron'].mass, &c.num_or_nil        # allows specification of an alternate proton mass
-
-        def process(output_file, *inputs)
-          return output_file if inputs.empty?
-
-          dta_files = inputs.collect do |file| 
-            if File.directory?(file)
-              Dir.glob(File.expand_path(File.join(file, "*.dta")))
-            else
-              raise "Not a .dta file: #{file}" unless file =~ /\.(dta)$/
-              file
-            end
-          end
-
-          prepare(output_file) 
-          File.open(output_file, "wb") do |target|
-            h = proton_mass
-
-            dta_files.flatten.each do |file|
-              #log_basename(:merging, file)
+        config :proton_mass, Element['H'].mass - Particle['Electron'].mass, &c.num_or_nil # Specify the proton mass
+        config :output, $stdout, &c.io(:<<, :binmode) # The output file
+        
+        def process(*dta_files)
+          prepare(output) if output.kind_of?(String)
+          open_io(output, 'w') do |target|
+            target.binmode
+            
+            log :convert, "#{dta_files.length} dta files"
+            dta_files.each do |file|
+              check_terminate
               lines = File.read(file).split(/\r?\n/)
 
               # get the mh and z
@@ -70,19 +72,15 @@ module Ms
               target << %Q{BEGIN IONS
 TITLE=#{File.basename(file)}
 CHARGE=#{z}+
-PEPMASS=#{(mh + (z-1) * h)/ z}
+PEPMASS=#{(mh + (z-1) * proton_mass)/ z}
 #{lines.join("\n")}
 END IONS
-
+
 }
             end
           end
-          log(:made, output_file)
-
-          output_file
         end
       end
-      
     end
   end
 end

data/lib/ms/xcalibur/convert/raw_to_dta.rb

@@ -1,38 +1,54 @@
 module Ms
   module Xcalibur
     module Convert
+      
       # :startdoc::manifest convert RAW files to dta format
-      # Converts a .RAW file to dta files using extract_msn.exe 
       #
-      # extract_msn.exe is an Xcalibur/BioWorks tool that extracts spectra from .RAW
-      # files into .dta (Sequest) format and must be installed for RawToDta to work.
-      # RawToDta was developed against extract_msn version 4.0.  You can check if
-      # extract_msn is installed at the default location, as well as determine the  
-      # version of your executable using:
+      # Converts a RAW file to dta files using extract_msn.exe.  Returns an
+      # array of the output dta files.  By default extracted files are put
+      # in a directory named after the RAW file, but an alternate extraction
+      # directory can be specified iwth the output-dir option.
       #
-      #   % tap run -- xcalibur/convert/raw_to_dta  --extract_msn_help
+      # RawToDta will skip extraction of an 'lcq_dta.txt' file and all the dta
+      # files listed therein exist in the output directory.  This is good in
+      # most cases; if you want to force execution set force true for the run:
+      #
+      #   % tap run --force -- raw_to_dta ...
+      #
+      # === extract_msn
+      #
+      # extract_msn.exe is an Xcalibur/BioWorks tool that extracts spectra from
+      # RAW files into dta (Sequest) format and must be installed for RawToDta
+      # to work.  At present this means that RawToDta can only work on Windows.
+      #
+      # RawToDta was developed against extract_msn version 4.0.  You can check
+      # if extract_msn is installed at the default location, as well as
+      # determine the version of your executable using:
+      #
+      #   % tap run -- raw_to_dta  --extract_msn_help
       #
       class RawToDta < Tap::FileTask
-        config :extract_msn, 'C:\Xcalibur\System\Programs\extract_msn.exe' # the full path to the extract_msn executable
-        config :first_scan, nil, &c.integer_or_nil              # (-F)
-        config :last_scan, nil, &c.integer_or_nil               # (-L)
-        config :lower_MW, nil, &c.num_or_nil                    # (-B)
-        config :upper_MW, nil, &c.num_or_nil                    # (-T)
-        config :precursor_mass_tol, 1.4, &c.num                 # (-M)
-        config :num_allowed_intermediate_scans_for_grouping, 1, &c.integer # (-S)
-        config :charge_state, nil, &c.integer_or_nil            # (-C)
-        config :num_required_group_scans, 1, &c.integer_or_nil  # (-G)
-        config :num_ions_required, 0, &c.integer_or_nil         # (-I)
-        config :intensity_threshold, nil, &c.integer_or_nil     # (-E)
-        config :use_unified_search_file, nil, &c.flag           # (-U)
-        config :subsequence, nil                                # (-Y)
-        config :write_zta_files, nil, &c.flag                   # (-Z)
-        config :perform_charge_calculations, nil, &c.flag       # (-K)
-        config :template_file, nil                              # (-O)
-        config :options_string, nil                             # (-A)
-        config :minimum_signal_to_noise, 3, &c.num              # (-R)
-        config :minimum_number_of_peaks, 5, &c.integer          # (-r)
-
+        config :extract_msn, 'C:\Xcalibur\System\Programs\extract_msn.exe' # The full path to the extract_msn executable
+        config :first_scan, nil, :short => :F, &c.integer_or_nil
+        config :last_scan, nil, :short => :L, &c.integer_or_nil
+        config :lower_MW, nil, :short => :B, &c.num_or_nil
+        config :upper_MW, nil, :short => :T, &c.num_or_nil
+        config :precursor_mass_tol, 1.4, :short => :M, &c.num
+        config :num_allowed_intermediate_scans_for_grouping, 1, :short => :S, &c.integer
+        config :charge_state, nil, :short => :C, &c.integer_or_nil
+        config :num_required_group_scans, 1, :short => :G, &c.integer_or_nil
+        config :num_ions_required, 0, :short => :I, &c.integer_or_nil
+        config :intensity_threshold, nil, :short => :E, &c.integer_or_nil
+        config :use_unified_search_file, nil, :short => :U, &c.flag
+        config :subsequence, nil, :short => :Y
+        config :write_zta_files, nil, :short => :Z, &c.flag
+        config :perform_charge_calculations, nil, :short => :K, &c.flag
+        config :template_file, nil, :short => :O
+        config :options_string, nil, :short => :A
+        config :minimum_signal_to_noise, 3, :short => :R, &c.num
+        config :minimum_number_of_peaks, 5, :short => :r, &c.integer
+        
+        config :output_dir, nil, &c.string_or_nil # The output directory
         config_attr(:extract_msn_help, nil, :arg_type => :flag) do |value|  # Print the extract_msn help         
           if value
             sh(extract_msn)
@@ -114,29 +130,52 @@ module Ms
           args.join(' ')
         end
 
-        def process(input_file, output_dir=nil)
+        def process(input_file)
           extname = File.extname(input_file)
           raise "Expected .RAW file: #{input_file}" unless  extname =~ /\.RAW$/i
 
           # Target the output to a directory with the same basename 
           # as the raw file, unless otherwise specified.
-          output_dir = input_file.chomp(File.extname(input_file)) if output_dir == nil
-
-          mkdir(output_dir)
-          command = cmd(input_file, output_dir)
-
-          log :sh, command
-          if app.quiet
-            capture_sh(command, true)
+          output_dir = self.output_dir || input_file.chomp(File.extname(input_file))
+          current_dta_files = dta_files(output_dir)
+          if !current_dta_files.empty? && uptodate?(current_dta_files, input_file)
+            log_basename :uptodate, input_file
+            current_dta_files
           else
-            sh(command)
-            puts ""  # add extra line to make logging nice
-          end
+            unless File.exists?(extract_msn)
+              raise "extract_msn does not exist at: #{extract_msn}"
+            end
+            
+            mkdir(output_dir)
+            command = cmd(input_file, output_dir)
 
-          # This may select additional .dta files that existed before raw_to_dta
-          # TODO - maybe read lcq_dta for files? 
-          Dir.glob( File.expand_path(File.join(output_dir, "*.dta")) ) 
+            log :sh, command
+            if app.quiet
+              capture_sh(command, true)
+            else
+              sh(command)
+              puts ""  # add extra line to make logging nice
+            end
+            
+            dta_files(output_dir)
+          end
+        end
+        
+        # Returns an array of dta_files specified in the lcq_dta.txt file under
+        # output_dir.  A simple glob is less preferable than reading the list of
+        # files from lcq_dta because there is no guarantee all the .dta file in
+        # the output directory should be used for a particular file.
+        def dta_files(output_dir)
+          lcq_dta = File.join(output_dir, 'lcq_dta.txt')
+          
+          dta_files = []
+          File.read(lcq_dta).scan(/Datafile:\s(.*?\.dta)\s/) do |dta_file|
+            dta_files << File.join(output_dir, dta_file)
+          end if File.exists?(lcq_dta)
+          
+          dta_files
         end
+        
       end
     end
   end

data/lib/ms/xcalibur/peak_file.rb

@@ -3,7 +3,7 @@ module Ms
     # A simple representation of a peak file exported from Xcalibur Qual 
     # Browser (v 2.0).  The expected format of a peak file is as shown below:
     #
-    #  [peak_file.txt]
+    #   [peak_file.txt]
     #   SPECTRUM - MS
     #   GSE_T29K_080703143635.raw
     #   ITMS + c ESI Full ms [300.00-2000.00]

data/lib/ms/xcalibur/peakify.rb

@@ -3,11 +3,12 @@ require 'ms/xcalibur/peak_file'
 module Ms
   module Xcalibur
     # :startdoc::manifest adds graph data to an exported peak file
-    # Peakify adds points to signify the relative intensity 
-    # (ie the rounded intensity/max_intensity) of peaks in 
-    # an exported peak list.  This can be useful as a visual aid. 
     #
-    #   [a_sample_result.txt]
+    # Peakify adds points to signify the relative intensity (ie the rounded
+    # intensity/max_intensity) of peaks to a peak list extracted from Xcalibur
+    # Qual Browser (v 2.0)..  This can be useful as a visual aid. 
+    #
+    #   [peakfile.txt]
     #   SPECTRUM - MS
     #   GSE_T29K_080703143635.raw
     #   ITMS + c ESI Full ms [300.00-2000.00]
@@ -20,45 +21,44 @@ module Ms
     #   302.465759	3000.0	..................................................
     #   ...
     #
-    # Options can be specified to filter out points within a
-    # range of relative intensities.  Peakify can handle exported 
-    # peak lists from Xcalibur Qual  Browser (v 2.0).
+    # Options can be specified to filter out points within a range of relative
+    # intensities.
     #
     class Peakify < Tap::FileTask
 
-      config :point_char, '.'           # a character used for each intensity point
-      config :min, 0, &c.num            # min relative intenisty
-      config :max, 100, &c.num          # max relative intenisty
-      config :sort, false, &c.flag      # sort by intensity
+      config :point_char, '.'                          # A character used for each intensity point
+      config :min, 0, &c.num                           # Min relative intenisty
+      config :max, 100, &c.num                         # Max relative intenisty
+      config :sort, false, &c.flag                     # Sort by intensity
+      config :output, $stdout, &c.io(:<<, :binmode)    # The output file
 
-      def process(source, target=basepath(source, 'peaks.txt'))
-        prepare(target)
+      def process(source)
+        prepare(output) if output.kind_of?(String)
+        open_io(output, 'w') do |target|
+          target.binmode
+          
+          # now perform the task...
+          peak_file = PeakFile.parse File.read(source)
+          max_intensity = peak_file.data.inject(0) do |max, (mz, intensity)|
+            intensity > max ? intensity : max
+          end
 
-        # now perform the task...
-        peak_file = PeakFile.parse File.read(source)
-        max_intensity = peak_file.data.inject(0) do |max, (mz, intensity)|
-          intensity > max ? intensity : max
-        end
+          range = min..max
+          peak_file.data = peak_file.data.collect do |(mz, intensity)|
+            percent = (intensity / max_intensity * 100)
+            next unless range.include?(percent)
 
-        range = min..max
-        peak_file.data = peak_file.data.collect do |(mz, intensity)|
-          percent = (intensity / max_intensity * 100)
-          next unless range.include?(percent)
+            [mz, intensity, point_char * percent.round]
+          end.compact
 
-          [mz, intensity, point_char * percent.round]
-        end.compact
+          if sort
+            peak_file.data = peak_file.data.sort_by do |(mz, intensity)|
+              intensity
+            end.reverse
+          end
 
-        if sort
-          peak_file.data = peak_file.data.sort_by do |(mz, intensity)|
-            intensity
-          end.reverse
+          target << peak_file.to_s
         end
-
-        File.open(target, "wb") do |file|
-          file << peak_file.to_s
-        end
-
-        target
       end
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: ms-xcalibur
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Simon Chiang
@@ -9,9 +9,19 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-12-03 00:00:00 -07:00
+date: 2009-03-31 00:00:00 -06:00
 default_executable: 
 dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: configurable
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.4.2
+    version: 
 - !ruby/object:Gem::Dependency 
   name: tap
   type: :runtime
@@ -20,7 +30,7 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        version: "0.11"
+        version: 0.12.4
     version: 
 - !ruby/object:Gem::Dependency 
   name: constants
@@ -39,15 +49,16 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
+- History
 - README
 - MIT-LICENSE
 files: 
 - lib/ms/xcalibur/convert/dta_to_mgf.rb
 - lib/ms/xcalibur/convert/raw_to_dta.rb
-- lib/ms/xcalibur/convert/raw_to_mgf.rb
 - lib/ms/xcalibur/peak_file.rb
 - lib/ms/xcalibur/peakify.rb
 - tap.yml
+- History
 - README
 - MIT-LICENSE
 has_rdoc: true

data/lib/ms/xcalibur/convert/raw_to_mgf.rb

@@ -1,86 +0,0 @@
-require 'ms/xcalibur/convert/raw_to_dta'
-require 'ms/xcalibur/convert/dta_to_mgf'
-
-module Ms
-  module Xcalibur
-    module Convert
-      # :startdoc::manifest convert RAW files to mgf format
-      # Extracts spectra from a .RAW file and formats them as mgf (Mascot
-      # Generic Format).  RawToMgf is a workflow that uses the RawToDta
-      # and DtaToMgf tasks, and can be configured through these tasks
-      # using the following configuration files:
-      #
-      #   config/xcalibur/convert
-      #   |- raw_to_mgf.yml               # configures RawToMgf
-      #   `- raw_to_mgf
-      #    |- raw_to_dta.yml              # configures RawToDta
-      #    `- dta_to_mgf.yml              # configures DtaToMgf
-      #
-      # Mgf files are named after the RAW file they represent; the group
-      # merge file is named 'merge.mgf' although an alternate merge file
-      # name can be specified in the options.
-      #
-      class RawToMgf < Tap::Task
-        
-        define :raw_to_dta, Xcalibur::Convert::RawToDta
-        define :dta_to_mgf, Xcalibur::Convert::DtaToMgf
-        define :cleanup  do |raw_dir|           
-          log :rm, raw_dir
-
-          # take this stepwise to be a little safer...
-          FileUtils.rm Dir.glob(raw_dir + "/*.dta")
-          FileUtils.rm ["#{raw_dir }/lcq_dta.txt", "#{raw_dir }/lcq_profile.txt"]
-          FileUtils.rmdir raw_dir
-        end
-                
-        config :merge_file, 'merge.mgf'            # the group merge file
-        config :merge_individual, true, &c.switch  # merge the dta's for each RAW file
-        config :merge_group, true, &c.switch       # merge the dta's for all RAW files
-        config :remove_dta_files, true, &c.switch  # clean up dta files upon completion
-        
-        def workflow
-          group_results = []
-          raw_to_dta.on_complete do |_result|
-            if merge_individual
-              input_file = _result._original[0]
-              output_file = File.join( File.dirname(merge_file), File.basename(input_file).chomp(File.extname(input_file)) + ".mgf")
-              dta_to_mgf.execute(output_file, *_result._iterate)
-            end
-
-            # collect _results to determine when all the input
-            # files have been processed by raw_to_dta
-            group_results << _result
-
-            # When all the input files have been converted, merge the
-            # group and enque a task to cleanup the dta files, as specified.
-            if group_results.length == @n_inputs
-              if merge_group
-                all_results = group_results.collect {|_result| _result._iterate }.flatten
-                dta_to_mgf.execute(merge_file, *all_results)
-              end
-            end
-          end
-        end
-        
-        def process(*input_files)
-          @n_inputs = input_files.length
-          
-          dta_dirs = []
-          input_files.each do |input_file|
-            dta_dir = File.basename(input_file).chomp(File.extname(input_file))
-            dta_dirs << dta_dir
-            raw_to_dta.execute(input_file, dta_dir)
-          end
-          
-          if remove_dta_files
-            dta_dirs.each {|dir| cleanup.process(dir) }
-          end
-              
-          @n_inputs = nil
-          nil
-        end
-        
-      end
-    end
-  end
-end