ms-sequest 0.0.9 → 0.0.10

data/History

@@ -1,3 +1,7 @@
+== 0.0.10 / 2009-12-03
+
+* turned off warning if print_duplicates == 0
+
 == 0.0.9 / 2009-09-08
 
 * added capability to read srf files created by reading in .out/.dta folders (combined).

data/bin/srf_to_search.rb

@@ -1,19 +1,64 @@
-#!/usr/bin/env ruby
+#!/usr/bin/ruby
 
 require 'rubygems'
-require 'tap/task'
+require 'optparse'
 require 'ms/sequest/srf/search'
 
+opt = {
+  :format => 'mgf'
+}
+
+opts = OptionParser.new do |op|
+  op.banner = "usage: #{File.basename(__FILE__)} <file>.srf"
+  op.separator "outputs: <file>.mgf"
+  op.on("-f", "--format <mgf|dat>", "the output format (default: #{opt[:format]})") {|v| opt[:format] = v }
+end
+
 if ARGV.size == 0
-  ARGV << "--help"
+  puts opts
+  exit
 end
 
+format = opt[:format]
+
+ARGV.each do |srf_file|
+  base = srf_file.sub(/\.srf$/i, '')
+  newfile = 
+    case format
+    when 'dta'
+      base
+    when 'mgf'
+      base << '.' << format
+    end
+  srf = Ms::Sequest::Srf.new(srf_file, :link_protein_hits => false, :filter_by_precursor_mass_tolerance => false, :read_pephits => false )
+  # options just speed up reading since we don't need .out info anyway
+  case format
+  when 'mgf'
+    srf.to_mgf(newfile)
+  when 'dta'
+    srf.to_dta_files(newfile)
+  end
+end
+
+
+
+
+
+
+
+
+
+
+
+=begin
+
+#require 'tap/task'
 task_class = Ms::Sequest::Srf::SrfToSearch
 
 parser = ConfigParser.new do |opts|
   opts.separator "configurations"
   opts.add task_class.configurations
- 
+
   opts.on "--help", "Print this help" do
     puts "usage: #{File.basename(__FILE__)} <file>.srf ..."
     puts
@@ -23,11 +68,11 @@ parser = ConfigParser.new do |opts|
 end
 
 parser.parse!(ARGV)
- 
+
 task = task_class.new(parser.config)
 
 ARGV.each do |file|
   task.execute(file)
 end
 
-
+=end

data/lib/ms/sequest.rb

@@ -1,6 +1,6 @@
 
 module Ms
   module Sequest
-    VERSION = '0.0.9'
+    VERSION = '0.0.10'
   end
 end

data/lib/ms/sequest/srf.rb

@@ -2,6 +2,7 @@
 # standard lib
 require 'set'
 require 'fileutils'
+require 'scanf'
 
 # other gems
 require 'arrayclass'
@@ -12,14 +13,15 @@ require 'ms/id/protein'
 require 'ms/id/search'
 require 'ms/sequest/params'
 
-# for conversions
-require 'ms/sequest/srf/search'
-require 'ms/sequest/srf/sqt'
 
 module Ms ; end
 module Ms::Sequest ; end
 
 class Ms::Sequest::Srf
+
+  class NoSequestParamsError < ArgumentError
+  end
+
   include Ms::Id::Search
 
   # inherits peps and prots from Search
@@ -70,6 +72,7 @@ class Ms::Sequest::Srf
     end
   end
 
+  
   # opts:
   #     :filter_by_precursor_mass_tolerance => true | false (default true)
   #     # this will filter by the sequest params prec tolerance as is
@@ -87,6 +90,9 @@ class Ms::Sequest::Srf
   #     :read_pephits => true | false (default true)
   #     # will attempt to read peptide hit information (equivalent to .out
   #     # files), otherwise, just reads the dta information.
+  #
+  #     :params => <path/to/sequest.params> Some srf files do not include
+  #     their sequest params file - include it here if necessary.
   def initialize(filename=nil, opts={})
     @peps = []
 
@@ -164,33 +170,38 @@ class Ms::Sequest::Srf
   # opts are the same as for 'new'
   def from_file(filename, opts)
     opts = { :filter_by_precursor_mass_tolerance => true, :link_protein_hits => true, :read_pephits => true}.merge(opts)
-    params = Ms::Sequest::Srf.get_sequest_params(filename)
+
+    @params = 
+      if opts[:params]
+        Ms::Sequest::Params.new(opts[:params])
+      else
+        Ms::Sequest::Srf.get_sequest_params(filename)
+      end
+
     dup_references = 0
     dup_refs_gt_0 = false
-    if params
-      dup_references = params.print_duplicate_references.to_i
+    if @params
+      dup_references = @params.print_duplicate_references.to_i
       if dup_references == 0
-        warn <<END
-*****************************************************************************
-WARNING: This srf file lists only 1 protein per peptide! (based on the
-print_duplicate_references parameter in the sequest.params file used in its
-creation)  So, downstream output will likewise only contain a single protein
-for each peptide hit.  In many instances this is OK since downstream programs
-will recalculate protein-to-peptide linkages from the database file anyway.
-For complete protein lists per peptide hit, .srf files must be created with
-print_duplicate_references > 0. HINT: to capture all duplicate references, 
-set the sequest parameter 'print_duplicate_references' to 100 or greater.
-*****************************************************************************
-END
+        # warn %Q{
+#*****************************************************************************
+#WARNING: This srf file lists only 1 protein per peptide! (based on the
+#print_duplicate_references parameter in the sequest.params file used in its
+#creation)  So, downstream output will likewise only contain a single protein
+#for each peptide hit.  In many instances this is OK since downstream programs
+#will recalculate protein-to-peptide linkages from the database file anyway.
+#For complete protein lists per peptide hit, .srf files must be created with
+#print_duplicate_references > 0. HINT: to capture all duplicate references, 
+#set the sequest parameter 'print_duplicate_references' to 100 or greater.
+#*****************************************************************************
+#        }
       else
         dup_refs_gt_0 = true
       end
-    else
-      warn "no params file found in srf, could be combined file or truncated/corrupt file!"
     end
 
     File.open(filename, 'rb') do |fh|
-      @header = Ms::Sequest::Srf::Header.new.from_io(fh)      
+      @header = Ms::Sequest::Srf::Header.new.from_io(fh)
       @version = @header.version
 
       unpack_35 = case @version
@@ -215,6 +226,8 @@ END
         @base_name = @header.raw_filename.scan(/[\\\/]([^\\\/]+)\.RAW$/).first.first
         @dta_files = read_dta_files(fh, @header.num_dta_files, unpack_35)
         if opts[:read_pephits]
+          # need the params file to know if the duplicate_references is set > 0
+          raise NoSequestParamsError, "no sequest params info in srf file!\npass in path to sequest.params file" if @params.nil?
           @out_files = read_out_files(fh,@header.num_dta_files, unpack_35, dup_refs_gt_0)
           if fh.eof?
             #warn "FILE: '#{filename}' appears to be an abortive run (no params in srf file)\nstill continuing..."
@@ -228,38 +241,44 @@ END
       if @params.nil?
         fh.pos = start_pos_in_case
         # seek to the index
-        fh.scanf "\000\000\000\000"  
+        fh.scanf "\000\000\000\000" do |m|
+          puts "MATCHING NULLS: "
+          p m
+        end
+        warn "no params file, no index, corrupt file"
       else # we have a params file
         # This is very sensitive to the grab_params method in sequest params
         fh.read(12)  ## gap between last params entry and index 
       end
       @index = read_scan_index(fh,@header.num_dta_files)
-      #p @index
     end
 
 
     ### UPDATE SOME THINGS:
     # give each hit a base_name, first_scan, last_scan
-    @index.each_with_index do |ind,i|
-      mass_measured = @dta_files[i][0]
-      @out_files[i][0,3] = *ind
-      pep_hits = @out_files[i][6]
-      @peps.push( *pep_hits )
-      pep_hits.each do |pep_hit|
-        pep_hit[14,4] = @base_name, *ind
-        # add the deltamass
-        pep_hit[11] = pep_hit[0] - mass_measured  # real - measured (deltamass)
-        pep_hit[12] = 1.0e6 * pep_hit[11].abs / mass_measured ## ppm
-        pep_hit[18] = self  ## link with the srf object
+    if opts[:read_pephits] && !@header.combined
+      @index.each_with_index do |ind,i|
+        mass_measured = @dta_files[i][0]
+        @out_files[i][0,3] = *ind
+        pep_hits = @out_files[i][6]
+        @peps.push( *pep_hits )
+        pep_hits.each do |pep_hit|
+          pep_hit[14,4] = @base_name, *ind
+          # add the deltamass
+          pep_hit[11] = pep_hit[0] - mass_measured  # real - measured (deltamass)
+          pep_hit[12] = 1.0e6 * pep_hit[11].abs / mass_measured ## ppm
+          pep_hit[18] = self  ## link with the srf object
+        end
       end
-    end
 
-    filter_by_precursor_mass_tolerance! if params
+      filter_by_precursor_mass_tolerance! if params
 
-    if opts[:link_protein_hits]
-      (@peps, @prots) = merge!([peps]) do |_prot, _peps|
-        prot = Ms::Sequest::Srf::Out::Prot.new(_prot.reference, _peps)
+      if opts[:link_protein_hits]
+        (@peps, @prots) = merge!([peps]) do |_prot, _peps|
+          prot = Ms::Sequest::Srf::Out::Prot.new(_prot.reference, _peps)
+        end
       end
+
     end
 
     self
@@ -761,3 +780,4 @@ end
 
 
 
+

data/lib/ms/sequest/srf/search.rb

@@ -1,9 +1,7 @@
 
-require 'tap/task'
 require 'ms/sequest/srf'
 require 'ms/mass'
 
-
 # These are for outputting formats used in MS/MS Search engines
 
 module Ms
@@ -101,35 +99,6 @@ module Ms
         end
       end
 
-      # Ms::Sequest::Srf::SrfToSearch::task converts to MS formats for DB
-      # searching
-      #
-      # outputs the appropriate file or directory structure for <file>.srf:
-      #     <file>.mgf    # file for mgf
-      #     <file>        # the basename directory for dta
-      class SrfToSearch < Tap::Task
-        config :format, "mgf", :short => 'f' # mgf|dta (default: mgf)
-        def process(srf_file)
-          base = srf_file.sub(/\.srf$/i, '')
-          newfile = 
-            case format
-            when 'dta'
-              base
-            when 'mgf'
-              base << '.' << format
-            end
-          srf = Ms::Sequest::Srf.new(srf_file, :link_protein_hits => false, :filter_by_precursor_mass_tolerance => false )
-          # options just speed up reading since we don't need .out info anyway
-          case format
-          when 'mgf'
-            srf.to_mgf(newfile)
-          when 'dta'
-            srf.to_dta_files(newfile)
-          end
-        end
-      end
-
-
     end # Srf
   end # Sequest
 end # Ms

data/lib/ms/sequest/srf/search/tap.rb

@@ -0,0 +1,39 @@
+require 'tap/task'
+
+module Ms
+  module Sequest
+    class Srf
+
+      # Ms::Sequest::Srf::SrfToSearch::task converts to MS formats for DB
+      # searching
+      #
+      # outputs the appropriate file or directory structure for <file>.srf:
+      #     <file>.mgf    # file for mgf
+      #     <file>        # the basename directory for dta
+      class SrfToSearch < Tap::Task
+        config :format, "mgf", :short => 'f' # mgf|dta (default: mgf)
+        def process(srf_file)
+          base = srf_file.sub(/\.srf$/i, '')
+          newfile = 
+            case format
+            when 'dta'
+              base
+            when 'mgf'
+              base << '.' << format
+            end
+          srf = Ms::Sequest::Srf.new(srf_file, :link_protein_hits => false, :filter_by_precursor_mass_tolerance => false, :read_pephits => false )
+          # options just speed up reading since we don't need .out info anyway
+          case format
+          when 'mgf'
+            srf.to_mgf(newfile)
+          when 'dta'
+            srf.to_dta_files(newfile)
+          end
+        end
+      end
+
+
+    end # Srf
+  end # Sequest
+end # Ms
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: ms-sequest
 version: !ruby/object:Gem::Version 
-  version: 0.0.9
+  version: 0.0.10
 platform: ruby
 authors: 
 - John Prince
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-09-08 00:00:00 -06:00
+date: 2009-12-03 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -67,6 +67,7 @@ files:
 - lib/ms/sequest.rb
 - lib/ms/sequest/sqt.rb
 - lib/ms/sequest/params.rb
+- lib/ms/sequest/srf/search/tap.rb
 - lib/ms/sequest/srf/sqt.rb
 - lib/ms/sequest/srf/search.rb
 - lib/ms/sequest/srf.rb
@@ -102,7 +103,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements: []
 
 rubyforge_project: mspire
-rubygems_version: 1.3.2
+rubygems_version: 1.3.5
 signing_key: 
 specification_version: 3
 summary: An mspire library supporting SEQUEST, Bioworks, SQT, etc