ms-sequest 0.0.2 → 0.0.4

data/History

@@ -1,8 +1,21 @@
-== 0.0.1 / 2009-05-11
 
-* pulled out of mspire core
+== 0.0.4 / 2009-06-18
+
+* srf_to_sqt.rb and srf_to_search.rb both working now
+
+== 0.0.3 / 2009-06-16
+
+* only dependent on very simple ms/fasta interface, no more on digest info, etc.
 
 == 0.0.2 / 2009-05-14
 
 * Basic SRF to SQT translation working
 * SQT reading working
+
+== 0.0.1 / 2009-05-11
+
+* pulled out of mspire core
+
+
+
+

data/MIT-LICENSE

@@ -1,5 +1,6 @@
-Copyright (c) 2006 University of Texas at Austin, Regents of the University of
-Colorado, and Howard Hughes Medical Institute.
+Copyright shared among contributing institutions:
+Copyright (c) 2006-2008 University of Texas at Austin (the initial project)
+Copyright (c) 2009 Regents of the University of Colorado and Howard Hughes Medical Institute. (modularization of the project)
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/bin/srf_to_search.rb

@@ -0,0 +1,33 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'tap/task'
+require 'ms/sequest/srf/search'
+
+if ARGV.size == 0
+  ARGV << "--help"
+end
+
+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
+    puts opts
+    exit(0)
+  end
+end
+
+parser.parse!(ARGV)
+ 
+task = task_class.new(parser.config)
+
+ARGV.each do |file|
+  task.execute(file)
+end
+
+

data/bin/srf_to_sqt.rb

@@ -0,0 +1,39 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'tap/task'
+require 'ms/sequest/srf/sqt'
+
+if ARGV.size == 0
+  ARGV << "--help"
+end
+
+task_class = Ms::Sequest::Srf::SrfToSqt
+
+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 "outputs: <file>.sqt ..."
+    puts
+    #puts task_class::desc.wrap
+    #puts
+    puts opts
+    #puts
+    #puts "in tap workflow: tap run -- glob '*.srf' --:i srf_to_sqt"
+    exit(0)
+  end
+end
+
+parser.parse!(ARGV)
+ 
+
+task = task_class.new(parser.config)
+
+ARGV.each do |file|
+  task.execute(file)
+end
+
+

data/lib/ms/sequest.rb

@@ -1,6 +1,6 @@
 
 module Ms
   module Sequest
-    VERSION = '0.0.2'
+    VERSION = '0.0.4'
   end
 end

data/lib/ms/sequest/sqt.rb

@@ -1,8 +1,11 @@
 
-require 'ms/fasta'
 require 'arrayclass'
 require 'set'
 
+require 'ms/fasta'
+require 'digest/md5'
+
+
 require 'ms/id/peptide'
 require 'ms/id/search'
 
@@ -62,12 +65,37 @@ module Ms
       # boolean
       attr_accessor :percolator_results
 
-      # assumes the file exists and is readable
-      # returns [DBSeqLength, DBLocusCount, DBMD5Sum] or nil if no file
-      def self.get_db_info(dbfile)
+      # returns [sequence_length, locus_count] of the fasta file
+      def self.db_seq_length_and_locus_count(dbfile)
+        total_sequence_length = 0
+        fastasize = 0
         Ms::Fasta.open(dbfile) do |fasta|
-          [fasta.total_sequence_length, fasta.size, fasta.md5_sum]
+          fasta.each {|entry| total_sequence_length += entry.sequence.size }
+          fastasize = fasta.size
+        end
+        [total_sequence_length, fastasize]
+      end
+
+      #--
+      # this is implemented separate from sequence length because seq length
+      # uses Archive which doesn't preserve carriage returns and newlines.
+      #++
+      def self.db_md5sum(dbfile)
+        chunksize = 61440
+        digest = Digest::MD5.new
+        File.open(dbfile) do |io|
+          while chunk = io.read(chunksize)
+            digest << chunk 
+          end
         end
+        digest.hexdigest
+      end
+
+      # assumes the file exists and is readable
+      # returns [DBSeqLength, DBLocusCount, DBMD5Sum]
+      def self.db_info(dbfile)
+        # returns the 3 member array
+        self.db_seq_length_and_locus_count(dbfile) << self.db_md5sum(dbfile)
       end
 
       def protein_class

data/lib/ms/sequest/srf.rb

@@ -13,9 +13,8 @@ require 'ms/id/search'
 require 'ms/sequest/params'
 
 # for conversions
-require 'ms/sequest/srf/mgf'
+require 'ms/sequest/srf/search'
 require 'ms/sequest/srf/sqt'
-require 'ms/sequest/srf/dta'
 
 module Ms ; end
 module Ms::Sequest ; end
@@ -96,9 +95,6 @@ class Ms::Sequest::Srf
     end
   end
 
-  def round(float, decimal_places)
-    sprintf("%.#{decimal_places}f", float)
-  end
 
   # 1. updates the out_file's list of hits based on passing peptides (but not
   # the original hit id; rank is implicit in array ordering)
@@ -202,7 +198,6 @@ END
     # give each hit a base_name, first_scan, last_scan
     @index.each_with_index do |ind,i|
       mass_measured = @dta_files[i][0]
-      #puts @out_files[i].join(", ")
       @out_files[i][0,3] = *ind
       pep_hits = @out_files[i][6]
       @peps.push( *pep_hits )
@@ -212,6 +207,9 @@ END
         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 pep_hit.first_scan == 5719
+          puts [pep_hit.sequence, pep_hit.xcorr].join(' ')
+        end
       end
     end
 
@@ -391,6 +389,7 @@ class Ms::Sequest::Srf::DTA
   Unpack_32 = "EeIvvvv"
   Unpack_35 = "Ex8eVx2vvvv"
 
+
   # note on peaks (self[7])
   # this is a byte array of floats, you can get the peaks out with
   # unpack("e*")
@@ -442,6 +441,10 @@ class Ms::Sequest::Srf::DTA
     io.print to_dta_file_data
   end
 
+  def round(float, decimal_places)
+    sprintf("%.#{decimal_places}f", float)
+  end
+
 end
 
 
@@ -518,7 +521,6 @@ end
 
 
 Ms::Sequest::Srf::Out::Pep = Arrayclass.new( %w(mh deltacn_orig sp xcorr id num_other_loci rsp ions_matched ions_total sequence prots deltamass ppm aaseq base_name first_scan last_scan charge srf deltacn deltacn_orig_updated) )
-
 # 0=mh 1=deltacn_orig 2=sp 3=xcorr 4=id 5=num_other_loci 6=rsp 7=ions_matched 8=ions_total 9=sequence 10=prots 11=deltamass 12=ppm 13=aaseq 14=base_name 15=first_scan 16=last_scan 17=charge 18=srf 19=deltacn 20=deltacn_orig_updated
 
 class Ms::Sequest::Srf::Out::Pep

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

@@ -0,0 +1,135 @@
+
+require 'ms/sequest/srf'
+require 'ms/mass'
+
+# These are for outputting formats used in MS/MS Search engines
+
+module Ms
+  module Sequest
+    class Srf
+
+      # Writes an MGF file to given filename or base_name + '.mgf' if no
+      # filename given.
+      #
+      # This mimicks the output of merge.pl from mascot The only difference is
+      # that this does not include the "\r\n" that is found after the peak
+      # lists, instead, it uses "\n" throughout the file (thinking that this
+      # is preferable to mixing newline styles!)
+      def to_mgf(filename=nil)
+        filename =
+          if filename ; filename
+          else
+            base_name + '.mgf'
+          end
+        h_plus = Ms::Mass::MASCOT_H_PLUS
+        File.open(filename, 'wb') do |out|
+          dta_files.zip(index) do |dta, i_ar|
+            chrg = dta.charge
+            out.print "BEGIN IONS\n"
+            out.print "TITLE=#{[base_name, *i_ar].push('dta').join('.')}\n"
+            out.print "CHARGE=#{chrg}+\n"
+            out.print "PEPMASS=#{(dta.mh+((chrg-1)*h_plus))/chrg}\n"
+            peak_ar = dta.peaks.unpack('e*')
+            (0...(peak_ar.size)).step(2) do |i|
+              out.print( peak_ar[i,2].join(' '), "\n")
+            end
+            out.print "END IONS\n"
+            out.print "\n"
+          end
+        end
+      end
+
+      # not given an out_folder, will make one with the basename
+      # compress may be: :zip, :tgz, or nil (no compression)
+      # :zip requires gem rubyzip to be installed and is *very* bloated
+      # as it writes out all the files first!
+      # :tgz requires gem archive-tar-minitar to be installed
+      def to_dta_files(out_folder=nil, compress=nil)
+        outdir = 
+          if out_folder ; out_folder
+          else base_name
+          end
+
+        case compress
+        when :tgz
+          begin
+            require 'archive/tar/minitar'
+          rescue LoadError
+            abort "need gem 'archive-tar-minitar' installed' for tgz compression!\n#{$!}"
+          end
+          require 'archive/targz'  # my own simplified interface!
+          require 'zlib'
+          names = index.map do |i_ar|
+            [outdir, '/', [base_name, *i_ar].join('.'), '.dta'].join('')
+          end
+          #Archive::Targz.archive_as_files(outdir + '.tgz', names, dta_file_data)
+
+          tgz = Zlib::GzipWriter.new(File.open(outdir + '.tgz', 'wb'))
+
+          Archive::Tar::Minitar::Output.open(tgz) do |outp|
+            dta_files.each_with_index do |dta_file, i|
+              Archive::Tar::Minitar.pack_as_file(names[i], dta_file.to_dta_file_data, outp)
+            end
+          end
+        when :zip
+          begin
+            require 'zip/zipfilesystem'
+          rescue LoadError
+            abort "need gem 'rubyzip' installed' for zip compression!\n#{$!}"
+          end
+          #begin ; require 'zip/zipfilesystem' ; rescue LoadError, "need gem 'rubyzip' installed' for zip compression!\n#{$!}" ; end
+          Zip::ZipFile.open(outdir + ".zip", Zip::ZipFile::CREATE) do |zfs|
+            dta_files.zip(index) do |dta,i_ar|
+              #zfs.mkdir(outdir)
+              zfs.get_output_stream(outdir + '/' + [base_name, *i_ar].join('.') + '.dta') do |out|
+                dta.write_dta_file(out)
+                #zfs.commit
+              end
+            end
+          end
+        else  # no compression
+          FileUtils.mkpath(outdir)
+          Dir.chdir(outdir) do
+            dta_files.zip(index) do |dta,i_ar|
+              File.open([base_name, *i_ar].join('.') << '.dta', 'wb') do |out|
+                dta.write_dta_file(out)
+              end
+            end
+          end
+        end
+      end
+
+      # Ms::Sequest::Srf::SrfToSearch::task converts to MS formats for DB
+      # searching
+      #
+      # outputs the appropriate file or directory structure for <file>.srf:
+      #     <file>.mgf    # file for mgf
+      #     <file>        # the basename directory for dta
+      class SrfToSearch < Tap::Task
+        config :format, "mgf", :short => 'f' # mgf|dta (default: mgf)
+        def process(srf_file)
+          base = srf_file.sub(/\.srf$/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/sqt.rb

@@ -1,4 +1,5 @@
-
+require 'tap/task'
+require 'configurable'
 require 'ms/sequest'
 require 'ms/sequest/srf'
 require 'ms/sequest/sqt'
@@ -93,7 +94,7 @@ module Ms
 
         if opt[:db_info]
           if File.exist?(db_filename)
-            reply = Ms::Sequest::Sqt.get_db_info(db_filename)
+            reply = Ms::Sequest::Sqt.db_info(db_filename)
             %w(DBSeqLength DBLocusCount DBMD5Sum).zip(reply) do |label,val|
               hh[label] = val
             end
@@ -164,6 +165,27 @@ module Ms
         end # close the filehandle
       end # method
 
+      # SrfToSqt::task convert .srf to .sqt files
+      class SrfToSqt < Tap::Task
+        config :db_info, false, :short => 'd', &c.flag   # calculates num aa's and md5sum on db
+        # if your database path has changed
+        # and you want db-info, then give the
+        # path to the new *directory*
+        # e.g. /my/new/path 
+        config :db_path, nil, :short => 'p'              
+        config :db_update, false, :short => 'u', &c.flag # update the sqt file to reflect --db_path
+        config :no_filter, false, :short => 'n', &c.flag # by default, pephit must be within peptide_mass_tolerance (defined in sequest.params) to be included.  Turns this off.
+        config :round, false, :short => 'r', &c.flag     # round floating point values reasonably
+
+        def process(srf_file)
+          new_filename = srf_file.sub(/\.srf$/i, '') << '.sqt'
+
+          srf = Ms::Sequest::Srf.new(srf_file, :link_protein_hits => false, :filter_by_precursor_mass_tolerance => !no_filter)
+
+          srf.to_sqt(new_filename, :db_info => db_info, :new_db_path => db_path, :update_db_path => db_update, :round => round)
+
+        end # process
+      end # SrfToSqt
     end # Srf
   end # Sequest
 end # Ms

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: ms-sequest
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.4
 platform: ruby
 authors: 
 - John Prince
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-05-14 00:00:00 -06:00
+date: 2009-06-18 00:00:00 -06:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -32,10 +32,31 @@ dependencies:
       - !ruby/object:Gem::Version 
         version: 0.0.1
     version: 
-description: 
+- !ruby/object:Gem::Dependency 
+  name: tap
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.17.1
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: ms-fasta
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 0.2.3
+    version: 
+description: reads .SRF, .SQT and supports conversions
 email: jtprince@gmail.com
-executables: []
-
+executables: 
+- srf_to_sqt.rb
+- srf_to_search.rb
 extensions: []
 
 extra_rdoc_files: 
@@ -44,6 +65,7 @@ extra_rdoc_files:
 - History
 files: 
 - lib/ms/sequest/params.rb
+- lib/ms/sequest/srf/search.rb
 - lib/ms/sequest/srf/sqt.rb
 - lib/ms/sequest/srf.rb
 - lib/ms/sequest/sqt.rb