ms-sequest 0.1.2 → 0.2.1

data/History

@@ -1,6 +1,6 @@
-== 0.1.2 / 2011-07-05
+== 0.2.0 / 2011-09-13
 
-* fixed a few bugs caused by newer ms-search
+Breaking backwards compatbility.  Based on new msplat gem instead of ms-core, ms-ident, etc.  MS module instead of Ms module.
 
 == 0.1.0 / 2011-04-11
 

data/README.rdoc

@@ -2,7 +2,7 @@
 
 An {mspire}[http://mspire.rubyforge.org] library supporting SEQUEST, Bioworks, SQT and associated formats.
 
-== {API}[http://yardoc.org/docs/jtprince-ms-sequest]
+== {Current API}[http://rubydoc.info/gems/ms-sequest]
 
 == Examples
 
@@ -11,12 +11,12 @@ Provides two executables for extracting information from an Srf file (run withou
     srf_to_sqt.rb file.srf     # => file.sqt
     srf_to_search.rb file.srf  # => file.mgf  (also can make .dta files)
 
-=== Ms::Sequest::Srf
+=== MS::Sequest::Srf
 
 Can read and convert Bioworks Sequest Results Files (SRF).
 
     require 'ms/sequest/srf'
-    srf = Ms::Sequest::Srf.new("file.srf")
+    srf = MS::Sequest::Srf.new("file.srf")
 
 Conversions (see api for options):
 
@@ -28,20 +28,20 @@ Conversions (see api for options):
     srf.to_dta            # (outputs a dir)  -> file
     srf.to_dta("file.tgz", :tgz)  # on the fly tgz (requires archive-tar-minitar)
 
-Object access (see Ms::Sequest::Srf for much more):
+Object access (see MS::Sequest::Srf for much more):
 
-    srf.header         # Ms::Sequest::Srf::Header object
-    srf.params         # Ms::Sequest::Params object
-    srf.dta_files      # Ms::Sequest::Srf::DTA objects
-    srf.peps           # Ms::Sequest::Srf::Out::Pep objects
-    srf.prots          # Ms::Sequest::Srf::Out::Prot objects
+    srf.header         # MS::Sequest::Srf::Header object
+    srf.params         # MS::Sequest::Params object
+    srf.dta_files      # MS::Sequest::Srf::Dta objects
+    srf.out_files      # MS::Sequest::Srf::Out objects
+    srf.peptide_hits   # MS::Sequest::Srf::Out::Peptide objects
 
-=== Ms::Sequest::Params
+=== MS::Sequest::Params
 
 Object or hash access to any parameter in the file.  Also provides a unified interface across several versions (3.1 - 3.3)
 
     require 'ms/sequest/params'
-    params = Ms::Sequest::Params.new("sequest.params")
+    params = MS::Sequest::Params.new("sequest.params")
     params.any_existing_param    # -> some value or empty string if no value
     params['any_existing_param'] # -> some value or empty string if no value
     params.non_existent_param    # -> nil
@@ -53,25 +53,24 @@ Object or hash access to any parameter in the file.  Also provides a unified int
     params.precursor_mass_type  # => "average" | "monoisotopic"
     params.fragment_mass_type   # => "average" | "monoisotopic"
 
-=== Ms::Sequest::Sqt
+=== MS::Sequest::Sqt
 
-    sqt = Ms::Sequest::Sqt.new("file.sqt")
+    sqt = MS::Sequest::Sqt.new("file.sqt")
     sqt.header
-    sqt.spectra.each do |spectrum|      # an Ms::Sequest::Sqt::Spectrum object
-      spectrum.matches.each do |match|    # an Ms::Sequest::Sqt::Match object
-        match.loci.each do |locus|          # an Ms::Sequest::Sqt::Locus object
+    sqt.spectra.each do |spectrum|      # an MS::Sequest::Sqt::Spectrum object
+      spectrum.matches.each do |match|    # an MS::Sequest::Sqt::Match object
+        match.loci.each do |locus|          # an MS::Sequest::Sqt::Locus object
         end
       end
     end
 
-    # or more direct access to Match and Locus objects:
-    sqt.peps
-    sqt.prots
+    # or more direct access to Match objects:
+    sqt.peptide_hits
 
 Also reads Percolator SQT output files intelligently:
 
-    psqt = Ms::Sequest::Sqt.new("percolator_output.sqt")
-    psqt.peps.each do |pmatch|
+    psqt = MS::Sequest::Sqt.new("percolator_output.sqt")
+    psqt.peptide_hits.each do |pmatch|
       pmatch.percolator_score  ==  pmatch.xcorr
       pmatch.negative_q_value  ==  pmatch.sp
       pmatch.q_value           ==  -pmatch.negative_q_value 

data/Rakefile

@@ -11,13 +11,13 @@ Jeweler::Tasks.new do |gem|
   gem.email = "jtprince@gmail.com"
   gem.authors = ["John T. Prince"]
   gem.rubyforge_project = 'mspire'
-  gem.add_runtime_dependency "ms-ident", ">= 0.1.1"
-  gem.add_runtime_dependency "ms-core", ">= 0.0.19"
+  gem.add_runtime_dependency "msplat", ">= 0.0.6"
+  #gem.add_runtime_dependency "ms-core", ">= 0.0.17"
   #gem.add_runtime_dependency "ms-msrun", ">= 0.3.4"
-  gem.add_runtime_dependency "trollop", "~> 1.16.2"
+  gem.add_runtime_dependency "trollop", "~> 1.16"
   gem.add_development_dependency "jeweler", "~> 1.5.2"
-  gem.add_development_dependency "ms-testdata", ">= 0.1.1"
-  gem.add_development_dependency "spec-more", ">= 0.0.4"
+  gem.add_development_dependency "ms-testdata", ">= 0.2.1"
+  gem.add_development_dependency "spec-more", ">= 0"
 end
 Jeweler::RubygemsDotOrgTasks.new
 

data/VERSION

@@ -1 +1 @@
-0.1.2
+0.2.1

data/lib/ms/sequest.rb

@@ -1,5 +1,5 @@
 
-module Ms
+module MS
   module Sequest
     VERSION = File.open(File.dirname(__FILE__) + '/../../VERSION') {|io| io.gets.chomp }
   end

data/lib/ms/sequest/params.rb

@@ -3,13 +3,13 @@ require 'ms/mass/aa'
 # In the future, this guy should accept any version of bioworks params file
 # and spit out any param queried.
 
-module Ms ; end
-module Ms::Sequest ; end
+module MS ; end
+module MS::Sequest ; end
 
 # 1) provides a reader and simple parameter lookup for SEQUEST params files
 # supporting Bioworks 3.1-3.3.1.  
-#     params = Ms::Sequest::Params.new("sequest.params") # filename by default
-#     params = Ms::Sequest::Params.new.parse_io(some_io_object)
+#     params = MS::Sequest::Params.new("sequest.params") # filename by default
+#     params = MS::Sequest::Params.new.parse_io(some_io_object)
 #
 #     params.some_parameter  # => any parameter defined has a method
 #     params.nonexistent_parameter # => nil 
@@ -29,7 +29,7 @@ module Ms::Sequest ; end
 #     params.max_num_internal_cleavages  # == max_num_internal_cleavage_sites
 #     params.fragment_ion_tol     # => fragment_ion_tolerance
 #     
-class Ms::Sequest::Params
+class MS::Sequest::Params
 
   Bioworks31_Enzyme_Info_Array = [
     ['No_Enzyme', 0, '-', '-'],   # 0
@@ -234,7 +234,7 @@ class Ms::Sequest::Params
     @opts["first_database_name"]
   end
 
-  # returns the appropriate aminoacid mass lookup table from Ms::Mass::AA
+  # returns the appropriate aminoacid mass lookup table from MS::Mass::AA
   # based_on may be :precursor or :fragment
   def mass_index(based_on=:precursor)
     reply = case based_on
@@ -243,9 +243,9 @@ class Ms::Sequest::Params
             end
     case reply
     when 'average'
-      Ms::Mass::AA::AVG
+      MS::Mass::AA::AVG
     when 'monoisotopic'
-      Ms::Mass::AA::MONO
+      MS::Mass::AA::MONO
     end
   end
 

data/lib/ms/sequest/pepxml/modifications.rb

@@ -1,10 +1,10 @@
 require 'ms/ident/pepxml/search_hit/modification_info'
 
-module Ms ; end
-module Ms::Sequest ; end
-class Ms::Sequest::Pepxml ; end
+module MS ; end
+module MS::Sequest ; end
+class MS::Sequest::Pepxml ; end
 
-class Ms::Sequest::Pepxml::Modifications
+class MS::Sequest::Pepxml::Modifications
   # sequest params object
   attr_accessor :params
   # array holding AAModifications 
@@ -100,7 +100,7 @@ class Ms::Sequest::Pepxml::Modifications
         :variable => 'N',
         :binary => 'Y',
       } 
-      Ms::Ident::Pepxml::AminoacidModification.new(hash)
+      MS::Ident::Pepxml::AminoacidModification.new(hash)
     end
 
     ## Create the static_terminal_mods objects
@@ -122,7 +122,7 @@ class Ms::Sequest::Pepxml::Modifications
         :description => mod[0],
       }
       hash[:protein_terminus] = protein_terminus if protein_terminus
-      Ms::Ident::Pepxml::TerminalModification.new(hash)
+      MS::Ident::Pepxml::TerminalModification.new(hash)
     end
     [static_mods, static_terminal_mods]
   end
@@ -160,7 +160,7 @@ class Ms::Sequest::Pepxml::Modifications
           :binary => 'N',
           :symbol => @mod_symbols_hash[[aa.to_sym, mod[1]]],
         }
-        mod_objects << Ms::Ident::Pepxml::AminoacidModification.new(hash)
+        mod_objects << MS::Ident::Pepxml::AminoacidModification.new(hash)
       end
     end
 
@@ -186,7 +186,7 @@ class Ms::Sequest::Pepxml::Modifications
         :variable => 'Y',
         :symbol => symb,
       }
-      Ms::Ident::Pepxml::TerminalModification.new(hash)
+      MS::Ident::Pepxml::TerminalModification.new(hash)
     end
 
     #########################
@@ -202,7 +202,7 @@ class Ms::Sequest::Pepxml::Modifications
   #  if there are no modifications, returns nil
   def modification_info(mod_peptide)
     return nil if @aa_mod_to_tot_mass.size == 0 
-    mod_info = Ms::Ident::Pepxml::SearchHit::ModificationInfo.new( mod_peptide.dup )
+    mod_info = MS::Ident::Pepxml::SearchHit::ModificationInfo.new( mod_peptide.dup )
     mass_table = @params.mass_index(:precursor)
 
     # TERMINI:
@@ -227,7 +227,7 @@ class Ms::Sequest::Pepxml::Modifications
       if @aa_mod_to_tot_mass.key?( last_normal_aa + mod_peptide[i,1] )
         # we don't save the result because most amino acids will not be
         # modified
-        mod_array << Ms::Ident::Pepxml::SearchHit::ModificationInfo::ModAminoacidMass.new(bare_cnt, @aa_mod_to_tot_mass[last_normal_aa + mod_peptide[i,1]])
+        mod_array << MS::Ident::Pepxml::SearchHit::ModificationInfo::ModAminoacidMass.new(bare_cnt, @aa_mod_to_tot_mass[last_normal_aa + mod_peptide[i,1]])
       else
         last_normal_aa = mod_peptide[i,1]
         bare_cnt += 1

data/lib/ms/sequest/pepxml/params.rb

@@ -1,15 +1,15 @@
 
-module Ms ; end
-module Ms::Sequest ; end
+module MS ; end
+module MS::Sequest ; end
 
-class Ms::Sequest::Params
+class MS::Sequest::Params
 
-  # returns a Ms::Ident::Pepxml::SampleEnzyme object
+  # returns a MS::Ident::Pepxml::SampleEnzyme object
   def sample_enzyme
-    Ms::Ident::Pepxml::SampleEnzyme.new(sample_enzyme_hash)
+    MS::Ident::Pepxml::SampleEnzyme.new(sample_enzyme_hash)
   end
 
-  # returns a hash suitable for setting a Ms::Ident::Pepxml::SampleEnzyme object
+  # returns a hash suitable for setting a MS::Ident::Pepxml::SampleEnzyme object
   def sample_enzyme_hash
     (offset, cleave_at, except_if_after) = enzyme_specificity.map do |v|
       if v == '' ; nil ; else v end

data/lib/ms/sequest/sqt.rb

@@ -8,15 +8,15 @@ require 'digest/md5'
 require 'ms/ident/peptide'
 require 'ms/ident/search'
 
-module Ms
+module MS
   module Sequest
     class SqtGroup
-      include Ms::Ident::SearchGroup
+      include MS::Ident::SearchGroup
 
       #attr_accessor :sqts, :filenames
 
       def search_class
-        Ms::Sequest::Sqt
+        MS::Sequest::Sqt
       end
 
       def extension() 'sqg' end
@@ -27,7 +27,7 @@ module Ms
         super(arg, opts.merge(indiv_opts)) do
           unless orig_opts[:link_protein_hits] == false
             puts "MERGING GROUP!"
-            (@peptides, @proteins) = merge!(@searches.map {|v| v.peptides }, &Ms::Sequest::Sqt::NEW_PROT)
+            (@peptides, @proteins) = merge!(@searches.map {|v| v.peptides }, &MS::Sequest::Sqt::NEW_PROT)
           end
         end
         block.call(self) if block_given?
@@ -54,7 +54,8 @@ module Ms
     end # SqtGroup
 
 
-    class Sqt < Ms::Ident::Search
+    class Sqt
+      include MS::Ident::SearchLike
       PercolatorHeaderMatch = /^Percolator v/
         Delimiter = "\t"
       attr_accessor :header
@@ -67,7 +68,7 @@ module Ms
       def self.db_seq_length_and_locus_count(dbfile)
         total_sequence_length = 0
         fastasize = 0
-        Ms::Fasta.open(dbfile) do |fasta|
+        MS::Fasta.open(dbfile) do |fasta|
           fasta.each do |entry| 
             total_sequence_length += entry.sequence.size 
             fastasize += 1
@@ -99,22 +100,21 @@ module Ms
       end
 
       def protein_class
-        Ms::Sequest::Sqt::Locus
+        MS::Sequest::Sqt::Locus
       end
 
       # opts = 
       #     :percolator_results => false | true (default false)
       #     :link_protein_hits => true | false (default true)
       def initialize(filename=nil, opts={})
-        @peptides = []
-        @proteins = []
+        peptide_hits = []
         if filename
           from_file(filename, opts)
         end
       end
 
       NEW_PROT = lambda do |_prot, _peptides|
-        Ms::Sequest::Sqt::Locus.new(_prot.locus, _prot.description, _peptides)
+        MS::Sequest::Sqt::Locus.new(_prot.locus, _prot.description, _peptides)
       end
 
       # if the file contains the header key '/$Percolator v/' then the results
@@ -125,14 +125,11 @@ module Ms
         @percolator_results = opts[:percolator_results]
         @base_name = File.basename( filename.gsub('\\','/') ).sub(/\.\w+$/, '')
         File.open(filename) do |fh| 
-          @header = Ms::Sequest::Sqt::Header.new.from_handle(fh)
+          @header = MS::Sequest::Sqt::Header.new.from_handle(fh)
           if @header.keys.any? {|v| v =~ PercolatorHeaderMatch }
             @percolator_results = true
           end
-          (@spectra, @peptides) = Ms::Sequest::Sqt::Spectrum.spectra_from_handle(fh, @base_name, @percolator_results)
-        end
-        if opts[:link_protein_hits]
-          (@peptides, @proteins) = merge!([@peptides], &NEW_PROT)
+          (@spectra, @peptides) = MS::Sequest::Sqt::Spectrum.spectra_from_handle(fh, @base_name, @percolator_results)
         end
       end
 
@@ -185,7 +182,7 @@ module Ms
           lines = []
           loop do 
             line = fh.gets
-            if line && (line[0,1] == Ms::Sequest::Sqt::Header::Leader )
+            if line && (line[0,1] == MS::Sequest::Sqt::Header::Leader )
               lines << line
             else # reset the fh.pos and we're done
               fh.pos = pos
@@ -199,9 +196,9 @@ module Ms
         def from_lines(array_of_header_lines)
           array_of_header_lines.each do |line|
             line.chomp!
-            (ky, *rest) = line.split(Ms::Sequest::Sqt::Delimiter)[1..-1]
+            (ky, *rest) = line.split(MS::Sequest::Sqt::Delimiter)[1..-1]
             # just in case they have any tabs in their field
-            value = rest.join(Ms::Sequest::Sqt::Delimiter)
+            value = rest.join(MS::Sequest::Sqt::Delimiter)
             if Arrayed.include?(ky)
               self[ky] << value
             elsif self.key? ky  # already exists
@@ -227,11 +224,11 @@ end
 
 # all are cast as expected (total_intensity is a float)
 # mh = observed mh
-Ms::Sequest::Sqt::Spectrum = Struct.new(* %w(first_scan last_scan charge time_to_process node mh total_intensity lowest_sp num_matched_peptides matches).map(&:to_sym) )
+MS::Sequest::Sqt::Spectrum = Struct.new(* %w(first_scan last_scan charge time_to_process node mh total_intensity lowest_sp num_matched_peptides matches).map(&:to_sym) )
 
 # 0=first_scan 1=last_scan 2=charge 3=time_to_process 4=node 5=mh 6=total_intensity 7=lowest_sp 8=num_matched_peptides 9=matches
 
-class Ms::Sequest::Sqt::Spectrum
+class MS::Sequest::Sqt::Spectrum
   Leader = 'S'
 
   # assumes the first line starts with an 'S'
@@ -241,16 +238,16 @@ class Ms::Sequest::Sqt::Spectrum
     
     while line = fh.gets
       case line[0,1]
-      when Ms::Sequest::Sqt::Spectrum::Leader
-        spectrum = Ms::Sequest::Sqt::Spectrum.new.from_line( line )
+      when MS::Sequest::Sqt::Spectrum::Leader
+        spectrum = MS::Sequest::Sqt::Spectrum.new.from_line( line )
         spectra << spectrum
         matches = []
         spectrum.matches = matches
-      when Ms::Sequest::Sqt::Match::Leader
+      when MS::Sequest::Sqt::Match::Leader
         match_klass = if percolator_results
-                        Ms::Sequest::Sqt::Match::Percolator
+                        MS::Sequest::Sqt::Match::Percolator
                       else
-                        Ms::Sequest::Sqt::Match
+                        MS::Sequest::Sqt::Match
                       end
         match = match_klass.new.from_line( line )
         #match[10,3] = spectrum[0,3]
@@ -264,10 +261,10 @@ class Ms::Sequest::Sqt::Spectrum
         loci = []
         match.loci = loci
         matches << match
-      when Ms::Sequest::Sqt::Locus::Leader
+      when MS::Sequest::Sqt::Locus::Leader
         line.chomp!
-        key = line.split(Ms::Sequest::Sqt::Delimiter)[1]
-        locus = Ms::Sequest::Sqt::Locus.from_line( line )
+        key = line.split(MS::Sequest::Sqt::Delimiter)[1]
+        locus = MS::Sequest::Sqt::Locus.from_line( line )
         loci << locus
       end
     end
@@ -294,7 +291,7 @@ class Ms::Sequest::Sqt::Spectrum
   # returns an array -> [the next spectra line (or nil if eof), spectrum]
   def from_line(line)
     line.chomp!
-    ar = line.split(Ms::Sequest::Sqt::Delimiter)
+    ar = line.split(MS::Sequest::Sqt::Delimiter)
     self[0] = ar[1].to_i
     self[1] = ar[2].to_i
     self[2] = ar[3].to_i
@@ -310,7 +307,7 @@ class Ms::Sequest::Sqt::Spectrum
 end
 
 # Sqt format uses only indices 0 - 9
-Ms::Sequest::Sqt::Match = Struct.new( *%w[rxcorr rsp mh deltacn_orig xcorr sp ions_matched ions_total sequence manual_validation_status first_scan last_scan charge deltacn aaseq base_name loci].map(&:to_sym) )
+MS::Sequest::Sqt::Match = Struct.new( *%w[rxcorr rsp mh deltacn_orig xcorr sp ions_matched ions_total sequence manual_validation_status first_scan last_scan charge deltacn aaseq base_name loci].map(&:to_sym) )
 
 # 0=rxcorr 1=rsp 2=mh 3=deltacn_orig 4=xcorr 5=sp 6=ions_matched 7=ions_total 8=sequence 9=manual_validation_status 10=first_scan 11=last_scan 12=charge 13=deltacn 14=aaseq 15=base_name 16=loci
 
@@ -320,7 +317,7 @@ Ms::Sequest::Sqt::Match = Struct.new( *%w[rxcorr rsp mh deltacn_orig xcorr sp io
 # deltacn_orig
 # deltacn is the adjusted deltacn (like Bioworks - shift all scores up and
 # give the last one 1.1)
-class Ms::Sequest::Sqt::Match
+class MS::Sequest::Sqt::Match
   Leader = 'M'
 
   # same as 'loci'
@@ -330,7 +327,7 @@ class Ms::Sequest::Sqt::Match
 
   def from_line(line)
     line.chomp!
-    ar = line.split(Ms::Sequest::Sqt::Delimiter)
+    ar = line.split(MS::Sequest::Sqt::Delimiter)
     self[0] = ar[1].to_i
     self[1] = ar[2].to_i
     self[2] = ar[3].to_f
@@ -341,13 +338,13 @@ class Ms::Sequest::Sqt::Match
     self[7] = ar[8].to_i
     self[8] = ar[9]
     self[9] = ar[10]
-    self[14] = Ms::Ident::Peptide.sequence_to_aaseq(self[8])
+    self[14] = MS::Ident::Peptide.sequence_to_aaseq(self[8])
     self
   end
 end
 
 
-class Ms::Sequest::Sqt::Match::Percolator < Ms::Sequest::Sqt::Match
+class MS::Sequest::Sqt::Match::Percolator < MS::Sequest::Sqt::Match
   # we will keep access to these old terms since we can then access routines
   # that sort on xcorr...
   #undef_method :xcorr
@@ -376,22 +373,23 @@ class Ms::Sequest::Sqt::Match::Percolator < Ms::Sequest::Sqt::Match
   end
 end
 
-Ms::Sequest::Sqt::Locus = Struct.new( :locus, :description, :peptides )
+MS::Sequest::Sqt::Locus = Struct.new( :locus, :description )
 
-class Ms::Sequest::Sqt::Locus
+class MS::Sequest::Sqt::Locus
   Leader = 'L'
 
   def first_entry ; self[0] end
   def reference ; self[0] end
+  def id ; self[0] end
 
   def initialize(locus=nil, description=nil, peptides=[])
-    super(locus, description, peptides)
+    super(locus, description)
   end
 
   # returns a new Locus object
   def self.from_line(line)
     line.chomp!
-    self.new( *line.split(Ms::Sequest::Sqt::Delimiter) )  # fills in the first two values 
+    self.new( *line.split(MS::Sequest::Sqt::Delimiter) )  # fills in the first two values 
   end
 
 end