ms-ident 0.0.23 → 0.1.1

data/VERSION

@@ -1 +1 @@
-0.0.23
+0.1.1

data/lib/ms/ident/peptide/db.rb

@@ -1,5 +1,6 @@
 require 'ms/in_silico/digester'
 require 'ms/fasta'
+require 'optparse'
 
 module Ms ; end
 module Ms::Ident ; end

data/lib/ms/ident/peptide_hit.rb

@@ -2,7 +2,12 @@ module Ms ; end
 module Ms::Ident ; end
 
 class Ms::Ident::PeptideHit
+  attr_accessor :id
+  attr_accessor :search
+  attr_accessor :missed_cleavages
   attr_accessor :aaseq
   attr_accessor :charge
   attr_accessor :proteins
+  attr_accessor :qvalue
 end
+

data/lib/ms/ident/peptide_hit/qvalue.rb

@@ -1,3 +1,4 @@
+require 'ms/ident/search'
 require 'ms/ident/peptide_hit'
 
 module Ms ; end
@@ -5,10 +6,9 @@ module Ms::Ident ; end
 
 class Ms::Ident::PeptideHit
   module Qvalue
-    attr_accessor :qvalue
     FILE_EXTENSION = '.phq.tsv'
     FILE_DELIMITER = "\t"
-    HEADER = %w(aaseq charge qvalue)
+    HEADER = %w(run_id id aaseq charge qvalue)
 
     class << self
 
@@ -24,7 +24,7 @@ class Ms::Ident::PeptideHit
         File.open(filename,'w') do |out|
           out.puts HEADER.join(FILE_DELIMITER)
           hits.zip(qvalues) do |hit, qvalue|
-            out.puts [hit.aaseq, hit.charge, qvalue || hit.qvalue].join(FILE_DELIMITER)
+            out.puts [hit.search.id, hit.id, hit.aaseq, hit.charge, qvalue || hit.qvalue].join(FILE_DELIMITER)
           end
         end
         filename
@@ -32,15 +32,17 @@ class Ms::Ident::PeptideHit
 
       # returns an array of PeptideHit objects from a phq.tsv
       def from_file(filename)
+        searches = Hash.new {|h,id|  h[id] = Ms::Ident::Search.new(id) }
         peptide_hits = []
         File.open(filename) do |io|
           header = io.readline.chomp.split(FILE_DELIMITER)
           raise "bad headers" unless header == HEADER 
           io.each do |line|
             line.chomp!
-            (aaseq, charge, qvalue) = line.split(FILE_DELIMITER)
+            (run_id, id, aaseq, charge, qvalue) = line.split(FILE_DELIMITER)
             ph = Ms::Ident::PeptideHit.new
-            ph.aaseq = aaseq ; ph.charge = charge.to_i ; ph.qvalue = qvalue.to_f
+            ph.search = searches[run_id]
+            ph.id = id; ph.aaseq = aaseq ; ph.charge = charge.to_i ; ph.qvalue = qvalue.to_f
             peptide_hits << ph
           end
         end
@@ -51,5 +53,4 @@ class Ms::Ident::PeptideHit
 
     end
   end # Qvalue
-  include Qvalue
 end # Peptide Hit

data/lib/ms/ident/pepxml.rb

@@ -27,12 +27,12 @@ class Ms::Ident::Pepxml
   # returns an array of Ms::Ident::Pepxml::SearchHit::Simple structs
   def self.simple_search_hits(file)
     hit_values = File.open(file) do |io|
-      doc = Nokogiri::XML.parse(io, nil, nil, Nokogiri::XML::ParseOptions::DEFAULT_XML | Nokogiri::XML::ParseOptions::NOBLANKS)
+      doc = Nokogiri::XML.parse(io, nil, nil, Nokogiri::XML::ParseOptions::DEFAULT_XML | Nokogiri::XML::ParseOptions::NOBLANKS | Nokogiri::XML::ParseOptions::STRICT)
       # we can work with namespaces, or just remove them ...
       doc.remove_namespaces!
       root = doc.root
       search_hits = root.xpath('//search_hit')
-      search_hits.map do |search_hit| 
+      search_hits.each_with_index.map do |search_hit,i| 
         aaseq = search_hit['peptide']
         charge = search_hit.parent.parent['assumed_charge'].to_i
         search_score_nodes = search_hit.children.select {|node| node.name == 'search_score' }
@@ -40,7 +40,7 @@ class Ms::Ident::Pepxml
         search_score_nodes.each do |node|
           search_scores[node['name'].to_sym] = node['value'].to_f
         end
-        Ms::Ident::Pepxml::SearchHit::Simple.new(aaseq, charge, search_scores)
+        Ms::Ident::Pepxml::SearchHit::Simple.new("hit_#{i}", Ms::Ident::Search.new(file.chomp(File.extname(file))), aaseq, charge, search_scores)
       end
     end
   end

data/lib/ms/ident/pepxml/search_hit.rb

@@ -137,7 +137,7 @@ class Ms::Ident::Pepxml
       self
     end
 
-    Simple = Struct.new(:aaseq, :charge, :search_scores)
+    Simple = Struct.new(:id, :search, :aaseq, :charge, :search_scores)
   end
 
 end

data/lib/ms/ident/protein.rb

@@ -2,11 +2,24 @@ module Ms ; end
 module Ms::Ident ; end
 
 
-module Ms::Ident::Protein
-  # gives the information up until the first space or carriage return.
-  # Assumes the protein can respond_to? :reference
-  def first_entry
-    reference.split(/[\s\r]/)[0]
+class Ms::Ident::Protein
+
+  attr_accessor :id
+  attr_accessor :seq
+  alias_method :sequence, :seq
+  alias_method :sequence=, :seq=
+
+  attr_accessor :description
+
+  def initialize(id=nil, seq=nil)
+    (@id, @seq) = id, seq
   end
+
+  # DEPRECATING THIS GUY
+  ## gives the information up until the first space or carriage return.
+  ## Assumes the protein can respond_to? :reference
+  #def first_entry
+  #  reference.split(/[\s\r]/)[0]
+  #end
 end
 

data/lib/ms/ident/protein_group.rb

@@ -28,7 +28,12 @@ module Ms
       # accuracy.
       #
       # returns an array of ProteinGroup objects, each set with :peptide_hits
-      def self.peptide_hits_to_protein_groups(peptide_hits, &sort_by)
+      #
+      # If update_peptide_hits is true, then each peptide_hit is linked to the array
+      # of protein_groups it is associated with using :protein_groups.  A
+      # symbol can also be passed in, and that method will be called instead.
+      def self.peptide_hits_to_protein_groups(peptide_hits, update_peptide_hits=false, &sort_by)
+        update_peptide_hits = 'protein_groups='.to_sym if (update_peptide_hits==true)
         sort_by ||= PRIORITIZE_PROTEINS
         # note to self: I wrote this in 2011, so I think I know what I'm doing now
         protein_to_peptides = Hash.new {|h,k| h[k] = Set.new }
@@ -64,6 +69,9 @@ module Ms
           group.peptide_hits = peptide_set if has_an_unaccounted_peptide
           has_an_unaccounted_peptide
         end
+        if update_peptide_hits
+          greedy_first.each {|pg, pephits| pephits.each {|hit| hit.send(update_peptide_hits, pg) } } 
+        end
         greedy_first.map(&:first)
       end
 

data/lib/ms/ident/protein_hit.rb

@@ -1,17 +1,21 @@
+require 'andand'
+
 
 module Ms ; end
 module Ms::Ident ; end
 
-class Ms::Ident::ProteinHit
-  attr_accessor :id
-  attr_accessor :seq
-  alias_method :sequence, :seq
-  alias_method :sequence=, :seq=
+class Ms::Ident::ProteinHit < Ms::Ident::Protein
   attr_accessor :peptide_hits
 
-  def initialize(id=nil)
-    @peptide_hits = []
+  def initialize(id=nil, peptide_hits=[])
+    @peptide_hits = peptide_hits
     @id = id
   end
+
+  # if the GN=([^\s]+) regexp is found in the description, returns the first
+  # match, or nil if not found
+  def gene_id
+    description.andand.match(/ GN=(\w+) ?/)[1]
+  end
 end
 

data/lib/ms/ident/search.rb

@@ -2,9 +2,15 @@
 module Ms
   module Ident
 
-    module Search
-      attr_accessor :proteins
-      attr_accessor :peptides
+    class Search
+      attr_accessor :id
+      attr_accessor :peptide_hits
+      alias_method :hits, :peptide_hits
+
+      def initialize(id=nil, peptide_hits=[])
+        @id = id
+        @peptide_hits = peptide_hits
+      end
 
       # returns an array of peptide_hits and protein_hits that are linked to
       # one another.  NOTE: this will update peptide and protein
@@ -40,7 +46,6 @@ module Ms
 
 
     module SearchGroup 
-      include Search
 
       # an array of search objects
       attr_accessor :searches

metadata

@@ -1,12 +1,8 @@
 --- !ruby/object:Gem::Specification 
 name: ms-ident
 version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 0
-  - 23
-  version: 0.0.23
+  prerelease: 
+  version: 0.1.1
 platform: ruby
 authors: 
 - John T. Prince
@@ -14,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-03-31 00:00:00 -06:00
+date: 2011-04-26 00:00:00 -06:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -25,8 +21,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id001
@@ -38,10 +32,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 0
-        - 12
         version: 0.0.12
   type: :runtime
   version_requirements: *id002
@@ -53,8 +43,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id003
@@ -66,8 +54,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :runtime
   version_requirements: *id004
@@ -79,8 +65,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :development
   version_requirements: *id005
@@ -92,8 +76,6 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        segments: 
-        - 0
         version: "0"
   type: :development
   version_requirements: *id006
@@ -160,21 +142,17 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      segments: 
-      - 0
       version: "0"
 requirements: []
 
 rubyforge_project: mspire
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: mspire library for working with mzIdentML and pepxml