goruby 0.1.0 → 0.2.0

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.0

data/lib/go.rb

@@ -15,11 +15,11 @@ module Bio
     def go_offspring(go_id)
       o = ontology_abbreviation(go_id)
       case o
-      when 'MF'
+        when 'MF'
         return molecular_function_offspring(go_id)
-      when 'CC'
+        when 'CC'
         return cellular_component_offspring(go_id)
-      when 'BP'
+        when 'BP'
         return biological_process_offspring(go_id)
       else
         raise Exception, "Unknown ontology abbreviation found: #{o} for go id: #{go_id}"
@@ -32,7 +32,7 @@ module Bio
     def cellular_component_offspring(go_term)
       go_get(go_term, 'GOCCOFFSPRING')
     end
-
+    
     # Return an array of GO identifiers that are the offspring (all the descendents)
     # of the given GO term given that it is a molecular function
     # GO term.     
@@ -73,13 +73,17 @@ module Bio
       # A performance note:
       # According to some tests that I ran, finding GOID by searching GOTERM
       # is much faster than by GOSYNONYM. A
-    
+      
       begin
         # Assume it is a primary ID, as it likely will be most of the time.
         return @r.eval_R("GOID(get('#{go_id_or_synonym_id}', GOTERM))")
       rescue RException
         # if no primary is found, try to finding it by synonym. raise RException if none is found
-        return @r.eval_R("GOID(get('#{go_id_or_synonym_id}', GOSYNONYM))")
+        begin
+          return @r.eval_R("GOID(get('#{go_id_or_synonym_id}', GOSYNONYM))")
+        rescue RException => e
+          raise RException, "#{e.message}: GO Identifier '#{go_id_or_synonym_id}' does not appear to be a primary ID nor synonym. Is the GO.db database up to date?"
+        end  
       end
     end
     
@@ -112,7 +116,7 @@ module Bio
       
       return gos.flatten.uniq
     end
-  
+    
     # Does the subsumer subsume the subsumee? i.e. Does it include
     # the subsumee as one of its children in the GO tree?
     # 
@@ -122,10 +126,10 @@ module Bio
       # map the subsumee to non-synonomic id
       primaree = self.primary_go_id(subsumee_go_id)
       primarer = self.primary_go_id(subsumer_go_id)
-    
+      
       # return if they are the same - the obvious case
       return true if primaree == primarer
-    
+      
       # return if subsumee is a descendent of sumsumer
       return go_offspring(primarer).include?(primaree)
     end
@@ -135,18 +139,59 @@ module Bio
     def subsume_tester(subsumer_go_id, check_for_synonym=true)
       Go::SubsumeTester.new(self, subsumer_go_id, check_for_synonym)
     end
-  
+    
     # Return 'MF', 'CC' or 'BP' corresponding to the
     def ontology_abbreviation(go_id)
       @r.eval_R("Ontology(get('#{go_id}', GOTERM))")
     end
-
+    
+    # Return an array of GO ids that correspond to the parent GO terms
+    # in the ontology. This isn't the most efficient this could be, because it
+    # probably gets the parents for a single id multiple times. 
+    def ancestors_cc(primary_go_id)
+      go_get(primary_go_id, 'GOCCANCESTOR')
+    end
+    
+    # Return an array of ancestors of the GO term or any
+    # of the GO terms' children, in no particular order. This is useful
+    # when wanting to know if a term has an annotation that is 
+    # non-overlapping with a particular go term. For instance, 'membrane'
+    # is cordial with 'nucleus', they are boths is an ancestors of 
+    # 'nuclear membrane'. However, 'mitochondrion' and 'nucleus' are 
+    # not cordial, since they share no common offspring.
+    def cordial_cc(primary_go_id)
+      # cordial can be direct ancestors of a term - then the common term
+      # is this term itself
+      cordial_ids = ancestors_cc(primary_go_id)
+      
+      # collect all ancestors of all offspring
+      offspring = cellular_component_offspring(primary_go_id)
+      offspring.each do |o|
+        cordial_ids.push ancestors_cc(o)
+        cordial_ids.push o
+      end
+      
+      # remove the term itself and any children - they are not
+      # merely cordial
+      cordial_ids = cordial_ids.flatten.uniq.reject do |i|
+        offspring.include?(i) or primary_go_id==i
+      end
+      
+      # return a uniq array of cordial terms
+      cordial_ids
+    end
+    
+    # When repeatedly testing subsumtion by a certain GO term,
+    # it is faster to instantiate a SubsumeTester and use
+    # Bio::GO::SubsumeTester#subsume?, rather than
+    # repeatedly calling Bio::GO#subsume? because SubsumeTester
+    # does caching.
     class SubsumeTester
       attr_reader :subsumer_offspring, :master_go_id
-    
+      
       def initialize(go_object, subsumer_go_id, check_for_synonym=true)
         @go = go_object
-      
+        
         if check_for_synonym
           @master_go_id = @go.primary_go_id(subsumer_go_id)
         else
@@ -155,11 +200,11 @@ module Bio
         @subsumer_offspring = @go.go_offspring(@master_go_id)
         @subsumer_offspring_hash = [@subsumer_offspring].flatten.to_hash
       end
-    
+      
       def subsume?(subsumer_go_id, check_for_synonym=true)
         primaree = check_for_synonym ?
-          @go.primary_go_id(subsumer_go_id) :
-          subsumer_go_id
+        @go.primary_go_id(subsumer_go_id) :
+        subsumer_go_id
         return true if @master_go_id == primaree
         @subsumer_offspring_hash.has_key?(primaree)
       end

data/test/test_goruby.rb

@@ -15,12 +15,12 @@ class GoTest < Test::Unit::TestCase
     assert_equal [], @go.cellular_component_offspring('GO:0031676')
     
     # test multiple offspring
-    assert_equal ["GO:0030075","GO:0030077","GO:0030078","GO:0030079","GO:0030080",
-      "GO:0030081","GO:0030082","GO:0030089","GO:0030094","GO:0030096",
-      "GO:0031633","GO:0031676","GO:0031979","GO:0042717","GO:0048493",
-      "GO:0048494"
-    ],
-      @go.cellular_component_offspring('GO:0042716')
+    old_offspring = ["GO:0030077", "GO:0030078", "GO:0030079", "GO:0030080", "GO:0030081", "GO:0030082", "GO:0031633", "GO:0031676", "GO:0042717", "GO:0048493", "GO:0048494"]
+    offspring = @go.cellular_component_offspring('GO:0042716')
+    assert offspring.length >= old_offspring.length
+    assert offspring.include?(old_offspring[0])
+    assert offspring.include?(old_offspring[1])
+    assert offspring.include?(old_offspring[old_offspring.length-2])
     
     # test not in CC
     assert_raise RException do
@@ -39,7 +39,7 @@ class GoTest < Test::Unit::TestCase
   def test_go_term
     # test MF
     assert_equal "G-protein coupled receptor activity", @go.term('GO:0004930')
-   
+    
     # test CC
     assert_equal 'endoplasmic reticulum', @go.term('GO:0005783')
   end
@@ -60,13 +60,13 @@ class GoTest < Test::Unit::TestCase
   def test_subsume
     # test normal truth
     assert @go.subsume?('GO:0003824', 'GO:0050333')
-      
+    
     # test subsumee is synonym
     assert @go.subsume?('GO:0003824', 'GO:0048253')
-      
+    
     # test equal terms
     assert @go.subsume?('GO:0009536','GO:0009536')
-      
+    
     # test falsity - plastid part does not subsume plastid
     assert_equal false, @go.subsume?('GO:0044435','GO:0009536')
   end
@@ -83,26 +83,35 @@ class GoTest < Test::Unit::TestCase
     tester = @go.subsume_tester('GO:0044435')
     assert tester.subsume?('GO:0044435')
   end
-
+  
   def test_subsume_tester_no_check_synonym
     # test normal truth
     tester = @go.subsume_tester('GO:0003824')
     assert_equal true, tester.subsume?('GO:0050333', false)
     assert_equal true, tester.subsume?('GO:0050333', true)
-
+    
     # test subsumee is synonym
     tester = @go.subsume_tester('GO:0003824')
     assert_equal false, tester.subsume?('GO:0048253', false)
     assert_equal true, tester.subsume?('GO:0048253', true)
-
+    
     # test equal terms
     tester = @go.subsume_tester('GO:0050333')
     assert_equal true, tester.subsume?('GO:0050333', false)
     assert_equal true, tester.subsume?('GO:0050333', true)
-
+    
     # test equal that is synonym
     tester = @go.subsume_tester('GO:0050333')
     assert_equal false, tester.subsume?('GO:0048253', false)
     assert_equal true, tester.subsume?('GO:0048253', true)
   end
+  
+  def test_cordial_cc
+    nucleus_cordial = @go.cordial_cc('GO:0005634')
+    
+    assert nucleus_cordial.include?('GO:0005575'), "include cellular component itself"
+    assert_equal false,  nucleus_cordial.include?('GO:0005634'), 'don\'t include nucleus itself'
+    assert nucleus_cordial.include?('GO:0005623'), 'include a direct ancestor of nucleus'
+    assert nucleus_cordial.include?('GO:0005623'), 'include membrane, a \'indirect\' direct ancestor of nucleus (it is an ancestor of nuclear membrane)'
+  end
 end

metadata

@@ -1,7 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: goruby
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  hash: 23
+  prerelease: false
+  segments: 
+  - 0
+  - 2
+  - 0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Ben J Woodcroft
@@ -9,49 +15,65 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-02-11 00:00:00 +11:00
+date: 2010-11-03 00:00:00 +11:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: thoughtbot-shoulda
-  type: :development
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :development
+  version_requirements: *id001
 - !ruby/object:Gem::Dependency 
   name: array_pair
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :runtime
+  version_requirements: *id002
 - !ruby/object:Gem::Dependency 
   name: rsruby
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :runtime
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: bio
-  type: :runtime
-  version_requirement: 
-  version_requirements: !ruby/object:Gem::Requirement 
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
         version: "0"
-    version: 
+  type: :runtime
+  version_requirements: *id004
 description: GoRuby makes it easy to interact with the Gene Ontology by using the infrastructure setup in R. By connecting to R using RSRuby, the database and methods can be interrogated. Plus, keeping the R library up to date is much simpler than having to keep a GO implementation up to date.
 email: donttrustben near gmail.com
 executables: []
@@ -80,21 +102,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
       version: "0"
-  version: 
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.5
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Gene Ontology (GO) interface for Ruby