Merge branch 'new_model_prediction_format' into development

3 files changed, 95 insertions, 75 deletions

diff --git a/lib/dataset.rb b/lib/dataset.rb
index 4005c1c..4dc4296 100644
--- a/lib/dataset.rb
+++ b/lib/dataset.rb
@@ -179,7 +179,6 @@ module OpenTox
       end
     end
 
-=begin
     # Detect feature type(s) in the dataset
     # @return [String] `classification", "regression", "mixed" or unknown`
     def feature_type(subjectid=nil)
@@ -193,6 +192,7 @@ module OpenTox
         "unknown"
       end
     end
+=begin
 =end
 
     # Get Spreadsheet representation
@@ -369,12 +369,11 @@ module OpenTox
     end
 
     def value(compound)
-      @data_entries[compound.uri].collect{|f,v| v.first if f.match(/prediction/)}.compact.first
+      @data_entries[compound.uri].collect{|f,v| v.first if f.match(/value/)}.compact.first
     end
 
     def confidence(compound)
-      feature_uri = @data_entries[compound.uri].collect{|f,v| f if f.match(/prediction/)}.compact.first
-      @features[feature_uri][OT.confidence]
+      @data_entries[compound.uri].collect{|f,v| v.first if f.match(/confidence/)}.compact.first
     end
 
     def descriptors(compound)
diff --git a/lib/model.rb b/lib/model.rb
index 998d2dc..d46152d 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -164,8 +164,6 @@ module OpenTox
         features = {}
 
         unless @prediction_dataset
-          #@prediction_dataset = cached_prediction
-          #return @prediction_dataset if cached_prediction
           @prediction_dataset = Dataset.create(CONFIG[:services]["opentox-dataset"], subjectid)
           @prediction_dataset.add_metadata( {
             OT.hasSource => @uri,
@@ -237,38 +235,90 @@ module OpenTox
           prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values})")
         end
         
-        prediction_feature_uri = File.join( @prediction_dataset.uri, "feature", "prediction", File.basename(@metadata[OT.dependentVariables]),@prediction_dataset.compounds.size.to_s)
-        # TODO: fix dependentVariable
-        @prediction_dataset.metadata[OT.dependentVariables] = prediction_feature_uri
+       # TODO: reasonable feature name
+        #prediction_feature_uri = File.join( @prediction_dataset.uri, "feature", "prediction", File.basename(@metadata[OT.dependentVariables]),@prediction_dataset.compounds.size.to_s)
+        value_feature_uri = File.join( @prediction_dataset.uri, "feature", "prediction", File.basename(@metadata[OT.dependentVariables]),"value")
+        confidence_feature_uri = File.join( @prediction_dataset.uri, "feature", "prediction", File.basename(@metadata[OT.dependentVariables]),"confidence")
 
+        prediction_feature_uris = {value_feature_uri => prediction[:prediction], confidence_feature_uri => prediction[:confidence]}
+        prediction_feature_uris[value_feature_uri] = "No similar compounds in training dataset." if @neighbors.size == 0 or prediction[:prediction].nil?
+
+        
+        #@prediction_dataset.metadata[OT.dependentVariables] = prediction_feature_uri
+        @prediction_dataset.metadata[OT.dependentVariables] = @metadata[OT.dependentVariables]
+
+=begin
         if @neighbors.size == 0
-          @prediction_dataset.add_feature(prediction_feature_uri, {
-            RDF.type => [OT.MeasuredFeature],
-            OT.hasSource => @uri,
-            DC.creator => @uri,
-            DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )),
-            OT.error => "No similar compounds in training dataset.",
-            OT.parameters => [{DC.title => "compound_uri", OT.paramValue => compound_uri}]
-          })
-          @prediction_dataset.add @compound.uri, prediction_feature_uri, prediction[:prediction]
+          prediction_feature_uris.each do |prediction_feature_uri,value|
+            @prediction_dataset.add_feature(prediction_feature_uri, {
+              RDF.type => [OT.MeasuredFeature],
+              OT.hasSource => @uri,
+              DC.creator => @uri,
+              DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )),
+              OT.error => "No similar compounds in training dataset.",
+              #OT.parameters => [{DC.title => "compound_uri", OT.paramValue => compound_uri}]
+            })
+            @prediction_dataset.add @compound.uri, prediction_feature_uri, value
+          end
 
         else
+=end
+        prediction_feature_uris.each do |prediction_feature_uri,value|
+          @prediction_dataset.metadata[OT.predictedVariables] = [] unless @prediction_dataset.metadata[OT.predictedVariables] 
+          @prediction_dataset.metadata[OT.predictedVariables] << prediction_feature_uri
           @prediction_dataset.add_feature(prediction_feature_uri, {
             RDF.type => [OT.ModelPrediction],
             OT.hasSource => @uri,
             DC.creator => @uri,
             DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )),
-            OT.prediction => prediction[:prediction],
-            OT.confidence => prediction[:confidence],
-            OT.parameters => [{DC.title => "compound_uri", OT.paramValue => compound_uri}]
+            # TODO: factor information to value
           })
-          @prediction_dataset.add @compound.uri, prediction_feature_uri, prediction[:prediction]
+            #OT.prediction => prediction[:prediction],
+            #OT.confidence => prediction[:confidence],
+            #OT.parameters => [{DC.title => "compound_uri", OT.paramValue => compound_uri}]
+            @prediction_dataset.add @compound.uri, prediction_feature_uri, value
+        end
 
-          if verbose
-            if @feature_calculation_algorithm == "Substructure.match"
-              f = 0
-              @compound_features.each do |feature|
-                feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s)
+        if verbose
+          if @feature_calculation_algorithm == "Substructure.match"
+            f = 0
+            @compound_features.each do |feature|
+              feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s)
+              features[feature] = feature_uri
+              @prediction_dataset.add_feature(feature_uri, {
+                RDF.type => [OT.Substructure],
+                OT.smarts => feature,
+                OT.pValue => @p_values[feature],
+                OT.effect => @effects[feature]
+              })
+              @prediction_dataset.add @compound.uri, feature_uri, true
+              f+=1
+            end
+          else
+            @compound_features.each do |feature|
+              features[feature] = feature
+              @prediction_dataset.add @compound.uri, feature, true
+            end
+          end
+          n = 0
+          @neighbors.each do |neighbor|
+            neighbor_uri = File.join( @prediction_dataset.uri, "feature", "neighbor", n.to_s )
+            @prediction_dataset.add_feature(neighbor_uri, {
+              OT.compound => neighbor[:compound],
+              OT.similarity => neighbor[:similarity],
+              OT.measuredActivity => neighbor[:activity],
+              RDF.type => [OT.Neighbor]
+            })
+            @prediction_dataset.add @compound.uri, neighbor_uri, true
+            f = 0 unless f
+            neighbor[:features].each do |feature|
+              if @feature_calculation_algorithm == "Substructure.match"
+                feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s) unless feature_uri = features[feature]
+              else
+                feature_uri = feature
+              end
+              @prediction_dataset.add neighbor[:compound], feature_uri, true
+              unless features.has_key? feature
                 features[feature] = feature_uri
                 @prediction_dataset.add_feature(feature_uri, {
                   RDF.type => [OT.Substructure],
@@ -276,49 +326,13 @@ module OpenTox
                   OT.pValue => @p_values[feature],
                   OT.effect => @effects[feature]
                 })
-                @prediction_dataset.add @compound.uri, feature_uri, true
                 f+=1
               end
-            else
-              @compound_features.each do |feature|
-                features[feature] = feature
-                @prediction_dataset.add @compound.uri, feature, true
-              end
-            end
-            n = 0
-            @neighbors.each do |neighbor|
-              neighbor_uri = File.join( @prediction_dataset.uri, "feature", "neighbor", n.to_s )
-              @prediction_dataset.add_feature(neighbor_uri, {
-                OT.compound => neighbor[:compound],
-                OT.similarity => neighbor[:similarity],
-                OT.measuredActivity => neighbor[:activity],
-                RDF.type => [OT.Neighbor]
-              })
-              @prediction_dataset.add @compound.uri, neighbor_uri, true
-              f = 0 unless f
-              neighbor[:features].each do |feature|
-                if @feature_calculation_algorithm == "Substructure.match"
-                  feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s) unless feature_uri = features[feature]
-                else
-                  feature_uri = feature
-                end
-                @prediction_dataset.add neighbor[:compound], feature_uri, true
-                unless features.has_key? feature
-                  features[feature] = feature_uri
-                  @prediction_dataset.add_feature(feature_uri, {
-                    RDF.type => [OT.Substructure],
-                    OT.smarts => feature,
-                    OT.pValue => @p_values[feature],
-                    OT.effect => @effects[feature]
-                  })
-                  f+=1
-                end
-              end
-              n+=1
             end
-            # what happens with dataset predictions?
+            n+=1
           end
         end
+        #end
 
         @prediction_dataset.save(subjectid)
         @prediction_dataset
diff --git a/lib/serializer.rb b/lib/serializer.rb
index e4cb541..78e7709 100644
--- a/lib/serializer.rb
+++ b/lib/serializer.rb
@@ -17,6 +17,7 @@ module OpenTox
           # this should come from opentox.owl
           OT.Compound => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OT.Feature => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
+          OT.Model => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OT.NominalFeature => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OT.NumericFeature => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OT.StringFeature => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
@@ -27,6 +28,8 @@ module OpenTox
           OT.Parameter => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OT.Task => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
           OTA.PatternMiningSupervised => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
+          OTA.ClassificationLazySingleTarget => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
+          OTA.RegressionLazySingleTarget => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
 
           #classes for validation
           OT.Validation => { RDF["type"] => [{ "type" => "uri", "value" => OWL['Class'] }] } ,
@@ -45,6 +48,9 @@ module OpenTox
           OT.values => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
           OT.algorithm => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
           OT.parameters => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
+          OT.featureDataset => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
+          OT.dependentVariables => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
+          OT.paramValue => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
 
           #object props for validation#           
           OT.model => { RDF["type"] => [{ "type" => "uri", "value" => OWL.ObjectProperty }] } ,
@@ -126,7 +132,7 @@ module OpenTox
           OT.hasSource => { RDF["type"] => [{ "type" => "uri", "value" => OWL.DatatypeProperty }] } ,
           OT.value => { RDF["type"] => [{ "type" => "uri", "value" => OWL.DatatypeProperty }] } ,
           OT.paramScope => { RDF["type"] => [{ "type" => "uri", "value" => OWL.DatatypeProperty }] } ,
-          OT.paramValue => { RDF["type"] => [{ "type" => "uri", "value" => OWL.DatatypeProperty }] } ,
+          #OT.paramValue => { RDF["type"] => [{ "type" => "uri", "value" => OWL.DatatypeProperty }] } ,
         }
 
         @data_entries = {}
@@ -157,23 +163,16 @@ module OpenTox
       # Add a dataset
       # @param [String] uri Dataset URI
       def add_dataset(dataset)
-
         @dataset = dataset.uri
-
         @object[dataset.uri] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Dataset }] }
-
         add_metadata dataset.uri, dataset.metadata
-
         dataset.compounds.each { |compound| add_compound compound }
-        
         dataset.features.each { |feature,metadata| add_feature feature,metadata }
-        
         dataset.data_entries.each do |compound,entry|
           entry.each do |feature,values|
             values.each { |value| add_data_entry compound,feature,value }
           end
         end
-
       end
 
       # Add a algorithm
@@ -188,6 +187,13 @@ module OpenTox
       def add_model(uri,metadata)
         @object[uri] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Model }] }
         add_metadata uri, metadata
+        @object[metadata[OT.featureDataset]] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Dataset }] }
+        @object[metadata[OT.trainingDataset]] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Dataset }] }
+        @object[metadata[OT.dependentVariables]] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Feature }] }
+        # TODO: add algorithms from parameters
+        @object["http://ot-dev.in-silico.ch/algorithm/fminer/bbrc"] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Algorithm }] }
+        @object["http://ot-dev.in-silico.ch/algorithm/fminer/last"] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Algorithm }] }
+        @object["http://ot-dev.in-silico.ch/algorithm/lazar"] = { RDF["type"] => [{ "type" => "uri", "value" => OT.Algorithm }] }
       end
 
       # Add a task
@@ -272,7 +278,7 @@ module OpenTox
                 @object[genid][name] = [{"type" => type(entry), "value" => entry }]
               end
             end
-          elsif v.is_a? Array and u == RDF.type
+          elsif v.is_a? Array #and u == RDF.type
             @object[uri] = {} unless @object[uri]
             v.each do |value|
               @object[uri][u] = [] unless @object[uri][u]
@@ -354,7 +360,8 @@ module OpenTox
       # @return [text/plain] Object OWL-DL in RDF/XML format
       def to_rdfxml
         Tempfile.open("owl-serializer"){|f| f.write(self.to_ntriples); @path = f.path}
-        `rapper -i ntriples -f 'xmlns:ot="#{OT.uri}"' -f 'xmlns:dc="#{DC.uri}"' -f 'xmlns:rdf="#{RDF.uri}"' -f 'xmlns:owl="#{OWL.uri}"' -o rdfxml #{@path} 2>/dev/null`
+        # TODO: add base uri for ist services
+        `rapper -i ntriples -f 'xmlns:ot="#{OT.uri}"' -f 'xmlns:ota="#{OTA.uri}"' -f 'xmlns:dc="#{DC.uri}"' -f 'xmlns:rdf="#{RDF.uri}"' -f 'xmlns:owl="#{OWL.uri}"' -o rdfxml #{@path} 2>/dev/null`
       end
 
       # Convert to JSON as specified in http://n2.talis.com/wiki/RDF_JSON_Specification