proteomics regression validation

2 files changed, 20 insertions, 38 deletions

diff --git a/lib/model.rb b/lib/model.rb
index 3482aee..277bca3 100644
--- a/lib/model.rb
+++ b/lib/model.rb
@@ -31,7 +31,7 @@ module OpenTox
         self.neighbor_algorithm_parameters ||= {}
         self.neighbor_algorithm_parameters[:dataset_id] = training_dataset.id
 
-        #send(feature_selection_algorithm.to_sym) if feature_selection_algorithm
+        send(feature_selection_algorithm.to_sym) if feature_selection_algorithm
         save
       end
 
@@ -49,25 +49,31 @@ module OpenTox
         feature_ids = training_dataset.substances.collect{ |s| s["physchem_descriptors"].keys}.flatten.uniq
         feature_ids.each do |feature_id|
           feature_values = substances.collect{|s| s["physchem_descriptors"][feature_id].first if s["physchem_descriptors"][feature_id]}
-          R.assign "feature", feature_values
-          begin
-            R.eval "cor <- cor.test(tox,feature,method = 'pearson',use='pairwise')"
-            pvalue = R.eval("cor$p.value").to_ruby
-            if pvalue <= 0.05
-              r = R.eval("cor$estimate").to_ruby
-              self.relevant_features[feature_id] = {}
-              self.relevant_features[feature_id]["pvalue"] = pvalue
-              self.relevant_features[feature_id]["r"] = r
+          unless feature_values.uniq.size == 1
+            R.assign "feature", feature_values
+            begin
+              R.eval "cor <- cor.test(tox,feature,method = 'pearson',use='pairwise')"
+              pvalue = R.eval("cor$p.value").to_ruby
+              if pvalue <= 0.05
+                r = R.eval("cor$estimate").to_ruby
+                self.relevant_features[feature_id] = {}
+                self.relevant_features[feature_id]["pvalue"] = pvalue
+                self.relevant_features[feature_id]["r"] = r
+                self.relevant_features[feature_id]["mean"] = R.eval("mean(feature, na.rm=TRUE)").to_ruby
+                self.relevant_features[feature_id]["sd"] = R.eval("sd(feature, na.rm=TRUE)").to_ruby
+              end
+            rescue
+              warn "Correlation of '#{Feature.find(feature_id).name}' (#{feature_values}) with '#{Feature.find(prediction_feature_id).name}' (#{measurements}) failed."
             end
-          rescue
-            warn "Correlation of '#{Feature.find(feature_id).name}' (#{feature_values}) with '#{Feature.find(prediction_feature_id).name}' (#{measurements}) failed."
           end
         end
         self.relevant_features = self.relevant_features.sort{|a,b| a[1]["pvalue"] <=> b[1]["pvalue"]}.to_h
+        p self.relevant_features
       end
 
       def predict_substance substance
         neighbor_algorithm_parameters = Hash[self.neighbor_algorithm_parameters.map{ |k, v| [k.to_sym, v] }] # convert string keys to symbols
+        neighbor_algorithm_parameters[:relevant_features] = self.relevant_features if self.relevant_features
         neighbors = substance.send(neighbor_algorithm, neighbor_algorithm_parameters)
         measurements = nil
         prediction = {}
diff --git a/lib/nanoparticle.rb b/lib/nanoparticle.rb
index 3e29ae1..c1bf1b5 100644
--- a/lib/nanoparticle.rb
+++ b/lib/nanoparticle.rb
@@ -9,10 +9,10 @@ module OpenTox
 
     attr_accessor :scaled_values
  
-    def physchem_neighbors min_sim: 0.9, dataset_id:, prediction_feature_id:
+    def physchem_neighbors min_sim: 0.9, dataset_id:, prediction_feature_id:, relevant_features:
       p name
       dataset = Dataset.find(dataset_id)
-      relevant_features = {}
+      #relevant_features = {}
       measurements = []
       substances = []
       # TODO: exclude query activities!!!
@@ -24,30 +24,6 @@ module OpenTox
           end
         end
       end
-      R.assign "tox", measurements
-      feature_ids = physchem_descriptors.keys.select{|fid| Feature.find(fid).is_a? NumericFeature}
-      # identify relevant features
-      feature_ids.each do |feature_id|
-        feature_values = substances.collect{|s| s["physchem_descriptors"][feature_id].first if s["physchem_descriptors"][feature_id]}
-        unless feature_values.uniq.size == 1
-          R.assign "feature", feature_values
-          begin
-            R.eval "cor <- cor.test(tox,feature,method = 'pearson',use='pairwise')"
-            p_value = R.eval("cor$p.value").to_ruby
-            if p_value <= 0.05
-              r = R.eval("cor$estimate").to_ruby
-              relevant_features[feature_id] = {}
-              relevant_features[feature_id]["p_value"] = p_value
-              relevant_features[feature_id]["r"] = r
-              relevant_features[feature_id]["mean"] = R.eval("mean(feature, na.rm=TRUE)").to_ruby
-              relevant_features[feature_id]["sd"] = R.eval("sd(feature, na.rm=TRUE)").to_ruby
-            end
-          rescue
-            warn "Correlation of '#{Feature.find(feature_id).name}' (#{feature_values}) with '#{Feature.find(prediction_feature_id).name}' (#{measurements}) failed."
-          end
-        end
-      end
-      #p relevant_features.keys.collect{|i| Feature.find(i).name}
       neighbors = []
       substances.each do |substance|
         values = dataset.values(substance,prediction_feature_id)