From 5d4e5e463c2b87241bbb56e4658e1e26c0ed084f Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Wed, 5 Oct 2016 13:22:12 +0200
Subject: substance and nanoparticle model creation and predictions

---
 lib/feature_selection.rb | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)
 create mode 100644 lib/feature_selection.rb

(limited to 'lib/feature_selection.rb')

diff --git a/lib/feature_selection.rb b/lib/feature_selection.rb
new file mode 100644
index 0000000..43e3bea
--- /dev/null
+++ b/lib/feature_selection.rb
@@ -0,0 +1,46 @@
+module OpenTox
+  module Algorithm
+    
+    class FeatureSelection
+
+      def self.correlation_filter dataset:, prediction_feature:, types:nil
+        # TODO: speedup, single assignment of all features to R+ parallel computation of significance?
+        relevant_features = {}
+        measurements = []
+        substances = []
+        dataset.substances.each do |s|
+          dataset.values(s,prediction_feature).each do |act|
+            measurements << act
+            substances << s
+          end
+        end
+        R.assign "tox", measurements
+        feature_ids = dataset.substances.collect{ |s| s["properties"].keys}.flatten.uniq
+        feature_ids.select!{|fid| types.include? Feature.find(fid).category} if types
+        feature_ids.each do |feature_id|
+          feature_values = substances.collect{|s| s["properties"][feature_id].first if s["properties"][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')"
+              pvalue = R.eval("cor$p.value").to_ruby
+              if pvalue <= 0.05
+                r = R.eval("cor$estimate").to_ruby
+                relevant_features[feature_id] = {}
+                relevant_features[feature_id]["pvalue"] = pvalue
+                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
+        relevant_features.sort{|a,b| a[1]["pvalue"] <=> b[1]["pvalue"]}.to_h
+      end
+
+    end
+
+  end
+end
-- 
cgit v1.2.3