From 611bac891177f8d9185d45486dd574b6ef4d1912 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Mon, 9 May 2016 15:11:46 +0200
Subject: nanoparticle models fixed

---
 lib/nanoparticle.rb | 37 +++++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 16 deletions(-)

(limited to 'lib/nanoparticle.rb')

diff --git a/lib/nanoparticle.rb b/lib/nanoparticle.rb
index 9bf419d..b79981d 100644
--- a/lib/nanoparticle.rb
+++ b/lib/nanoparticle.rb
@@ -9,10 +9,14 @@ module OpenTox
     field :proteomics, type: Hash, default: {}
 
     def nanoparticle_neighbors params
-      Dataset.find(params[:training_dataset_id]).nanoparticles.collect{|np| np["tanimoto"] = 1; np}
+      dataset = Dataset.find(params[:training_dataset_id])
+      Dataset.find(params[:training_dataset_id]).nanoparticles.collect do |np|
+        np["tanimoto"] = 1
+        np unless np.toxicities.empty?
+      end.compact
     end
 
-    def add_feature feature, value
+    def add_feature feature, value, dataset_id
       case feature.category
       when "P-CHEM"
         physchem_descriptors[feature.id.to_s] ||= []
@@ -23,51 +27,52 @@ module OpenTox
         proteomics[feature.id.to_s] << value
         proteomics[feature.id.to_s].uniq!
       when "TOX"
-        toxicities[feature.id.to_s] ||= []
+        toxicities[feature.id.to_s] ||= {}
+        toxicities[feature.id.to_s][dataset_id.to_s] ||= []
         # TODO generic way of parsing TOX values
         if feature.name == "7.99 Toxicity (other) ICP-AES" and feature.unit == "mL/ug(Mg)" 
-          toxicities[feature.id.to_s] << -Math.log10(value)
+          toxicities[feature.id.to_s][dataset_id.to_s] << -Math.log10(value)
         else
-          toxicities[feature.id.to_s] << value
+          toxicities[feature.id.to_s][dataset_id.to_s] << value
         end
-        toxicities[feature.id.to_s].uniq!
+        toxicities[feature.id.to_s][dataset_id.to_s].uniq!
       else
         warn "Unknown feature type '#{feature.category}'. Value '#{value}' not inserted."
       end
     end
 
-    def parse_ambit_value feature, v
+    def parse_ambit_value feature, v, dataset_id
       v.delete "unit"
       # TODO: ppm instead of weights
       if v.keys == ["textValue"]
-        add_feature feature, v["textValue"]
+        add_feature feature, v["textValue"], dataset_id
       elsif v.keys == ["loValue"]
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
       elsif v.keys.size == 2 and v["errorValue"]
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
         warn "Ignoring errorValue '#{v["errorValue"]}' for '#{feature.name}'."
       elsif v.keys.size == 2 and v["loQualifier"] == "mean"
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
         warn "'#{feature.name}' is a mean value. Original data is not available."
       elsif v.keys.size == 2 and v["loQualifier"] #== ">="
         warn "Only min value available for '#{feature.name}', entry ignored"
       elsif v.keys.size == 2 and v["upQualifier"] #== ">="
         warn "Only max value available for '#{feature.name}', entry ignored"
       elsif v.keys.size == 3 and v["loValue"] and v["loQualifier"].nil? and v["upQualifier"].nil?
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
         warn "loQualifier and upQualifier are empty."
       elsif v.keys.size == 3 and v["loValue"] and v["loQualifier"] == "" and v["upQualifier"] == ""
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
         warn "loQualifier and upQualifier are empty."
       elsif v.keys.size == 4 and v["loValue"] and v["loQualifier"].nil? and v["upQualifier"].nil?
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
         warn "loQualifier and upQualifier are empty."
       elsif v.size == 4 and v["loQualifier"] and v["upQualifier"] and v["loValue"] and v["upValue"]
-        add_feature feature, [v["loValue"],v["upValue"]].mean
+        add_feature feature, [v["loValue"],v["upValue"]].mean, dataset_id
         warn "Using mean value of range #{v["loValue"]} - #{v["upValue"]} for '#{feature.name}'. Original data is not available."
       elsif v.size == 4 and v["loQualifier"] == "mean" and v["errorValue"]
         warn "'#{feature.name}' is a mean value. Original data is not available. Ignoring errorValue '#{v["errorValue"]}' for '#{feature.name}'."
-        add_feature feature, v["loValue"]
+        add_feature feature, v["loValue"], dataset_id
       elsif v == {} # do nothing
       else
         warn "Cannot parse Ambit eNanoMapper value '#{v}' for feature '#{feature.name}'."
-- 
cgit v1.2.3