From f3780d7507092b643216054fa3ca1e6146281e43 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Fri, 8 Apr 2016 13:04:56 +0200
Subject: enm import test

---
 data/enm-import.rb  | 25 +++++++++++--------------
 lib/compound.rb     |  1 +
 lib/lazar.rb        |  1 +
 lib/nanoparticle.rb | 45 ++++++++++++++++++++++++++++++++++++++++-----
 test/setup.rb       |  4 ++--
 5 files changed, 55 insertions(+), 21 deletions(-)

diff --git a/data/enm-import.rb b/data/enm-import.rb
index 65fd3c7..37bc22b 100644
--- a/data/enm-import.rb
+++ b/data/enm-import.rb
@@ -1,6 +1,7 @@
 require_relative '../lib/lazar.rb'
 include OpenTox
-
+$mongo.database.drop
+$gridfs = $mongo.database.fs
 
 #get list of bundle URIs
 bundles = JSON.parse(RestClientWrapper.get('https://data.enanomapper.net/bundle?media=application%2Fjson'))["dataset"]
@@ -13,38 +14,34 @@ bundles.each do |bundle|
         :name => np["values"]["https://data.enanomapper.net/identifier/name"],
         :source => np["compound"]["URI"],
       )
+      nanoparticle.bundles << uri
+      nanoparticle.bundles.uniq!
       np["composition"].each do |comp|
         case comp["relation"]
         when "HAS_CORE"
-          nanoparticle[:core] = comp["component"]["compound"]["URI"]
+          nanoparticle.core = comp["component"]["compound"]["URI"]
         when "HAS_COATING"
-          nanoparticle[:coating] ||= []
-          nanoparticle[:coating] << comp["component"]["compound"]["URI"]
+          nanoparticle.coating << comp["component"]["compound"]["URI"]
         end
       end if np["composition"]
       np["values"].each do |u,v|
         if u.match(/property/)
-          name, unit = nil
+          name, unit, source = nil
           features.each do |uri,feat|
             if u.match(/#{uri}/)
               name = feat["title"]
               unit = feat["units"]
+              source = uri
             end
           end
           feature = Feature.find_or_create_by(
             :name => name,
             :unit => unit,
-            #:source => uri
+            :source => source
           )
-          nanoparticle[:features] ||= {}
-          if v.size == 1 and v.first.keys == ["loValue"]
-            nanoparticle[:features][feature.id] = v.first["loValue"]
-          else
-            #TODO
-          end
         end
+        v.each{|value| nanoparticle.parse_ambit_value feature, value} if v.is_a? Array
       end
-      p nanoparticle
-      nanoparticle.save
+      nanoparticle.save!
   end
 end
diff --git a/lib/compound.rb b/lib/compound.rb
index 2a79fd6..a7518ed 100644
--- a/lib/compound.rb
+++ b/lib/compound.rb
@@ -21,6 +21,7 @@ module OpenTox
     field :default_fingerprint_size, type: Integer
     field :physchem_descriptors, type: Hash, default: {}
     field :dataset_ids, type: Array, default: []
+    # TODO separate between physchem, bio and tox
     field :features, type: Hash, default: {}
 
     index({smiles: 1}, {unique: true})
diff --git a/lib/lazar.rb b/lib/lazar.rb
index 39dd8fa..0e2cec2 100644
--- a/lib/lazar.rb
+++ b/lib/lazar.rb
@@ -81,5 +81,6 @@ CLASSES = ["Feature","Compound","Dataset","Validation","CrossValidation","LeaveO
   "crossvalidation.rb",
   "leave-one-out-validation.rb",
   "experiment.rb",
+  "import.rb",
 ].each{ |f| require_relative f }
 OpenTox::PhysChem.descriptors # load descriptor features
diff --git a/lib/nanoparticle.rb b/lib/nanoparticle.rb
index 3783ece..cda431a 100644
--- a/lib/nanoparticle.rb
+++ b/lib/nanoparticle.rb
@@ -3,13 +3,48 @@ module OpenTox
   class Nanoparticle
     include OpenTox
 
-    field :particle_id, type: String
+    #field :particle_id, type: String
     field :core, type: String
-    field :coatings, type: Array
+    field :coating, type: Array, default: []
 
-    #field :physchem_descriptors, type: Hash, default: {}
-    #field :toxicities, type: Hash, default: {}
-    field :features, type: Hash, default: {}
+    field :physchem_descriptors, type: Hash, default: {}
+    field :toxicities, type: Hash, default: {}
+    #field :features, type: Hash, default: {}
+    field :bundles, type: Array, default: []
+
+    def predict
+    end
+
+    def add_feature feature, value
+      if feature.source.match /property\/P-CHEM/
+        physchem_descriptors[feature.id.to_s] ||= []
+        physchem_descriptors[feature.id.to_s] << value
+      elsif feature.source.match /property\/TOX/
+        toxicities[feature.id.to_s] ||= []
+        toxicities[feature.id.to_s] << value
+      else
+        $logger.warn "Unknown feature type '#{feature.source}'. Value '#{value}' not inserted."
+        warnings << "Unknown feature type '#{feature.source}'. Value '#{value}' not inserted."
+      end
+    end
+
+    def parse_ambit_value feature, v
+      if v.keys == ["loValue"]
+        add_feature feature, v["loValue"]
+      elsif v.keys.size == 2 and v["loQualifier"] == "mean"
+        add_feature feature, {:mean => v["loValue"]}
+      elsif v.keys.size == 2 and v["loQualifier"] #== ">="
+        add_feature feature, {:min => v["loValue"],:max => Float::INFINITY}
+      elsif v.keys.size == 2 and v["upQualifier"] #== ">="
+        add_feature feature, {:max => v["upValue"],:min => -Float::INFINITY}
+      elsif v.size == 4 and v["loQualifier"] and v["upQualifier"] 
+        add_feature feature, {:min => v["loValue"],:max => v["upValue"]}
+      elsif v == {} # do nothing
+      else
+        $logger.warn "Cannot parse Ambit eNanoMapper value '#{v}' for feature '#{feature.name}'."
+        warnings << "Cannot parse Ambit eNanoMapper value '#{v}' for feature '#{feature.name}'."
+      end
+    end
 
   end
 end
diff --git a/test/setup.rb b/test/setup.rb
index be3140a..e7c32b4 100644
--- a/test/setup.rb
+++ b/test/setup.rb
@@ -1,7 +1,7 @@
 ENV["LAZAR_ENV"] = "development"
 require 'minitest/autorun'
-#require_relative '../lib/lazar.rb'
-require 'lazar'
+require_relative '../lib/lazar.rb'
+#require 'lazar'
 include OpenTox
 TEST_DIR ||= File.expand_path(File.dirname(__FILE__))
 DATA_DIR ||= File.join(TEST_DIR,"data")
-- 
cgit v1.2.3