From 5b08a8c6d8e5567d253bec92d5bf5d18fd040cdc Mon Sep 17 00:00:00 2001
From: "helma@in-silico.ch" <helma@in-silico.ch>
Date: Wed, 31 Oct 2018 14:50:42 +0100
Subject: pubchem import for openrisknet

---
 test/use_cases.rb | 50 +++++++++++++++++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 17 deletions(-)

(limited to 'test')

diff --git a/test/use_cases.rb b/test/use_cases.rb
index 4959f16..4e072d8 100644
--- a/test/use_cases.rb
+++ b/test/use_cases.rb
@@ -3,27 +3,43 @@ require_relative "setup.rb"
 class UseCasesTest < MiniTest::Test
 
   def test_PA
-    kazius = Dataset.from_sdf_file "#{DATA_DIR}/cas_4337.sdf"
-    hansen = Dataset.from_csv_file "#{DATA_DIR}/hansen.csv"
-    efsa = Dataset.from_csv_file "#{DATA_DIR}/efsa.csv"
-    datasets = [kazius,hansen,efsa]
-    map = {"1" => "mutagen", "0" => "nonmutagen"}
-    p "merging"
-    training_dataset = Dataset.merge datasets: datasets, features: datasets.collect{|d| d.bioactivity_features.first}, value_maps: [nil,map,map], keep_original_features: false, remove_duplicates: true
-    assert_equal 8281, training_dataset.compounds.size
-    p training_dataset.features.size
-    p training_dataset.id
-    training_dataset = Dataset.find('5bd8ac8fca62695d767fca6b')
+    #kazius = Dataset.from_sdf_file "#{DATA_DIR}/cas_4337.sdf"
+    #hansen = Dataset.from_csv_file "#{DATA_DIR}/hansen.csv"
+    #efsa = Dataset.from_csv_file "#{DATA_DIR}/efsa.csv"
+    #datasets = [kazius,hansen,efsa]
+    #map = {"1" => "mutagen", "0" => "nonmutagen"}
+    #p "merging"
+    #training_dataset = Dataset.merge datasets: datasets, features: datasets.collect{|d| d.bioactivity_features.first}, value_maps: [nil,map,map], keep_original_features: false, remove_duplicates: true
+    #assert_equal 8281, training_dataset.compounds.size
+    #p training_dataset.features.size
+    #p training_dataset.id
+    #training_dataset = Dataset.find('5bd8ac8fca62695d767fca6b')
+    #training_dataset = Dataset.find('5bd8bbadca62695f69e7a33b')
+    #puts training_dataset.to_csv
     p "create model_validation"
-    model_validation = Model::Validation.from_dataset training_dataset: training_dataset, prediction_feature: training_dataset.merged_features.first, species: "Salmonella typhimurium", endpoint: "Mutagenicity"
-    p model_validation.id
-    p "predict"
-    pa = Dataset.from_sdf_file "#{DATA_DIR}/PA.sdf"
-    prediction_dataset = model_dataset.predict pa
-    p prediction_dataset.id
+    #model_validation = Model::Validation.from_dataset training_dataset: training_dataset, prediction_feature: training_dataset.merged_features.first, species: "Salmonella typhimurium", endpoint: "Mutagenicity"
+    #p model_validation.id
+    #model_validation = Model::Validation.find '5bd8df47ca6269604590ab38'
+    #p "predict"
+    #pa = Dataset.from_sdf_file "#{DATA_DIR}/PA.sdf"
+    #prediction_dataset = model_validation.predict pa
+    #p prediction_dataset.id
+    prediction_dataset = Dataset.find('5bd98b88ca6269609aab79f4')
     puts prediction_dataset.to_csv
   end
 
+  def test_tox21
+    training_dataset = Dataset.from_pubchem_aid 743122
+    p training_dataset.id
+    #'5bd9a1dbca626969d97fb421'
+    File.open("AID743122.csv","w+"){|f| f.puts training_dataset.to_csv}
+    model = Model::Lazar.create training_dataset: training_dataset
+    p model.id
+    #p Model::Lazar.find('5bd9a70bca626969d97fc9df')
+    model_validation = Model::Validation.from_dataset training_dataset: training_dataset, prediction_feature: training_dataset.bioactivity_features.first, species: "Human HG2L7.5c1 cell line", endpoint: "aryl hydrocarbon receptor (AhR) signaling pathway activation"
+    p model_validation.id
+  end
+
   def test_public_models
     skip
 =begin
-- 
cgit v1.2.3