lazar 0.9.3 → 1.0.0

data/test/validation-nanoparticle.rb

@@ -0,0 +1,133 @@
+require_relative "setup.rb"
+
+class NanoparticleValidationTest  < MiniTest::Test
+  include OpenTox::Validation
+
+  def setup
+    @training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first
+    @prediction_feature = @training_dataset.features.select{|f| f["name"] == 'log2(Net cell association)'}.first
+  end
+
+  def test_validate_default_nanoparticle_model
+    model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature
+    cv = CrossValidation.create model
+    p cv.id
+    #File.open("tmp.pdf","w+"){|f| f.puts cv.correlation_plot format:"pdf"}
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+  def test_validate_pls_pchem_model
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :categories => ["P-CHEM"]
+      },
+      :prediction => {:method => 'Algorithm::Caret.pls' },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    assert_equal "Algorithm::Caret.pls", model.algorithms[:prediction][:method]
+    cv = CrossValidation.create model
+    p cv.id
+    #File.open("tmp2.pdf","w+"){|f| f.puts cv.correlation_plot format:"pdf"}
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+=begin
+  def test_validate_proteomics_pls_pchem_model
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :categories => ["Proteomics"]
+      },
+      :prediction => {:method => 'Algorithm::Caret.pls' },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    assert_equal "Algorithm::Caret.pls", model.algorithms[:prediction][:method]
+    cv = CrossValidation.create model
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+=end
+
+  def test_validate_proteomics_pchem_default_model
+    algorithms = {
+      :descriptors => {
+        :method => "properties",
+        :categories => ["Proteomics","P-CHEM"]
+      },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    cv = CrossValidation.create model
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+  def test_nanoparticle_fingerprint_model_without_feature_selection
+    algorithms = {
+      :descriptors => {
+        :method => "fingerprint",
+        :type => "MP2D",
+      },
+      :similarity => {
+        :method => "Algorithm::Similarity.tanimoto",
+        :min => 0.1
+      },
+      :feature_selection => nil
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    cv = CrossValidation.create model
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+  def test_nanoparticle_fingerprint_weighted_average_model_without_feature_selection
+    algorithms = {
+      :descriptors => {
+        :method => "fingerprint",
+        :type => "MP2D",
+      },
+      :similarity => {
+        :method => "Algorithm::Similarity.tanimoto",
+        :min => 0.1
+      },
+      :prediction => { :method => "OpenTox::Algorithm::Regression.weighted_average" },
+      :feature_selection => nil
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    cv = CrossValidation.create model
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+  def test_nanoparticle_fingerprint_model_with_feature_selection
+    algorithms = {
+      :descriptors => {
+        :method => "fingerprint",
+        :type => "MP2D",
+      },
+      :similarity => {
+        :method => "Algorithm::Similarity.tanimoto",
+        :min => 0.1
+      },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
+    }
+    model = Model::Lazar.create prediction_feature: @prediction_feature, training_dataset: @training_dataset, algorithms: algorithms
+    cv = CrossValidation.create model
+    refute_nil cv.r_squared
+    refute_nil cv.rmse
+  end
+
+end

data/test/validation-regression.rb

@@ -0,0 +1,92 @@
+require_relative "setup.rb"
+
+class ValidationRegressionTest < MiniTest::Test
+  include OpenTox::Validation
+
+  # defaults
+  
+  def test_default_regression_crossvalidation
+    dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv"
+    model = Model::Lazar.create training_dataset: dataset
+    cv = RegressionCrossValidation.create model
+    assert cv.rmse < 1.5, "RMSE #{cv.rmse} should be smaller than 1.5, this may occur due to unfavorable training/test set splits"
+    assert cv.mae < 1.1, "MAE #{cv.mae} should be smaller than 1.1, this may occur due to unfavorable training/test set splits"
+    assert cv.percent_within_prediction_interval > 80, "Only #{cv.percent_within_prediction_interval.round(2)}% of measurement within prediction interval. This may occur due to unfavorable training/test set splits"
+  end
+
+  # parameters
+  
+  def test_regression_crossvalidation_params
+    dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv"
+    algorithms = {
+      :prediction => { :method => "OpenTox::Algorithm::Regression.weighted_average" },
+      :descriptors => { :type => "MACCS", },
+      :similarity => {:min => 0.7}
+    }
+    model = Model::Lazar.create training_dataset: dataset, algorithms: algorithms
+    assert_equal algorithms[:descriptors][:type], model.algorithms[:descriptors][:type]
+    cv = RegressionCrossValidation.create model
+    cv.validation_ids.each do |vid|
+      model = Model::Lazar.find(Validation.find(vid).model_id)
+      assert_equal algorithms[:descriptors][:type], model.algorithms[:descriptors][:type]
+      assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min]
+      refute_nil model.training_dataset_id
+      refute_equal dataset.id, model.training_dataset_id
+    end
+
+    refute_nil cv.rmse
+    refute_nil cv.mae 
+  end
+
+  def test_physchem_regression_crossvalidation
+    training_dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
+    model = Model::Lazar.create training_dataset:training_dataset
+    cv = RegressionCrossValidation.create model
+    refute_nil cv.rmse
+    refute_nil cv.mae 
+  end
+
+  # LOO
+
+  def test_regression_loo_validation
+    dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
+    model = Model::Lazar.create training_dataset: dataset
+    loo = RegressionLeaveOneOut.create model
+    assert loo.r_squared > 0.34, "R^2 (#{loo.r_squared}) should be larger than 0.034"
+  end
+
+  def test_regression_loo_validation_with_feature_selection
+    dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
+    algorithms = {
+      :descriptors => {
+        :method => "calculate_properties",
+        :features => PhysChem.openbabel_descriptors,
+      },
+      :similarity => {
+        :method => "Algorithm::Similarity.weighted_cosine",
+        :min => 0.5
+      },
+      :feature_selection => {
+        :method => "Algorithm::FeatureSelection.correlation_filter",
+      },
+    }
+    model = Model::Lazar.create training_dataset: dataset, algorithms: algorithms
+    assert_raises OpenTox::BadRequestError do
+      loo = RegressionLeaveOneOut.create model
+    end
+  end
+
+  # repeated CV
+
+  def test_repeated_crossvalidation
+    dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
+    model = Model::Lazar.create training_dataset: dataset
+    repeated_cv = RepeatedCrossValidation.create model
+    repeated_cv.crossvalidations.each do |cv|
+      #assert cv.r_squared > 0.34, "R^2 (#{cv.r_squared}) should be larger than 0.034"
+      #assert_operator cv.accuracy, :>, 0.7, "model accuracy < 0.7, this may happen by chance due to an unfavorable training/test set split"
+    end
+    File.open("tmp.png","w+"){|f| f.puts repeated_cv.correlation_plot}
+  end
+
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lazar
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 1.0.0
 platform: ruby
 authors:
 - Christoph Helma, Martin Guetlein, Andreas Maunz, Micha Rautenberg, David Vorgrimmler,
@@ -9,98 +9,92 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-12 00:00:00.000000000 Z
+date: 2016-12-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rest-client
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rserve-client
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: mongoid
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: openbabel
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.3'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.2.2
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.3'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 2.3.2.2
+        version: '0'
 description: Libraries for lazy structure-activity relationships and read-across.
 email:
 - helma@in-silico.ch
@@ -129,11 +123,12 @@ files:
 - java/JoelibDescriptors.class
 - java/JoelibDescriptors.java
 - java/Rakefile
-- java/cdk-1.4.19.jar
+- java/cdk-2.0-SNAPSHOT.jar
 - java/joelib2.jar
 - java/log4j.jar
 - lazar.gemspec
 - lib/algorithm.rb
+- lib/caret.rb
 - lib/classification.rb
 - lib/compound.rb
 - lib/crossvalidation.rb
@@ -141,77 +136,72 @@ files:
 - lib/error.rb
 - lib/experiment.rb
 - lib/feature.rb
+- lib/feature_selection.rb
+- lib/import.rb
 - lib/lazar.rb
 - lib/leave-one-out-validation.rb
 - lib/model.rb
+- lib/nanoparticle.rb
 - lib/opentox.rb
 - lib/overwrite.rb
 - lib/physchem.rb
 - lib/regression.rb
 - lib/rest-client-wrapper.rb
+- lib/similarity.rb
+- lib/substance.rb
+- lib/train-test-validation.rb
 - lib/unique_descriptors.rb
+- lib/validation-statistics.rb
 - lib/validation.rb
+- scripts/mg2mmol.rb
+- scripts/mirror-enm2test.rb
+- scripts/mmol2-log10.rb
 - test/all.rb
-- test/classification.rb
 - test/compound.rb
-- test/data/CPDBAS_v5c_1547_29Apr2008part.sdf
-- test/data/CPDBAS_v5d_cleaned/CPDBAS_v5d_20Nov2008_mouse_TD50.csv
-- test/data/CPDBAS_v5d_cleaned/CPDBAS_v5d_20Nov2008_rat_TD50.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Hamster.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mouse.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_MultiCellCall.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_MultiCellCall_no_duplicates.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mutagenicity.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mutagenicity_no_duplicates.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Rat.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_SingleCellCall.csv
 - test/data/EPAFHM.csv
 - test/data/EPAFHM.medi.csv
+- test/data/EPAFHM.medi_log10.csv
 - test/data/EPAFHM.mini.csv
-- test/data/EPA_v4b_Fathead_Minnow_Acute_Toxicity_LC50_mmol.csv
-- test/data/FDA_v3b_Maximum_Recommended_Daily_Dose_mmol.csv
+- test/data/EPAFHM.mini_log10.csv
+- test/data/EPAFHM_log10.csv
 - test/data/ISSCAN-multi.csv
-- test/data/LOAEL_log_mg_corrected_smiles.csv
-- test/data/LOAEL_log_mmol_corrected_smiles.csv
 - test/data/LOAEL_mmol_corrected_smiles.csv
 - test/data/acetaldehyde.sdf
 - test/data/batch_prediction.csv
 - test/data/batch_prediction_inchi_small.csv
 - test/data/batch_prediction_smiles_small.csv
-- test/data/boiling_points.ext.sdf
-- test/data/cpdb_100.csv
 - test/data/hamster_carcinogenicity.csv
 - test/data/hamster_carcinogenicity.json
 - test/data/hamster_carcinogenicity.mini.bool_float.csv
 - test/data/hamster_carcinogenicity.mini.bool_int.csv
 - test/data/hamster_carcinogenicity.mini.bool_string.csv
 - test/data/hamster_carcinogenicity.mini.csv
-- test/data/hamster_carcinogenicity.ntriples
-- test/data/hamster_carcinogenicity.sdf
-- test/data/hamster_carcinogenicity.xls
-- test/data/hamster_carcinogenicity.yaml
 - test/data/hamster_carcinogenicity_with_errors.csv
 - test/data/kazius.csv
 - test/data/loael.csv
+- test/data/loael_log10.csv
 - test/data/multi_cell_call.csv
 - test/data/multi_cell_call_no_dup.csv
 - test/data/multicolumn.csv
 - test/data/rat_feature_dataset.csv
 - test/data/wrong_dataset.csv
-- test/dataset-long.rb
 - test/dataset.rb
 - test/default_environment.rb
 - test/descriptor.rb
 - test/error.rb
 - test/experiment.rb
 - test/feature.rb
-- test/lazar-long.rb
-- test/lazar-physchem-short.rb
-- test/prediction_models.rb
-- test/regression.rb
+- test/gridfs.rb
+- test/model-classification.rb
+- test/model-nanoparticle.rb
+- test/model-regression.rb
+- test/model-validation.rb
+- test/nanomaterial-model-validation.rb
 - test/setup.rb
 - test/test_environment.rb
-- test/validation.rb
+- test/validation-classification.rb
+- test/validation-nanoparticle.rb
+- test/validation-regression.rb
 homepage: http://github.com/opentox/lazar
 licenses:
 - GPL-3.0
@@ -236,65 +226,4 @@ rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Lazar framework
-test_files:
-- test/all.rb
-- test/classification.rb
-- test/compound.rb
-- test/data/CPDBAS_v5c_1547_29Apr2008part.sdf
-- test/data/CPDBAS_v5d_cleaned/CPDBAS_v5d_20Nov2008_mouse_TD50.csv
-- test/data/CPDBAS_v5d_cleaned/CPDBAS_v5d_20Nov2008_rat_TD50.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Hamster.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mouse.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_MultiCellCall.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_MultiCellCall_no_duplicates.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mutagenicity.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Mutagenicity_no_duplicates.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_Rat.csv
-- test/data/CPDBAS_v5d_cleaned/DSSTox_Carcinogenic_Potency_DBS_SingleCellCall.csv
-- test/data/EPAFHM.csv
-- test/data/EPAFHM.medi.csv
-- test/data/EPAFHM.mini.csv
-- test/data/EPA_v4b_Fathead_Minnow_Acute_Toxicity_LC50_mmol.csv
-- test/data/FDA_v3b_Maximum_Recommended_Daily_Dose_mmol.csv
-- test/data/ISSCAN-multi.csv
-- test/data/LOAEL_log_mg_corrected_smiles.csv
-- test/data/LOAEL_log_mmol_corrected_smiles.csv
-- test/data/LOAEL_mmol_corrected_smiles.csv
-- test/data/acetaldehyde.sdf
-- test/data/batch_prediction.csv
-- test/data/batch_prediction_inchi_small.csv
-- test/data/batch_prediction_smiles_small.csv
-- test/data/boiling_points.ext.sdf
-- test/data/cpdb_100.csv
-- test/data/hamster_carcinogenicity.csv
-- test/data/hamster_carcinogenicity.json
-- test/data/hamster_carcinogenicity.mini.bool_float.csv
-- test/data/hamster_carcinogenicity.mini.bool_int.csv
-- test/data/hamster_carcinogenicity.mini.bool_string.csv
-- test/data/hamster_carcinogenicity.mini.csv
-- test/data/hamster_carcinogenicity.ntriples
-- test/data/hamster_carcinogenicity.sdf
-- test/data/hamster_carcinogenicity.xls
-- test/data/hamster_carcinogenicity.yaml
-- test/data/hamster_carcinogenicity_with_errors.csv
-- test/data/kazius.csv
-- test/data/loael.csv
-- test/data/multi_cell_call.csv
-- test/data/multi_cell_call_no_dup.csv
-- test/data/multicolumn.csv
-- test/data/rat_feature_dataset.csv
-- test/data/wrong_dataset.csv
-- test/dataset-long.rb
-- test/dataset.rb
-- test/default_environment.rb
-- test/descriptor.rb
-- test/error.rb
-- test/experiment.rb
-- test/feature.rb
-- test/lazar-long.rb
-- test/lazar-physchem-short.rb
-- test/prediction_models.rb
-- test/regression.rb
-- test/setup.rb
-- test/test_environment.rb
-- test/validation.rb
+test_files: []

data/test/classification.rb

@@ -1,41 +0,0 @@
-require_relative "setup.rb"
-
-class LazarClassificationTest < MiniTest::Test
-
-  def test_lazar_classification
-    training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"hamster_carcinogenicity.csv")
-    model = Model::LazarClassification.create training_dataset
-
-    [ {
-      :compound => OpenTox::Compound.from_inchi("InChI=1S/C6H6/c1-2-4-6-5-3-1/h1-6H"),
-      :prediction => "false",
-      :confidence => 0.25281385281385277,
-      :nr_neighbors => 11
-    },{
-      :compound => OpenTox::Compound.from_smiles("c1ccccc1NN"),
-      :prediction => "false",
-      :confidence => 0.3639589577089577,
-      :nr_neighbors => 14
-    } ].each do |example|
-      prediction = model.predict example[:compound]
-      assert_equal example[:prediction], prediction[:value]
-      #assert_equal example[:confidence], prediction[:confidence]
-      #assert_equal example[:nr_neighbors], prediction[:neighbors].size
-    end
-
-    compound = Compound.from_smiles "CCO"
-    prediction = model.predict compound
-    assert_equal ["false"], prediction[:database_activities]
-    assert_equal "true", prediction[:value]
-
-    # make a dataset prediction
-    compound_dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini.csv")
-    prediction = model.predict compound_dataset
-    assert_equal compound_dataset.compounds, prediction.compounds
-
-    assert_equal "Could not find similar compounds with experimental data in the training dataset.", prediction.data_entries[7][3]
-    assert_equal "1 compounds have been removed from neighbors, because they have the same structure as the query compound.", prediction.data_entries[14][3]
-    # cleanup
-    [training_dataset,model,compound_dataset].each{|o| o.delete}
-  end
-end