diff options
-rw-r--r-- | lib/model.rb | 40 | ||||
-rw-r--r-- | lib/similarity.rb | 1 | ||||
-rw-r--r-- | test/model-nanoparticle.rb | 42 | ||||
-rw-r--r-- | test/model-regression.rb (renamed from test/model.rb) | 136 | ||||
-rw-r--r-- | test/regression.rb | 86 | ||||
-rw-r--r-- | test/validation-nanoparticle.rb (renamed from test/nanoparticles.rb) | 12 |
6 files changed, 169 insertions, 148 deletions
diff --git a/lib/model.rb b/lib/model.rb index b949042..4bbb7da 100644 --- a/lib/model.rb +++ b/lib/model.rb @@ -82,7 +82,7 @@ module OpenTox model.algorithms = { :descriptors => { :method => "properties", - :category => "P-CHEM", + :categories => ["P-CHEM"], }, #:descriptors => ["P-CHEM","Proteomics"], :similarity => { @@ -150,9 +150,14 @@ module OpenTox end # parse independent_variables when "properties" + categories = model.algorithms[:descriptors][:categories] + feature_ids = [] + categories.each do |category| + Feature.where(category:category).each{|f| feature_ids << f.id.to_s} + end properties = model.substances.collect { |s| s.properties } - all_property_ids = properties.collect{|p| p.keys}.flatten.uniq - model.descriptor_ids = all_property_ids.select{|id| model.algorithms[:descriptors].include? Feature.find(id).category } + property_ids = properties.collect{|p| p.keys}.flatten.uniq + model.descriptor_ids = feature_ids & property_ids model.independent_variables = model.descriptor_ids.collect{|i| properties.collect{|p| p[i] ? p[i].median : nil}} else bad_request_error "Descriptor method '#{descriptor_method}' not implemented." @@ -180,18 +185,25 @@ module OpenTox when /tanimoto/ # binary features similarity_descriptors = substance.fingerprint algorithms[:descriptors][:type] # TODO this excludes descriptors only present in the query substance + # use for applicability domain? query_descriptors = descriptor_ids.collect{|id| similarity_descriptors.include? id} when /euclid|cosine/ # quantitative features - similarity_descriptors = descriptor_ids.collect_with_index{|id,i| - prop = substance.properties[id] - prop = prop.median if prop.is_a? Array # measured - (prop-descriptor_means[i])/descriptor_sds[i] - } - query_descriptors = descriptor_ids.collect_with_index{|id,i| - prop = substance.properties[id] - prop = prop.median if prop.is_a? Array # measured - substance.properties[id] - } + if algorithms[:descriptors][:method] == "calculate_properties" # calculate descriptors + features = descriptor_ids.collect{|id| Feature.find(id)} + query_descriptors = substance.calculate_properties(features) + similarity_descriptors = query_descriptors.collect_with_index{|v,i| (v-descriptor_means[i])/descriptor_sds[i]} + else + similarity_descriptors = descriptor_ids.collect_with_index{|id,i| + prop = substance.properties[id] + prop = prop.median if prop.is_a? Array # measured + (prop-descriptor_means[i])/descriptor_sds[i] + } + query_descriptors = descriptor_ids.collect_with_index{|id,i| + prop = substance.properties[id] + prop = prop.median if prop.is_a? Array # measured + substance.properties[id] + } + end else bad_request_error "Unknown descriptor type '#{descriptors}' for similarity method '#{similarity[:method]}'." end @@ -218,7 +230,7 @@ module OpenTox neighbor_descriptors = scaled_variables.collect{|v| v[i]} end sim = Algorithm.run algorithms[:similarity][:method], [similarity_descriptors, neighbor_descriptors, descriptor_weights] - if sim > algorithms[:similarity][:min] + if sim >= algorithms[:similarity][:min] neighbor_ids << s neighbor_similarities << sim neighbor_dependent_variables << dependent_variables[i] diff --git a/lib/similarity.rb b/lib/similarity.rb index 328d42a..772e812 100644 --- a/lib/similarity.rb +++ b/lib/similarity.rb @@ -32,6 +32,7 @@ module OpenTox def self.weighted_cosine scaled_properties # [a,b,weights] a,b,w = remove_nils scaled_properties + return cosine(scaled_properties) if w.uniq.size == 1 dot_product = 0 magnitude_a = 0 magnitude_b = 0 diff --git a/test/model-nanoparticle.rb b/test/model-nanoparticle.rb new file mode 100644 index 0000000..fb81b83 --- /dev/null +++ b/test/model-nanoparticle.rb @@ -0,0 +1,42 @@ +require_relative "setup.rb" + +class NanoparticleTest < 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 + unless @training_dataset + Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm") + @training_dataset = Dataset.where(name: "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first + end + @prediction_feature = @training_dataset.features.select{|f| f["name"] == 'log2(Net cell association)'}.first + end + + def test_nanoparticle_model + assert true, @prediction_feature.measured + model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature + refute_empty model.dependent_variables + refute_empty model.descriptor_ids + refute_empty model.independent_variables + assert_equal "Algorithm::Caret.rf", model.algorithms[:prediction][:method] + assert_equal "Algorithm::Similarity.weighted_cosine", model.algorithms[:similarity][:method] + nanoparticle = @training_dataset.nanoparticles[-34] + assert_includes nanoparticle.dataset_ids, @training_dataset.id + prediction = model.predict nanoparticle + refute_nil prediction[:value] + assert_includes prediction[:prediction_interval][0]..prediction[:prediction_interval][1], prediction[:measurements].median, "This assertion assures that measured values are within the prediction interval. It may fail in 5% of the predictions." + prediction = model.predict @training_dataset.substances[14] + refute_nil prediction[:value] + assert_includes prediction[:prediction_interval][0]..prediction[:prediction_interval][1], prediction[:measurements].median, "This assertion assures that measured values are within the prediction interval. It may fail in 5% of the predictions." + model.delete + end + + def test_nanoparticle_parameters + skip + end + + def test_import_ld + skip # Ambit JSON-LD export defunct + dataset_ids = Import::Enanomapper.import_ld + end +end diff --git a/test/model.rb b/test/model-regression.rb index 027efe4..644ca1c 100644 --- a/test/model.rb +++ b/test/model-regression.rb @@ -1,10 +1,13 @@ require_relative "setup.rb" -class ModelTest < MiniTest::Test +class LazarRegressionTest < MiniTest::Test def test_default_regression algorithms = { - :descriptors => [ "MP2D" ], + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, :similarity => { :method => "Algorithm::Similarity.tanimoto", :min => 0.1 @@ -21,33 +24,85 @@ class ModelTest < MiniTest::Test substance = training_dataset.substances[10] prediction = model.predict substance assert_includes prediction[:prediction_interval][0]..prediction[:prediction_interval][1], prediction[:measurements].median, "This assertion assures that measured values are within the prediction interval. It may fail in 5% of the predictions." + substance = Compound.from_smiles "NC(=O)OCCC" + prediction = model.predict substance + refute_nil prediction[:value] + refute_nil prediction[:prediction_interval] + refute_empty prediction[:neighbors] end - def test_regression_parameters + def test_weighted_average + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" algorithms = { - :descriptors => [ "MP2D" ], :similarity => { - :method => "Algorithm::Similarity.tanimoto", - :min => 0.3 + :min => 0 }, :prediction => { :method => "Algorithm::Regression.weighted_average", }, - :feature_selection => nil, } - training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv") - model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms - assert_kind_of Model::LazarRegression, model - assert_equal "Algorithm::Regression.weighted_average", model.algorithms[:prediction][:method] - assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method] - assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min] - assert_equal algorithms[:prediction][:parameters], model.algorithms[:prediction][:parameters] - substance = training_dataset.substances[10] - prediction = model.predict substance - assert_equal 0.83, prediction[:value].round(2) + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + compound = Compound.from_smiles "CC(C)(C)CN" + prediction = model.predict compound + assert_equal -0.86, prediction[:value].round(2) + assert_equal model.substance_ids.size, prediction[:neighbors].size end - def test_physchem_regression + def test_mpd_fingerprints + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, + } + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + compound = Compound.from_smiles "CCCSCCSCC" + prediction = model.predict compound + assert_equal 4, prediction[:neighbors].size + assert_equal 1.37, prediction[:value].round(2) + end + + def test_local_physchem_regression + training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" + algorithms = { + :descriptors => { + :method => "calculate_properties", + :features => PhysChem.openbabel_descriptors, + }, + :similarity => { + :method => "Algorithm::Similarity.weighted_cosine", + :min => 0.5 + }, + } + model = Model::Lazar.create(training_dataset:training_dataset, algorithms:algorithms) + compound = Compound.from_smiles "NC(=O)OCCC" + prediction = model.predict compound + refute_nil prediction[:value] + end + + def test_local_physchem_regression_with_feature_selection + training_dataset = Dataset.from_csv_file "#{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:training_dataset, algorithms:algorithms) + compound = Compound.from_smiles "NC(=O)OCCC" + prediction = model.predict compound + refute_nil prediction[:value] + end + + def test_unweighted_cosine_physchem_regression algorithms = { :descriptors => { :method => "calculate_properties", @@ -70,24 +125,6 @@ class ModelTest < MiniTest::Test # TODO test predictin end - def test_nanoparticle_default - training_dataset = Dataset.where(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first - unless training_dataset - Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm") - training_dataset = Dataset.where(name: "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles").first - end - model = Model::Lazar.create training_dataset: training_dataset - assert_equal "Algorithm::Caret.rf", model.algorithms[:prediction][:method] - assert_equal "Algorithm::Similarity.weighted_cosine", model.algorithms[:similarity][:method] - prediction = model.predict training_dataset.substances[14] - assert_includes prediction[:prediction_interval][0]..prediction[:prediction_interval][1], prediction[:measurements].median, "This assertion assures that measured values are within the prediction interval. It may fail in 5% of the predictions." - - end - - def test_nanoparticle_parameters - skip - end - def test_regression_with_feature_selection algorithms = { :feature_selection => { @@ -103,4 +140,31 @@ class ModelTest < MiniTest::Test assert_equal algorithms[:feature_selection][:method], model.algorithms[:feature_selection][:method] end + def test_regression_parameters + algorithms = { + :descriptors => { + :method => "fingerprint", + :type => "MP2D" + }, + :similarity => { + :method => "Algorithm::Similarity.tanimoto", + :min => 0.3 + }, + :prediction => { + :method => "Algorithm::Regression.weighted_average", + }, + :feature_selection => nil, + } + training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv") + model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms + assert_kind_of Model::LazarRegression, model + assert_equal "Algorithm::Regression.weighted_average", model.algorithms[:prediction][:method] + assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method] + assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min] + assert_equal algorithms[:prediction][:parameters], model.algorithms[:prediction][:parameters] + substance = training_dataset.substances[10] + prediction = model.predict substance + assert_equal 0.83, prediction[:value].round(2) + end + end diff --git a/test/regression.rb b/test/regression.rb deleted file mode 100644 index cdbac4b..0000000 --- a/test/regression.rb +++ /dev/null @@ -1,86 +0,0 @@ -require_relative "setup.rb" - -class LazarRegressionTest < MiniTest::Test - - def test_weighted_average - training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" - algorithms = { - :similarity => { - :min => 0 - }, - :prediction => { - :method => "Algorithm::Regression.weighted_average", - }, - } - model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms - compound = Compound.from_smiles "CC(C)(C)CN" - prediction = model.predict compound - assert_equal -0.86, prediction[:value].round(2) - assert_equal 88, prediction[:neighbors].size - end - - def test_mpd_fingerprints - training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" - algorithms = { - :descriptors => [ "MP2D" ] - } - model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms - compound = Compound.from_smiles "CCCSCCSCC" - prediction = model.predict compound - assert_equal 3, prediction[:neighbors].size - assert_equal 1.37, prediction[:value].round(2) - end - - def test_local_fingerprint_regression - training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" - model = Model::Lazar.create training_dataset: training_dataset - compound = Compound.from_smiles "NC(=O)OCCC" - prediction = model.predict compound - refute_nil prediction[:value] - refute_nil prediction[:prediction_interval] - refute_empty prediction[:neighbors] - end - - def test_local_physchem_regression - training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" - algorithms = { - :descriptors => [PhysChem::OPENBABEL], - :similarity => { - :method => "Algorithm::Similarity.weighted_cosine", - :min => 0.5 - }, - } - model = Model::Lazar.create(training_dataset:training_dataset, algorithms:algorithms) - p model - compound = Compound.from_smiles "NC(=O)OCCC" - prediction = model.predict compound - refute_nil prediction[:value] - end - - def test_local_physchem_regression_with_feature_selection - training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv" - algorithms = { - :descriptors => { - :method => "calculated_properties", - :types => ["OPENBABEL"] - }, - :similarity => { - :method => "Algorithm::Similarity.weighted_cosine", - :min => 0.5 - }, - :feature_selection => { - :method => "Algorithm::FeatureSelection.correlation_filter", - }, - } - model = Model::Lazar.create(training_dataset.features.first, training_dataset, algorithms) - p model - compound = Compound.from_smiles "NC(=O)OCCC" - prediction = model.predict compound - refute_nil prediction[:value] - end - - def test_local_physchem_classification - skip - end - -end diff --git a/test/nanoparticles.rb b/test/validation-nanoparticle.rb index 9a67e63..3692515 100644 --- a/test/nanoparticles.rb +++ b/test/validation-nanoparticle.rb @@ -12,18 +12,6 @@ class NanoparticleTest < MiniTest::Test @prediction_feature = @training_dataset.features.select{|f| f["name"] == 'log2(Net cell association)'}.first end - def test_nanoparticle_model - model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature - nanoparticle = @training_dataset.nanoparticles[-34] - prediction = model.predict nanoparticle - refute_nil prediction[:value] - assert_includes nanoparticle.dataset_ids, @training_dataset.id - assert true, @prediction_feature.measured - model.delete - end - - # validations - def test_validate_default_nanoparticle_model model = Model::Lazar.create training_dataset: @training_dataset, prediction_feature: @prediction_feature cv = CrossValidation.create model |