lazar 0.0.1

data/test/lazar-long.rb

@@ -0,0 +1,72 @@
+require_relative "setup.rb"
+
+class LazarExtendedTest < MiniTest::Test
+
+  def test_lazar_bbrc_ham_minfreq
+    dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"hamster_carcinogenicity.csv")
+    model = OpenTox::Model::Lazar.create dataset, OpenTox::Algorithm::Fminer.bbrc(dataset, :min_frequency => 5)
+    feature_dataset = OpenTox::Dataset.find model.feature_dataset_id
+    assert_equal dataset.compounds.size, feature_dataset.compounds.size
+    assert_equal 41, feature_dataset.features.size
+    assert_equal 'N-C=N', feature_dataset.features.first.smarts
+    compound = OpenTox::Compound.from_inchi("InChI=1S/C6H6/c1-2-4-6-5-3-1/h1-6H")
+    prediction = model.predict compound
+    assert_equal "false", prediction[:value]
+    assert_equal 0.12380952380952381, prediction[:confidence]
+    dataset.delete
+    model.delete
+    feature_dataset.delete
+  end
+
+  def test_lazar_bbrc_large_ds
+    # TODO fminer crashes with these settings
+    skip "it seems that fminer aborts without further notice"
+    dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"multi_cell_call_no_dup.csv")
+    feature_dataset = OpenTox::Algorithm::Fminer.bbrc dataset#, :min_frequency => 15)
+    model = OpenTox::Model::Lazar.create dataset, feature_dataset
+    model.save
+    p model.id
+    feature_dataset = OpenTox::CalculatedDataset.find model.feature_dataset_id
+    assert_equal dataset.compounds.size, feature_dataset.compounds.size
+    assert_equal 52, feature_dataset.features.size
+    assert_equal '[#17&A]-[#6&A]', feature_dataset.features.first.title
+    compound = OpenTox::Compound.from_inchi("InChI=1S/C10H9NO2S/c1-8-2-4-9(5-3-8)13-6-10(12)11-7-14/h2-5H,6H2,1H3")
+    prediction_dataset = model.predict compound
+    prediction = prediction_dataset.data_entries.first
+    assert_in_delta 0.025, prediction[:confidence], 0.001
+    #assert_equal 0.025885845574483608, prediction[:confidence]
+    # with compound change in training_dataset see:
+    # https://github.com/opentox/opentox-test/commit/0e78c9c59d087adbd4cc58bab60fb29cbe0c1da0
+    #assert_equal 0.02422364949075546, prediction[:confidence]
+    dataset.delete
+    model.delete
+    feature_dataset.delete
+    prediction_dataset.delete
+  end
+
+  def test_lazar_kazius
+    t = Time.now
+    dataset = Dataset.from_csv_file File.join(DATA_DIR,"kazius.csv")
+    p "Dataset upload: #{Time.now-t}"
+    t = Time.now
+    feature_dataset = Algorithm::Fminer.bbrc(dataset, :min_frequency => 100)
+    p "Feature mining: #{Time.now-t}"
+    t = Time.now
+    assert_equal feature_dataset.compounds.size, dataset.compounds.size
+    model = Model::Lazar.create dataset, feature_dataset
+=begin
+=end
+    #model = Model::Lazar.find('55bcf5bf7a7838381200017e')
+    #p model.id
+    #prediction_times = []
+    2.times do
+      compound = Compound.from_smiles("Clc1ccccc1NN")
+      prediction = model.predict compound
+      assert_equal "1", prediction[:value]
+      assert_in_delta 0.019858401199860445, prediction[:confidence], 0.001
+    end
+    #dataset.delete
+    #feature_dataset.delete
+  end
+
+end

data/test/lazar-physchem-short.rb

@@ -0,0 +1,27 @@
+require_relative "setup.rb"
+
+class LazarPhyschemDescriptorTest < MiniTest::Test
+  def test_epafhm
+    # check available descriptors
+    @descriptors = OpenTox::Algorithm::Descriptor::DESCRIPTORS.keys
+    assert_equal 111,@descriptors.size,"wrong number of physchem descriptors"
+    @descriptor_values = OpenTox::Algorithm::Descriptor::DESCRIPTOR_VALUES
+
+    # select descriptors for test
+    @num_features_offset = 0
+    @descriptors.keep_if{|x| x=~/^Openbabel\./}
+    @descriptors.delete("Openbabel.L5") # TODO Openbabel.L5 does not work, investigate!!!
+    puts "Descriptors: #{@descriptors}"
+
+    # UPLOAD DATA
+    training_dataset = OpenTox::Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi.csv")
+    puts "Dataset: "+training_dataset.id
+#    feature_dataset = Algorithm::Descriptor.physchem training_dataset, @descriptors
+    model = Model::LazarRegression.create training_dataset#, feature_dataset
+    #p model
+    compound = Compound.from_smiles "CC(C)(C)CN"
+    prediction = model.predict compound
+    p prediction
+
+  end
+end

data/test/setup.rb

@@ -0,0 +1,6 @@
+require 'minitest/autorun'
+require_relative '../lib/lazar.rb'
+include OpenTox
+TEST_DIR ||= File.expand_path(File.dirname(__FILE__))
+DATA_DIR ||= File.join(TEST_DIR,"data")
+#$mongo.database.drop

data/test/validation.rb

@@ -0,0 +1,41 @@
+require_relative "setup.rb"
+
+class ValidationTest < MiniTest::Test
+
+  def test_fminer_crossvalidation
+    dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
+    model = Model::LazarFminerClassification.create dataset#, features
+    cv = ClassificationCrossValidation.create model
+    p cv.accuracy
+    p cv.weighted_accuracy
+    assert cv.accuracy > 0.8
+    assert cv.weighted_accuracy > cv.accuracy, "Weighted accuracy (#{cv.weighted_accuracy}) larger than unweighted accuracy(#{cv.accuracy}) "
+  end
+
+  def test_classification_crossvalidation
+    dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
+    model = Model::LazarClassification.create dataset#, features
+    cv = ClassificationCrossValidation.create model
+    p cv.accuracy
+    p cv.weighted_accuracy
+    assert cv.accuracy > 0.7
+    assert cv.weighted_accuracy > cv.accuracy, "Weighted accuracy should be larger than unweighted accuracy."
+  end
+
+  def test_regression_crossvalidation
+    dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi.csv"
+    #dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.csv"
+    model = Model::LazarRegression.create dataset
+    cv = RegressionCrossValidation.create model
+    p cv.rmse 
+    p cv.weighted_rmse
+    p cv.mae
+    p cv.weighted_mae
+    `inkview #{cv.plot}`
+    assert cv.rmse < 30, "RMSE > 30"
+    assert cv.weighted_rmse < cv.rmse, "Weighted RMSE (#{cv.weighted_rmse}) larger than unweighted RMSE(#{cv.rmse}) "
+    assert cv.mae < 12
+    assert cv.weighted_mae < cv.mae
+  end
+
+end

metadata

@@ -0,0 +1,212 @@
+--- !ruby/object:Gem::Specification
+name: lazar
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Christoph Helma, Martin Guetlein, Andreas Maunz, Micha Rautenberg, David Vorgrimmler,
+  Denis Gebele
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-08-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rest-client
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rserve-client
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mongoid
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.0beta
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.0beta
+description: Libraries for lazy structure-activity relationships and read-across.
+email:
+- helma@in-silico.ch
+executables: []
+extensions:
+- ext/lazar/extconf.rb
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".yardopts"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- VERSION
+- ext/lazar/extconf.rb
+- java/CdkDescriptorInfo.class
+- java/CdkDescriptorInfo.java
+- java/CdkDescriptors.class
+- java/CdkDescriptors.java
+- java/Jmol.jar
+- java/JoelibDescriptorInfo.class
+- java/JoelibDescriptorInfo.java
+- java/JoelibDescriptors.class
+- java/JoelibDescriptors.java
+- java/Rakefile
+- java/cdk-1.4.19.jar
+- java/joelib2.jar
+- java/log4j.jar
+- lazar.gemspec
+- lib/SMARTS_InteLigand.txt
+- lib/algorithm.rb
+- lib/bbrc.rb
+- lib/classification.rb
+- lib/compound.rb
+- lib/crossvalidation.rb
+- lib/dataset.rb
+- lib/descriptor.rb
+- lib/error.rb
+- lib/feature.rb
+- lib/lazar-model.rb
+- lib/lazar.rb
+- lib/neighbor.rb
+- lib/opentox.rb
+- lib/overwrite.rb
+- lib/regression.rb
+- lib/rest-client-wrapper.rb
+- lib/similarity.rb
+- lib/unique_descriptors.rb
+- lib/validation.rb
+- mongoid.yml
+- test/all.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/acetaldehyde.sdf
+- test/data/boiling_points.ext.sdf
+- test/data/cpdb_100.csv
+- test/data/hamster_carcinogenicity.csv
+- 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/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/descriptor-long.rb
+- test/descriptor.rb
+- test/error.rb
+- test/feature.rb
+- test/fminer-long.rb
+- test/fminer.rb
+- test/lazar-fminer.rb
+- test/lazar-long.rb
+- test/lazar-physchem-short.rb
+- test/setup.rb
+- test/validation.rb
+homepage: http://github.com/opentox/lazar
+licenses:
+- GPL-3
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: lazar
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Lazar framework
+test_files: []