summaryrefslogtreecommitdiff
path: root/test/regression-model.rb
blob: f09a0fb88b9ee1ba664bdaab9a7d48e21ecaf4c0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
require_relative "setup.rb"

class LazarRegressionTest < MiniTest::Test

  def test_default_regression
    algorithms = {
      :descriptors => {
        :method => "fingerprint",
        :type => "MP2D"
      },
      :similarity => {
        :method => "Algorithm::Similarity.tanimoto",
        :min => [0.5,0.2]
      },
      :prediction => {
        :method => "Algorithm::Caret.rf",
      },
      :feature_selection => nil,
    }
    training_dataset = Dataset.from_csv_file File.join(Download::DATA, "Acute_toxicity-Fathead_minnow.csv")
    model = Model::Lazar.create  training_dataset: training_dataset
    assert_kind_of Model::LazarRegression, model
    assert_equal algorithms, model.algorithms
    substance = training_dataset.substances[145]
    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 "c1ccc(cc1)Oc1ccccc1"
    prediction = model.predict substance
    refute_nil prediction[:value]
    refute_nil prediction[:prediction_interval]
    refute_empty prediction[:neighbors]
  end

  def test_weighted_average
    training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi_log10.csv"
    algorithms = {
      :similarity => {
        :min => [0,0]
      },
      :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 model.substance_ids.size, prediction[:neighbors].size
  end

  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 3, prediction[:neighbors].size
    assert prediction[:value].round(2) > 1.37, "Prediction value (#{prediction[:value].round(2)}) should be larger than 1.37."
  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 => [0.5,0.1]
      },
    }
    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 => [0.5,0.1]
      },
      :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",
        :features => PhysChem.openbabel_descriptors,
      },
      :similarity => {
        :method => "Algorithm::Similarity.cosine",
      }
    }
    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::Caret.rf", model.algorithms[:prediction][:method]
    assert_equal "Algorithm::Similarity.cosine", model.algorithms[:similarity][:method]
    assert_equal 0.5, model.algorithms[:similarity][:min].first
    algorithms[:descriptors].delete :features
    assert_equal algorithms[:descriptors], model.algorithms[:descriptors]
    prediction = model.predict training_dataset.substances[10]
    refute_nil prediction[:value]
  end

  def test_regression_with_feature_selection
    algorithms = {
      :feature_selection => {
        :method => "Algorithm::FeatureSelection.correlation_filter",
      },
    }
    training_dataset = Dataset.from_csv_file File.join(Download::DATA, "Acute_toxicity-Fathead_minnow.csv")
    model = Model::Lazar.create  training_dataset: training_dataset, algorithms: algorithms
    assert_kind_of Model::LazarRegression, model
    assert_equal "Algorithm::Caret.rf", model.algorithms[:prediction][:method]
    assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method]
    assert_equal 0.5, model.algorithms[:similarity][:min].first
    assert_equal algorithms[:feature_selection][:method], model.algorithms[:feature_selection][:method]
    prediction = model.predict training_dataset.substances[145]
    refute_nil prediction[:value]
  end

  def test_regression_parameters
    algorithms = {
      :descriptors => {
        :method => "fingerprint",
        :type => "MP2D"
      },
      :similarity => {
        :method => "Algorithm::Similarity.tanimoto",
        :min => [0.3,0.1]
      },
      :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

  def test_dataset_prediction
    training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.medi_log10.csv")
    model = Model::Lazar.create training_dataset: training_dataset
    result = model.predict training_dataset
    assert_kind_of Dataset, result
    assert_equal 8, result.features.size
    assert_equal 88, result.compounds.size
    assert_equal [1.95], result.values(result.compounds.first, result.bioactivity_features[0]).collect{|v| v.round(2)}
    assert_equal [1.37], result.values(result.compounds[6], result.bioactivity_features[0]).collect{|v| v.round(2)}
    assert_equal [1.79], result.values(result.compounds[6], result.prediction_feature).collect{|v| v.round(2)}
    assert_equal [1.84,1.73], result.values(result.compounds[7], result.bioactivity_features[0]).collect{|v| v.round(2)}
    assert_match /Low/i, result.predictions[result.compounds[6]][:confidence]
    csv = result.to_prediction_csv
    rows = csv.split("\n")
    assert_equal "ID,Original SMILES,Canonical SMILES,Prediction,Confidence,Lower prediction interval,Upper prediction interval,Measurements", rows[0]
    items = rows[3].split(",")
    # prediction and measurement within prediciton interval
    prediction = items[3].to_f
    pi_low = items[5].to_f
    pi_hi = items[6].to_f
    measurement = items[7].to_f
    [prediction,measurement].each do |v|
      assert(v > pi_low)
      assert(v < pi_hi)
    end
  end

  def test_fhm_prediction
    training_dataset = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","data","Acute_toxicity-Fathead_minnow.csv")
    model = Model::Lazar.create training_dataset: training_dataset
    prediction = model.predict Compound.from_smiles("N=Nc1ccccc1")
    assert_equal 0.65, prediction[:neighbors][0][:measurement].round(2)
  end

end