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
|
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
|
