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
|
require_relative "setup.rb"
class ModelTest < MiniTest::Test
def test_default_regression
algorithms = {
:descriptors => {
:method => "fingerprint",
:type => "MP2D"
},
:similarity => {
:method => "Algorithm::Similarity.tanimoto",
:min => 0.1
},
:prediction => {
:method => "Algorithm::Caret.regression",
:parameters => "pls",
},
: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
assert_kind_of Model::LazarRegression, model
assert_equal algorithms, model.algorithms
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."
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",
:parameters => "rf",
},
: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_physchem_regression
algorithms = {
:descriptors => "physchem",
:similarity => {
:method => "Algorithm::Similarity.weighted_cosine",
}
}
training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini_log10.csv")
model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms
assert_kind_of Model::LazarRegression, model
assert_equal "Algorithm::Caret.regression", model.algorithms[:prediction][:method]
assert_equal "Algorithm::Similarity.weighted_cosine", model.algorithms[:similarity][:method]
assert_equal 0.1, model.algorithms[:similarity][:min]
assert_equal algorithms[:descriptors], model.algorithms[:descriptors]
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.regression", model.algorithms[:prediction][:method]
assert_equal "rf", model.algorithms[:prediction][:parameters]
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 => {
:method => "Algorithm::FeatureSelection.correlation_filter",
},
}
training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"EPAFHM.mini_log10.csv")
model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms
assert_kind_of Model::LazarRegression, model
assert_equal "Algorithm::Caret.regression", model.algorithms[:prediction][:method]
assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method]
assert_equal 0.1, model.algorithms[:similarity][:min]
assert_equal algorithms[:feature_selection][:method], model.algorithms[:feature_selection][:method]
end
def test_caret_parameters
skip
end
def test_default_classification
algorithms = {
:descriptors => {
:method => "fingerprint",
:type => 'MP2D',
},
:similarity => {
:method => "Algorithm::Similarity.tanimoto",
:min => 0.1
},
:prediction => {
:method => "Algorithm::Classification.weighted_majority_vote",
},
:feature_selection => nil,
}
training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"hamster_carcinogenicity.csv")
model = Model::Lazar.create training_dataset: training_dataset
assert_kind_of Model::LazarClassification, model
assert_equal algorithms, model.algorithms
substance = training_dataset.substances[10]
prediction = model.predict substance
assert_equal "false", prediction[:value]
end
def test_classification_parameters
algorithms = {
:descriptors => {
:method => "fingerprint",
:type => 'MACCS',
},
:similarity => {
:min => 0.4
},
}
training_dataset = Dataset.from_csv_file File.join(DATA_DIR,"hamster_carcinogenicity.csv")
model = Model::Lazar.create training_dataset: training_dataset, algorithms: algorithms
assert_kind_of Model::LazarClassification, model
assert_equal "Algorithm::Classification.weighted_majority_vote", model.algorithms[:prediction][:method]
assert_equal "Algorithm::Similarity.tanimoto", model.algorithms[:similarity][:method]
assert_equal algorithms[:similarity][:min], model.algorithms[:similarity][:min]
substance = training_dataset.substances[10]
prediction = model.predict substance
assert_equal "false", prediction[:value]
assert_equal 4, prediction[:neighbors].size
end
end
|
