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
|
require_relative "setup.rb"
class NanoparticleTest < MiniTest::Test
include OpenTox::Validation
def setup
# TODO: multiple runs create duplicates
#Import::Enanomapper.import File.join(File.dirname(__FILE__),"data","enm")
end
def test_create_model_with_feature_selection
skip
training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
model = Model::LazarRegression.create(feature, training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average", :neighbor_algorithm => "physchem_neighbors", :feature_selection_algorithm => "correlation_filter"})
nanoparticle = training_dataset.nanoparticles[-34]
#p nanoparticle.neighbors
prediction = model.predict nanoparticle
p prediction
#p prediction
refute_nil prediction[:value]
end
def test_create_model
skip
training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
model = Model::LazarRegression.create(feature, training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average", :neighbor_algorithm => "physchem_neighbors"})
nanoparticle = training_dataset.nanoparticles[-34]
prediction = model.predict nanoparticle
refute_nil prediction[:value]
assert_includes nanoparticle.dataset_ids, training_dataset.id
model.delete
end
# TODO move to validation-statistics
def test_inspect_cv
cv = CrossValidation.all.sort_by{|cv| cv.created_at}.last
cv.correlation_plot_id = nil
File.open("tmp.pdf","w+"){|f| f.puts cv.correlation_plot}
p cv.statistics
end
def test_inspect_worst_prediction
cv = CrossValidation.all.sort_by{|cv| cv.created_at}.last
worst_predictions = cv.worst_predictions(n: 3,show_neigbors: false)
assert_equal 3, worst_predictions.size
assert_kind_of Integer, worst_predictions.first[:neighbors]
worst_predictions = cv.worst_predictions
#puts worst_predictions.to_yaml
assert_equal 5, worst_predictions.size
assert_kind_of Array, worst_predictions.first[:neighbors]
assert_kind_of Integer, worst_predictions.first[:neighbors].first[:common_descriptors]
worst_predictions = cv.worst_predictions(n: 2, show_common_descriptors: true)
puts worst_predictions.to_yaml
assert_equal 2, worst_predictions.size
assert_kind_of Array, worst_predictions.first[:neighbors]
refute_nil worst_predictions.first[:neighbors].first[:common_descriptors]
#p cv.model.training_dataset.features
end
def test_validate_model
training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
#feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
model = Model::LazarRegression.create(feature, training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_weighted_average", :neighbor_algorithm => "physchem_neighbors", :neighbor_algorithm_parameters => {:min_sim => 0.5}})
cv = RegressionCrossValidation.create model
p cv
#p cv.predictions.sort_by{|sid,p| (p["value"] - p["measurements"].median).abs}
p cv.rmse
p cv.r_squared
#File.open("tmp.pdf","w+"){|f| f.puts cv.correlation_plot}
refute_nil cv.r_squared
refute_nil cv.rmse
end
def test_validate_pls_model
training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
#feature = Feature.find_or_create_by(name: "Net cell association", category: "TOX", unit: "mL/ug(Mg)")
feature = Feature.find_or_create_by(name: "Log2 transformed", category: "TOX")
model = Model::LazarRegression.create(feature, training_dataset, {:prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression", :neighbor_algorithm => "physchem_neighbors", :neighbor_algorithm_parameters => {:min_sim => 0.5}})
cv = RegressionCrossValidation.create model
p cv
#p cv.predictions.sort_by{|sid,p| (p["value"] - p["measurements"].median).abs}
p cv.rmse
p cv.r_squared
File.open("tmp.pdf","w+"){|f| f.puts cv.correlation_plot}
refute_nil cv.r_squared
refute_nil cv.rmse
end
def test_export
skip
Dataset.all.each do |d|
puts d.to_csv
end
end
def test_summaries
skip
datasets = Dataset.all
datasets = datasets.select{|d| !d.name.nil?}
datasets.each do |d|
#p d.features.select{|f| f.name.match (/Total/)}
#p d.features.collect{|f| "#{f.name} #{f.unit} #{f.conditions}"}
p d.features.uniq.collect{|f| f.name}
end
assert_equal 9, datasets.size
=begin
features = Feature.all.to_a
#p features.collect do |f|
#f if f.category == "TOX"
#end.to_a.flatten.size
toxcounts = {}
pccounts = {}
Nanoparticle.all.each do |np|
np.measurements.each do |t,v|
toxcounts[t] ||= 0
toxcounts[t] += 1#v.uniq.size
end
np.physchem_descriptors.each do |t,v|
pccounts[t] ||= 0
pccounts[t] += 1#v.uniq.size
end
end
#puts counts.keys.collect{|i| Feature.find(i)}.to_yaml
#pccounts.each{|e,n| p Feature.find(e),n if n > 100}
#p toxcounts.collect{|e,n| Feature.find(e).name if n > 1}.uniq
toxcounts.each{|e,n| p Feature.find(e),n if n > 100}
=end
end
def test_import_ld
skip
dataset_ids = Import::Enanomapper.import_ld
end
end
|
