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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
|
module OpenTox
module Model
class Lazar
include OpenTox
include Mongoid::Document
include Mongoid::Timestamps
store_in collection: "models"
field :name, type: String
field :creator, type: String, default: __FILE__
field :training_dataset_id, type: BSON::ObjectId
field :prediction_feature_id, type: BSON::ObjectId
field :prediction_algorithm, type: String
field :prediction_algorithm_parameters, type: Hash, default: {}
field :neighbor_algorithm, type: String
field :neighbor_algorithm_parameters, type: Hash, default: {}
field :feature_selection_algorithm, type: String
field :feature_selection_algorithm_parameters, type: Hash, default: {}
field :relevant_features, type: Hash
# Create a lazar model from a training_dataset and a feature_dataset
# @param [OpenTox::Dataset] training_dataset
# @return [OpenTox::Model::Lazar] Regression or classification model
def initialize prediction_feature, training_dataset, params={}
super params
# set defaults for empty parameters
self.prediction_feature_id ||= prediction_feature.id
self.training_dataset_id ||= training_dataset.id
self.name ||= "#{training_dataset.name} #{prediction_feature.name}"
self.neighbor_algorithm_parameters ||= {}
self.neighbor_algorithm_parameters[:dataset_id] = training_dataset.id
send(feature_selection_algorithm.to_sym) if feature_selection_algorithm
save
end
def correlation_filter
# TODO: speedup, single assignment of all features to R+ parallel computation of significance?
self.relevant_features = {}
measurements = []
substances = []
training_dataset.substances.each do |s|
training_dataset.values(s,prediction_feature_id).each do |act|
measurements << act
substances << s
end
end
R.assign "tox", measurements
feature_ids = training_dataset.substances.collect{ |s| s["physchem_descriptors"].keys}.flatten.uniq
feature_ids.select!{|fid| Feature.find(fid).category == feature_selection_algorithm_parameters[:category]} if feature_selection_algorithm_parameters[:category]
feature_ids.each do |feature_id|
feature_values = substances.collect{|s| s["physchem_descriptors"][feature_id].first if s["physchem_descriptors"][feature_id]}
unless feature_values.uniq.size == 1
R.assign "feature", feature_values
begin
R.eval "cor <- cor.test(tox,feature,method = 'pearson',use='pairwise')"
pvalue = R.eval("cor$p.value").to_ruby
if pvalue <= 0.05
r = R.eval("cor$estimate").to_ruby
self.relevant_features[feature_id] = {}
self.relevant_features[feature_id]["pvalue"] = pvalue
self.relevant_features[feature_id]["r"] = r
self.relevant_features[feature_id]["mean"] = R.eval("mean(feature, na.rm=TRUE)").to_ruby
self.relevant_features[feature_id]["sd"] = R.eval("sd(feature, na.rm=TRUE)").to_ruby
end
rescue
warn "Correlation of '#{Feature.find(feature_id).name}' (#{feature_values}) with '#{Feature.find(prediction_feature_id).name}' (#{measurements}) failed."
end
end
end
self.relevant_features = self.relevant_features.sort{|a,b| a[1]["pvalue"] <=> b[1]["pvalue"]}.to_h
end
def predict_substance substance
neighbor_algorithm_parameters = Hash[self.neighbor_algorithm_parameters.map{ |k, v| [k.to_sym, v] }] # convert string keys to symbols
neighbor_algorithm_parameters[:relevant_features] = self.relevant_features if self.relevant_features
neighbors = substance.send(neighbor_algorithm, neighbor_algorithm_parameters)
measurements = nil
prediction = {}
# handle query substance
if neighbors.collect{|n| n["_id"]}.include? substance.id
query = neighbors.select{|n| n["_id"] == substance.id}.first
measurements = training_dataset.values(query["_id"],prediction_feature_id)
prediction[:measurements] = measurements
prediction[:warning] = "#{measurements.size} substances have been removed from neighbors, because they are identical with the query substance."
neighbors.delete_if{|n| n["_id"] == substance.id} # remove query substance for an unbiased prediction (also useful for loo validation)
end
if neighbors.empty?
prediction.merge!({:value => nil,:probabilities => nil,:warning => "Could not find similar substances with experimental data in the training dataset.",:neighbors => []})
elsif neighbors.size == 1
value = nil
m = neighbors.first["measurements"]
if m.size == 1 # single measurement
value = m.first
else # multiple measurement
if m.collect{|t| t.numeric?}.uniq == [true] # numeric
value = m.median
elsif m.uniq.size == 1 # single value
value = m.first
else # contradictory results
# TODO add majority vote??
end
end
prediction.merge!({:value => value, :probabilities => nil, :warning => "Only one similar compound in the training set. Predicting median of its experimental values.", :neighbors => neighbors}) if value
else
# call prediction algorithm
klass,method = prediction_algorithm.split('.')
params = prediction_algorithm_parameters.merge({:substance => substance, :neighbors => neighbors})
result = Object.const_get(klass).send(method,params)
prediction.merge! result
prediction[:neighbors] = neighbors
prediction[:neighbors] ||= []
end
prediction
end
def predict object
training_dataset = Dataset.find training_dataset_id
# parse data
substances = []
if object.is_a? Substance
substances = [object]
elsif object.is_a? Array
substances = object
elsif object.is_a? Dataset
substances = object.substances
else
bad_request_error "Please provide a OpenTox::Compound an Array of OpenTox::Compounds or an OpenTox::Dataset as parameter."
end
# make predictions
predictions = {}
substances.each do |c|
predictions[c.id.to_s] = predict_substance c
predictions[c.id.to_s][:prediction_feature_id] = prediction_feature_id
end
# serialize result
if object.is_a? Substance
prediction = predictions[substances.first.id.to_s]
prediction[:neighbors].sort!{|a,b| b[1] <=> a[1]} # sort according to similarity
return prediction
elsif object.is_a? Array
return predictions
elsif object.is_a? Dataset
#predictions.each{|cid,p| p.delete(:neighbors)}
# prepare prediction dataset
measurement_feature = Feature.find prediction_feature_id
prediction_feature = NumericFeature.find_or_create_by( "name" => measurement_feature.name + " (Prediction)" )
prediction_dataset = LazarPrediction.create(
:name => "Lazar prediction for #{prediction_feature.name}",
:creator => __FILE__,
:prediction_feature_id => prediction_feature.id,
:predictions => predictions
)
#prediction_dataset.save
return prediction_dataset
end
end
def training_dataset
Dataset.find(training_dataset_id)
end
def prediction_feature
Feature.find(prediction_feature_id)
end
end
class LazarClassification < Lazar
def self.create prediction_feature, training_dataset, params={}
model = self.new prediction_feature, training_dataset, params
model.prediction_algorithm = "OpenTox::Algorithm::Classification.weighted_majority_vote" unless model.prediction_algorithm
model.neighbor_algorithm ||= "fingerprint_neighbors"
model.neighbor_algorithm_parameters ||= {}
{
:type => "MP2D",
:dataset_id => training_dataset.id,
:prediction_feature_id => prediction_feature.id,
:min_sim => 0.1
}.each do |key,value|
model.neighbor_algorithm_parameters[key] ||= value
end
model.save
model
end
end
class LazarRegression < Lazar
def self.create prediction_feature, training_dataset, params={}
model = self.new prediction_feature, training_dataset, params
model.neighbor_algorithm ||= "fingerprint_neighbors"
model.prediction_algorithm ||= "OpenTox::Algorithm::Regression.local_fingerprint_regression"
model.neighbor_algorithm_parameters ||= {}
{
:min_sim => 0.1,
:dataset_id => training_dataset.id,
:prediction_feature_id => prediction_feature.id,
}.each do |key,value|
model.neighbor_algorithm_parameters[key] ||= value
end
model.neighbor_algorithm_parameters[:type] ||= "MP2D" if training_dataset.substances.first.is_a? Compound
model.save
model
end
end
class Prediction
include OpenTox
include Mongoid::Document
include Mongoid::Timestamps
field :endpoint, type: String
field :species, type: String
field :source, type: String
field :unit, type: String
field :model_id, type: BSON::ObjectId
field :repeated_crossvalidation_id, type: BSON::ObjectId
field :leave_one_out_validation_id, type: BSON::ObjectId
def predict object
Lazar.find(model_id).predict object
end
def training_dataset
model.training_dataset
end
def model
Lazar.find model_id
end
def repeated_crossvalidation
Validation::RepeatedCrossValidation.find repeated_crossvalidation_id
end
def crossvalidations
repeated_crossvalidation.crossvalidations
end
def leave_one_out_validation
Validation::LeaveOneOut.find leave_one_out_validation_id
end
def regression?
model.is_a? LazarRegression
end
def classification?
model.is_a? LazarClassification
end
def self.from_csv_file file
metadata_file = file.sub(/csv$/,"json")
bad_request_error "No metadata file #{metadata_file}" unless File.exist? metadata_file
prediction_model = self.new JSON.parse(File.read(metadata_file))
training_dataset = Dataset.from_csv_file file
prediction_feature = training_dataset.features.first
model = nil
if prediction_feature.nominal?
model = LazarClassification.create prediction_feature, training_dataset
elsif prediction_feature.numeric?
model = LazarRegression.create prediction_feature, training_dataset
end
prediction_model[:model_id] = model.id
prediction_model[:prediction_feature_id] = prediction_feature.id
prediction_model[:repeated_crossvalidation_id] = Validation::RepeatedCrossValidation.create(model).id
#prediction_model[:leave_one_out_validation_id] = Validation::LeaveOneOut.create(model).id
prediction_model.save
prediction_model
end
end
class NanoPrediction < Prediction
def self.from_json_dump dir, category
Import::Enanomapper.import dir
prediction_model = self.new(
:endpoint => "log2(Net cell association)",
:source => "https://data.enanomapper.net/",
:species => "A549 human lung epithelial carcinoma cells",
:unit => "log2(ug/Mg)"
)
params = {
:feature_selection_algorithm => :correlation_filter,
:feature_selection_algorithm_parameters => {:category => category},
:neighbor_algorithm => "physchem_neighbors",
:neighbor_algorithm_parameters => {:min_sim => 0.5},
:prediction_algorithm => "OpenTox::Algorithm::Regression.local_physchem_regression",
:prediction_algorithm_parameters => {:method => 'rf'}, # random forests
}
training_dataset = Dataset.find_or_create_by(:name => "Protein Corona Fingerprinting Predicts the Cellular Interaction of Gold and Silver Nanoparticles")
prediction_feature = Feature.find_or_create_by(name: "log2(Net cell association)", category: "TOX")
#prediction_feature = Feature.find("579621b84de73e267b414e55")
prediction_model[:prediction_feature_id] = prediction_feature.id
model = Model::LazarRegression.create(prediction_feature, training_dataset, params)
prediction_model[:model_id] = model.id
repeated_cv = Validation::RepeatedCrossValidation.create model
prediction_model[:repeated_crossvalidation_id] = Validation::RepeatedCrossValidation.create(model).id
#prediction_model[:leave_one_out_validation_id] = Validation::LeaveOneOut.create(model).id
prediction_model.save
prediction_model
end
end
end
end
|