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
|
=begin
* Name: lazar.rb
* Description: Lazar model representation
* Author: Andreas Maunz <andreas@maunz.de>, Christoph Helma
* Date: 10/2012
=end
module OpenTox
module Model
class Lazar
include OpenTox
include Mongoid::Document
include Mongoid::Timestamps
store_in collection: "models"
field :title, type: String
field :description, type: String
#field :parameters, type: Array, default: []
field :creator, type: String, default: __FILE__
# datasets
field :training_dataset_id, type: BSON::ObjectId
field :feature_dataset_id, type: BSON::ObjectId
# algorithms
#field :feature_generation, type: String
#field :feature_calculation_algorithm, type: String
field :prediction_algorithm, type: String
field :similarity_algorithm, type: String
# prediction features
field :prediction_feature_id, type: BSON::ObjectId
field :predicted_value_id, type: BSON::ObjectId
field :predicted_variables, type: Array
# parameters
field :nr_hits, type: Boolean
field :min_sim, type: Float
#field :propositionalized, type:Boolean
field :min_train_performance, type: Float
attr_accessor :prediction_dataset
attr_accessor :training_dataset
attr_accessor :feature_dataset
attr_accessor :query_fingerprint
attr_accessor :neighbors
# Check parameters for plausibility
# Prepare lazar object (includes graph mining)
# @param[Array] lazar parameters as strings
# @param[Hash] REST parameters, as input by user
def self.create training_dataset, feature_dataset, prediction_feature=nil, nr_hits=false, params={}
lazar = OpenTox::Model::Lazar.new
bad_request_error "No features found in feature dataset #{feature_dataset.id}." if feature_dataset.features.empty?
lazar.feature_dataset_id = feature_dataset.id
@training_dataset = training_dataset
bad_request_error "Training dataset compounds do not match feature dataset compounds. Please ensure that they are in the same order." unless @training_dataset.compounds == feature_dataset.compounds
lazar.training_dataset_id = @training_dataset.id
if prediction_feature
resource_not_found_error "No feature '#{params[:prediction_feature]}' in dataset '#{@training_dataset.id}'" unless @training_dataset.features.include?( params[:prediction_feature] )
else # try to read prediction_feature from dataset
resource_not_found_error "Please provide a prediction_feature parameter" unless @training_dataset.features.size == 1
prediction_feature = @training_dataset.features.first
end
lazar.prediction_feature_id = prediction_feature.id
lazar.title = prediction_feature.title
if params and params[:prediction_algorithm]
bad_request_error "Unknown prediction_algorithm #{params[:prediction_algorithm]}" unless OpenTox::Algorithm::Neighbors.respond_to?(params[:prediction_algorithm])
lazar.prediction_algorithm = params[:prediction_algorithm]
end
unless lazar.prediction_algorithm # set defaults
# TODO consider params
if prediction_feature.nominal
lazar.prediction_algorithm = "OpenTox::Algorithm::Classification.weighted_majority_vote"
lazar.similarity_algorithm = "OpenTox::Algorithm::Similarity.tanimoto"
lazar.min_sim = 0.3 unless lazar.min_sim
elsif prediction_feature.numeric
lazar.prediction_algorithm = "OpenTox::Algorithm::Regression.local_svm_regression"
lazar.similarity_algorithm = "OpenTox::Algorithm::Similarity.cosine"
# cosine similartiy is default
lazar.min_sim = 0.7 unless lazar.min_sim
end
end
#lazar.prediction_algorithm =~ /majority_vote/ ? lazar.propositionalized = false : lazar.propositionalized = true
lazar.min_sim = params[:min_sim].to_f if params[:min_sim] and params[:min_sim].numeric?
# TODO: get info from training_dataset
lazar.nr_hits = nr_hits
#lazar.feature_generation = feature_dataset.training_algorithm
#lazar.parameters << {"title" => "feature_generation_uri", "paramValue" => params[:feature_generation_uri]}
bad_request_error "Parameter min_train_performance is not numeric." if params[:min_train_performance] and !params[:min_train_performance].numeric?
lazar.min_train_performance = params[:min_train_performance].to_f if params[:min_train_performance] and params[:min_train_performance].numeric?
lazar.min_train_performance = 0.1 unless lazar.min_train_performance
lazar.save
lazar
end
def predict object
# tailored for performance
# all consistency checks should be done during model creation
time = Time.now
# prepare prediction dataset
prediction_dataset = LazarPrediction.new
prediction_feature = OpenTox::Feature.find prediction_feature_id
prediction_dataset.title = "Lazar prediction for #{prediction_feature.title}",
prediction_dataset.creator = __FILE__,
confidence_feature = OpenTox::Feature.find_or_create_by({
"title" => "Prediction confidence",
"numeric" => true
})
prediction_dataset.features = [ confidence_feature, prediction_feature ]
@training_dataset = OpenTox::Dataset.find(training_dataset_id)
@feature_dataset = OpenTox::Dataset.find(feature_dataset_id)
compounds = []
case object.class.to_s
when "OpenTox::Compound"
compounds = [object]
when "Array"
compounds = object
when "OpenTox::Dataset"
compounds = object.compounds
else
bad_request_error "Please provide a OpenTox::Compound an Array of OpenTox::Compounds or an OpenTox::Dataset as parameter."
end
$logger.debug "Setup: #{Time.now-time}"
time = Time.now
@query_fingerprint = Algorithm.run(feature_dataset.feature_calculation_algorithm, compounds, @feature_dataset.features.collect{|f| f.name} )
$logger.debug "Fingerprint calculation: #{Time.now-time}"
time = Time.now
# AM: transform to cosine space
min_sim = (min_sim.to_f*2.0-1.0).to_s if similarity_algorithm =~ /cosine/
compounds.each_with_index do |compound,c|
$logger.debug "predict compound #{c+1}/#{compounds.size} #{compound.inchi}"
database_activities = @training_dataset.values(compound,prediction_feature)
if database_activities and !database_activities.empty?
database_activities.each do |database_activity|
$logger.debug "do not predict compound, it occurs in dataset with activity #{database_activity}"
prediction_dataset.compound_ids << compound.id
prediction_dataset[c,0] = database_activity
prediction_dataset[c,1] = nil
end
next
else
t = Time.new
if prediction_algorithm =~ /Regression/
mtf = OpenTox::Algorithm::Transform::ModelTransformer.new(self)
mtf.transform
training_fingerprints = mtf.n_prop
training_activities = mtf.activities
p training_activities
query_fingerprint = mtf.q_prop
neighbors = [[nil,nil,nil,query_fingerprint]]
else
training_fingerprints = @feature_dataset.data_entries
# TODO fix for multi feature datasets
training_activities = @training_dataset.data_entries[i].first
query_fingerprint = @query_fingerprint[c]
neighbors = []
end
$logger.debug "Transform: #{Time.now-t}"
t = Time.new
# find neighbors
training_fingerprints.each_with_index do |fingerprint, i|
sim = Algorithm.run(similarity_algorithm,fingerprint, query_fingerprint)
if sim > self.min_sim
if prediction_algorithm =~ /Regression/
neighbors << [@feature_dataset.compounds[i],sim,training_activities[i], fingerprint]
else
neighbors << [@feature_dataset.compounds[i],sim,training_activities[i]]
end
end
end
if prediction_algorithm =~ /Regression/
prediction = Algorithm.run(prediction_algorithm, neighbors, :min_train_performance => self.min_train_performance)
else
prediction = Algorithm.run(prediction_algorithm, neighbors)
end
$logger.debug "Prediction time: #{Time.now-time}"
time = Time.now
p prediction
# AM: transform to original space (TODO)
confidence_value = ((confidence_value+1.0)/2.0).abs if prediction.first and similarity_algorithm =~ /cosine/
$logger.debug "predicted value: #{prediction[0]}, confidence: #{prediction[1]}"
end
prediction_dataset.compound_ids << compound
prediction_dataset[c,0] = prediction[0]
prediction_dataset[c,1] = prediction[1]
end
prediction_dataset
end
def training_activities
# TODO select predicted variable
#@training_activities = @training_dataset.data_entries.collect{|entry|
#act = entry[prediction_feature_pos] if entry
#@prediction_feature.feature_type=="classification" ? @prediction_feature.value_map.invert[act] : act
#}
@training_dataset.data_entries.flatten
end
end
end
end
|
