summaryrefslogtreecommitdiff
path: root/lib/lazar-model.rb
blob: 4ca34037a0904f271404d2b0c45d1bb46b7b7d85 (plain)
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
module OpenTox

  module Model

    class Lazar 
      include OpenTox
      include Mongoid::Document
      include Mongoid::Timestamps
      store_in collection: "models"

      field :title, type: String
      field :endpoint, type: String
      field :creator, type: String, default: __FILE__
      # datasets
      field :training_dataset_id, type: BSON::ObjectId
      # algorithms
      field :prediction_algorithm, type: String
      field :neighbor_algorithm, type: String
      field :neighbor_algorithm_parameters, type: Hash
      # prediction feature
      field :prediction_feature_id, type: BSON::ObjectId

      attr_accessor :prediction_dataset
      attr_accessor :training_dataset

      # 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 self.create training_dataset

        bad_request_error "More than one prediction feature found in training_dataset #{training_dataset.id}" unless training_dataset.features.size == 1

        # TODO document convention
        prediction_feature = training_dataset.features.first
        prediction_feature.nominal ?  lazar = OpenTox::Model::LazarClassification.new : lazar = OpenTox::Model::LazarRegression.new
        lazar.training_dataset_id = training_dataset.id
        lazar.prediction_feature_id = prediction_feature.id
        lazar.title = prediction_feature.title 

        lazar.save
        lazar
      end

      def predict object

        t = Time.now
        at = Time.now

        training_dataset = Dataset.find training_dataset_id
        prediction_feature = Feature.find prediction_feature_id

        # parse data
        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

        # make predictions
        predictions = []
        compounds.each_with_index do |compound,c|
          t = Time.new
          neighbors = Algorithm.run(neighbor_algorithm, compound, neighbor_algorithm_parameters)
          # add activities
          # TODO: improve efficiency, takes 3 times longer than previous version
          # TODO database activity??
          neighbors.collect! do |n|
            rows = training_dataset.compound_ids.each_index.select{|i| training_dataset.compound_ids[i] == n.first}
            acts = rows.collect{|row| training_dataset.data_entries[row][0]}.compact
            acts.empty? ? nil : n << acts
          end
          neighbors.compact! # remove neighbors without training activities
          predictions << Algorithm.run(prediction_algorithm, neighbors)
        end 

        # serialize result
        case object.class.to_s
        when "OpenTox::Compound"
          return predictions.first
        when "Array"
          return predictions
        when "OpenTox::Dataset"
          # prepare prediction dataset
          prediction_dataset = LazarPrediction.new(
            :title => "Lazar prediction for #{prediction_feature.title}",
            :creator =>  __FILE__,
            :prediction_feature_id => prediction_feature.id

          )
          confidence_feature = OpenTox::NumericFeature.find_or_create_by( "title" => "Prediction confidence" )
          # TODO move into warnings field
          warning_feature = OpenTox::NominalFeature.find_or_create_by("title" => "Warnings")
          prediction_dataset.features = [ prediction_feature, confidence_feature, warning_feature ]
          prediction_dataset.compounds = compounds
          prediction_dataset.data_entries = predictions
          prediction_dataset.save_all
          return prediction_dataset
        end

      end
      
      def training_activities
        i = training_dataset.feature_ids.index prediction_feature_id
        training_dataset.data_entries.collect{|de| de[i]}
      end

    end

    class LazarClassification < Lazar
      def initialize
        super
        self.prediction_algorithm = "OpenTox::Algorithm::Classification.weighted_majority_vote"
        self.neighbor_algorithm = "OpenTox::Algorithm::Neighbor.fingerprint_similarity"
        self.neighbor_algorithm_parameters = {:min_sim => 0.7}
      end
    end

    class LazarFminerClassification < LazarClassification
      #field :feature_dataset_id, type: BSON::ObjectId
      #field :feature_calculation_algorithm, type: String

      def self.create training_dataset
        model = super(training_dataset)
        model.update "_type" => self.to_s # adjust class
        model = self.find model.id # adjust class
        model.neighbor_algorithm = "OpenTox::Algorithm::Neighbor.fminer_similarity"
        model.neighbor_algorithm_parameters = {
          :feature_calculation_algorithm => "OpenTox::Algorithm::Descriptor.smarts_match",
          :feature_dataset_id => Algorithm::Fminer.bbrc(training_dataset).id,
          :min_sim => 0.3
        }
        model.save
        model
      end

=begin
      def predict object

        t = Time.now
        at = Time.now

        @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-t}"
        t = Time.now

        @query_fingerprint = Algorithm.run(feature_calculation_algorithm, compounds, @feature_dataset.features.collect{|f| f.name} )

        $logger.debug "Query fingerprint calculation: #{Time.now-t}"
        t = Time.now

        predictions = []
        prediction_feature = OpenTox::Feature.find prediction_feature_id
        tt = 0
        pt = 0
        nt = 0
        st = 0
        nit = 0
        @training_fingerprints ||= @feature_dataset.data_entries
        compounds.each_with_index do |compound,c|
          t = Time.new

          $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 = database_activities.first if database_activities.size == 1
            $logger.debug "Compound #{compound.inchi} occurs in training dataset with activity #{database_activities}"
            predictions << {:compound => compound, :value => database_activities, :confidence => "measured"}
            next
          else

            #training_fingerprints = @feature_dataset.data_entries
            query_fingerprint = @query_fingerprint[c]
            neighbors = []
            tt += Time.now-t
            t = Time.new
            

            # find neighbors
            @training_fingerprints.each_with_index do |fingerprint, i|
              ts = Time.new
              sim = Algorithm.run(similarity_algorithm,fingerprint, query_fingerprint)
              st += Time.now-ts
              ts = Time.new
              if sim > self.min_sim
                if prediction_algorithm =~ /Regression/
                  neighbors << [@feature_dataset.compound_ids[i],sim,training_activities[i], fingerprint]
                else
                  neighbors << [@feature_dataset.compound_ids[i],sim,training_activities[i]] # use compound_ids, instantiation of Compounds is too time consuming
                end
              end
              nit += Time.now-ts
            end

            if neighbors.empty?
              predictions << {:compound => compound, :value => nil, :confidence => nil, :warning => "No neighbors with similarity > #{min_sim} in dataset #{training_dataset.id}"}
              next
            end
            nt += Time.now-t
            t = Time.new

            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
            prediction[:compound] = compound
            prediction[:neighbors] = neighbors.sort{|a,b| b[1] <=> a[1]} # sort with ascending similarities


            # 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[:value]}, confidence: #{prediction[:confidence]}"
            predictions << prediction
            pt += Time.now-t
          end

        end 
        $logger.debug "Transform time: #{tt}"
        $logger.debug "Neighbor search time: #{nt} (Similarity calculation: #{st}, Neighbor insert: #{nit})"
        $logger.debug "Prediction time: #{pt}"
        $logger.debug "Total prediction time: #{Time.now-at}"

        # serialize result
        case object.class.to_s
        when "OpenTox::Compound"
          return predictions.first
        when "Array"
          return predictions
        when "OpenTox::Dataset"
          # prepare prediction dataset
          prediction_dataset = LazarPrediction.new(
            :title => "Lazar prediction for #{prediction_feature.title}",
            :creator =>  __FILE__,
            :prediction_feature_id => prediction_feature.id

          )
          confidence_feature = OpenTox::NumericFeature.find_or_create_by( "title" => "Prediction confidence" )
          warning_feature = OpenTox::NominalFeature.find_or_create_by("title" => "Warnings")
          prediction_dataset.features = [ prediction_feature, confidence_feature, warning_feature ]
          prediction_dataset.compounds = compounds
          prediction_dataset.data_entries = predictions.collect{|p| [p[:value], p[:confidence],p[:warning]]}
          prediction_dataset.save_all
          return prediction_dataset
        end

      end
=end
    end

    class LazarRegression < Lazar

      def initialize
        super
        self.neighbor_algorithm = "OpenTox::Algorithm::Neighbor.fingerprint_similarity"
        self.prediction_algorithm = "OpenTox::Algorithm::Regression.weighted_average" 
        self.neighbor_algorithm_parameters = {:min_sim => 0.7}
      end

    end

  end

end