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
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
|
module OpenTox
module Model
include OpenTox
# Run a model with parameters
# @param [Hash] params Parameters for OpenTox model
# @param [optional,OpenTox::Task] waiting_task (can be a OpenTox::Subtask as well), progress is updated accordingly
# @return [text/uri-list] Task or resource URI
def run( params, accept_header=nil, waiting_task=nil )
unless accept_header
if CONFIG[:yaml_hosts].include?(URI.parse(@uri).host)
accept_header = 'application/x-yaml'
else
accept_header = 'application/rdf+xml'
end
end
LOGGER.info "running model "+@uri.to_s+", params: "+params.inspect+", accept: "+accept_header.to_s
RestClientWrapper.post(@uri,params,{:accept => accept_header},waiting_task).to_s
end
# Generic OpenTox model class for all API compliant services
class Generic
include Model
# Find Generic Opentox Model via URI, and loads metadata, could raise NotFound/NotAuthorized error
# @param [String] uri Model URI
# @return [OpenTox::Model::Generic] Model instance
def self.find(uri,subjectid=nil)
return nil unless uri
model = Generic.new(uri)
model.load_metadata(subjectid)
raise "could not load model metadata '"+uri.to_s+"'" if model.metadata==nil or model.metadata.size==0
model
end
# provides feature type, possible types are "regression" or "classification"
# @return [String] feature type, "unknown" if type could not be estimated
def feature_type(subjectid=nil)
unless @feature_type
load_predicted_variables( subjectid ) unless @predicted_variable
@feature_type = OpenTox::Feature.find( @predicted_variable, subjectid ).feature_type
end
@feature_type
end
def predicted_variable( subjectid )
load_predicted_variables( subjectid ) unless @predicted_variable
@predicted_variable
end
def predicted_confidence( subjectid )
load_predicted_variables( subjectid ) unless @predicted_confidence
@predicted_confidence
end
private
def load_predicted_variables( subjectid=nil )
load_metadata(subjectid) if @metadata==nil or @metadata.size==0 or (@metadata.size==1 && @metadata.values[0]==@uri)
if @metadata[OT.predictedVariables]
predictedVariables = @metadata[OT.predictedVariables]
if predictedVariables.is_a?(Array)
if (predictedVariables.size==1)
@predicted_variable = predictedVariables[0]
elsif (predictedVariables.size==2)
# PENDING identify confidence
conf_index = -1
predictedVariables.size.times do |i|
f = OpenTox::Feature.find(predictedVariables[i])
conf_index = i if f.metadata[DC.title]=~/(?i)confidence/
end
raise "could not estimate predicted variable from model: '"+uri.to_s+
"', number of predicted-variables==2, but no confidence found" if conf_index==-1
@predicted_variable = predictedVariables[1-conf_index]
@predicted_confidence = predictedVariables[conf_index]
else
raise "could not estimate predicted variable from model: '"+uri.to_s+"', number of predicted-variables > 2"
end
else
raise "could not estimate predicted variable from model: '"+uri.to_s+"', predicted-variables is no array"
end
end
raise "could not estimate predicted variable from model: '"+uri.to_s+"'" unless @predicted_variable
end
end
# Lazy Structure Activity Relationship class
class Lazar
include Model
include Algorithm
attr_accessor :compound, :prediction_dataset, :features, :effects, :activities, :p_values, :fingerprints, :feature_calculation_algorithm, :similarity_algorithm, :prediction_algorithm, :min_sim, :subjectid, :prop_kernel
def initialize(uri=nil)
if uri
super uri
else
super CONFIG[:services]["opentox-model"]
end
@metadata[OT.algorithm] = File.join(CONFIG[:services]["opentox-algorithm"],"lazar")
@features = []
@effects = {}
@activities = {}
@p_values = {}
@fingerprints = {}
@feature_calculation_algorithm = "Substructure.match"
@similarity_algorithm = "Similarity.tanimoto"
@prediction_algorithm = "Neighbors.weighted_majority_vote"
@min_sim = 0.3
@prop_kernel = false
end
# Get URIs of all lazar models
# @return [Array] List of lazar model URIs
def self.all(subjectid=nil)
RestClientWrapper.get(CONFIG[:services]["opentox-model"], :subjectid => subjectid).to_s.split("\n")
end
# Find a lazar model
# @param [String] uri Model URI
# @return [OpenTox::Model::Lazar] lazar model
def self.find(uri, subjectid=nil)
YAML.load RestClientWrapper.get(uri,{:accept => 'application/x-yaml', :subjectid => subjectid})
end
# Create a new lazar model
# @param [optional,Hash] params Parameters for the lazar algorithm (OpenTox::Algorithm::Lazar)
# @return [OpenTox::Model::Lazar] lazar model
def self.create(params)
subjectid = params[:subjectid]
lazar_algorithm = OpenTox::Algorithm::Generic.new File.join( CONFIG[:services]["opentox-algorithm"],"lazar")
model_uri = lazar_algorithm.run(params)
OpenTox::Model::Lazar.find(model_uri, subjectid)
end
# Get a parameter value
# @param [String] param Parameter name
# @return [String] Parameter value
def parameter(param)
@metadata[OT.parameters].collect{|p| p[OT.paramValue] if p[DC.title] == param}.compact.first
end
# Predict a dataset
# @param [String] dataset_uri Dataset URI
# @param [optional,subjectid]
# @param [optional,OpenTox::Task] waiting_task (can be a OpenTox::Subtask as well), progress is updated accordingly
# @return [OpenTox::Dataset] Dataset with predictions
def predict_dataset(dataset_uri, subjectid=nil, waiting_task=nil)
@prediction_dataset = Dataset.create(CONFIG[:services]["opentox-dataset"], subjectid)
@prediction_dataset.add_metadata({
OT.hasSource => @uri,
DC.creator => @uri,
DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )),
OT.parameters => [{DC.title => "dataset_uri", OT.paramValue => dataset_uri}]
})
d = Dataset.new(dataset_uri,subjectid)
d.load_compounds(subjectid)
count = 0
d.compounds.each do |compound_uri|
begin
predict(compound_uri,false,subjectid)
count += 1
waiting_task.progress( count/d.compounds.size.to_f*100.0 ) if waiting_task
rescue => ex
LOGGER.warn "prediction for compound "+compound_uri.to_s+" failed: "+ex.message
end
end
@prediction_dataset.save(subjectid)
@prediction_dataset
end
# Predict a compound
# @param [String] compound_uri Compound URI
# @param [optinal,Boolean] verbose Verbose prediction (output includes neighbors and features)
# @return [OpenTox::Dataset] Dataset with prediction
def predict(compound_uri,verbose=false,subjectid=nil)
@compound = Compound.new compound_uri
features = {}
unless @prediction_dataset
@prediction_dataset = Dataset.create(CONFIG[:services]["opentox-dataset"], subjectid)
@prediction_dataset.add_metadata( {
OT.hasSource => @uri,
DC.creator => @uri,
DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )),
OT.parameters => [{DC.title => "compound_uri", OT.paramValue => compound_uri}]
} )
end
return @prediction_dataset if database_activity(subjectid)
load_metadata(subjectid)
case OpenTox::Feature.find(metadata[OT.dependentVariables]).feature_type
when "classification"
# AM: Balancing, see http://www.maunz.de/wordpress/opentox/2011/balanced-lazar
l = Array.new # larger
s = Array.new # smaller fraction
raise "no fingerprints in model" if @fingerprints.size==0
@fingerprints.each do |training_compound,training_features|
@activities[training_compound].each do |act|
case act.to_s
when "false"
l << training_compound
when "true"
s << training_compound
else
LOGGER.warn "BLAZAR: Activity #{act.to_s} should not be reached."
end
end
end
if s.size > l.size then
l,s = s,l # happy swapping
LOGGER.info "BLAZAR: |s|=#{s.size}, |l|=#{l.size}."
end
# determine ratio
modulo = l.size.divmod(s.size)# modulo[0]=ratio, modulo[1]=rest
LOGGER.info "BLAZAR: Balance: #{modulo[0]}, rest #{modulo[1]}."
# AM: Balanced predictions
addon = (modulo[1].to_f/modulo[0]).ceil # what will be added in each round
slack = (addon!=0 ? modulo[1].divmod(addon)[1] : 0) # what remains for the last round
position = 0
predictions = Array.new
prediction_best=nil
neighbors_best=nil
begin
for i in 1..modulo[0] do
(i == modulo[0]) && (slack>0) ? lr_size = s.size + slack : lr_size = s.size + addon # determine fraction
LOGGER.info "BLAZAR: Neighbors round #{i}: #{position} + #{lr_size}."
neighbors_balanced(s, l, position, lr_size) # get ratio fraction of larger part
if @prop_kernel && @prediction_algorithm.include?("svm")
props = get_props
else
props = nil
end
prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values}, props)")
if prediction_best.nil? || prediction[:confidence].abs > prediction_best[:confidence].abs
prediction_best=prediction
neighbors_best=@neighbors
end
position = position + lr_size
end
rescue Exception => e
LOGGER.error "BLAZAR failed in prediction: "+e.class.to_s+": "+e.message
end
prediction=prediction_best
@neighbors=neighbors_best
### END AM balanced predictions
else # AM: no balancing
LOGGER.info "LAZAR: Unbalanced."
neighbors
if @prop_kernel && @prediction_algorithm.include?("svm")
props = get_props
else
props = nil
end
prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values}, props)")
end
value_feature_uri = File.join( @uri, "predicted", "value")
confidence_feature_uri = File.join( @uri, "predicted", "confidence")
prediction_feature_uris = {value_feature_uri => prediction[:prediction], confidence_feature_uri => prediction[:confidence]}
prediction_feature_uris[value_feature_uri] = nil if @neighbors.size == 0 or prediction[:prediction].nil?
@prediction_dataset.metadata[OT.dependentVariables] = @metadata[OT.dependentVariables]
@prediction_dataset.metadata[OT.predictedVariables] = [value_feature_uri, confidence_feature_uri]
prediction_feature_uris.each do |prediction_feature_uri,value|
@prediction_dataset.add @compound.uri, prediction_feature_uri, value
end
if verbose
if @feature_calculation_algorithm == "Substructure.match"
f = 0
@compound_features.each do |feature|
feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s)
features[feature] = feature_uri
@prediction_dataset.add_feature(feature_uri, {
RDF.type => [OT.Substructure],
OT.smarts => feature,
OT.pValue => @p_values[feature],
OT.effect => @effects[feature]
})
@prediction_dataset.add @compound.uri, feature_uri, true
f+=1
end
else
@compound_features.each do |feature|
features[feature] = feature
@prediction_dataset.add @compound.uri, feature, true
end
end
n = 0
@neighbors.each do |neighbor|
neighbor_uri = File.join( @prediction_dataset.uri, "feature", "neighbor", n.to_s )
@prediction_dataset.add_feature(neighbor_uri, {
OT.compound => neighbor[:compound],
OT.similarity => neighbor[:similarity],
OT.measuredActivity => neighbor[:activity],
RDF.type => [OT.Neighbor]
})
@prediction_dataset.add @compound.uri, neighbor_uri, true
f = 0 unless f
neighbor[:features].each do |feature|
if @feature_calculation_algorithm == "Substructure.match"
feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s) unless feature_uri = features[feature]
else
feature_uri = feature
end
@prediction_dataset.add neighbor[:compound], feature_uri, true
unless features.has_key? feature
features[feature] = feature_uri
@prediction_dataset.add_feature(feature_uri, {
RDF.type => [OT.Substructure],
OT.smarts => feature,
OT.pValue => @p_values[feature],
OT.effect => @effects[feature]
})
f+=1
end
end
n+=1
end
end
#end
@prediction_dataset.save(subjectid)
@prediction_dataset
end
# Calculate the propositionalization matrix aka instantiation matrix (0/1 entries for features)
# Same for the vector describing the query compound
def get_props
matrix = Array.new
begin
@neighbors.each do |n|
n = n[:compound]
row = []
@features.each do |f|
if ! @fingerprints[n].nil?
row << (@fingerprints[n].include?(f) ? 0.0 : @p_values[f])
else
row << 0.0
end
end
matrix << row
end
row = []
@features.each do |f|
row << (@compound.match([f]).size == 0 ? 0.0 : @p_values[f])
end
rescue Exception => e
LOGGER.debug "get_props failed with '" + $! + "'"
end
[ matrix, row ]
end
# Find neighbors and store them as object variable, access only a subset of compounds for that.
def neighbors_balanced(s, l, start, offset)
@compound_features = eval("#{@feature_calculation_algorithm}(@compound,@features)") if @feature_calculation_algorithm
@neighbors = []
[ l[start, offset ] , s ].flatten.each do |training_compound| # AM: access only a balanced subset
training_features = @fingerprints[training_compound]
add_neighbor training_features, training_compound
end
end
# Find neighbors and store them as object variable, access all compounds for that.
def neighbors
@compound_features = eval("#{@feature_calculation_algorithm}(@compound,@features)") if @feature_calculation_algorithm
@neighbors = []
@fingerprints.each do |training_compound,training_features| # AM: access all compounds
add_neighbor training_features, training_compound
end
end
# Adds a neighbor to @neighbors if it passes the similarity threshold.
def add_neighbor(training_features, training_compound)
sim = eval("#{@similarity_algorithm}(@compound_features,training_features,@p_values)")
if sim > @min_sim
@activities[training_compound].each do |act|
@neighbors << {
:compound => training_compound,
:similarity => sim,
:features => training_features,
:activity => act
}
end
end
end
# Find database activities and store them in @prediction_dataset
# @return [Boolean] true if compound has databasse activities, false if not
def database_activity(subjectid)
if @activities[@compound.uri]
@activities[@compound.uri].each { |act| @prediction_dataset.add @compound.uri, @metadata[OT.dependentVariables], act }
@prediction_dataset.add_metadata(OT.hasSource => @metadata[OT.trainingDataset])
@prediction_dataset.save(subjectid)
true
else
false
end
end
def prediction_features
[prediction_value_feature,prediction_confidence_feature]
end
def prediction_value_feature
dependent_uri = @metadata[OT.dependentVariables].first
feature = OpenTox::Feature.new File.join( @uri, "predicted", "value")
feature.add_metadata( {
RDF.type => [OT.ModelPrediction],
OT.hasSource => @uri,
DC.creator => @uri,
DC.title => URI.decode(File.basename( dependent_uri )),
OWL.sameAs => dependent_uri
})
feature
end
def prediction_confidence_feature
dependent_uri = @metadata[OT.dependentVariables].first
feature = OpenTox::Feature.new File.join( @uri, "predicted", "confidence")
feature.add_metadata( {
RDF.type => [OT.ModelPrediction],
OT.hasSource => @uri,
DC.creator => @uri,
DC.title => "#{URI.decode(File.basename( dependent_uri ))} confidence"
})
feature
end
# Save model at model service
def save(subjectid)
self.uri = RestClientWrapper.post(@uri,self.to_yaml,{:content_type => "application/x-yaml", :subjectid => subjectid})
end
# Delete model at model service
def delete(subjectid)
RestClientWrapper.delete(@uri, :subjectid => subjectid) unless @uri == CONFIG[:services]["opentox-model"]
end
end
end
end
|