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
|
# R integration
# workaround to initialize R non-interactively (former rinruby versions did this by default)
# avoids compiling R with X
R = nil
require "rinruby"
module OpenTox
# Wrapper for OpenTox Algorithms
module Algorithm
include OpenTox
# Execute algorithm with parameters, please consult the OpenTox API and the webservice documentation for acceptable parameters
# @param [optional,Hash] params Algorithm parameters
# @param [optional,OpenTox::Task] waiting_task (can be a OpenTox::Subtask as well), progress is updated accordingly
# @return [String] URI of new resource (dataset, model, ...)
def run(params=nil, waiting_task=nil)
RestClientWrapper.post(@uri, params, {:accept => 'text/uri-list'}, waiting_task).to_s
end
# Get OWL-DL representation in RDF/XML format
# @return [application/rdf+xml] RDF/XML representation
def to_rdfxml
s = Serializer::Owl.new
s.add_algorithm(@uri,@metadata)
s.to_rdfxml
end
# Generic Algorithm class, should work with all OpenTox webservices
class Generic
include Algorithm
# Find Generic Opentox Algorithm via URI, and loads metadata
# @param [String] uri Algorithm URI
# @return [OpenTox::Algorithm::Generic] Algorithm instance, nil if alogrithm was not found
def self.find(uri, subjectid)
return nil unless uri
alg = Generic.new(uri)
alg.load_metadata( subjectid )
if alg.metadata==nil or alg.metadata.size==0
nil
else
alg
end
end
end
# Fminer algorithms (https://github.com/amaunz/fminer2)
module Fminer
include Algorithm
# Backbone Refinement Class mining (http://bbrc.maunz.de/)
class BBRC
include Fminer
# Initialize bbrc algorithm
def initialize
super File.join(CONFIG[:services]["opentox-algorithm"], "fminer/bbrc")
load_metadata
end
end
# LAtent STructure Pattern Mining (http://last-pm.maunz.de)
class LAST
include Fminer
# Initialize last algorithm
def initialize
super File.join(CONFIG[:services]["opentox-algorithm"], "fminer/last")
load_metadata
end
end
end
# Create lazar prediction model
class Lazar
include Algorithm
# Initialize lazar algorithm
def initialize
super File.join(CONFIG[:services]["opentox-algorithm"], "lazar")
load_metadata
end
end
# Utility methods without dedicated webservices
# Similarity calculations
module Similarity
include Algorithm
# Tanimoto similarity
# @param [Array] features_a Features of first compound
# @param [Array] features_b Features of second compound
# @param [optional, Hash] weights Weights for all features
# @return [Float] (Weighted) tanimoto similarity
def self.tanimoto(features_a,features_b,weights=nil)
common_features = features_a & features_b
all_features = (features_a + features_b).uniq
common_p_sum = 0.0
if common_features.size > 0
if weights
common_features.each{|f| common_p_sum += Algorithm.gauss(weights[f])}
all_p_sum = 0.0
all_features.each{|f| all_p_sum += Algorithm.gauss(weights[f])}
common_p_sum/all_p_sum
else
common_features.to_f/all_features
end
else
0.0
end
end
# Euclidean similarity
# @param [Hash] properties_a Properties of first compound
# @param [Hash] properties_b Properties of second compound
# @param [optional, Hash] weights Weights for all properties
# @return [Float] (Weighted) euclidean similarity
def self.euclidean(properties_a,properties_b,weights=nil)
common_properties = properties_a.keys & properties_b.keys
if common_properties.size > 1
dist_sum = 0
common_properties.each do |p|
if weights
dist_sum += ( (properties_a[p] - properties_b[p]) * Algorithm.gauss(weights[p]) )**2
else
dist_sum += (properties_a[p] - properties_b[p])**2
end
end
1/(1+Math.sqrt(dist_sum))
else
0.0
end
end
end
module Neighbors
# Classification with majority vote from neighbors weighted by similarity
# @param [Array] neighbors, each neighbor is a hash with keys `:similarity, :activity`
# @param [optional] params Ignored (only for compatibility with local_svm_regression)
# @return [Hash] Hash with keys `:prediction, :confidence`
def self.weighted_majority_vote(neighbors,params={})
conf = 0.0
confidence = 0.0
neighbors.each do |neighbor|
case neighbor[:activity].to_s
when 'true'
conf += Algorithm.gauss(neighbor[:similarity])
when 'false'
conf -= Algorithm.gauss(neighbor[:similarity])
end
end
if conf > 0.0
prediction = true
elsif conf < 0.0
prediction = false
else
prediction = nil
end
confidence = conf/neighbors.size if neighbors.size > 0
{:prediction => prediction, :confidence => confidence.abs}
end
# Local support vector regression from neighbors
# @param [Array] neighbors, each neighbor is a hash with keys `:similarity, :activity, :features`
# @param [Hash] params Keys `:similarity_algorithm,:p_values` are required
# @return [Hash] Hash with keys `:prediction, :confidence`
def self.local_svm_regression(neighbors,params )
sims = neighbors.collect{ |n| n[:similarity] } # similarity values between query and neighbors
conf = sims.inject{|sum,x| sum + x }
acts = neighbors.collect do |n|
act = n[:activity]
Math.log10(act.to_f)
end # activities of neighbors for supervised learning
neighbor_matches = neighbors.collect{ |n| n[:features] } # as in classification: URIs of matches
gram_matrix = [] # square matrix of similarities between neighbors; implements weighted tanimoto kernel
if neighbor_matches.size == 0
raise "No neighbors found"
else
# gram matrix
(0..(neighbor_matches.length-1)).each do |i|
gram_matrix[i] = [] unless gram_matrix[i]
# upper triangle
((i+1)..(neighbor_matches.length-1)).each do |j|
sim = eval("#{params[:similarity_algorithm]}(neighbor_matches[i], neighbor_matches[j], params[:p_values])")
gram_matrix[i][j] = Algorithm.gauss(sim)
gram_matrix[j] = [] unless gram_matrix[j]
gram_matrix[j][i] = gram_matrix[i][j] # lower triangle
end
gram_matrix[i][i] = 1.0
end
LOGGER.debug gram_matrix.to_yaml
@r = RinRuby.new(false,false) # global R instance leads to Socket errors after a large number of requests
@r.eval "library('kernlab')" # this requires R package "kernlab" to be installed
LOGGER.debug "Setting R data ..."
# set data
@r.gram_matrix = gram_matrix.flatten
@r.n = neighbor_matches.size
@r.y = acts
@r.sims = sims
LOGGER.debug "Preparing R data ..."
# prepare data
@r.eval "y<-as.vector(y)"
@r.eval "gram_matrix<-as.kernelMatrix(matrix(gram_matrix,n,n))"
@r.eval "sims<-as.vector(sims)"
# model + support vectors
LOGGER.debug "Creating SVM model ..."
@r.eval "model<-ksvm(gram_matrix, y, kernel=matrix, type=\"nu-svr\", nu=0.8)"
@r.eval "sv<-as.vector(SVindex(model))"
@r.eval "sims<-sims[sv]"
@r.eval "sims<-as.kernelMatrix(matrix(sims,1))"
LOGGER.debug "Predicting ..."
@r.eval "p<-predict(model,sims)[1,1]"
prediction = 10**(@r.p.to_f)
LOGGER.debug "Prediction is: '" + @prediction.to_s + "'."
@r.quit # free R
end
confidence = conf/neighbors.size if neighbors.size > 0
{:prediction => prediction, :confidence => confidence}
end
end
module Substructure
include Algorithm
# Substructure matching
# @param [OpenTox::Compound] compound Compound
# @param [Array] features Array with Smarts strings
# @return [Array] Array with matching Smarts
def self.match(compound,features)
compound.match(features)
end
end
module Dataset
include Algorithm
# API should match Substructure.match
def features(dataset_uri,compound_uri)
end
end
# Gauss kernel
# @return [Float]
def self.gauss(x, sigma = 0.3)
d = 1.0 - x
Math.exp(-(d*d)/(2*sigma*sigma))
end
# Median of an array
# @param [Array] Array with values
# @return [Float] Median
def self.median(array)
return nil if array.empty?
array.sort!
m_pos = array.size / 2
return array.size % 2 == 1 ? array[m_pos] : (array[m_pos-1] + array[m_pos])/2
end
end
end
|