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
|
require 'csv'
module OpenTox
module Algorithm
include OpenTox
# Calculate physico-chemical descriptors.
# @param[Hash] Required keys: :dataset_uri, :pc_type
# @return[String] dataset uri
def self.pc_descriptors(params)
begin
ds = OpenTox::Dataset.find(params[:dataset_uri])
compounds = ds.compounds.collect
ambit_result_uri, smiles_to_inchi = get_pc_descriptors( { :compounds => compounds, :pc_type => params[:pc_type] } )
#ambit_result_uri = ["http://apps.ideaconsult.net:8080/ambit2/dataset/987103?" ,"feature_uris[]=http%3A%2F%2Fapps.ideaconsult.net%3A8080%2Fambit2%2Ffeature%2F4276789&", "feature_uris[]=http%3A%2F%2Fapps.ideaconsult.net%3A8080%2Fambit2%2Fmodel%2F16%2Fpredicted"] # for testing
LOGGER.debug "Ambit result uri for #{params.inspect}: '#{ambit_result_uri.to_yaml}'"
load_ds_csv(ambit_result_uri, smiles_to_inchi)
rescue Exception => e
LOGGER.debug "#{e.class}: #{e.message}"
LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
end
end
# Calculates PC descriptors via Ambit -- DO NOT OVERLOAD Ambit.
# @param[Hash] Required keys: :compounds, :pc_type
# @return[Array] Ambit result uri, piecewise (1st: base, 2nd: SMILES, 3rd+: features
def self.get_pc_descriptors(params)
begin
ambit_ds_service_uri = "http://apps.ideaconsult.net:8080/ambit2/dataset/"
ambit_mopac_model_uri = "http://apps.ideaconsult.net:8080/ambit2/model/69632"
descs = YAML::load_file( File.join(ENV['HOME'], ".opentox", "config", "ambit_descriptors.yaml") )
descs_uris = []
params[:pc_type] = "electronic,cpsa" if params[:pc_type].nil? # rescue missing pc_type
types = params[:pc_type].split(",")
descs.each { |uri, cat_name|
if types.include? cat_name[:category]
descs_uris << uri
end
}
if descs_uris.size == 0
raise "Error! Empty set of descriptors. Did you supply one of [geometrical, topological, electronic, constitutional, hybrid, cpsa] ?"
end
#LOGGER.debug "Ambit descriptor URIs: #{descs_uris.join(", ")}"
begin
# Create SMI
smiles_array = []; smiles_to_inchi = {}
params[:compounds].each do |n|
cmpd = OpenTox::Compound.new(n)
smiles_string = cmpd.to_smiles
smiles_to_inchi[smiles_string] = URI.encode_www_form_component(cmpd.to_inchi)
smiles_array << smiles_string
end
smi_file = Tempfile.open(['pc_ambit', '.csv'])
pc_descriptors = nil
# Create Ambit dataset
smi_file.puts( "SMILES\n" )
smi_file.puts( smiles_array.join("\n") )
smi_file.flush
ambit_ds_uri = OpenTox::RestClientWrapper.post(ambit_ds_service_uri, {:file => File.new(smi_file.path)}, {:content_type => "multipart/form-data", :accept => "text/uri-list"} )
rescue Exception => e
LOGGER.debug "#{e.class}: #{e.message}"
LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
ensure
smi_file.close! if smi_file
end
ambit_smiles_uri = OpenTox::RestClientWrapper.get(ambit_ds_uri + "/features", {:accept=> "text/uri-list"} ).chomp
# Calculate 3D for CPSA
if types.include? "cpsa"
ambit_ds_mopac_uri = OpenTox::RestClientWrapper.post(ambit_mopac_model_uri, {:dataset_uri => ambit_ds_uri}, {:accept => "text/uri-list"} )
LOGGER.debug "MOPAC dataset: #{ambit_ds_mopac_uri }"
end
# Get Ambit results
ambit_result_uri = [] # 1st pos: base uri, then features
ambit_result_uri << ambit_ds_uri + "?"
ambit_result_uri << ("feature_uris[]=" + URI.encode_www_form_component(ambit_smiles_uri) + "&")
descs_uris.each_with_index do |uri, i|
algorithm = Algorithm::Generic.new(uri)
result_uri = algorithm.run({:dataset_uri => ambit_ds_uri})
ambit_result_uri << result_uri.split("?")[1] + "&"
LOGGER.debug "Ambit (#{descs_uris.size}): #{i+1}"
end
#LOGGER.debug "Ambit result: #{ambit_result_uri.join('')}"
[ ambit_result_uri, smiles_to_inchi ]
rescue Exception => e
LOGGER.debug "#{e.class}: #{e.message}"
LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
end
end
# Load dataset via CSV
# @param[Array] Ambit result uri, piecewise (1st: base, 2nd: SMILES, 3rd+: features
# @return[String] dataset uri
def self.load_ds_csv(ambit_result_uri, smiles_to_inchi, subjectid=nil)
master=nil
(1...ambit_result_uri.size).collect { |idx|
curr_uri = ambit_result_uri[0] + ambit_result_uri[idx]
LOGGER.debug "Requesting #{curr_uri}"
csv_data = CSV.parse( OpenTox::RestClientWrapper.get(curr_uri, {:accept => "text/csv", :subjectid => subjectid}) )
if csv_data[0] && csv_data[0].size>1
if master.nil? # This is the smiles entry
(1...csv_data.size).each{ |idx| csv_data[idx][1] = smiles_to_inchi[csv_data[idx][1]] }
master = csv_data
next
else
index_uri = csv_data[0].index("SMILES")
csv_data.map {|i| i.delete_at(index_uri)} if index_uri #Removes additional SMILES information
nr_cols = (csv_data[0].size)-1
LOGGER.debug "Merging #{nr_cols} new columns"
master.each {|row| nr_cols.times { row.push(nil) } } # Adds empty columns to all rows
csv_data.each do |row|
temp = master.assoc(row[0]) # Finds the appropriate line in master
((-1*nr_cols)..-1).collect.each { |idx|
temp[idx] = row[nr_cols+idx+1] if temp # Updates columns if line is found
}
end
end
end
}
index_uri = master[0].index("Compound")
master.map {|i| i.delete_at(index_uri)}
master[0].each {|cell| cell.chomp!(" ")}
master[0][0] = "Compound" #"SMILES"
index_smi = master[0].index("SMILES")
master.map {|i| i.delete_at(index_smi)} if index_smi
#master[0][0] = "SMILES"
#LOGGER.debug "-------- AM: Writing to dumpfile"
#File.open("/tmp/test.csv", 'w') {|f| f.write( master.collect {|r| r.join(",")}.join("\n") ) }
parser = OpenTox::Parser::Spreadsheets.new
ds = OpenTox::Dataset.new(nil,subjectid)
ds.save(subjectid)
parser.dataset = ds
ds = parser.load_csv(master.collect{|r| r.join(",")}.join("\n"))
ds.save(subjectid)
end
# Gauss kernel
# @return [Float]
def self.gauss(x, sigma = 0.3)
d = 1.0 - x.to_f
Math.exp(-(d*d)/(2*sigma*sigma))
end
# For symbolic features
# @param [Array] Array to test, must indicate non-occurrence with 0.
# @return [Boolean] Whether the feature is singular or non-occurring or present everywhere.
def self.isnull_or_singular?(array)
nr_zeroes = array.count(0)
return (nr_zeroes == array.size) || # remove non-occurring feature
(nr_zeroes == array.size-1) || # remove singular feature
(nr_zeroes == 0) # also remove feature present everywhere
end
# Numeric value test
# @param[Object] value
# @return [Boolean] Whether value is a number
def self.numeric?(value)
true if Float(value) rescue false
end
# For symbolic features
# @param [Array] Array to test, must indicate non-occurrence with 0.
# @return [Boolean] Whether the feature has variance zero.
def self.zero_variance?(array)
return array.uniq.size == 1
end
# Sum of an array for Arrays.
# @param [Array] Array with values
# @return [Integer] Sum of size of values
def self.sum_size(array)
sum=0
array.each { |e| sum += e.size }
return sum
end
# Minimum Frequency
# @param [Integer] per-mil value
# return [Integer] min-frequency
def self.min_frequency(training_dataset,per_mil)
minfreq = per_mil * training_dataset.compounds.size.to_f / 1000.0 # AM sugg. 8-10 per mil for BBRC, 50 per mil for LAST
minfreq = 2 unless minfreq > 2
Integer (minfreq)
end
# Effect calculation for classification
# @param [Array] Array of occurrences per class in the form of Enumerables.
# @param [Array] Array of database instance counts per class.
def self.effect(occurrences, db_instances)
max=0
max_value=0
nr_o = self.sum_size(occurrences)
nr_db = db_instances.to_scale.sum
occurrences.each_with_index { |o,i| # fminer outputs occurrences sorted reverse by activity.
actual = o.size.to_f/nr_o
expected = db_instances[i].to_f/nr_db
if actual > expected
if ((actual - expected) / actual) > max_value
max_value = (actual - expected) / actual # 'Schleppzeiger'
max = i
end
end
}
max
end
# neighbors
module Neighbors
# Get confidence.
# @param[Hash] Required keys: :sims, :acts
# @return[Float] Confidence
def self.get_confidence(params)
conf = params[:sims].inject{|sum,x| sum + x }
confidence = conf/params[:sims].size
LOGGER.debug "Confidence is: '" + confidence.to_s + "'."
return confidence
end
end
# Similarity calculations
module Similarity
# Tanimoto similarity
# @param [Hash, Array] fingerprints of first compound
# @param [Hash, Array] fingerprints of second compound
# @return [Float] (Weighted) tanimoto similarity
def self.tanimoto(fingerprints_a,fingerprints_b,weights=nil,params=nil)
common_p_sum = 0.0
all_p_sum = 0.0
# fingerprints are hashes
if fingerprints_a.class == Hash && fingerprints_b.class == Hash
common_features = fingerprints_a.keys & fingerprints_b.keys
all_features = (fingerprints_a.keys + fingerprints_b.keys).uniq
if common_features.size > 0
common_features.each{ |f| common_p_sum += [ fingerprints_a[f], fingerprints_b[f] ].min }
all_features.each{ |f| all_p_sum += [ fingerprints_a[f],fingerprints_b[f] ].compact.max } # compact, since one fp may be empty at that pos
end
# fingerprints are arrays
elsif fingerprints_a.class == Array && fingerprints_b.class == Array
size = [ fingerprints_a.size, fingerprints_b.size ].min
LOGGER.warn "fingerprints don't have equal size" if fingerprints_a.size != fingerprints_b.size
(0...size).each { |idx|
common_p_sum += [ fingerprints_a[idx], fingerprints_b[idx] ].min
all_p_sum += [ fingerprints_a[idx], fingerprints_b[idx] ].max
}
end
(all_p_sum > 0.0) ? (common_p_sum/all_p_sum) : 0.0
end
# Cosine similarity
# @param [Hash] properties_a key-value properties of first compound
# @param [Hash] properties_b key-value properties of second compound
# @return [Float] cosine of angle enclosed between vectors induced by keys present in both a and b
def self.cosine(fingerprints_a,fingerprints_b,weights=nil)
# fingerprints are hashes
if fingerprints_a.class == Hash && fingerprints_b.class == Hash
a = []; b = []
common_features = fingerprints_a.keys & fingerprints_b.keys
if common_features.size > 1
common_features.each do |p|
a << fingerprints_a[p]
b << fingerprints_b[p]
end
end
# fingerprints are arrays
elsif fingerprints_a.class == Array && fingerprints_b.class == Array
a = fingerprints_a
b = fingerprints_b
end
(a.size > 0 && b.size > 0) ? self.cosine_num(a.to_gv, b.to_gv) : 0.0
end
# Cosine similarity
# @param [GSL::Vector] a
# @param [GSL::Vector] b
# @return [Float] cosine of angle enclosed between a and b
def self.cosine_num(a, b)
if a.size>12 && b.size>12
a = a[0..11]
b = b[0..11]
end
a.dot(b) / (a.norm * b.norm)
end
# Outlier detection based on Mahalanobis distances
# Multivariate detection on X, univariate detection on y
# Uses an existing Rinruby instance, if possible
# @param[Hash] Keys query_matrix, data_matrix, acts are required; r, p_outlier optional
# @return[Array] indices identifying outliers (may occur several times, this is intended)
def self.outliers(params)
outlier_array = []
data_matrix = params[:data_matrix]
query_matrix = params[:query_matrix]
acts = params[:acts]
begin
LOGGER.debug "Outliers (p=#{params[:p_outlier] || 0.9999})..."
r = ( params[:r] || RinRuby.new(false,false) )
r.eval "suppressPackageStartupMessages(library(\"robustbase\"))"
r.eval "outlier_threshold = #{params[:p_outlier] || 0.999}"
nr_cases, nr_features = data_matrix.to_a.size, data_matrix.to_a[0].size
r.odx = data_matrix.to_a.flatten
r.q = query_matrix.to_a.flatten
r.y = acts.to_a.flatten
r.eval "odx = matrix(odx, #{nr_cases}, #{nr_features}, byrow=T)"
r.eval 'odx = rbind(q,odx)' # query is nr 0 (1) in ruby (R)
r.eval 'mah = covMcd(odx)$mah' # run MCD alg
r.eval "mah = pchisq(mah,#{nr_features})"
r.eval 'outlier_array = which(mah>outlier_threshold)' # multivariate outliers using robust mahalanobis
outlier_array = r.outlier_array.to_a.collect{|v| v-2 } # translate to ruby index (-1 for q, -1 due to ruby)
r.eval 'fqu = matrix(summary(y))[2]'
r.eval 'tqu = matrix(summary(y))[5]'
r.eval 'outlier_array = which(y>(tqu+1.5*IQR(y)))' # univariate outliers due to Tukey (http://goo.gl/mwzNH)
outlier_array += r.outlier_array.to_a.collect{|v| v-1 } # translate to ruby index (-1 due to ruby)
r.eval 'outlier_array = which(y<(fqu-1.5*IQR(y)))'
outlier_array += r.outlier_array.to_a.collect{|v| v-1 }
rescue Exception => e
LOGGER.debug "#{e.class}: #{e.message}"
#LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
end
outlier_array
end
end
end
end
|