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
|
module OpenTox
module Algorithm
class Regression
def self.local_weighted_average compound, params
weighted_sum = 0.0
sim_sum = 0.0
neighbors = params[:neighbors]
neighbors.each do |row|
sim = row["tanimoto"]
if row["features"][params[:prediction_feature_id].to_s]
row["features"][params[:prediction_feature_id].to_s].each do |act|
weighted_sum += sim*Math.log10(act)
sim_sum += sim
end
end
end
sim_sum == 0 ? prediction = nil : prediction = 10**(weighted_sum/sim_sum)
{:value => prediction}
end
# TODO explicit neighbors, also for physchem
def self.local_fingerprint_regression compound, params, method='pls'#, method_params="sigma=0.05"
neighbors = params[:neighbors]
return {:value => nil, :confidence => nil, :warning => "No similar compounds in the training data"} unless neighbors.size > 0
activities = []
fingerprints = {}
weights = []
fingerprint_ids = neighbors.collect{|row| Compound.find(row["_id"]).fingerprint}.flatten.uniq.sort
neighbors.each_with_index do |row,i|
neighbor = Compound.find row["_id"]
fingerprint = neighbor.fingerprint
if row["features"][params[:prediction_feature_id].to_s]
row["features"][params[:prediction_feature_id].to_s].each do |act|
activities << Math.log10(act)
weights << row["tanimoto"]
fingerprint_ids.each_with_index do |id,j|
fingerprints[id] ||= []
fingerprints[id] << fingerprint.include?(id)
end
end
end
end
variables = []
data_frame = [activities]
fingerprints.each do |k,v|
unless v.uniq.size == 1
data_frame << v.collect{|m| m ? "T" : "F"}
variables << k
end
end
if variables.empty?
result = local_weighted_average(compound, params)
result[:warning] = "No variables for regression model. Using weighted average of similar compounds."
return result
else
compound_features = variables.collect{|f| compound.fingerprint.include?(f) ? "T" : "F"}
prediction = r_model_prediction method, data_frame, variables, weights, compound_features
if prediction.nil? or prediction[:value].nil?
prediction = local_weighted_average(compound, params)
prediction[:warning] = "Could not create local PLS model. Using weighted average of similar compounds."
return prediction
else
prediction[:prediction_interval] = [10**(prediction[:value]-1.96*prediction[:rmse]), 10**(prediction[:value]+1.96*prediction[:rmse])]
prediction[:value] = 10**prediction[:value]
prediction[:rmse] = 10**prediction[:rmse]
prediction
end
end
end
def self.local_physchem_regression compound, params, method="plsr"#, method_params="ncomp = 4"
neighbors = params[:neighbors]
return {:value => nil, :confidence => nil, :warning => "No similar compounds in the training data"} unless neighbors.size > 0
return {:value => neighbors.first["features"][params[:prediction_feature_id]], :confidence => nil, :warning => "Only one similar compound in the training set"} unless neighbors.size > 1
activities = []
weights = []
physchem = {}
neighbors.each_with_index do |row,i|
neighbor = Compound.find row["_id"]
if row["features"][params[:prediction_feature_id].to_s]
row["features"][params[:prediction_feature_id].to_s].each do |act|
activities << Math.log10(act)
weights << row["tanimoto"] # TODO cosine ?
neighbor.physchem.each do |pid,v| # insert physchem only if there is an activity
physchem[pid] ||= []
physchem[pid] << v
end
end
end
end
# remove properties with a single value
physchem.each do |pid,v|
physchem.delete(pid) if v.uniq.size <= 1
end
if physchem.empty?
result = local_weighted_average(compound, params)
result[:warning] = "No variables for regression model. Using weighted average of similar compounds."
return result
else
data_frame = [activities] + physchem.keys.collect { |pid| physchem[pid] }
prediction = r_model_prediction method, data_frame, physchem.keys, weights, physchem.keys.collect{|pid| compound.physchem[pid]}
if prediction.nil?
prediction = local_weighted_average(compound, params)
prediction[:warning] = "Could not create local PLS model. Using weighted average of similar compounds."
return prediction
else
prediction[:value] = 10**prediction[:value]
prediction
end
end
end
def self.r_model_prediction method, training_data, training_features, training_weights, query_feature_values
R.assign "weights", training_weights
r_data_frame = "data.frame(#{training_data.collect{|r| "c(#{r.join(',')})"}.join(', ')})"
R.eval "data <- #{r_data_frame}"
R.assign "features", training_features
R.eval "names(data) <- append(c('activities'),features)" #
begin
R.eval "model <- train(activities ~ ., data = data, method = '#{method}')"
rescue
return nil
end
R.eval "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
R.eval "names(fingerprint) <- features"
R.eval "prediction <- predict(model,fingerprint)"
{
:value => R.eval("prediction").to_f,
:rmse => R.eval("getTrainPerf(model)$TrainRMSE").to_f,
:r_squared => R.eval("getTrainPerf(model)$TrainRsquared").to_f,
}
end
end
end
end
|
