summaryrefslogtreecommitdiff
path: root/lib/model.rb
blob: 172669041981afafcde2b67ac95fd67149bd765f (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
class String
  def numeric?
    Float(self) != nil rescue false
  end
end

class Model 

  attr_reader :train, :dependent_variable_name, :independent_variable_names, :minsim

  def initialize file
    puts "Reading training data from #{file}."
    @train = File.readlines(file).collect{|l| l.chomp.split(",")}
    header = @train.shift
    @dependent_variable_name = header[1]
    @independent_variable_names = header[2..-1]
    model_type
  end

  def model_type
    puts "Determining model type."
    if dependent_variables.uniq.sort == ["0","1"]
      @dependent_variable_type = "binary"
      @train.each {|t| t[1] = t[1].to_i}
    elsif dependent_variables.collect{|v| v.numeric?}.uniq == [true]
      @dependent_variable_type = "numeric"
      @train.each {|t| t[1] = t[1].to_f }
    else
      raise "Incorrect model dependent variables [#{dependent_variables.uniq}]. Must be either [0,1] or numeric."
    end
    if independent_variables.flatten.collect{|v| v.numeric?}.uniq == [false]
      @independent_variable_type = "set"
      @minsim = [0.5,0.2]
    elsif independent_variables.flatten.collect{|v| v.numeric?}.uniq == [true]
      @independent_variable_type = "numeric"
      @train.each {|t| t[2..-1] = t[2..-1].collect{|v| v = v.to_f}}
      @minsim = [0.9,0.7]
    else
      raise "Incorrect model independent variables [#{independent_variables.flatten.uniq}]. Must be either a set (fingerprints) or numeric."
    end
  end

  def predict file
    puts "Reading prediction data from #{file}."
    @batch = File.readlines(file).collect{|l| l.chomp.split(",")}
    header = @batch.shift
    unless (@batch.collect{|b| b[1..-1]}.flatten.collect{|v| v.numeric?}.uniq == [false] and @independent_variable_type == "set") or (batch_independent_variables.flatten.collect{|v| v.numeric?}.uniq == [true] and @independent_variable_type == "numeric")
      raise "Incorrect batch independent variables [#{independent_variables.flatten.uniq}]. Must be #{@independent_variable_type}."
    end
    if @independent_variable_type == "numeric"
      @batch_independent_variable_names = header[1..-1]
      @batch.each {|t| t[1..-1] = t[1..-1].collect{|v| v = v.to_f}}
      select(@independent_variable_names & @batch_independent_variable_names)
      File.open(File.join(File.dirname(file),"common-variables.csv"),"w+") do |f|
        f.print "CANSMI,dataset,"
        f.puts @independent_variable_names.join(",")
        @train.each do |row|
          f.puts ([row[0],"train"]+row[2..-1]).join(",")
        end
        @batch.each do |row|
          f.puts ([row[0],"predict"]+row[1..-1]).join(",")
        end
      end
      puts "Feature selection and scaling."
      puts `Rscript #{File.join(File.dirname(__FILE__),"..","bin","preprocessing.R")} #{File.join(File.dirname(file),"common-variables.csv")} #{File.join(File.dirname(file),"scaled-variables.csv")}`
      puts "Reading scaled features."
      lines = File.readlines(File.join(File.dirname(file),"scaled-variables.csv"))
      @independent_variable_names = @batch_independent_variable_names = lines.shift.chomp.split(",")[2..-1]
      @scaled_train = []
      @scaled_batch = []
      lines.each_with_index do |line,i|
        items = line.chomp.split(",")
        if items[1] == "train"
          items[1] = @train[i][1]
          @scaled_train << items.collect{|i| i.to_s.numeric? ? i.to_f : i}
        elsif items[1] == "predict"
          items.delete_at(1)
          @scaled_batch << items.collect{|i| i.to_s.numeric? ? i.to_f : i}
        end
      end
      puts "Predicting #{file}."
      File.open(file.sub(".csv","-prediction.csv"),"w+") do |f|
        f.puts ["Canonical SMILES","Experimental","Prediction","p-inactive","p-active","Max Simimilarity","Nr. Neighbors"].join(",")
        @scaled_batch.each do |pred|
          classification(pred[0], @scaled_train.collect{|row| row[0..1] + [cosine([row[2..-1],pred[1..-1]])]}).each do |pred|
            f.puts pred.join(",")
          end
        end
      end
    elsif @independent_variable_type == "set"
      puts "Predicting #{file}."
      File.open(file.sub(".csv","-prediction.csv"),"w+") do |f|
        f.puts ["Canonical SMILES","Experimental","Prediction","p-inactive","p-active","Max Simimilarity","Nr. Neighbors"].join(",")
        @batch.each do |fingerprints|
          smi = fingerprints.shift
          classification(smi, @train.collect{|row| row[0..1] + [tanimoto([row[2..-1],fingerprints])]}).each do |pred|
            f.puts pred.join(",")
          end
        end
      end
    end
  end

  def select variable_names
    model_variable_idx = [0,1]+variable_names.collect{|n| @independent_variable_names.index(n)+2}
    batch_variable_idx = [0]+variable_names.collect{|n| @batch_independent_variable_names.index(n)+1}
    @train.collect!{|r| model_variable_idx.collect{|i| r[i]}}
    @batch.collect!{|r| batch_variable_idx.collect{|i| r[i]}}
    @independent_variable_names = variable_names
    @batch_independent_variable_names = variable_names
  end

  def classification smiles, train
    experimental = train.select{|row| row[0] == smiles}
    train = train-experimental
    n = train.select{|row| row[2] > @minsim[0]}
    n = train.select!{|row| row[2] > @minsim[1]} if n.size < 2
    train = n
    #p train.sort_by{|r| r[2]}[0..5]#.collect{|r| r.join(",")}.join("\n")
    if train.size < 2
      classification = nil
      probabilities = [nil,nil]
    else
      probabilities = weighted_majority_vote(train)
      probabilities[1] > probabilities[0] ? classification = 1 : classification = 0
    end
    experimental = [[nil,nil,nil]] if experimental.empty?
    experimental.collect do 
      [ smiles, experimental[1], classification ] + probabilities + [ train.collect{|t| t[2]}.max, train.size ]
    end
  end

  # Get Euclidean distance 
  # @param [Array<Array<Float>>]
  # @return [Float]
  def euclid variables
    sq = variables[0].zip(variables[1]).map{|a,b| (a - b) ** 2}
    Math.sqrt(sq.inject(0) {|s,c| s + c})
  end

  # Get Tanimoto similarity
  # @param [Array<Array<String>>]
  # @return [Float]
  def tanimoto fingerprints
    ( fingerprints[0] & fingerprints[1] ).size/( fingerprints[0] | fingerprints[1] ).size.to_f
  end

  # Get cosine similarity
  #   http://stackoverflow.com/questions/1838806/euclidean-distance-vs-pearson-correlation-vs-cosine-similarity
  # @param [Array<Array<Float>>]
  # @return [Float]
  def cosine variables
    variables[0].dot_product(variables[1]) / (variables[0].magnitude * variables[1].magnitude)
  end

  def weighted_majority_vote neighbors
    w = [neighbors.select{|n| n[1] == 0}.collect{|n| n[2]}, neighbors.select{|n| n[1] == 1}.collect{|n| n[2]}]
    weights_sum = neighbors.collect{|n| n[2]}.sum.to_f
    weights_max = neighbors.collect{|n| n[2]}.max.to_f
    [weights_max*w[0].sum/weights_sum, weights_max*w[1].sum/weights_sum]
  end


  def smiles
    @train.collect{|t| t[0]}
  end

  def dependent_variables
    @train.collect{|t| t[1]}
  end

  def independent_variables
    @train.collect{|t| t[2..-1]}
  end

  def batch_smiles
    @batch.collect{|t| t[0]}
  end

  def batch_independent_variables
    @batch.collect{|t| t[1..-1]}
  end

end