Module: OpenTox::Algorithm::Neighbors

Defined in:

lib/algorithm.rb

Class Method Summary

• .local_svm_regression(neighbors, params) ⇒ Hash

  Local support vector regression from neighbors.

• .weighted_majority_vote(neighbors, params = {}) ⇒ Hash

  Classification with majority vote from neighbors weighted by similarity.

Class Method Details

.local_svm_regression(neighbors, params) ⇒ Hash

Local support vector regression from neighbors

Parameters:

• neighbors, (Array) —

  each neighbor is a hash with keys ‘:similarity, :activity, :features`

• params (Hash) —

  Keys ‘:similarity_algorithm,:p_values` are required

Returns:

• (Hash) —

  Hash with keys ‘:prediction, :confidence`

# File 'lib/algorithm.rb', line 167

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

.weighted_majority_vote(neighbors, params = {}) ⇒ Hash

Classification with majority vote from neighbors weighted by similarity

Parameters:

• neighbors, (Array) —

  each neighbor is a hash with keys ‘:similarity, :activity`

• params (optional) (defaults to: {}) —

  Ignored (only for compatibility with local_svm_regression)

Returns:

• (Hash) —

  Hash with keys ‘:prediction, :confidence`

# File 'lib/algorithm.rb', line 141

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