diff options
Diffstat (limited to 'lib/model.rb')
| -rw-r--r-- | lib/model.rb | 146 |
1 files changed, 115 insertions, 31 deletions
diff --git a/lib/model.rb b/lib/model.rb index 74408d8..998d2dc 100644 --- a/lib/model.rb +++ b/lib/model.rb @@ -23,7 +23,7 @@ module OpenTox # Generic OpenTox model class for all API compliant services class Generic include Model - + # Find Generic Opentox Model via URI, and loads metadata, could raise NotFound/NotAuthorized error # @param [String] uri Model URI # @return [OpenTox::Model::Generic] Model instance @@ -34,21 +34,20 @@ module OpenTox raise "could not load model metadata '"+uri.to_s+"'" if model.metadata==nil or model.metadata.size==0 model end - - # provides feature type, possible types are "regression" or "classification" - # @return [String] feature type, "unknown" if type could not be estimated + + # provides feature type, possible types are "regression" or "classification" + # @return [String] feature type, "unknown" if type could not be estimated def feature_type(subjectid=nil) return @feature_type if @feature_type - + # dynamically perform restcalls if necessary load_metadata(subjectid) if @metadata==nil or @metadata.size==0 or (@metadata.size==1 && @metadata.values[0]==@uri) algorithm = OpenTox::Algorithm::Generic.find(@metadata[OT.algorithm], subjectid) algorithm_title = algorithm ? algorithm.metadata[DC.title] : nil - algorithm_type = algorithm ? algorithm.metadata[OT.isA] : nil + algorithm_type = algorithm ? algorithm.metadata[RDF.type] : nil dependent_variable = OpenTox::Feature.find( @metadata[OT.dependentVariables],subjectid ) dependent_variable_type = dependent_variable ? dependent_variable.feature_type : nil - type_indicators = [dependent_variable_type, @metadata[OT.isA], @metadata[DC.title], - @uri, algorithm_type, algorithm_title] + type_indicators = [dependent_variable_type, @metadata[RDF.type], @metadata[DC.title], @uri, algorithm_type, algorithm_title].flatten type_indicators.each do |type| case type when /(?i)classification/ @@ -61,9 +60,9 @@ module OpenTox raise "unknown model "+type_indicators.inspect unless @feature_type @feature_type end - + end - + # Lazy Structure Activity Relationship class class Lazar @@ -79,7 +78,7 @@ module OpenTox else super CONFIG[:services]["opentox-model"] end - + @metadata[OT.algorithm] = File.join(CONFIG[:services]["opentox-algorithm"],"lazar") @features = [] @@ -113,9 +112,10 @@ module OpenTox # @param [optional,Hash] params Parameters for the lazar algorithm (OpenTox::Algorithm::Lazar) # @return [OpenTox::Model::Lazar] lazar model def self.create(params) + subjectid = params[:subjectid] lazar_algorithm = OpenTox::Algorithm::Generic.new File.join( CONFIG[:services]["opentox-algorithm"],"lazar") model_uri = lazar_algorithm.run(params) - OpenTox::Model::Lazar.find(model_uri, params[:subjectid]) + OpenTox::Model::Lazar.find(model_uri, subjectid) end # Get a parameter value @@ -178,16 +178,72 @@ module OpenTox return @prediction_dataset if database_activity(subjectid) - neighbors - prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values})") + if metadata[RDF.type] == [OTA.ClassificationLazySingleTarget] + # AM: Balancing, see http://www.maunz.de/wordpress/opentox/2011/balanced-lazar + l = Array.new # larger + s = Array.new # smaller fraction + @fingerprints.each do |training_compound,training_features| + @activities[training_compound].each do |act| + case act.to_s + when "false" + l << training_compound + when "true" + s << training_compound + else + LOGGER.warn "BLAZAR: Activity #{act.to_s} should not be reached." + end + end + end + if s.size > l.size then + l,s = s,l # happy swapping + LOGGER.info "BLAZAR: |s|=#{s.size}, |l|=#{l.size}." + end + # determine ratio + modulo = l.size.divmod(s.size)# modulo[0]=ratio, modulo[1]=rest + LOGGER.info "BLAZAR: Balance: #{modulo[0]}, rest #{modulo[1]}." + + # AM: Balanced predictions + addon = (modulo[1].to_f/modulo[0]).ceil # what will be added in each round + slack = modulo[1].divmod(addon)[1] # what remains for the last round + position = 0 + predictions = Array.new + + prediction_best=nil + neighbors_best=nil + + begin + for i in 1..modulo[0] do + (i == modulo[0]) && (slack>0) ? lr_size = s.size + slack : lr_size = s.size + addon # determine fraction + LOGGER.info "BLAZAR: Neighbors round #{i}: #{position} + #{lr_size}." + neighbors_balanced(s, l, position, lr_size) # get ratio fraction of larger part + prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values})") + if prediction_best.nil? || prediction[:confidence].abs > prediction_best[:confidence].abs + prediction_best=prediction + neighbors_best=@neighbors + end + position = position + lr_size + end + rescue Exception => e + LOGGER.error "BLAZAR failed in prediction: "+e.class.to_s+": "+e.message + end + + prediction=prediction_best + @neighbors=neighbors_best + ### END AM balanced predictions + + else # regression case: no balancing + neighbors + prediction = eval("#{@prediction_algorithm}(@neighbors,{:similarity_algorithm => @similarity_algorithm, :p_values => @p_values})") + end + prediction_feature_uri = File.join( @prediction_dataset.uri, "feature", "prediction", File.basename(@metadata[OT.dependentVariables]),@prediction_dataset.compounds.size.to_s) # TODO: fix dependentVariable @prediction_dataset.metadata[OT.dependentVariables] = prediction_feature_uri if @neighbors.size == 0 @prediction_dataset.add_feature(prediction_feature_uri, { - OT.isA => OT.MeasuredFeature, + RDF.type => [OT.MeasuredFeature], OT.hasSource => @uri, DC.creator => @uri, DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )), @@ -198,7 +254,7 @@ module OpenTox else @prediction_dataset.add_feature(prediction_feature_uri, { - OT.isA => OT.ModelPrediction, + RDF.type => [OT.ModelPrediction], OT.hasSource => @uri, DC.creator => @uri, DC.title => URI.decode(File.basename( @metadata[OT.dependentVariables] )), @@ -215,7 +271,7 @@ module OpenTox feature_uri = File.join( @prediction_dataset.uri, "feature", "descriptor", f.to_s) features[feature] = feature_uri @prediction_dataset.add_feature(feature_uri, { - OT.isA => OT.Substructure, + RDF.type => [OT.Substructure], OT.smarts => feature, OT.pValue => @p_values[feature], OT.effect => @effects[feature] @@ -236,7 +292,7 @@ module OpenTox OT.compound => neighbor[:compound], OT.similarity => neighbor[:similarity], OT.measuredActivity => neighbor[:activity], - OT.isA => OT.Neighbor + RDF.type => [OT.Neighbor] }) @prediction_dataset.add @compound.uri, neighbor_uri, true f = 0 unless f @@ -250,7 +306,7 @@ module OpenTox unless features.has_key? feature features[feature] = feature_uri @prediction_dataset.add_feature(feature_uri, { - OT.isA => OT.Substructure, + RDF.type => [OT.Substructure], OT.smarts => feature, OT.pValue => @p_values[feature], OT.effect => @effects[feature] @@ -269,27 +325,55 @@ module OpenTox end # Find neighbors and store them as object variable - def neighbors - + def neighbors_balanced(s, l, start, offset) @compound_features = eval("#{@feature_calculation_algorithm}(@compound,@features)") if @feature_calculation_algorithm @neighbors = [] - @fingerprints.each do |training_compound,training_features| - sim = eval("#{@similarity_algorithm}(@compound_features,training_features,@p_values)") - if sim > @min_sim - @activities[training_compound].each do |act| - @neighbors << { - :compound => training_compound, - :similarity => sim, - :features => training_features, - :activity => act - } + begin + #@fingerprints.each do |training_compound,training_features| # AM: this is original by CH + [ l[start, offset ] , s ].flatten.each do |training_compound| # AM: access only a balanced subset + training_features = @fingerprints[training_compound] + sim = eval("#{@similarity_algorithm}(@compound_features,training_features,@p_values)") + if sim > @min_sim + @activities[training_compound].each do |act| + this_neighbor = { + :compound => training_compound, + :similarity => sim, + :features => training_features, + :activity => act + } + @neighbors << this_neighbor + end end end + rescue Exception => e + LOGGER.error "BLAZAR failed in neighbors: "+e.class.to_s+": "+e.message end end + + # Find neighbors and store them as object variable + def neighbors + + @compound_features = eval("#{@feature_calculation_algorithm}(@compound,@features)") if @feature_calculation_algorithm + + @neighbors = [] + @fingerprints.each do |training_compound,training_features| + sim = eval("#{@similarity_algorithm}(@compound_features,training_features,@p_values)") + if sim > @min_sim + @activities[training_compound].each do |act| + @neighbors << { + :compound => training_compound, + :similarity => sim, + :features => training_features, + :activity => act + } + end + end + end + end + # Find database activities and store them in @prediction_dataset # @return [Boolean] true if compound has databasse activities, false if not def database_activity(subjectid) |