GPASDiscrimination {RFreak}R Documentation

Execute the GPAS algorithm for discrimination

Description

Working on categorical data with binary response, the algorithm searches for multi-valued logic expressions in disjunctive normal form discriminating between response 0 and response 1. The algorithm is intended for genetic association studies on SNP data.

Usage

GPASDiscrimination(resp.train, preds.train, resp.test=NULL,
  preds.test=NULL, runs = 1, generations = 10000)

Arguments

resp.train Vector with the response variables of the training data set
preds.train Matrix or data frame with the predictors of the training data set
resp.test Optional vector with the response variables of the test data set
preds.test Optional matrix or data frame with the predictors of the test data set
runs Number of independent runs of GPAS
generations Number of generations after which the algorithm will be stopped

Value

Returns an object of class GPAS with a data.frame in its slot summary containing information about the last population of the executed discrimination runs. For each individual in the last population the following information is contained:

data set Either 'training' or 'test' or omitted
run The run the individual was found in
generation The generation the individual was created in
objective value 1 Correctly predicted cases
objective value 2 Correctly predicted controls
objective value 3 Length of the individual
individual A string representation of the individual

Author(s)

Robin Nunkesser Robin.Nunkesser@tu-dortmund.de

References

R. Nunkesser, T. Bernholt, H. Schwender, K. Ickstadt, and I. Wegener (2007). Detecting High-Order Interactions of Single Nucleotide Polymorphisms Using Genetic Programming. Bioinformatics, 23, 3280-3288.

See Also

"GPAS", GPASInteractions

Examples

# load example data
data(data.logicfs)

# execute GPAS to discriminate between cases and controls
GPASDiscrimination(cl.logicfs,data.logicfs,runs=1,generations=1000)

[Package RFreak version 0.2-5 Index]