kebabs (version 1.6.2)

ModelSelectionResultAccessors: ModelSelectionResult Accessors

Description

ModelSelectionResult Accessors

Usage

## S3 method for class 'ModelSelectionResult':
gridRows(object)

Arguments

object

a model selection result object (can be extracted from KeBABS model with accessor modelSelResult)

Value

• gridRows: returns a list of kernel objects gridColumns: returns a DataFrame object with grid column parameters gridErrors: returns a matrix with grid errors performance: returns a list of matrices with performance values selGridRow: returns the selected kernel selGridCol: returns the selected SVM and/or hyperparameter(s) fullModel: returns a kebabs model of class KBModel

References

http://www.bioinf.jku.at/software/kebabs J. Palme, S. Hochreiter, and U. Bodenhofer (2015) KeBABS: an R package for kernel-based analysis of biological sequences. Bioinformatics, 31(15):2574-2576, 2015. DOI: http://dx.doi.org/10.1093/bioinformatics/btv176{10.1093/bioinformatics/btv176}.

Examples

## create kernel object for normalized spectrum kernel
specK5 <- spectrumKernel(k=5)
## load data
data(TFBS)

## perform training - feature weights are computed by default
model <- kbsvm(enhancerFB, yFB, specK5, pkg="LiblineaR",
               svm="C-svc", cost=c(1,15,50,100), cross=10,
               perfParameters="ALL", showProgress=TRUE)

## show model selection result
mres <- modelSelResult(model)
mres

## extract grid errors
gridErrors(mres)

## extract other performance parameters
performance(mres)