sigFeature.enfold {sigFeature} | R Documentation |
After converting the dataset into k-folds the function named "sigFeature.enfold()" is used to select significant features from the classes. The randomization process is used to sub-sample the dataset.
sigFeature.enfold(x, y, CV, CVnumber=0)
x |
n-by-d data matrix to train (n chips/patients, d clones/genes) |
y |
vector of class labels -1 or 1 s (for n chips/patiens ) |
CV |
the number of folds in case of k-fold cross validation. |
CVnumber |
the number of folds in case of n fold cross validation. |
The "sigFeature()" function is further enhanced by incorporating one cross validation methods such as k-fold external cross validation. In this k-fold cross validation procedure k-1 fold are used for selecting the feature and one fold remain untouched which will latter used as test sample set.
feature.ids |
selected significant features. |
train.data.ids |
training chips/patients ids. |
test.data.ids |
testng chips/patients ids. |
train.data.level |
vector of class labels -1 or 1s (for n chips/patiens ) for train da. |
test.data.level |
vector of class labels -1 or 1s (for n chips/patiens ) for test da. |
This function will compute the feature with cross checking.
Pijush Das <topijush@gmail.com>, et al.
Zhang, H. H., Ahn, J., Lin, X. and Park, C. (2006). Gene selection using support vector machines with nonconvex penalty. Bioinformatics, 22, pp. 88-95.
findgacv.scad, predict.penSVM, sim.data
#Example for sigFeature.enfold() #Data set taken from GSE2280 #library(SummarizedExperiment) #data(ExampleRawData, package="sigFeature") #x <- t(assays(ExampleRawData)$counts) #y <- colData(ExampleRawData)$sampleLabels #For ten fold external cross validation. #results = sigFeature.enfold(x,y,"kfold",10) #Compactly display the internal structure of an R object named "results" data(results) str(results)