getFeatureScores: Compile network scores into a matrix

In BaderLab/netDx: Network-based patient classifier

Description

Compile network scores into a matrix

Usage

getFeatureScores(inDir, predClasses, getFullCons = TRUE)

Arguments

inDir	(char/list) directory containing directories with all split info or list of all CV score files. if inDir is a single directory then the expected format for CV score files is <inDir>/rngX/predClassX/GM_results/predClassX_pathway_CV_score.txt' if inDir is a list, it should have one key per class. The value should be the corresponding set of filenames for pathway_CV_score.txt
predClasses	(char) possible STATUS for patients
getFullCons	(logical) if TRUE, does not remove rows with NA. Recommended only when the number of input features is extensively pruned by first-pass feature selection.

Details

Given network scores over a set of train/test splits, compiles these into a matrix for downstream analysis. See the section on 'Output Files'

Value

(list) one key per patient class. Value is matrix of network scores across all train/test splits. Each score is the output of the inner fold of CV.

Examples

inDir <- system.file("extdata","example_output",package="netDx")
netScores <- getFeatureScores(inDir, predClasses = c('LumA','notLumA'))

BaderLab/netDx documentation built on Sept. 26, 2021, 9:13 a.m.