|
a |
|
b/OmicsFold/man/feature.selection.stability.Rd |
|
|
1 |
% Generated by roxygen2: do not edit by hand |
|
|
2 |
% Please edit documentation in R/feature_loadings.R |
|
|
3 |
\name{feature.selection.stability} |
|
|
4 |
\alias{feature.selection.stability} |
|
|
5 |
\title{Extract sPLS-DA feature selection stability} |
|
|
6 |
\usage{ |
|
|
7 |
feature.selection.stability(splsda.model, splsda.perf, comp) |
|
|
8 |
} |
|
|
9 |
\arguments{ |
|
|
10 |
\item{splsda.model}{Trained mixOmics sPLS-DA model.} |
|
|
11 |
|
|
|
12 |
\item{splsda.perf}{Performance evaluation of the sPLS-DA model generated by |
|
|
13 |
mixOmics perf.} |
|
|
14 |
|
|
|
15 |
\item{comp}{Component number of which to retrieve feature selection |
|
|
16 |
stabilities.} |
|
|
17 |
} |
|
|
18 |
\value{ |
|
|
19 |
A data frame containing the features selected for the specificed |
|
|
20 |
component and their relative stability, as a proportion of trained models |
|
|
21 |
0-1. |
|
|
22 |
} |
|
|
23 |
\description{ |
|
|
24 |
Extract feature selection stabilities for a given component from a |
|
|
25 |
performance validated mixOmics sPLS-DA model Feature stabilities are an |
|
|
26 |
important indicator of the confidence that a selected feature is predictive |
|
|
27 |
for the outcome classes in the model, and hence (in combination with the |
|
|
28 |
loading weight) is likely to be of biological significance. |
|
|
29 |
} |
|
|
30 |
\examples{ |
|
|
31 |
\dontrun{ |
|
|
32 |
feature.selection.stability(splsda.analysis, perf.splsda.analysis, comp=1) |
|
|
33 |
} |
|
|
34 |
} |