modelLda: Linear discriminant analysis model
In JEFworks/MUDAN: Multi-sample Unified Discriminant ANalysis

Description Usage Arguments Value Examples

Identifies components that maximally discriminate among groups using a linear discriminant analysis model

1 2	modelLda(mat, com, nfeatures = nrow(mat), random = FALSE, verbose = TRUE, retest = TRUE)

`mat`	Expression matrix with cells as columns, transferable features such as genes as rows.
`com`	Community annotations
`nfeatures`	Number of features (genes) in LDA model (default: all)
`random`	Wehther those features are random of chosen based on variance (most variable will be chosen by default)
`verbose`	Verbosity (default: TRUE)
`retest`	Whether to retest model for accuracy

LDA model

{
data(pbmcA)
cd <- pbmcA[, 1:500]
mat <- cleanCounts(cd)
mat <- normalizeVariance(mat)
pcs <- getPcs(mat)
com <- getComMembership(pcs, k=30)
model <- modelLda(mat, com)
}