pca {autonomics}R Documentation

Add PCA, SMA, LDA, PLS

Description

Perform a dimension reduction. Add sample scores, feature loadings, and dimension variances to object.

Usage

pca(object, ndim = 2, minvar = 0, verbose = TRUE, plot = FALSE, ...)

pls(
  object,
  subgroupvar = "subgroup",
  ndim = 2,
  minvar = 0,
  verbose = FALSE,
  plot = FALSE,
  ...
)

sma(object, ndim = 2, minvar = 0, verbose = TRUE, plot = FALSE, ...)

lda(
  object,
  subgroupvar = "subgroup",
  ndim = 2,
  minvar = 0,
  verbose = TRUE,
  plot = FALSE,
  ...
)

Arguments

object

SummarizedExperiment

ndim

number

minvar

number

verbose

TRUE (default) or FALSE

plot

TRUE/FALSE

...

passed to biplot

subgroupvar

subgroup svar

Value

SummarizedExperiment

Author(s)

Aditya Bhagwat, Laure Cougnaud (LDA)

Examples

file <- download_data('atkin18.metabolon.xlsx')
object <- read_metabolon(file, plot = FALSE)
pca(object, plot=TRUE, color = Group)  # Principal Component Analysis
pls(object, subgroupvar = 'Group')  # Partial Least Squares
lda(object, subgroupvar = 'Group')  # Linear Discriminant Analysis
sma(object)  # Spectral Map Analysis
pca(object, ndim=3)
pca(object, ndim=Inf, minvar=5)

[Package autonomics version 1.2.0 Index]