NonLinearEmbeddingMatrix class

Source: R/AllClasses.R, R/EM-methods.R

The NonLinearEmbeddingMatrix class is used for storing low-dimensional embeddings from non-linear dimensionality reduction techniques.

NonLinearEmbeddingMatrix(sampleFactors = matrix(nrow = 0, ncol = 0),
  featureLoadings = matrix(nrow = 0, ncol = 0), factorData = NULL,
  metadata = list(), param)

Arguments

sampleFactors

A matrix-like object of sample embeddings, where rows are samples and columns are factors.
featureLoadings

A matrix-like object of feature loadings, where rows are features and columns are factors.
factorData

A DataFrame containing factor-level information, with one row per factor.
metadata

An optional list of arbitrary content describing the overall experiment.
param

An NonLinearEmbeddingParam object

Details

The NonLinearEmbeddingMatrix class inherits from SingleCellExperiment::LinearEmbeddingMatrix() and is designed to be stored inside a TourExperiment() object. It gains an additional slot, storing NonLinearEmbeddingParam-class object, allowing us to maintain the arguments used to generate the embedding matrix. This is useful for running diagnostics over the same parameter set.

See also

SingleCellExperiment::LinearEmbeddingMatrix()