embed_nonlinear: Compute a non-linear embedding on a 'TourExperiment' object.

In sa-lee/sneezy: Interactively explore non-linear projections like t-SNE

Description

Compute a non-linear embedding on a TourExperiment object.

Usage

embed_nonlinear(.data, num_comp, .on = NULL, normalize = TRUE,
  .parallel = BiocParallel::SerialParam(), .engine = tsne_approx(30,
  12, 0.5))

Arguments

.data	A TourExperiment() object
num_comp	Number of components/dimensions to retain
.on	Where to compute the non-linear embedding? If NULL, the first assay is computed.
normalize	Avoid numerical precision issues by centering and scaling the input data. (Default = TRUE).
.parallel	Register a parallel backend, only used if computing nearest-neighbors prior to perfoming a non-linear embedding.
.engine	A NonLinearEmbeddingParam`` object used to define the arguments and algorithm for non-linear embedding. Deafults to tsne_approx()'

Details

This function computes a non-linear embedding over the parameters for a non-linear embedding algorithm and adjusts the reducedDim slot with the embedding coordinates.

See Also

Rtsne::Rtsne()

sa-lee/sneezy documentation built on Nov. 25, 2019, 12:38 p.m.