tSNE: Dimension Reduction.

In bioinfoDZ/RISC: Robust Integration of Single-Cell RNA-Seq Datasets

Dimension Reduction.

Description

The t-SNE is calculated based on the eigenvectors of single cell dataset, and the user can select the eigenvectors manually. Of note, the selected eigenvectors directly affect t-SNE values. For the integrated data (the result of "scMultiIntegrate" funciton), RISC utilizes the PCR output "PLS" to calculate the t-SNE, therefore, the user has to input "PLS" in "use = ", instead of the defaut parameter "PCA".

Usage

scTSNE(
  object,
  npc = 20,
  embedding = 2,
  use = "PCA",
  perplexity = 30,
  seed = 123,
  ...
)

Arguments

object	RISC object: a framework dataset.
npc	The number of PCs (or PLS) using for t-SNE, the default is 20, but need to be modified by the users. The PCA for individual dataset, while PLS for the integrated data.
embedding	The number of components t-SNE output.
use	What components used for t-SNE: PCA or PLS.
perplexity	Perplexity parameter: if the cell numbers are small, decrease this parameter, otherwise tSNE cannot be calculated.
seed	The random seed to keep tSNE result consistent.

Value

RISC single cell dataset, the DimReduction slot.

References

Laurens van der Maaten, JMLR (2014)

Examples

# RISC object
obj0 = raw.mat[[3]]
obj0 = scPCA(obj0, npc = 10)
obj0 = scTSNE(obj0, npc = 4, perplexity = 10)
DimPlot(obj0, slot = "cell.tsne", colFactor = 'Group', size = 2)

bioinfoDZ/RISC documentation built on March 30, 2024, 9:19 p.m.