ClusterCellsKmeans: Cluster cells with K-means clustering and mini-batch K-means...

In ncchung/SeuratAddon: Unsupervised evaluation of cell identities in Seurat

Description

Perform K-means clustering on cells, to obtain cell identities. Based on Seurat::DoKMeans.

Usage

ClusterCellsKmeans(object, genes.use = NULL, reduction.type = NULL,
  dims.use = NULL, num_init = 5, center = TRUE, k.cells = NULL,
  k.seed = 1, do.plot = FALSE, data.cut = NULL,
  k.cols = PurpleAndYellow(), set.ident = TRUE, minibatch = FALSE,
  do.constrained = FALSE, assay.type = "RNA", ...)

Arguments

object	Seurat object
genes.use	Genes to use for clustering
reduction.type	Name of dimensional reduction technique to use in k-means clustering. If NULL, genes will be used. (default is NULL)
dims.use	A vector of the dimensions to use in k-means clustering graph (e.g. To use the first 10 PCs, pass 1:10)
num_init	A number of times the algorithm will be run with different centroid seeds. (default is 5)
center	Center the cells/rows (default is TRUE)
k.cells	K value to use for clustering cells
k.seed	Random seed
do.plot	Draw heatmap of clustered genes/cells (default is FALSE).
data.cut	Clip all z-scores to have an absolute value below this. Reduces the effect of huge outliers in the data. (default is NULL)
k.cols	Color palette for heatmap
set.ident	If clustering cells (so k.cells>0), set the cell identity class to its K-means cluster (default is TRUE)
minibatch	FALSE by default. If TRUE, use the mini-batch K-means clustering implemented in the ClusterR package.
do.constrained	FALSE by default. If TRUE, use the constrained K-means function implemented in the tclust package.
assay.type	Type of data to normalize for (default is RNA), but can be changed for multimodal analyses.
...	Additional parameters passed to kmeans (or tkmeans)

Details

K-means clustering is performed on either scaled data or reduced dimensions, with a number of subpopulations set to k.cells. After the initial K-means clustering is performed, one can use EvaluateIdent to test individual cell identities, as given by K-means clustering.

Value

Seurat object where the k-means results for genes is stored in [e-mail][[1]]. The cluster for each cell is stored in [e-mail][,"kmeans.ident"] and also object@ident (if set.ident=TRUE)

Examples

pbmc_small
# Cluster single cells
pbmc_small <- ClusterCellsKmeans(pbmc_small, k.cells = 3)

ncchung/SeuratAddon documentation built on May 3, 2019, 3:17 p.m.