sc_clustering.umap_kmeans: Perform Single Cell data clustering using UMAP+kmeans

In pengminshi/MRtree: Multi-resolution Reconciled Tree

Perform Single Cell data clustering using UMAP+kmeans

Description

Perform Single Cell data clustering using UMAP+kmeans

Usage

sc_clustering.umap_kmeans(
  exprs,
  Ks,
  type = c("count", "log"),
  estimate.k = FALSE,
  subsample = FALSE,
  subsample.ratio = 0.9,
  scale.factor = 10000,
  n.neighbors = 30,
  n.components = 2,
  column.prefix = "umapkmeans_",
  n.cores = 1
)

Arguments

exprs	n.genes-by-n.cells expression matrix
Ks	vector of resolution, number of clusters
type	string, type of the expression matrix, choices are 'count' and 'log', and default by 'counts'
estimate.k	boolean whether to estimate optimal number of clusters by ADPclust
subsample	whether perform subsampling for each clustering
subsample.ratio	ratio of subsampled size to the total sample size (applicable when subsample=TRUE)
scale.factor	scalar sets the scale factor for cell-level normalization
n.neighbors	integer, number of neighbors to consider when build neighbor graph, default 30
n.components	integer, UMAP output dimensionality, default 2
column.prefix	string, output column prefix, default 'tsnekmeans_'
n.cores	number of cores used for parallel computation

Value

a list containing

labelmat

a data frame, columns are clusterings for each resolution specified

est.k

integer, estimated number of clusters

pengminshi/MRtree documentation built on March 6, 2023, 4:20 p.m.