CalcSilhInfo: Estimating optimal K using silhouette

CalcSilhInfoR Documentation

Estimating optimal K using silhouette

Description

The function estimates the optimal number of clusters K from the dendrogram of the hierarhical clustering using the silhouette method.

Usage

CalcSilhInfo.SingleCellExperiment(object, K.start, K.end)

## S4 method for signature 'SingleCellExperiment'
CalcSilhInfo(object, K.start = 2, K.end = 50)

Arguments

object

of SingleCellExperiment class

K.start

a numeric for the smallest K value to be tested. Default is 2.

K.end

a numeric for the largest K value to be tested. Default is 50.

Value

object of SingleCellExperiment class

Examples

library(SingleCellExperiment)
sce <- SingleCellExperiment(assays = list(logcounts = pbmc3k_500))
sce <- PrepareILoReg(sce)
## These settings are just to accelerate the example, use the defaults.
sce <- RunParallelICP(sce,L=2,threads=1,C=0.1,k=5,r=1)
sce <- RunPCA(sce,p=5)
sce <- HierarchicalClustering(sce)
sce <- CalcSilhInfo(sce)


elolab/iloreg documentation built on March 27, 2022, 4:19 a.m.