clustering: scTEP

In scTEP: Single-Cell Trajectory Inference using Ensemble Pseudotimes

scTEP

Description

The 'clustering' function conducts multiple clustering to the sc-RNA seq data using the 'scDHA' function from the 'scDHA' package. The 'scDHA' allows the user to set a specific cluster number for the clustering process. We set the cluster number from 6 to 10 and run the 'scDHA' function six times. The 'trajectoryinference' function will using those total six clustering results to generate pseudotimes.

Usage

clustering(data, ncores = 10L, seed = NULL)

Arguments

data	A list consists of gene expression matrix.
ncores	Number of processor cores to use. This values is set to seed = 10L by default.
seed	A parameter to set a seed for reproducibility.

Value

List with the following keys:

• allCluster - A list consists of clutering results using scDHA with k = 5:10.

References

1. Duc Tran, Hung Nguyen, Bang Tran, Carlo La Vecchia, Hung N. Luu, Tin Nguyen (2021). Fast and precise single-cell data analysis using a hierarchical autoencoder. Nature Communications, 12, 1029. doi: 10.1038/s41467-021-21312-2

Examples

# Load the package and the example data (goolam data set)
library(scTEP)
#Load pathway genesets
data('genesets')
#Load example data (SCE dataset)
data("goolam")
#Get data matrix and label
expr <- as.matrix(t(SummarizedExperiment::assay(goolam)))[, 1:100]

#Get data matrix and label
data = preprocessing(expr)

#Get clustering results using scDHA with k from 6 to 10.
allCluster = scTEP::clustering(data, ncores = 2)

scTEP documentation built on Sept. 26, 2022, 5:10 p.m.