survClust: perform supervised clustering for a particular 'k'

In arorarshi/survClust: Identification Of Clinically Relevant Genomic Subtypes Using Outcome Weighted Learning

perform supervised clustering for a particular k

Description

survClust function performs supervised clustering on a combineDist output for a particular k. It uses all n-1 dimensions for clustering.

survClust is an outcome weighted integrative clustering algorithm used to classify multi-omic samples on their available time to event information.

Usage

survClust(combine.dist, survdat, k, cmd.k = NULL)

Arguments

combine.dist	integrated weighted distance matrix from combineDist
survdat	A nx2 matrix consisting of survival data with n samples and first column as time and second column as events, with samples as rownames
k	choice of k to perform clustering on samples
cmd.k	number of dimensions used by cmdscale to perform clustering on samples. Defaults is n-1

Value

• fit returns a list , fit consisting of all clustering samples as in kmeans fit.lr, computed logrank statistic between k clusters

Author(s)

Arshi Arora

Maintainer: Arshi Arora [e-mail] (ORCID)

See Also

Useful links:

• https://github.com/arorarshi/survClust

• Report bugs at https://support.bioconductor.org/t/survClust

Examples

library(survClust)
dd <- getDist(datasets = simdat, survdat = simsurvdat)
cc <- combineDist(dd)
survclust_fit <- survClust(combine.dist = cc, survdat = simsurvdat, k = 3)

arorarshi/survClust documentation built on April 21, 2024, 1:51 p.m.