expMST: Minimum spanning tree of exponential dissimilarities

In aarkatkar/gelClust: Clustering and pathway analysis using exponential distributions

Minimum spanning tree of exponential dissimilarities

Description

Construct a tree that links all features together such that the likelihood of obtaining any of the linking correlations from the null distribution is minimized. Produce clusters from cutting this tree at links above a certain p-value threshold.

Usage

expMST(gm, cutoff = 0.05, min.size = 3)

Arguments

gm	the output of the gelMatrix function.
cutoff	the threshold p-value beyond which links will be severed.
min.size	minimum cluster size to be output.

Value

a numeric vector of cluster labels. 0 indicates "unclustered"

Author(s)

Anooj Arkatkar

Examples

data(foldChange)
data(traitData)
gm <- gelMatrix(foldChange, traitData, squared=TRUE, output="orig")

# Total number of links in the MST for Bonferroni correction
N <- dim(gm)[1]-1

clust <- expMST(gm, cutoff=0.05/N)
table(clust)

aarkatkar/gelClust documentation built on May 6, 2022, 12:24 a.m.