kmeans.init {integrativeME}R Documentation

Initialization of the parameters with K-means

Description

Parameters in integrativeME are first initialized via K-means clustering algorithm.

Usage

kmeans.init(data.cont)

Arguments

data.cont gene expression data, where a small number of genes has been selected beforehand. See integrativeME.

Details

The number of clusters in K-means is set by default to 2. K-means is used to initialize the parameters before applying the EM algorithm in integrativeME.

Value

prop.kmeans proportions.
means.kmeans estimated means.
var.kmeans estimated variance-covariance matrix.
continue boolean variable, set to FALSE if the number of observations is not sufficient to determine 2 clusters.

Author(s)

Kim-Anh Le Cao

References

Hartigan, J. A. and Wong, M. A. (1979). A K-means clustering algorithm. Applied Statistics, 28, 100-108.

See Also

integrativeME, MEfunctions, kmeans.


[Package integrativeME version 1.1 Index]