CNVrd2 (version 1.10.2)

groupCNVs: Cluster segmentation scores into groups.

Description

Use the EM algorithm (Dempster et al., 1977) to cluster segmentation scores into various groups.

Usage

groupCNVs(Object, ...)

Arguments

Object

An object of class clusteringCNVs.

...

Further arguments.

Value

allGroups

Samples and their corresponding groups

means

Means of groups.

sigma

Variances of groups.

p

Proportions of groups in all data set.

loglk

Value of loglikehood function.

Details

Users can set limits of segmentation scores: values being smaller than the left limit will be assigned to the smallest group and values being larger than righ limit will be assigned to the largest group.

References

Dempster, A. P., Laird, N. M., Rubin, D. B., 1977. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 1-38.

See Also

emnormalCNV, searchGroupCNVs

Examples

data("fcgr3bMXL")
#resultSegment <- segmentSamples(Object = objectCNVrd2, stdCntMatrix = readCountMatrix)
objectCluster <- new("clusteringCNVs",
                     x = resultSegment$segmentationScores[, 1], k = 4, EV = TRUE)

#searchGroupCNVs(Object = objectCluster)
copynumberGroups <- groupCNVs(Object = objectCluster)