clusterComp {clusterStab} | R Documentation |
This function estimates the stability of clustering solutions using microarray data. Currently only agglomerative hierarchical clustering is supported.
## S4 method for signature 'exprSet': clusterComp(object, cl, seednum = NULL, B = 100, sub.frac = 0.8, method = "ave", adj.score = FALSE) ## S4 method for signature 'matrix': clusterComp(object, cl, seednum = NULL, B = 100, sub.frac = 0.8, method = "ave", adj.score = FALSE)
object |
Either a matrix or exprSet |
cl |
The number of clusters. This may be estimated using benhur |
seednum |
A value to pass to set.seed , which will allow
for exact reproducibility at a later date. |
B |
The number of permutations. |
sub.frac |
The proportion of genes to use in each subsample. This value should be in the range of 0.75 - 0.85 for best results |
method |
The linkage method to pass to hclust . Valid values
include "average", "centroid", "ward", "single", "mcquitty", or
"median". |
adj.score |
Boolean. Should the stability scores be adjusted for
cluster size? Defaults to FALSE . |
This function estimates the stability of a clustering solution by repeatedly subsampling the data and comparing the cluster membership of the subsamples to the original clusters.
The output from this function is an object of class clusterComp
. See
the clusterComp-class
man page for more information.
James W. MacDonald <jmacdon@med.umich.edu>
A. Ben-Hur, A. Elisseeff and I. Guyon. A stability based method for discovering structure in clustered data. Pacific Symposium on Biocomputing, 2002. Smolkin, M. and Ghosh, D. (2003). Cluster stability scores for microarray data in cancer studies . BMC Bioinformatics 4, 36 - 42.
data(sample.exprSet) clusterComp(sample.exprSet, 3)