BenHur-class: Class "BenHur", a class for estimating clusters in microarray
data, and methods for visualizing them.
Description
A specialized class representation used for estimating
clusters in microarray data.Objects from the Class
Objects are usually created by a call to benhur, although
technically a new object can also be created by a call to
new("BenHur",...). However, this second method is usually not
worth the work required.Slots
jaccards:- Object of class
"list", containing the
jaccard vectors; these indicate the proportion of pairwise
similarity between clusters formed from subsets of the data. size:- Object of class
"vector", only used for plotting. iterations:- Object of class
"vector",
containing the number of iterations. Defaults to 100. freq:- Object of class
"vector", containing the
proportion of the data used for subsampling.
Methods
- ecdf
signature(x = "BenHur"): Plot an empirical
CDF. This can be used to help determine the number of clusters in
the data. The most likely (e.g., most stable number) of clusters
will have a CDF that is concentrated at or near one. See vignette
for more information.- hist
signature(x = "BenHur"): Plot histograms for all
clusters tested. The most likely (e.g., most stable number) of
clusters will have a histogram in which the data are clustered at
or near one. See vignette for more information.- show
signature(object = "BenHur"): Gives a nice
summary.
References
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.