\title{Cluster samples from an IcaSet}
   clusterSamplesByComp_multiple(icaSet, params,
     funClus = c("Mclust", "kmeans", "pam", "pamk", "hclust", "agnes"),
     filename, clusterOn = c("A", "S"),
     level = c("genes", "features"), nbClus,
     metric = "euclidean", method = "ward", ...)
   \item{icaSet}{An \code{IcaSet} object}
   \item{params}{A \code{MineICAParams} object}
   \item{funClus}{The function to be used for clustering,
   must be several of
   \item{filename}{A file name to write the results of the
   clustering in}
   \item{clusterOn}{Specifies the matrix used to apply
   clustering, can be several of: \describe{
   \item{\code{"A"}:}{the clustering is performed in one
   dimension, on the vector of sample contributions,}
   \item{\code{"S"}:}{the clustering is performed on the
   original data restricted to the contributing
   \item{level}{The level of projections to be used when
   \code{clusterOn="S"}, either \code{"features"} or
   \item{nbClus}{The number of clusters to be computed,
   either a single number or a numeric vector whose length
   equals the number of components. If missing (only allowed
   if \code{funClus} is one of \code{c("Mclust","pamk")})}
   \item{metric}{Metric used in \code{pam} and
   \code{hclust}, default is \code{"euclidean"}}
   \item{method}{Method of hierarchical clustering, used in
   \code{hclust} and \code{agnes}}
   \item{...}{Additional parameters required by the
   clustering function \code{funClus}.}
   A list consisting of three elements
   \describe{\item{clus:}{a data.frame specifying the sample
   clustering for each component using the different ways of
   clustering,}\item{resClus:}{the complete output of the
   clustering function(s),}\item{comparClus:}{the adjusted
   Rand indices, used to compare the clusterings obtained
   for a same component.}}
   This function allows to cluster samples according to the
   results of an ICA decomposition. Several clustering
   functions and several levels of data for clustering can
   be performed by the function.
   One clustering is run independently for each component.
 params <- buildMineICAParams(resPath="carbayo/", selCutoff=3)
 ## compare kmeans clustering applied to A and data restricted to the contributing genes
 ## on components 1 to 3
 res <- clusterSamplesByComp_multiple(icaSet=icaSetCarbayo[,,1:3], params=params, funClus="kmeans",
                                      nbClus=2, clusterOn=c("A","S"), level="features")
   \code{Mclust}, \code{adjustedRandIndex}, \code{kmeans},
   \code{pam}, \code{pamk}, \code{hclust}, \code{agnes},