% Generated by roxygen2: do not edit by hand

% Please edit documentation in R/tuneCluster.spls.R

\name{tuneCluster.spls}

\alias{tuneCluster.spls}

\title{Feature Selection Optimization for sPLS method}

\usage{

tuneCluster.spls(

  X,

  Y,

  ncomp = 2,

  test.keepX = rep(ncol(X), ncomp),

  test.keepY = rep(ncol(Y), ncomp),

  ...

)

}

\arguments{

\item{X}{numeric matrix (or data.frame) with features in columns and samples in rows}

\item{Y}{numeric matrix (or data.frame) with features in columns and samples in rows (same rows as \code{X})}

\item{ncomp}{integer, number of component to include in the model}

\item{test.keepX}{vector of integer containing the different value of keepX to test for block \code{X}.}

\item{test.keepY}{vector of integer containing the different value of keepY to test for block \code{Y}.}

\item{...}{other parameters to be included in the spls model (see \code{mixOmics::spls})}

}

\value{

\item{silhouette}{silhouette coef. computed for every combinasion of keepX/keepY}

\item{ncomp}{number of component included in the model}

\item{test.keepX}{list of tested keepX}

\item{test.keepY}{list of tested keepY}

\item{block}{names of blocks}

\item{slopes}{"slopes" computed from the silhouette coef. for each keepX and keepY, used to determine the best keepX and keepY}

\item{choice.keepX}{best \code{keepX} for each component}

\item{choice.keepY}{best \code{keepY} for each component}

}

\description{

This function identify the number of feautures to keep per component and thus by cluster in \code{mixOmics::spls} by optimizing the silhouette coefficient, which assesses the quality of clustering.

}

\details{

For each component and for each keepX/keepY value, a spls is done from these parameters.

Then the clustering is performed and the silhouette coefficient is calculated for this clustering.

We then calculate "slopes" where keepX/keepY are the coordinates and the silhouette is the intensity.

A z-score is assigned to each slope.

We then identify the most significant slope which indicates a drop in the silhouette coefficient and thus a deterioration of the clustering.

}

\examples{

demo <- suppressWarnings(get_demo_cluster())

X <- demo$X

Y <- demo$Y

# tuning

tune.spls <- tuneCluster.spls(X, Y, ncomp= 2, test.keepX= c(5,10,15,20), test.keepY= c(2,4,6))

keepX <- tune.spls$choice.keepX

keepY <- tune.spls$choice.keepY

# final model

spls.res <- mixOmics::spls(X, Y, ncomp= 2, keepX= keepX, keepY= keepY)

# get clusters and plot longitudinal profile by cluster

spls.cluster <- getCluster(spls.res)

plotLong(spls.res)

}

\seealso{

\code{\link[mixOmics]{spls}}, \code{\link[timeOmics]{getCluster}}, \code{\link[timeOmics]{plotLong}}

}