\HeaderA{ebam.wilc}{Empirical Bayes Analysis using Wilcoxon Rank Sums}{ebam.wilc}
\keyword{htest}{ebam.wilc}
\begin{Description}\relax
Performs an Empirical Bayes Analysis of Microarrays by using Wilcoxon Rank Sums
as expression scores for the genes.
\end{Description}
\begin{Usage}
\begin{verbatim}
    ebam.wilc(data,cl,delta=.9,p0=NA,ties.rand=TRUE,zero.rand=TRUE,gene.names=NULL,
        R.fold=TRUE,R.unlog=TRUE,file.out=NA,na.rm=FALSE,rand=NA)
\end{verbatim}
\end{Usage}
\begin{Arguments}
\begin{ldescription}
\item[\code{data}] the data set that should be analyzed. Every row of this data set must
correspond to a gene, and each column to a biological sample.
\item[\code{cl}] a vector containing the class labels of the samples. In the two class unpaired case,
the label of a sample is either 0 (e.g, control group) or 1 (e.g., case group).
In the two class paired case, the labels are the integers between 1 and \eqn{n/2}{}
(e.g., after treatment group) and between -1 and \eqn{-n/2}{} (e.g., before treatment
group), where \eqn{n}{} is the length of \code{cl} and \eqn{k}{} is paired with \eqn{-k}{}.
\item[\code{delta}] a gene will be called significant, if its posterior probability of
being differentially expressed is larger than or equal to \code{delta}.
\item[\code{p0}] prior probability that a gene is differentially expressed. If not specified,
it will automatically be computed.
\item[\code{ties.rand}] if \code{TRUE} (default), non-integer expression scores will be randomly
assigned to the next lower or upper integer. Otherwise, they are assigned to
the integer that is closer to the mean.
\item[\code{zero.rand}] if \code{TRUE} (default), the sign of each Zero in the computation of
the Wilcoxon signed rank sums will be randomly assigned. If \code{FALSE}, the
sign of the Zeros will be set to '--'.
\item[\code{gene.names}] a vector containing the names of the genes.
\item[\code{R.fold}] if \code{TRUE} (default), the fold change for each differentially
expressed gene will be computed.
\item[\code{R.unlog}] if \code{TRUE}, the anti-log of \code{data} will be used in the computation of the
R.fold. This is recommended if \code{data} consists of log2 transformed gene expression
data.
\item[\code{file.out}] if specified, general information like the number of significant 
genes and the estimated FDR and gene-specific information like the expression
scores, the q-values, the R fold etc. of the differentially expressed genes
are stored in this file.
\item[\code{na.rm}] if \code{FALSE} (default), the fold change of genes with at least one
missing value will be set to \code{NA}. If \code{TRUE}, missing values will be
replaced by the genewise mean.
\item[\code{rand}] if specified, the random number generator will be set in a reproducible state.
\end{ldescription}
\end{Arguments}
\begin{Value}
a plot of the expression scores vs.\ their posterior probability of being differentially
expressed, and (optionally) a file containing general information like the FDR and the
number of differentially expressed genes and gene-specific information on the differentially
expressed genes like their names, their q-values and their fold change.

\begin{ldescription}
\item[\code{nsig}] number of significant genes.
\item[\code{fdr}] estimated FDR.
\item[\code{ebam.output}] table containing gene-specific information on the differentially
expressed genes.
\item[\code{row.sig.genes}] vector containing of the row numbers that belong to the differentially
expressed genes.
\item[\code{...}] 
\end{ldescription}
\end{Value}
\begin{Author}\relax
Holger Schwender, \email{holger.schw@gmx.de}
\end{Author}
\begin{References}\relax
Efron, B., Storey, J.D., Tibshirani, R.\ (2001). Microarrays, empirical Bayes methods, and
the false discovery rate, \emph{Technical Report}, Department of Statistics, Stanford
University.

Storey, J.D., and Tibshirani, R. (2003). Statistical significance for genome-wide
experiments, \emph{Technical Report}, Department of Statistics, Stanford University.

Schwender, H. (2003). Assessing the false discovery rate in a statistical analysis of
gene expression data, Chapter 8, \emph{Diploma thesis}, Department of Statistics,
University of Dortmund, \url{http://de.geocities.com/holgerschw/thesis.pdf}.
\end{References}
\begin{SeeAlso}\relax
\code{\LinkA{ebam}{ebam}}
\end{SeeAlso}
\begin{Examples}
\begin{ExampleCode}## Not run: 
    library(multtest)
    # Load the data of Golub et al. (1999). data(golub) contains
    # a 3051x38 gene expression matrix called golub, a vector of
    # length called golub.cl that consists of the 38 class labels,
    # and a matrix called golub.gnames whose third column contains
    # the gene names.
    data(golub)
    
    # An EBAM-Wilc analysis of the Golub data is performed by
    
    ebam.wilc.out<-ebam.wilc(golub,golub.cl,gene.names=golub.gnames[,3],rand=123)
    
    # For further analyses, the row numbers of the differentially expressed
    # genes are obtained by
    
    ebam.wilc.out$row.sig.genes
## End(Not run)\end{ExampleCode}
\end{Examples}