\name{estimateExpression}
\alias{estimateExpression}
\title{Estimate expression of transcripts}
\description{Estimates the expression of transcripts using Markov chain Monte Carlo Algorithm}
\usage{
estimateExpression(probFile, outFile, parFile=NULL, outputType=NULL, gibbs=NULL, trInfoFile=NULL, thetaActFile=NULL, MCMC_burnIn=NULL, MCMC_samplesN=NULL, MCMC_samplesSave=NULL, MCMC_samplesNmax=NULL, MCMC_chainsN=NULL, MCMC_scaleReduction=NULL, MCMC_dirAlpha=NULL, verbose=NULL)
}
\arguments{
\item{probFile}{File with alignment probabilities produced by \code{parseAlignment}}
\item{outFile}{Prefix for the output files.}
\item{outputType}{Output type, possible values: \code{theta}, \code{RPKM}, \code{counts}, \code{tau}.}
\item{gibbs}{Use regular Gibbs sampling instead of Collapsed Gibbs sampling.}
\item{parFile}{File containing parameters for the sampler, which can be otherwise specified by [MCMC*] options. As the file is checked after every MCMC iteration, the parameters can be adjusted while running.}
\item{trInfoFile}{File containing transcript information. (Necessary for RPKM)}
% \item{procN}{Maximum number of threads to be used. The program will not use more threads that there are MCMC chains.}
\item{MCMC_burnIn}{Length of sampler's burn in period.}
\item{MCMC_samplesN}{Initial number of samples produced. Doubles after every iteration.}
\item{MCMC_samplesSave}{Number of samples recorder for each chain at the end.}
\item{MCMC_samplesNmax}{Maximum number of samples produced in one iteration. After producing samplesNmax samples sampler finishes.}
\item{MCMC_chainsN}{Number of parallel chains used. At least two chains will be used.}
\item{MCMC_scaleReduction}{Target scale reduction, sampler finishes after this value is met.}
\item{verbose}{Verbose output.}
Advanced options:
\item{thetaActFile}{File for logging noise parameter thetaAct, which is only generated when regular Gibbs sampling is used.}
\item{MCMC_dirAlpha}{Alpha parameter for the Dirichlet distribution.}
}
\details{
This function runs Collapse Gibbs algorithm to sample the MCMC samples of transcript expression. 
The input is the \code{.prob} file containing alignment probabilities which were produced by \code{\link{parseAlignment}}.
Other optional input is the transcript information file specified by \code{trInfoFile} and again produced by \code{parseAlignment}.

The sampling algorithm can be configured via parameters file \code{parFile} or by using the \code{MCMC*} options.
The advantage of using the file (at least an existing blank text document) is that by changing the configuration values while running, the new values such as \code{scaleReduction} do get updated after every iteration. 
}
\value{
\item{.thetaMeans}{file containing average relative expression of transcripts \eqn{\theta}{theta}}
Either one of sample files based on output type selected:
\item{.rpkm}{ for RPKM expression}
\item{.counts}{ for estimated read counts}
\item{.theta}{ for relative expression of fragments}
\item{.tau}{ for relative expression of transcripts}
}
\author{Peter Glaus}

\seealso{\code{\link{parseAlignment}}}
\examples{\dontrun{
estimateExpression( probFile="data.prob", outFile="data", outputType="RPKM", trInfoFile="data.tr", verbose=TRUE)
estimateExpression( probFile="data-c0b0.prob", outFile="data-c0b0", outputType="RPKM", trInfoFile="data.tr", MCMC_burnIn=200, MCMC_samplesN=200, MCMC_samplesSave=100, MCMC_scaleReduction=1.1, MCMC_chainsN=2 , MCMC_dirAlpha=NULL )
estimateExpression( probFile="data.prob", outFile="data-G", gibbs=TRUE, parFile="parameters1.txt", outputType="counts", trInfoFile="data.tr")
}}

\keyword{transcript expression}