gaga (version 2.18.0)

geneclus: Cluster genes into expression patterns.

Description

Performs supervised gene clustering. Clusters genes into the expression pattern with highest posterior probability, according to a GaGa or MiGaGa fit.

Usage

geneclus(gg.fit, method='posprob')

Arguments

gg.fit

GaGa or MiGaGa fit (object of type gagafit, as returned by fitGG).

method

For method=='posprob' samples are assigned to pattern with highest posterior probability, and for method=='likelihood' to the pattern with highest likelihood (e.g. assuming equal a priori prob for all patterns)

Value

List with components:

d

Vector indicating the pattern that each gene is assigned to.

posprob

Vector with posterior probabilities of the assigned patterns.

Details

Each gene is assigned to the pattern with highest posterior probability. This is similar to routine findgenes, which also assigns genes to the pattern with highest posterior probability, although findgenes applies an FDR-based correction i.e. tends to assign more genes to the null pattern of no differential expression.

References

Rossell D. GaGa: a simple and flexible hierarchical model for microarray data analysis. http://rosselldavid.googlepages.com.

See Also

fitGG, parest

Examples

#Not run. Example from the help manual
#library(gaga)
#set.seed(10)
#n <- 100; m <- c(6,6)
#a0 <- 25.5; nu <- 0.109
#balpha <- 1.183; nualpha <- 1683
#probpat <- c(.95,.05)
#xsim <- simGG(n,m,p.de=probpat[2],a0,nu,balpha,nualpha)
#
#ggfit <- fitGG(xsim$x[,c(-6,-12)],groups,patterns=patterns,nclust=1)
#ggfit <- parest(ggfit,x=xsim$x[,c(-6,-12)],groups,burnin=100,alpha=.05)
#
#dclus <- geneclus(ggfit)  #not use FDR correction
#dfdr <- findgenes(ggfit,xsim$x[,c(-6,-12)],groups,fdrmax=.05,parametric=TRUE) #use FDR correction
#table(dfdr$d,dclus$d) #compare results