RJaCGH (version 2.0.4)

plot.RJaCGH: 'plot' method for RJaCGH objects

Description

A plot is drawed with information from the fit of a RJaCGH object.

Usage

"plot"(x, array=NULL, k = NULL,
Chrom=NULL, show="average", weights=NULL,
model.averaging = TRUE, cex=1,
smoother=FALSE, ...)

Arguments

x

any of RJaCGH, RJaCGH.Chrom, RJaCGH.Genome, RJaCGH.array objects

array

Name of the array to be plotted. If NULL, the weigthed average of the arrays is plotted.

k

Model to plot (i.e., number of hidden states). If NULL, the most visited is taken (only if a single array is plotted and a single model (genome/chromosome).

Chrom

Chromosome to be plotted (only if a single array is plotted and a different model for each chromosome has been fitted.

show

one of "average" or "frequency". See details.

weights

vector of weights for each array. Must have the length of the number of arrays. If NULL, the weights are uniform.

model.averaging

if TRUE, modelAveraging is performed. If FALSE, a call to states is made to get hidden state sequence.

cex

A numerical value giving the amount by which plotting text and symbols should be scaled relative to the default.

smoother

Logical. Smoothed means by model averaging.

...

additional arguments passed to plot.

Value

A plot.

Details

Depending on the object and the parameters passed, a different plot is drawed: If array in the case of a single model to all genome or array and Chrom in the case of a different model to each chromosome are passed, a panel with 5 subplots is returned. The first one is a barplot with the posterior distribution of the number of hidden states. The second and third are a density plot of the posterior distribution of means and variances. The four one is the probability of staying in the same hidden state, as returned by plotQNH, and the last one shows the original observations colored by thir hidden state and the probability of being in that hidden state.

On every plot, the 'Normal' state is coloured black. The 'Gain' states are red and the 'Loss' ones green.

If array is NULL and show is 'average', the last one of the plots is drawn, but the hidden state sequence and its probability is computed averaging on all the arrays with weights according to weights vector. If show is 'frequency', again the last plot is drawn, but the percentage of arrays in which every gene is Gain/Lost is shown, weighted by the weights vector.

If smoother is TRUE, the smoothed mean is drawn. See smoothMeans, except when show is 'frequency'.

References

Rueda OM, Diaz-Uriarte R. Flexible and Accurate Detection of Genomic Copy-Number Changes from aCGH. PLoS Comput Biol. 2007;3(6):e122

See Also

RJaCGH, smoothMeans, summary.RJaCGH, modelAveraging, states, trace.plot

Examples

## Not run: 
# y <- c(rnorm(100, 0, 1), rnorm(10, -3, 1), rnorm(20, 3, 1), rnorm(100,
#                                                                   0, 1))
# Pos <- round(runif(230))
# Pos <- cumsum(Pos)
# Chrom <- rep(1:23, rep(10, 23))
# jp <- list(sigma.tau.mu=rep(0.5, 4), sigma.tau.sigma.2=rep(0.3, 4),
#            sigma.tau.beta=rep(0.7, 4), tau.split.mu=0.5, tau.split.beta=0.5)
# fit.Chrom <- RJaCGH(y=y, Pos=Pos, Chrom=Chrom, model="Chrom",
#                     burnin=100, TOT=1000, jump.parameters=jp, k.max=4)
# fit.Genom <- RJaCGH(y=y, Pos=Pos, Chrom=Chrom, model="Genome", burnin=100,
#                     TOT=1000, jump.parameters=jp, k.max=4)
# fit.none <- RJaCGH(y=y, Pos=Pos, Chrom=NULL, model="None",
#                    burnin=100, TOT=1000, jump.parameters=jp, k.max=4)
# 
# plot(fit.Chrom)
# plot(fit.Chrom, array="array1")
# plot(fit.Genom)
# plot(fit.none)
# 
# 
# y2 <- c(rnorm(100, 0, 1), rnorm(10, -3, 1), rnorm(20, 3, 1),
#         rnorm(100, 0, 1))
# 
# ya <- cbind(y, y2)
# 
# fit.Chrom.array <- RJaCGH(y=ya, Pos=Pos, Chrom=Chrom, model="Chrom",
#       burnin=100, TOT=1000, jump.parameters=jp, k.max=4)
# fit.Genom.array <- RJaCGH(y=ya, Pos=Pos, Chrom=Chrom, model="Genome",
#       burnin=100, TOT=1000, jump.parameters=jp, k.max=4)
# fit.none.array <- RJaCGH(y=ya, Pos=Pos, Chrom=NULL, model="None",
#       burnin=100, TOT=1000, jump.parameters=jp, k.max=4)
# 
# plot(fit.Chrom.array)
# plot(fit.Genom.array)
# plot(fit.none.array)
# 
# ## End(Not run)