Various plotting routines in the EBarrays package

Share:

Description

Various plotting routines, used for diagnostic purposes

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
checkCCV(data, useRank = FALSE, f = 1/2)
checkModel(data, fit, model = c("gamma", "lognormal", "lnnmv"),
           number = 9, nb = 10, cluster = 1, groupid = NULL)
checkVarsQQ(data, groupid, ...)
checkVarsMar(data, groupid, xlab, ylab, ...)
plotMarginal(fit, data, kernel = "rect", n = 100,
             bw = "nrd0", adjust = 1, xlab, ylab,...)
plotCluster(fit, data, cond = NULL, ncolors = 123, sep=TRUE,
            transform=NULL)

## S3 method for class 'ebarraysEMfit'
plot(x, data, plottype="cluster", ...)

Arguments

data

data, as a “matrix” or “ExpressionSet”

useRank

logical. If TRUE, ranks of means and c.v.-s are used in the scatterplot

f

passed on to lowess

fit, x

object of class “ebarraysEMfit”, typically produced by a call to emfit

model

which theoretical model use for Q-Q plot. Partial string matching is allowed

number

number of bins for checking model assumption.

nb

number of data rows included in each bin for checking model assumption

cluster

check model assumption for data in that cluster

groupid

an integer vector indicating which group each sample belongs to. groupid for samples not included in the analysis should be 0.

kernel, n, bw, adjust

passed on to density

cond

a vector specifying the condition for each replicate

ncolors

different number of colors in the plot

xlab, ylab

labels for x-axis and y-axis

sep

whether or not to draw horizontal lines between clusters

transform

a function to transform the original data in plotting

plottype

a character string specifying the type of the plot. Available options are "cluster" and "marginal". The default plottype "cluster" employs function 'plotCluster' whereas the "marginal" plottype uses function 'plotMarginal'.

...

extra arguments are passed to the qqmath, histogram and xyplot call used to produce the final result

Details

checkCCV checks the constant coefficient of variation assumption made in the GG and LNN models. checkModel generates QQ plots for subsets of (log) intensities in a small window. They are used to check the Log-Normal assumption on observation component of the LNN and LNNMV models and the Gamma assumption on observation component of the GG model. checkVarsQQ generates QQ plot for gene specific sample variances. It is used to check the assumption of a scaled inverse chi-square prior on gene specific variances, made in the LNNMV model. checkVarsMar is another diagnostic tool to check this assumption. The density histogram of gene specific sample variances and the density of the scaled inverse chi-square distribution with parameters estimated from data will be plotted. checkMarginal generates predictive marginal distribution from fitted model and compares with estimated marginal (kernel) density of data. Available for the GG and LNN models only. plotCluster generate heatmap for gene expression data with clusters

Value

checkModel, checkVarsQQ and checkVarsMar return an object of class “trellis”, using function in the Lattice package. Note that in certain situations, these may need to be explicitly ‘print’-ed to have any effect.

Author(s)

Ming Yuan, Ping Wang, Deepayan Sarkar, Michael Newton, and Christina Kendziorski

References

Newton, M.A., Kendziorski, C.M., Richmond, C.S., Blattner, F.R. (2001). On differential variability of expression ratios: Improving statistical inference about gene expression changes from microarray data. Journal of Computational Biology 8:37-52.

Kendziorski, C.M., Newton, M.A., Lan, H., Gould, M.N. (2003). On parametric empirical Bayes methods for comparing multiple groups using replicated gene expression profiles. Statistics in Medicine 22:3899-3914.

Newton, M.A. and Kendziorski, C.M. Parametric Empirical Bayes Methods for Microarrays in The analysis of gene expression data: methods and software. Eds. G. Parmigiani, E.S. Garrett, R. Irizarry and S.L. Zeger, New York: Springer Verlag, 2003.

Newton, M.A., Noueiry, A., Sarkar, D., and Ahlquist, P. (2004). Detecting differential gene expression with a semiparametric hierarchical mixture model. Biostatistics 5: 155-176.

Yuan, M. and Kendziorski, C. (2006). A unified approach for simultaneous gene clustering and differential expression identification. Biometrics 62(4): 1089-1098.

See Also

emfit, lowess