fastBMAcontrol: Control parameters for 'networkBMA' when using fastBMA...

In networkBMA: Regression-based network inference using Bayesian Model Averaging

Description

Assigns default control parameters for networkBMA when using fastBMA algorithm, and allows setting control parameter values.

Usage

fastBMAcontrol(OR = 10000, timeSeries = TRUE, rankOnly = FALSE, noPrune = FALSE,
               edgeMin = 0.5, edgeTol = -1, nThreads = 1,
			   selfie = FALSE, showPrune = FALSE, nVars = 0,
			   fastgCtrl = fastgControl(), start = -1,
			   end = -1, pruneFilterMin = 0, timeout = 0) 

Arguments

OR	A number specifying the maximum ratio for excluding models in Occam's window.
timeSeries	A logical value indicating whether the input the input data set is a time series data or static data.
rankOnly	A logical value indicating use priors to rank variables but uniform prior otherwise
noPrune	A logical value indicating whether not applying transitive reduction on the output edges or not
edgeMin	Threshold for the posterior probability to be shown
edgeTol	the error tolerance for determining whether an indirect path is as good as a direct path
nThreads	The number of threads used in the parallel computing of fastBMA
selfie	A logical value indicating whether showing self-loop edges or not
showPrune	A logical value indicating whether showing removed edges in transitive reduction or not. Ignored if noPrune is TRUE
nVars	the number of variables analyzed
fastgCtrl	A list of control variables affecting fastBMA computations when using Zellner's g-prior in model likelihhod evaluation. A function called fastgCtrl is provided to facilitate this setting, and the default is fastgCtrl().
start	start point of eval subset.
end	end point of eval subset.
pruneFilterMin	minimum posterior prob (0-1) before an edge will be included in the network to be pruned.
timeout	maximum number of seconds for the regression before it stops the search. 0 if not apply.

Value

A list of values for the named control parameters to be passed to fastBMA.

References

K. Lo, A. E. Raftery, K. M. Dombek, J. Zhu, E. E. Schadt, R. E. Bumgarner and K. Y. Yeung (2011), Integrating External Biological Knowledge in the Construction of Regulatory Networks from Time-series Expression Data, unpublished manuscript, University of Washington.

K. Y. Yeung, K. M. Dombek, K. Lo, J. E. Mittler, J. Zhu, E. E. Schadt, R. E. Bumgarner and A. E. Raftery (2011), Construction of regulatory networks using expression time-series data of a genotyped population, Proceedings of the National Academy of Sciences, 108(48):19436-41.

K. Y. Yeung, R. E. Bumgarner and A. E. Raftery (2005). Bayesian Model Averaging: Development of an improved multi-class, gene selection and classification tool for microarray data. Bioinformatics 21:2394-2402.

J. A. Hoeting, D. Madigan, A. E. Raftery, and C. T. Volinsky (1999). Bayesian Model Averaging: a tutorial, Statistical Science 14(4): 382-417.

L. H. Hong, M. Wu1, A. Lee, W. C. Young, A. E. Raftery and K. Y. Yeung, FastBMA and Transitive Reduction for Gene Network Inference. [in preparation]

See Also

fastgControl, networkBMA

Examples

data(dream4)

network <- 1

nTimePoints <- length(unique(dream4ts10[[network]]$time))

edges1ts10 <- networkBMA(data = dream4ts10[[network]][,-(1:2)],
                        nTimePoints = nTimePoints,
						 control=fastBMAcontrol(fastgCtrl=
						 fastgControl(optimize=4)))

networkBMA documentation built on Jan. 28, 2021, 2:02 a.m.