minet (version 3.30.0)

minet: Mutual Information Network

Description

For a given dataset, minet infers the network in two steps. First, the mutual information between all pairs of variables in dataset is computed according to the estimator argument. Then the algorithm given by method considers the estimated mutual informations in order to build the network. This package is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.

Usage

minet(dataset, method="mrnet", estimator="spearman", disc="none", nbins=sqrt(NROW(dataset)))

Arguments

dataset

data.frame where columns contain variables/features and rows contain outcomes/samples.

method

The name of the inference algorithm : "clr", "aracne", "mrnet" or "mrnetb" (default: "mrnet") - see references.

estimator

The name of an entropy estimator (or correlation) to be used for mutual information computation ("pearson","spearman","kendall" and from infotheo package:"mi.empirical", "mi.mm", "mi.shrink", "mi.sg"), (default: "spearman") . - see build.mim.

disc

The name of the discretization method to be used, if required by the estimator :"none" ,"equalfreq", "equalwidth" or "globalequalwidth" (default : "none") - see infotheo package.

nbins

Integer specifying the number of bins to be used for the discretization if disc is set properly. By default the number of bins is set to $\sqrt{N}$ where N is the number of samples.

Value

• minet returns a matrix which is the weighted adjacency matrix of the network. The weights range from 0 to 1 and can be seen as a confidence measure on the presence of the arcs. In order to display the network, load the package Rgraphviz and use the following command: plot( as(returned.matrix ,"graphNEL") )

References

Patrick E. Meyer, Frederic Lafitte, and Gianluca Bontempi. minet: A R/Bioconductor Package for Inferring Large Transcriptional Networks Using Mutual Information. BMC Bioinformatics, Vol 9, 2008.

See Also

build.mim, clr, mrnet, mrnetb, aracne

Examples

data(syn.data)
net1 <- minet( syn.data )
net2 <- minet( syn.data, estimator="pearson" )
net3 <- minet( syn.data, method="clr")