randomForest: Create an adjacency matrix based on random forest

In MetNet: Inferring metabolic networks from untargeted high-resolution mass spectrometry data

Description

'randomForest' infers an adjacency matrix using random forest using the 'GENIE3' function from the 'GENIE3' package. 'randomForest' returns the importance of the link between features in the form of an adjacency matrix.

Usage

randomForest(x, ...)

Arguments

x	matrix, where columns are the samples and the rows are features (metabolites), cell entries are intensity values
...	parameters passed to 'GENIE3'

Details

For use of the parameters used in the 'GENIE3' function, refer to '?GENIE3::GENIE3'. The arguments 'regulators' and 'targets' are set to 'NULL'. Element w_{i,j} (row i, column j) gives the importance of the link from i to j.

Value

matrix, matrix with the importance of the links inferred from random forest algorithm implemented by 'GENIE3'

Author(s)

Thomas Naake, [e-mail]

Examples

data("x_test", package = "MetNet")
x <- x_test[1:10, 3:ncol(x_test)]
x <- as.matrix(x)
randomForest(x)

MetNet documentation built on Nov. 8, 2020, 7:34 p.m.