cor2mi: Convert correlation matrix to MI matrix

In wyguo/RLowPC: Inference of co-expression gene network using relevance low order partial correlation from large scale expression data

Description

The correlation ρ_{ij} between node i and j is converted into mutual information (MI) matrix by using equation [1]:

MI=-\frac{1}{2} (1-ρ_{ij}^2)

if the observation data is normal distributed.

Usage

cor2mi(x)

Arguments

x	a correlation matrix

Value

cor2mi returns a mutual information matrix.

References

[1] Meyer PE, Kontos K, Lafitte F, Bontempi G: Information-theoretic inference of large transcriptional regulatory networks. EURASIP J Bioinform Syst Biol 2007:79879.

wyguo/RLowPC documentation built on May 4, 2019, 12:04 p.m.