LMGene (version 2.28.0)

glog: Generalized log transformation function

Description

This function transforms the input values by the generalized log function.

Usage

glog(y, lambda)

Arguments

y

A data matrix

lambda

Transformation parameter

Value

yt

A matrix of glog-transformed values

Details

The glog transformation of a variable y is defined as log(y + sqrt(y^2 + lambda)). Using lambda = 0 corresponds to the log transformation, up to a scale factor of 2. (Other, equivalent expressions exist for the glog transformation. See Durbin et al. (2002) and Huber et al. (2002) for futher details.)

The input matrix y may be modified prior to transformation by subtracting a constant or vector ("alpha"). The parameters lambda and alpha may be estimated from tranest.

References

Durbin, B.P., Hardin, J.S., Hawkins, D.M., and Rocke, D.M. (2002) A variance-stabilizing transformation for gene-expression microarray data, Bioinformatics, 18, S105--S110.

Huber, W., Von Heydebreck, A., Sueltmann, H., Poustka, A., and Vingron, M. (2002) Variance stabilization applied to microarray data calibration and to the quantification of differential expression, Bioinformatics, 18, S96--S104.

http://dmrocke.ucdavis.edu

See Also

tranest, transeS

Examples

#library
library(Biobase)
library(LMGene)

#data
data(sample.mat)
sample.mat[1:5,1:4]

GloggedSmpd<-glog(sample.mat-50,500)
GloggedSmpd[1:5,1:4]