tranest {LMGene} | R Documentation |
Finds the best parameters for glog transformation.
tranest(eS, ngenes = -1, starting = FALSE, lambda = 1000, alpha = 0, gradtol = 0.001, lowessnorm = FALSE)
eS |
Array data. must be exprSet type. |
ngenes |
Number of genes that is going to be used for the parameter estimation |
starting |
TRUE, if the given initial parameter values are used |
lambda |
Initial parameter value for lambda |
alpha |
Initial parameter value for alpha |
gradtol |
a positive scalar giving the tolerance at which the scaled gradient is considered close enough to zero to terminate the algorithm |
lowessnorm |
TRUE, if lowess method is going to be used |
The input argument, eS, must be exprSet type from Biobase package.
If you have a matrix data and information about the considered factors,
then you can use neweS
to conver the data into exprSet.
Please see neweS
in more detail.
tranpar |
A list containing the best parameter for 'lambda' and 'alpha' |
David Rocke and Geun-Cheol Lee
B. Durbin and D.M. Rocke, (2003) Estimation of Transformation Parameters for Microarray Data, Bioinformatics, 19, 1360-1367.
http://www.idav.ucdavis.edu/~dmrocke/
#library library(Biobase) library(LMGene) #data data(Smpd0) tranpar <- tranest(Smpd0, 100, FALSE, 500, 50, 1e-3, FALSE) tranpar tranpar <- tranest(Smpd0, -1, FALSE, 500, 50, 1e-3, FALSE) tranpar