Met.kopls {Metabonomic}R Documentation

Kernel-based orthogonal projections to latent structures (K-OPLS)

Description

An implementation of K-OPLS based on 'kopls' package with e.g. model training, prediction, cross-validation and plot tools.

Usage

Met.kopls(datos)

Arguments

datos Spectra data frame

Details

The application (Metabonomic Analysis / Partial Least Squares / Kernel-based Orthogonal PLS) is performed using the functions from the ''kopls'' package. Firstly, the function perform a K-OPLS cross-validation for a set of 'Y'-orthogonal components. The function returns a number of diagnostic parameters which can be used to determine the optimal number of model components. With the optimal parameters selected , the application performs prediction of no-model samples from the K-OPLS model. The function projects the Y-predictive and Y-orthogonal scores components to predict a value of the response matrix Y.

Author(s)

Jose L. Izquierdo izquierdo@ieb.ucm.es

References

Rantalainen M, Bylesjo M, Cloarec O, Nicholson JK, Holmes E and Trygg J. *Kernel-based orthogonal projections to latent structures (K-OPLS)*, _J Chemometrics_ 2007; 21:376-385.


[Package Metabonomic version 3.3.1 Index]