Molecular Diversity

, Volume 10, Issue 2, pp 187–205

Megavariate Analysis of Environmental QSAR Data. Part II – Investigating Very Complex Problem Formulations Using Hierarchical, Non-Linear and Batch-Wise Extensions of PCA and PLS

  • Lennart Eriksson
  • Patrik L. Andersson
  • Erik Johansson
  • Mats Tysklind
Full-length paper

DOI: 10.1007/s11030-006-9026-4

Cite this article as:
Eriksson, L., Andersson, P.L., Johansson, E. et al. Mol Divers (2006) 10: 187. doi:10.1007/s11030-006-9026-4

Summary

Three extensions of the basic PCA and PLS methodologies are described. These extensions are hierarchical, non-linear and batch-based in nature. The objectives of these methods are to assist in problem understanding and problem solving in very complex (QSAR) problem formulations. The method extensions are illustrated using two example QSAR data sets containing many X- and Y-variables.

Key words

megavariate data analysis hierarchical modelling non-linear modelling batch modelling time-resolved QSAR 

Abbreviations:

ACE

alternating conditional expectations

BIF-PLS

bifocal PLS

MARS

multivariate adaptive regression splines

MLR

multiple linear regression

NPLS

non-linear PLS

NN

neural networks

PARAFAC

parallel factor analysis

PCA

principal component analysis

PCB

polychlorinated biphenyls

PCR

principal component regression

PLS

partial least squares projections to latent structures

OPLS

orthogonal PLS

PLS-DA

PLS discriminant analysis

QSAR

quantitative structure-activity relationships

SIMCA

soft independent modelling of class analogy

SMD

statistical molecular design

SPLS

spline PLS

SVM

support vector machines

Copyright information

© Springer Science+Business Media, Inc. 2006

Authors and Affiliations

  • Lennart Eriksson
    • 1
  • Patrik L. Andersson
    • 2
  • Erik Johansson
    • 1
  • Mats Tysklind
    • 2
  1. 1.Umetrics ABUmeåSweden
  2. 2.Institute of Environmental Chemistry, Department of ChemistryUmeå UniversityUmeåSweden

Personalised recommendations