Variable selection and model validation of 2D and 3D molecular descriptors>

Author： Nicholls Anthony MacCuish Norah MacCuish John

ISSN： 0920-654X

Source： Journal of Computer-Aided Molecular Design, Vol.18, Iss.7-9, 2004-07, pp. : 451-474

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

We have found that molecular shape and electrostatics, in conjunction with 2D structural fingerprints, are important variables in discriminating classes of active and inactive compounds. The subject of this paper is how to explore the selection of these variables and identify their relative importance in quantitative structure–activity relationships (QSAR) analysis. We show the use of these variables in a form of similarity searching with respect to a crystal structure of a known bound ligand. This analysis is then validated through k-fold cross-validation of enrichments via several common classifiers. Additionally, we show an effective methodology using the variables in hypothesis generation; namely, when the crystal structure of a bound ligand is not known.