Support vector machine models in drug design: applications to drug transport processes and QSAR using simplex optimisations and variable selection

In this work, the performance and predictive capability of support vector machine (SVM) algorithms are investigated within the area of pharmaceutical drug design. The investigations in this paper clearly indicate the crucial importance of SVM parameter optimisation as well as variable selection in order to develop statistical models with good predictive capabilities on external test sets when using SVM regression. The simplex optimisation technique is applied to both traditional quantitative structure-activity relationships as well as important drug transport processes such as intestinal absorption and blood-brain barrier partitioning. (C) 2003 Elsevier B.V. All rights reserved.