Novel Computational Approaches in QSAR and Molecular Design Based on GA, Multi-Way PLS and NN

Title: Novel Computational Approaches in QSAR and Molecular Design Based on GA, Multi-Way PLS and NN

Volume: 1 Issue: 2

Author(s): Kiyoshi Hasegawa, Masamoto Arakawa and Kimito Funatsu

Affiliation:

Keywords: quantitative structure-activity relationship, molecular design, multi-way partial least squares, genetic algorithm, neural network, molecular surface, molecular alignment

Abstract: QSAR and subsequent molecular design are very important steps in drug discovery. Through QSAR, one derives a model that relates a set of molecular descriptors to a biological activity. The resulting model can be used to predict the activity values of new compounds in molecular design. QSAR models range from simple, parametric equations to complex, non-linear models. These models have each specific advantage and shortcoming derived from their own algorithms. We have developed hybrid approaches combining GA, multiway PLS and NN to utilize specific advantage and to cover specific shortcoming of each method. We have picked up five topics and outlined with the representative examples in this review article.

Cite this article as:

Hasegawa Kiyoshi, Arakawa Masamoto and Funatsu Kimito, Novel Computational Approaches in QSAR and Molecular Design Based on GA, Multi-Way PLS and NN, Current Computer-Aided Drug Design 2005; 1 (2) . https://dx.doi.org/10.2174/1573409053585672