Learning from Multiple Classifier Systems: Perspectives for Improving Decision Making of QSAR Models in Medicinal Chemistry

Publisher: Bentham Science Publishers

E-ISSN: 1873-4294|17|30|3269-3288

ISSN: 1568-0266

Source: Current Topics in Medicinal Chemistry, Vol.17, Iss.30, 2018-02, pp. : 3269-3288

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

Quantitative Structure - Activity Relationship (QSAR) modeling has been widely used inmedicinal chemistry and computational toxicology for many years. Today, as the amount of chemicalsis increasing dramatically, QSAR methods have become pivotal for the purpose of handling the data,identifying a decision, and gathering useful information from data processing. The advances in this fieldhave paved a way for numerous alternative approaches that require deep mathematics in order to enhancethe learning capability of QSAR models. One of these directions is the use of Multiple ClassifierSystems (MCSs) that potentially provide a means to exploit the advantages of manifold learning throughdecomposition frameworks, while improving generalization and predictive performance. In this paper,we presented MCS as a next generation of QSAR modeling techniques and discuss the chance to miningthe vast number of models already published in the literature. We systematically revisited the theoreticalframeworks of MCS as well as current advances in MCS application for QSAR practice. Furthermore,we illustrated our idea by describing ensemble approaches on modeling histone deacetylase (HDACs)inhibitors. We expect that our analysis would contribute to a better understanding about MCS applicationand its future perspectives for improving the decision making of QSAR models.