Machine learning-based modeling of drug toxicity

Abstract

Toxicity is an important reason for the failure of drug research and development (R&D). The traditional experimental testings for chemical toxicity profile are costly and time-consuming. Therefore, it is attractive to develop the effective and accurate alternatives, such as in silico prediction models. In this review, we discuss the practical use of some prediction models on three toxicity end points, including acute toxicity, carcinogenicity, and inhibition of the human ether-a-go-go-related gene ion channel (hERG). Special emphasis is put on the machine learning methods for developing in silico models, and their advantages and weaknesses are discussed. We conclude that machine learning methods are valuable for helping the process of designing new candidates with low toxicity in drug R&D studies. In the future, much still needs to be done to understand more completely the biological mechanisms for toxicity and to develop more accurate prediction models to screen compounds.