A review on machine learning methods for in silico toxicity prediction

Abstract

In silico toxicity prediction plays an important role in the regulatory decision making and selection of leads in drug design as in vitro/vivo methods are often limited by ethics, time, budget, and other resources. Many computational methods have been employed in predicting the toxicity profile of chemicals. This review provides a detailed end-to-end overview of the application of machine learning algorithms to Structure-Activity Relationship (SAR)-based predictive toxicology. From raw data to model validation, the importance of data quality is stressed as it greatly affects the predictive power of derived models. Commonly overlooked challenges such as data imbalance, activity cliff, model evaluation, and definition of applicability domain are highlighted, and plausible solutions for alleviating these challenges are discussed.

Keywords:

• Toxicity prediction
• machine learning
• structure-activity relationship
• prediction accuracy
• model reliability
• molecular descriptors

Disclosure statement

This paper is not an official U.S. Army Corps of Engineer (USACE) or U.S. Food and Drug Administration (FDA) guidance or policy statement. No official support or endorsement by the USACE or U.S. FDA is intended or should be inferred. The views expressed in this paper do not necessarily represent those of USACE and U.S. FDA.

Additional information

Funding

This work was partly supported by an intramural grant from the U.S. Army Environmental Quality and Installations Program. Permission to publish this paper was granted by the Chief of Engineers.