Recently there has been an effort to reduced the number of animals used in safety studies for new medicines, and part of that effort has been the increased use of machine learning for toxicity prediction. However, this has proved to be very challenging due to the limited and potentially biased data available.

This open access paper describes strategy for future work DOI

We focus on five crucial pillars for success with ML-driven molecular property and toxicity prediction: (1) data set selection, (2) structural representations, (3) model algorithm, (4) model validation, and (5) translation of predictions to decision-making. Understanding these key pillars will foster collaboration and coordination between ML researchers and toxicologists, which will help to advance drug discovery and development.