# Capturing Unanticipated Drug Toxicities Using an Ensemble Machine Learning Approach

## TL;DR

This paper uses machine learning to predict drug withdrawals due to unexpected toxicities by analyzing drug features without needing human trial data.

## Contribution

The novel contribution is an ensemble machine learning model that predicts drug toxicity with high accuracy using non-clinical features.

## Key findings

- An ensemble model achieved 92% accuracy in predicting drug withdrawal due to toxicity.
- Key predictive features include inhibition of cytochrome P450 and bile salt export pumps.
- The model uses protein targets, structure features, and chemical fingerprints for prediction.

## Abstract

Despite rigorous safety evaluations during development, numerous drugs have been withdrawn from the market due to serious toxicities. Here we investigate the features found in drugs with these unanticipated toxicities and apply a machine learning approach to predict if a drug is likely to be withdrawn due to intolerable side effects without the need for human trial data. Our best preforming classifier was an ensemble predictor trained on protein targets, protein structure features, chemical fingerprints, and chemical features that achieved 92% accuracy and 0.845 Matthews Correlation Coefficient with 10-fold holdout test set cross validation. Analysis of features predictive of unanticipated toxicity revealed both known factors such as inhibition of cytochrome P450 as well as yet uninvestigated factors including the inhibition of bile salt export pumps. This predictor and subsequent feature analysis pave the way for the larger role of computational methods in screening potential candidates during drug development.