Toxicity Prediction using Deep Learning

TL;DR

This paper demonstrates that deep learning models can effectively predict chemical toxicity, outperforming traditional methods, and automatically learn relevant toxic features, setting new standards in computational toxicology.

Contribution

First application of deep learning to toxicity prediction, showing it outperforms existing methods and learns meaningful toxicophores automatically.

Findings

Deep learning outperformed all other methods in Tox21 challenge.

Deep nets automatically learned features similar to toxicophores.

Our approach won multiple categories in the Tox21 challenge.

Abstract

Everyday we are exposed to various chemicals via food additives, cleaning and cosmetic products and medicines -- and some of them might be toxic. However testing the toxicity of all existing compounds by biological experiments is neither financially nor logistically feasible. Therefore the government agencies NIH, EPA and FDA launched the Tox21 Data Challenge within the "Toxicology in the 21st Century" (Tox21) initiative. The goal of this challenge was to assess the performance of computational methods in predicting the toxicity of chemical compounds. State of the art toxicity prediction methods build upon specifically-designed chemical descriptors developed over decades. Though Deep Learning is new to the field and was never applied to toxicity prediction before, it clearly outperformed all other participating methods. In this application paper we show that deep nets automatically learn features resembling well-established toxicophores. In total, our Deep Learning approach won both of the panel-challenges (nuclear receptors and stress response) as well as the overall Grand Challenge, and thereby sets a new standard in tox prediction.