Toxicity Prediction using Deep Learning

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.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Massively Multitask Networks for Drug Discovery
• Multi-task Neural Networks for QSAR Predictions

Cited by in corpus (15)

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• TopologyNet: Topology based deep convolutional neural networks for biomolecular property predictions
• Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening
• Computational Protein Design with Deep Learning Neural Networks
• Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networks
• Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
• Latent Molecular Optimization for Targeted Therapeutic Design
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
• Personalized Prognostic Models for Oncology: A Machine Learning Approach
• Relational dynamic memory networks
• Seed Stocking Via Multi-Task Learning
• libmolgrid: GPU Accelerated Molecular Gridding for Deep Learning Applications