Toxicity Prediction using Deep Learning

By Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Sepp Hochreiter. 2015

165 citations recorded by the source corpus.

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.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Convolutional Networks on Graphs for Learning Molecular Fingerprints (2015, background): “[27] constructed similar visualizations, but in a semi-manual way: to determine which toxic fragments activated a given neuron, they searched over a hand-made list of toxic substructures and chose the one most correlated with a given neuron.”
Molecular graph convolutions: moving beyond fingerprints (2016, methodology): “We follow the common approach (Ramsundar et al., 2015; Ma et al., 2015; Unterthiner et al., 2015) of a small number of fully connected layers on top of the molecule-level features followed by standard softmax classiﬁcation.”
AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery (2015, methodology): “Recently, deep neural networks have been shown to out-perform random forests and SVMs for QSAR and ligand-based virtual screening [9, 10, 11].”
Computational Protein Design with Deep Learning Neural Networks (2018, methodology): “…Particularly in computational biology/chemistry, it has been used in protein-ligand scoring, 40-42 protein-protein interaction prediction, 43 protein secondary structure prediction, 44-49 protein contact map prediction, 50-52 and compound toxicity 53,54 and liver injury prediction, 55 among others.”
DeepTox: Toxicity Prediction using Deep Learning (2016, methodology): “Deep Learning has already been applied to predict the outcome of biological assays (Dahl et al., 2014; Unterthiner et al., 2014, 2015; Ma et al., 2015), which made it our prime candidate for toxicity prediction.”
A renaissance of neural networks in drug discovery (2016, background): “It has also been demonstrated for toxicity prediction that, by combining reactive centers, such networks can learn complex internal representation that resemble well-established toxi-cophores [106].”
Applications of machine learning in drug discovery and development (2019, unknown): “55 ) .”
Boosting Docking-Based Virtual Screening with Deep Learning (2016, background): “19,20 Also in 2015, Ramsundar et al. 21 predicted drug activity us-ing Massively Multitask Neural Networks associated with ﬁngerprints.”