AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery

2015/10/10 by Izhar Wallach, Wallach, Izhar, Michael Dzamba +3 · 1 voice · 12 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Protein Structure and Dynamics #cs.LG #cs.NE #q-bio.BM #stat.ML

paper · pdf · doi:10.48550/arxiv.1510.02855

openalex publication_date 2015/10/10 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. Although DNNs have been used in drug discovery for QSAR and ligand-based bioactivity predictions, none of these models have benefited from this powerful convolutional architecture. This paper introduces AtomNet, the first structure-based, deep convolutional neural network designed to predict the bioactivity of small molecules for drug discovery applications. We demonstrate how to apply the convolutional concepts of feature locality and hierarchical composition to the modeling of bioactivity and chemical interactions. In further contrast to existing DNN techniques, we show that AtomNet's application of local convolutional filters to structural target information successfully predicts new active molecules for targets with no previously known modulators. Finally, we show that AtomNet outperforms previous docking approaches on a diverse set of benchmarks by a large margin, achieving an AUC greater than 0.9 on 57.8% of the targets in the DUDE benchmark.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Cited by

• Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning
• Landscape of Big Medical Data: A Pragmatic Survey on Prioritized Tasks
• TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
• Antibacterial Drug Discovery: Deep Learning Successes and Challenges through the Structural Biology Lens
• PotentialNet for Molecular Property Prediction
• Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
• Hierarchical, rotation‐equivariant neural networks to select structural models of protein complexes
• WideDTA: prediction of drug-target binding affinity
• DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks
• Learning a Continuous Representation of 3D Molecular Structures with\n Deep Generative Models
• IL-Net: Using Expert Knowledge to Guide the Design of Furcated Neural\n Networks

Discussions

• AtomNet: A Deep Convolutional Neural Network for Drug Discovery [hn, 5 points, 3 comments]

Related

• PotentialNet for Molecular Property Prediction
• Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
• PIGNet: A physics-informed deep learning model toward generalized drug-target interaction predictions
• Learning Hierarchical Interaction for Accurate Molecular Property Prediction
• Neural scaling laws for phenotypic drug discovery