mlsanityData to 14 Oct 2026

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

arXiv 1510.02855 ↗First posted 10 Oct 2015cs.LG cs.NE q-bio.BMcited by 38

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Oct 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 13; 2023: 5; 2024: 4; 2025: 3; 2026: 4.

38 papers.

Sort:

  1. 2022EquiBind: Geometric Deep Learning for Drug Binding Structure Predictioncited by 144
  2. 2021Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Dockingcited by 82
  3. 2021Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinitycited by 60
  4. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  5. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  6. 2021DOCKSTRING: easy molecular docking yields better benchmarks for ligand designcited by 35
  7. 2021SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networkscited by 30
  8. 2024textttMiniMol: A Parameter-Efficient Foundation Model for Molecular Learningcited by 20
  9. 2023Protein-ligand binding representation learning from fine-grained interactionscited by 14
  10. 2021Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networkscited by 10
  11. 2022Learning Neural Set Functions Under the Optimal Subset Oraclecited by 10
  12. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
26 more
  1. 2022SS-GNN: A Simple-Structured Graph Neural Network for Affinity Predictioncited by 7
  2. 2022Predicting Protein-Ligand Binding Affinity via Joint Global-Local Interaction Modelingcited by 5
  3. 2022An efficient graph generative model for navigating ultra-large combinatorial synthesis librariescited by 5
  4. 2022DEL-Dock: Molecular Docking-Enabled Modeling of DNA-Encoded Librariescited by 3
  5. 2022Structure-based drug discovery with deep learningcited by 3
  6. 2023Deep Learning and Geometric Deep Learning: an introduction for mathematicians and physicistscited by 3
  7. 2025AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Researchcited by 3
  8. 2021An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networkscited by 2
  9. 2021Improved Drug-target Interaction Prediction with Intermolecular Graph Transformercited by 2
  10. 2023FragXsiteDTI: Revealing Responsible Segments in Drug-Target Interaction with Transformer-Driven Interpretationcited by 2
  11. 2025Regulating Multifunctionalitycited by 2
  12. 2021A Novel Framework Integrating AI Model and Enzymological Experiments Promotes Identification of SARS-CoV-2 3CL Protease Inhibitors and Activity-based Probecited by 1
  13. 2023HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discoverycited by 1
  14. 2024FREED++: Improving RL Agents for Fragment-Based Molecule Generation by Thorough Reproductioncited by 1
  15. 2024Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structurecited by 1
  16. 2025Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learningcited by 1
  17. 2026Beyond the Desk: Barriers and Future Opportunities for AI to Assist Scientists in Embodied Physical Taskscited by 1
  18. 2021ParaVS: A Simple, Fast, Efficient and Flexible Graph Neural Network Framework for Structure-Based Virtual Screeningcited by 0
  19. 2022Before and After: Machine learning for perioperative patient carecited by 0
  20. 2022Meaningful machine learning models and machine-learned pharmacophores from fragment screening campaignscited by 0
  21. 2022Recent Developments in Structure-Based Virtual Screening Approachescited by 0
  22. 2022Drug-target affinity prediction method based on consistent expression of heterogeneous datacited by 0
  23. 2024General Machine Learning Models for Interpreting and Predicting Efficiency Degradation in Organic Solar Cellscited by 0
  24. 2026When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Predictioncited by 0
  25. 2026Multigrid Training for Molecular Generation using Graph Neural Networkscited by 0
  26. 2026Advancing Optimal Subset Oracle via Learning Relaxation of Neural Set Functionscited by 0