mlsanityData to 7 Oct 2026

Recent Developments in GNNs for Drug Discovery

arXiv 2506.01302 ↗First posted 2 Jun 2025cs.LG q-bio.QMcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we review recent developments and the role of Graph Neural Networks (GNNs) in computational drug discovery, including molecule generation, molecular property prediction, and drug-drug interaction prediction. By summarizing the most recent developments in this area, we underscore the capabilities of GNNs to comprehend intricate molecular patterns, while exploring both their current and prospective applications. We initiate our discussion by examining various molecular representations, followed by detailed discussions and categorization of existing GNN models based on their input types and downstream application tasks. We also collect a list of commonly used benchmark datasets for a variety of applications. We conclude the paper with brief discussions and summarize common trends in this important research area.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 49 of its 130 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

49 of 130 references.

References · 49

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  3. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  4. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  5. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  6. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  7. 2018Learning Deep Generative Models of Graphscited by 227
  8. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  9. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  10. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  11. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  12. 20213D Infomax improves GNNs for Molecular Property Predictioncited by 146
37 more
  1. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  2. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  3. 2024Discrete-state Continuous-time Diffusion for Graph Generationcited by 73
  4. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 70
  5. 2021MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graphcited by 65
  6. 2021GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Predictioncited by 61
  7. 2021An End-to-End Framework for Molecular Conformation Generation via Bilevel Programmingcited by 59
  8. 2021SafeDrug: Dual Molecular Graph Encoders for Recommending Effective and Safe Drug Combinationscited by 51
  9. 2021Molecular Contrastive Learning with Chemical Element Knowledge Graphcited by 50
  10. 2022Unified 2D and 3D Pre-Training of Molecular Representationscited by 45
  11. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 45
  12. 2020SkipGNN: Predicting Molecular Interactions with Skip-Graph Networkscited by 44
  13. 2019A Model to Search for Synthesizable Moleculescited by 37
  14. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  15. 2020Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inferencecited by 35
  16. 2022E3Bind: An End-to-End Equivariant Network for Protein-Ligand Dockingcited by 35
  17. 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretrainingcited by 32
  18. 2021DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinationscited by 27
  19. 2018DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generationcited by 24
  20. 2019MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactionscited by 24
  21. 2023Conditional Graph Information Bottleneck for Molecular Relational Learningcited by 24
  22. 2023Automated 3D Pre-Training for Molecular Property Predictioncited by 24
  23. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 23
  24. 2021Deep Molecular Representation Learning via Fusing Physical and Chemical Informationcited by 21
  25. 2019Drug-Drug Adverse Effect Prediction with Graph Co-Attentioncited by 20
  26. 2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
  27. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  28. 2023Drug Discovery with Dynamic Goal-aware Fragmentscited by 19
  29. 2023Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equationcited by 18
  30. 2023FABind: Fast and Accurate Protein-Ligand Bindingcited by 17
  31. 2023EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Predictioncited by 15
  32. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
  33. 2023Federated Few-shot Learningcited by 9
  34. 2020Bi-Level Graph Neural Networks for Drug-Drug Interaction Predictioncited by 8
  35. 2023Von Mises Mixture Distributions for Molecular Conformation Generationcited by 5
  36. 2025Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalizationcited by 2
  37. 2025MD-Syn: Synergistic drug combination prediction based on the multidimensional feature fusion method and attention mechanismscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classificationcited by 0
  2. 2025A Spectral Framework for Graph Neural Operators: Convergence Guarantees and Tradeoffscited by 0
  3. 2026Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networkscited by 0