mlsanityData to 7 Oct 2026

Graph-structured Small Molecule Drug Discovery Through Deep Learning: Progress, Challenges, and Opportunities

arXiv 2502.08975 ↗First posted 13 Feb 2025cs.LG q-bio.BMcited by 5

Not on the map. Why?

Abstract (arXiv)

Due to their excellent drug-like and pharmacokinetic properties, small molecule drugs are widely used to treat various diseases, making them a critical component of drug discovery. In recent years, with the rapid development of deep learning (DL) techniques, DL-based small molecule drug discovery methods have achieved excellent performance in prediction accuracy, speed, and complex molecular relationship modeling compared to traditional machine learning approaches. These advancements enhance drug screening efficiency and optimization and provide more precise and effective solutions for various drug discovery tasks. Contributing to this field's development, this paper aims to systematically summarize and generalize the recent key tasks and representative techniques in graph-structured small molecule drug discovery in recent years. Specifically, we provide an overview of the major tasks in small molecule drug discovery and their interrelationships. Next, we analyze the six core tasks, summarizing the related methods, commonly used datasets, and technological development trends. Finally, we discuss key challenges, such as interpretability and out-of-distribution generalization, and offer our insights into future research directions for small molecule drug discovery.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 44 of its 89 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

44 of 89 references.

References · 44

  1. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  2. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  3. 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equationscited by 273
  4. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  5. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  6. 2021ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Predictioncited by 204
  7. 2023Geometric Latent Diffusion Models for 3D Molecule Generationcited by 185
  8. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 179
  9. 2021Spherical Message Passing for 3D Graph Networkscited by 166
  10. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  11. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  12. 2021Learning Neural Generative Dynamics for Molecular Conformation Generationcited by 87
32 more
  1. 2024DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Designcited by 87
  2. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  3. 2022ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphscited by 69
  4. 2019Mol-CycleGAN - a generative model for molecular optimizationcited by 66
  5. 2020MolTrans: Molecular Interaction Transformer for Drug Target Interaction Predictioncited by 63
  6. 2021Differentiable Scaffolding Tree for Molecular Optimizationcited by 53
  7. 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
  8. 2024Graph Diffusion Transformers for Multi-Conditional Molecular Generationcited by 44
  9. 2022Interpretable bilinear attention network with domain adaptation improves drug-target predictioncited by 39
  10. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  11. 2020GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactionscited by 29
  12. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimizationcited by 27
  13. 2023Conditional Graph Information Bottleneck for Molecular Relational Learningcited by 24
  14. 2023Multimodal Molecular Pretraining via Modality Blendingcited by 21
  15. 2024Uni-Mol2: Exploring Molecular Pretraining Model at Scalecited by 20
  16. 2023Sliced Denoising: A Physics-Informed Molecular Pre-Training Methodcited by 18
  17. 2023Learning Topology-Specific Experts for Molecular Property Predictioncited by 15
  18. 2024Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformerscited by 12
  19. 2024Text-guided multi-property molecular optimization with a diffusion language modelcited by 11
  20. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
  21. 2024PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Predictioncited by 10
  22. 2020Bi-Level Graph Neural Networks for Drug-Drug Interaction Predictioncited by 8
  23. 2023Instructor-inspired Machine Learning for Robust Molecular Property Predictioncited by 8
  24. 2024Expressivity and Generalization: Fragment-Biases for Molecular GNNscited by 8
  25. 2024Representing Molecules as Random Walks Over Interpretable Grammarscited by 7
  26. 2024Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Modelscited by 7
  27. 2025Can Molecular Evolution Mechanism Enhance Molecular Representation?cited by 7
  28. 2023MolHF: A Hierarchical Normalizing Flow for Molecular Graph Generationcited by 6
  29. 2023Multi-channel learning for integrating structural hierarchies into context-dependent molecular representationcited by 6
  30. 2024A Cross-Field Fusion Strategy for Drug-Target Interaction Predictioncited by 5
  31. 2024ZeroDDI: A Zero-Shot Drug-Drug Interaction Event Prediction Method with Semantic Enhanced Learning and Dual-Modal Uniform Alignmentcited by 5
  32. 2024WISER: Weak supervISion and supErvised Representation learning to improve drug response prediction in cancercited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Transport-Coupled Bayesian Flows for Molecular Graph Generationcited by 1
  2. 2026PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionarycited by 1
  3. 2026Variational Bayesian Flow Network for Graph Generationcited by 1
  4. 2026From Single-Step Edit Response to Multi-Step Molecular Optimizationcited by 0
  5. 2026When Molecular Similarity Works: Property Cliffs Reveal Hidden Errorscited by 0