How Advanced Artificial Intelligence Technologies Shape Drug–Drug and Drug–Target Interaction Modeling
Source abstract
Abstract
ABSTRACT Drug molecular interactions, including drug–drug interactions (DDIs) and drug–target interactions (DTIs), are critical for drug discovery and clinical safety, increasingly propelled by artificial intelligence (AI) technologies. Although previously treated as separate domains, DDIs and DTIs are highly interconnected in terms of biological mechanisms and model design. To foster their co‐evolution, this review provides a comprehensive landscape of drug molecular interaction modeling by first summarizing the advanced AI technologies across various prediction tasks in both domains. Then, the parallel development paths are examined in core architecture, feature engineering, and model learning paradigms, highlighting the convergence in patterns of feature engineering and trends of model design. Furthermore, the key challenges, such as insufficient generalizability and shortcut learning, are identified and evaluated through quantitative experiments, and future directions are proposed for building unified models to leverage AI in accelerating drug discovery and therapeutics design.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Computational Drug Discovery Methods · Machine Learning in Materials Science · Machine Learning in Bioinformatics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Laboratory of Membrane Biology, Beijing Frontier Research Center for Biological Structure, Tsinghua‐Peking Center for Life Sciences, Center for Life Sciences and Artificial Intelligence, School of Life Sciences Tsinghua University Beijing China
Funding
National Key Research and Development Program of China
References (100+)
Show source-provided references
1. Machine Learning in Preclinical Drug Discovery10.1038/s41589-024-01679-1 ↗
2. Protein Language Models for Predicting Drug–Target Interactions: Novel Approaches, Emerging Methods, and Future Directions10.1016/j.sbi.2025.103017 ↗
3. Drug–Drug Interactions and Synergy: From Pharmacological Models to Clinical Application10.1124/pharmrev.124.000951 ↗
4. The Art of Finding the Right Drug Target: Emerging Methods and Strategies10.1124/pharmrev.123.001028 ↗
5. Drug–Drug Interaction Prediction: Databases, Web Servers and Computational Models10.1093/bib/bbad445 ↗
6. Drug–Drug Interaction Relation Extraction Based on Deep Learning: A Review10.1145/3645089 ↗
7. Elucidating the Role of Artificial Intelligence in Drug Development from the Perspective of Drug–Target Interactions10.1016/j.jpha.2024.101144 ↗
8. Evidential Deep Learning‐Based Drug–Target Interaction Prediction10.1038/s41467-025-62235-6 ↗
9. Drug–Drug Interaction Through Molecular Structure Similarity Analysis10.1136/amiajnl-2012-000935 ↗
10. Similarity‐Based Modeling in Large‐Scale Prediction of Drug–Drug Interactions10.1038/nprot.2014.151 ↗
11. Combining Drug and Gene Similarity Measures for Drug–Target Elucidation10.1089/cmb.2010.0213 ↗
12. J.‐Y.ShiandS.‐M.Yiu “SRP: A Concise Non‐Parametric Similarity‐Rank‐Based Model for Predicting Drug–Target Interactions ” in2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)(IEEE 2015) 1636–1641.10.1109/BIBM.2015.7359921 ↗
13. Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence10.1155/2023/8342104 ↗
14. Graph Neural Networks10.1038/s43586-024-00294-7 ↗
15. A Survey of Graph Neural Networks in Various Learning Paradigms: Methods, Applications, and Challenges10.1007/s10462-022-10321-2 ↗
16. Attention Is All You Need
17. Transformer Technology in Molecular Science
18. Large Language Models in Medicine10.1038/s41591-023-02448-8 ↗
19. Large Language Models in Medicine: The Potentials and Pitfalls: A Narrative Review10.7326/M23-2772 ↗
20. Knowledge Graphs: Opportunities and Challenges10.1007/s10462-023-10465-9 ↗
21. C.Wu H.Liu J.Flannick et al. “Desiderata for a Biomedical Knowledge Network: Opportunities Challenges and Future Directions ”arXiv Preprint arXiv:2509.22424(2025).10.1093/bioadv/vbag036 ↗
22. Exploring the Roles of Cytochrome P450 Enzymes and Their Inhibitors in Cancers and Non‐Neoplastic Human Diseases
23. Assessing Cytochrome P450 Drug Interaction Risk for Dordaviprone Using Physiologically Based Pharmacokinetic Modeling
24. Inhibition and Induction of CYP Enzymes in Humans: An Update10.1007/s00204-020-02936-7 ↗
25. A Review of CYP‐Mediated Drug Interactions: Mechanisms and In Vitro Drug–Drug Interaction Assessment10.3390/biom14010099 ↗
26. Pharmacodynamic Drug–Drug Interactions10.1002/cpt.1434 ↗
27. A General Pharmacodynamic Interaction Model Identifies Perpetrators and Victims in Drug Interactions10.1038/s41467-017-01929-y ↗
28. Evolutionary‐Scale Prediction of Atomic‐Level Protein Structure with a Language Model10.1126/science.ade2574 ↗
29. Simulating 500 Million Years of Evolution with a Language Model10.1126/science.ads0018 ↗
30. Hsu C. · 2022 · 8946
31. ChemBERTa‐3: an open source training framework for chemical foundation models
32. Self‐Supervised Learning: Generative or Contrastive
33. A Survey on Self‐Supervised Learning: Algorithms, Applications, and Future Trends10.1109/TPAMI.2024.3415112 ↗
34. Meta‐Learning in Neural Networks: A Survey
35. Advances and Challenges in Meta‐Learning: A Technical Review10.1109/TPAMI.2024.3357847 ↗
36. Generalizing to Unseen Domains: A Survey on Domain Generalization
37. Domain Generalization: A Survey
38. A Molecular Representation Learning Model Based on Multidimensional Joint and Cross‐Learning for Drug–Drug Interaction Prediction10.1021/acs.jcim.5c01171 ↗
39. DSN‐DDI: An Accurate and Generalized Framework for Drug–Drug Interaction Prediction by Dual‐View Representation Learning
40. An Effective Framework for Predicting Drug–Drug Interactions Based on Molecular Substructures and Knowledge Graph Neural Network10.1016/j.compbiomed.2023.107900 ↗
41. D.Wu W.Sun Y.He Z.Chen andX.Luo “MKG‐FENN: A Multimodal Knowledge Graph Fused End‐to‐End Neural Network for Accurate Drug–Drug Interaction Prediction ” inProceedings of the AAAI Conference on Artificial Intelligence38(2024):10216–10224.10.1609/aaai.v38i9.28887 ↗
42. Accurate and Interpretable Drug– Drug Interaction Prediction Enabled by Knowledge Subgraph Learning10.1038/s43856-024-00486-y ↗
43. Emerging Drug Interaction Prediction Enabled by a Flow‐Based Graph Neural Network with Biomedical Network10.1038/s43588-023-00558-4 ↗
44. LLM‐DDI: Leveraging Large Language Models for Drug–Drug Interaction Prediction on Biomedical Knowledge Graph10.1109/JBHI.2025.3585290 ↗
45. Knowledge Graph Neural Network with Spatial‐Aware Capsule for Drug–Drug Interaction Prediction10.1109/JBHI.2024.3419015 ↗
46. X.Su P.Hu Z.‐H.You P. S.Yu andL.Hu “Dual‐Channel Learning Framework for Drug–Drug Interaction Prediction via Relation‐Aware Heterogeneous Graph Transformer ” inProceedings of the AAAI Conference on Artificial Intelligence38(2024):249–256.10.1609/aaai.v38i1.27777 ↗
47. DrugDAGT: A Dual‐Attention Graph Transformer with Contrastive Learning Improves Drug–Drug Interaction Prediction10.1186/s12915-024-02030-9 ↗
48. Learning Motif‐Based Graphs for Drug–Drug Interaction Prediction via Local–Global Self‐Attention10.1038/s42256-024-00888-6 ↗
49. CTF‐DDI: Constrained Tensor Factorization for Drug–Drug Interactions Prediction10.1016/j.future.2024.06.060 ↗
50. RCAN‐DDI: Relation‐Aware Cross Adversarial Network for Drug–Drug Interaction Prediction10.1016/j.jpha.2024.101159 ↗
51. AutoDDI: Drug–Drug Interaction Prediction with Automated Graph Neural Network10.1109/JBHI.2024.3349570 ↗
52. Customized Subgraph Selection and Encoding for Drug–Drug Interaction Prediction10.52202/079017-3478 ↗
53. Systematic Review on Neural Architecture Search10.1007/s10462-024-11058-w ↗
54. Zero‐Shot Neural Architecture Search: Challenges, Solutions, and Opportunities10.1109/TPAMI.2024.3395423 ↗
55. Predicting Rare Drug–Drug Interaction Events with Dual‐Granular Structure‐Adaptive and Pair Variational Representation10.1038/s41467-025-59431-9 ↗
56. DSIL‐DDI: A Domain‐Invariant Substructure Interaction Learning for Generalizable Drug–Drug Interaction Prediction10.1109/TNNLS.2023.3242656 ↗
57. PHGL‐DDI: A Pre‐Training Based Hierarchical Graph Learning Framework for Drug–Drug Interaction Prediction10.1016/j.eswa.2025.126408 ↗
58. EDDINet: Enhancing Drug–Drug Interaction Prediction via Information Flow and Consensus Constrained Multi‐Graph Contrastive Learning10.1016/j.artmed.2024.103029 ↗
59. DDI‐GCN: Drug–Drug Interaction Prediction via Explainable Graph Convolutional Networks10.1016/j.artmed.2023.102640 ↗
60. GGI‐DDI: Identification for Key Molecular Substructures by Granule Learning to Interpret Predicted Drug–Drug Interactions10.1016/j.eswa.2023.122500 ↗
61. R.Zhang X.Wang G.Liu P.Wang Y.Zhou andP.Wang “Motif‐Oriented Representation Learning with Topology Refinement for Drug–Drug Interaction Prediction ” inProceedings of the AAAI Conference on Artificial Intelligence39(2025):1102–1110.10.1609/aaai.v39i1.32097 ↗
62. SRR‐DDI: A Drug–Drug Interaction Prediction Model with Substructure Refined Representation Learning Based on Self‐Attention Mechanism10.1016/j.knosys.2023.111337 ↗
63. TripletMultiDTI: Multimodal Representation Learning in Drug–Target Interaction Prediction with Triplet Loss Function10.1016/j.eswa.2023.120754 ↗
64. Efficient Deep Model Ensemble Framework for Drug–Target Interaction Prediction10.1021/acs.jpclett.4c01509 ↗
65. Evidential Deep Learning‐Based Drug–Target Interaction Prediction10.1038/s41467-025-62235-6 ↗
66. Geometry‐Enhanced Molecular Representation Learning for Property Prediction10.1038/s42256-021-00438-4 ↗
67. MGNDTI: A Drug–Target Interaction Prediction Framework Based on Multimodal Representation Learning and the Gating Mechanism10.1021/acs.jcim.4c00957 ↗
68. DMHGNN: Double Multi‐View Heterogeneous Graph Neural Network Framework for Drug–Target Interaction Prediction10.1016/j.artmed.2024.103023 ↗
69. GSRF‐DTI: A Framework for Drug–Target Interaction Prediction Based on a Drug–Target Pair Network and Representation Learning on a Large Graph10.1186/s12915-024-01949-3 ↗
70. DTI‐LM: Language Model Powered Drug–Target Interaction Prediction10.1093/bioinformatics/btae533 ↗
71. Improved Drug–Target Interaction Prediction with Intermolecular Graph Transformer
72. BindTI: A Bi‐Directional Intention Network for Drug–Target Interaction Identification Based on Attention Mechanisms10.1109/JBHI.2024.3375025 ↗
73. ReduMixDTI: Prediction of Drug–Target Interaction with Feature Redundancy Reduction and Interpretable Attention Mechanism10.1021/acs.jcim.4c01554 ↗
74. Flexible Drug–Target Interaction Prediction with Interactive Information Extraction and Trade‐Off10.1016/j.eswa.2024.123821 ↗
75. GENNDTI: Drug–Target Interaction Prediction Using Graph Neural Network Enhanced by Router Nodes10.1109/JBHI.2024.3402529 ↗
76. NASNet‐DTI: Accurate Drug–Target Interaction Prediction Using Heterogeneous Graphs and Node Adaptation10.1093/bib/bbaf342 ↗
77. DeFuseDTI: Interpretable Drug Target Interaction Prediction Model with Dual‐Branch Encoder and Multiview Fusion10.1016/j.future.2024.07.014 ↗
78. DTIAM: A Unified Framework for Predicting Drug–Target Interactions, Binding Affinities and Drug Mechanisms10.1038/s41467-025-57828-0 ↗
79. SSLDTI: A Novel Method for Drug–Target Interaction Prediction Based on Self‐Supervised Learning10.1016/j.artmed.2024.102778 ↗
80. MMDG‐DTI: Drug–Target Interaction Prediction via Multimodal Feature Fusion and Domain Generalization10.1016/j.patcog.2024.110887 ↗
81. Z.Xie S.Tu andL.Xu “Multilevel Attention Network with Semi‐Supervised Domain Adaptation for Drug–Target Prediction ” inProceedings of the AAAI Conference on Artificial Intelligence38(2024):329–337.10.1609/aaai.v38i1.27786 ↗
82. ZeroBind: A Protein‐Specific Zero‐Shot Predictor with Subgraph Matching for Drug–Target Interactions10.1038/s41467-023-43597-1 ↗
83. Drug–Target Interaction Prediction Based on Improved Heterogeneous Graph Representation Learning and Feature Projection Classification10.1016/j.eswa.2024.124289 ↗
84. Fuzzy Machine Learning: A Comprehensive Framework and Systematic Review10.1109/TFUZZ.2024.3387429 ↗
85. A Pseudo‐Label Supervised Graph Fusion Attention Network for Drug–Target Interaction Prediction10.1016/j.eswa.2024.125264 ↗
86. A Comprehensive Survey on Evidential Deep Learning and its Applications10.1109/TPAMI.2025.3625258 ↗
87. Evidential Deep Learning for Guided Molecular Property Prediction and Discovery10.1021/acscentsci.1c00546 ↗
88. Deep Contrastive Learning Enables Genome‐Wide Virtual Screening10.1126/science.ads9530 ↗
89. MSI‐DTI: Predicting Drug–Target Interaction Based on Multi‐Source Information and Multi‐Head Self‐Attention10.1093/bib/bbae238 ↗
90. MDF‐SA‐DDI: Predicting Drug–Drug Interaction Events Based on Multi‐Source Drug Fusion, Multi‐Source Feature Fusion and Transformer Self‐Attention Mechanism10.1093/bib/bbab421 ↗
91. DLM‐DTI: A Dual Language Model for the Prediction of Drug–Target Interaction with Hint‐Based Learning10.1186/s13321-024-00808-1 ↗
92. Benchmarking Molecular Conformer Augmentation with Context‐Enriched Training: Graph‐Based Transformer Versus GNN Models10.1186/s13321-025-01004-5 ↗
93. Explainable Artificial Intelligence in Drug Discovery: Bridging Predictive Power and Mechanistic Insight
94. Computational Approaches Streamlining Drug Discovery10.1038/s41586-023-05905-z ↗
95. Drug Discovery Through Biophysical Techniques: Methods and Applications10.1016/j.pharmthera.2025.108947 ↗
96. Multi‐Component, Time‐Course Screening to Develop Combination Cancer Therapies Based on Synergistic Toxicity10.1073/pnas.2413372121 ↗
97. State‐of‐the‐Art Strategies of Surface Plasmon Resonance Biosensors in Clinical Analysis: A Comprehensive Review10.1016/j.ccr.2024.216149 ↗
98. Isothermal Titration Calorimetry10.1038/s43586-023-00199-x ↗
99. Enhancing Geometric Representations for Molecules with Equivariant Vector‐Scalar Interactive Message Passing10.1038/s41467-023-43720-2 ↗
100. T.Cui Z.Wang andT.Wang “Enhancing Non‐Local Interaction Modeling for Ab Initio Biomolecular Calculations and Simulations with VisNet‐PIMA ”bioRxiv(2026):2026–03.10.64898/2026.03.18.712561 ↗