Anubha Bajaj*

Anusha Sunder¹*, Samyuktha Sunkara², Nikhilesh Anand² and Kirtikaa Chezhian²

*Corresponding Author: Dr. Anusha Sunder, Doctorate in Life Science/Human Nutrition, Lead Scientist and Nutrigenetic Expert, Xcode Life Sciences, Pvt. Ltd. Chennai, India.

Received: May 06, 2026; Published: June 24, 2026

Drug–drug interactions (DDIs) are a major contributor to adverse drug reactions, particularly in patients undergoing polypharmacy for chronic conditions such as diabetes. Although databases such as DrugBank provide validated interactions, their coverage remains incomplete, leaving many potential DDIs unreported. As a result, many computational approaches treat these unknown drug pairs as non-interacting, thereby introducing label noise and reducing prediction reliability. In this study, we propose a Graph Neural Network (GNN)-based framework that integrates heterogeneous biomedical data with Positive–Unlabeled (PU) learning to address these challenges. Known interactions are treated as positive samples, while unknown pairs are handled as unlabeled to identify reliable non-interactions through a data-driven approach. A heterogeneous graph incorporating drug–drug, drug–protein, protein–protein, and pathway relationships is constructed and further enriched with side effects and Gene Ontology annotations. The enriched model demonstrates improved predictive performance and generalization, and external validation on unseen diabetes drug combinations shows strong agreement with clinical literature. Overall, the proposed framework provides a clinically relevant and data-driven approach for DDI prediction, while also enabling extension to polypharmacy risk assessment.

Keywords: Drug–Drug Interactions (DDIs); DrugBank; Graph Neural Network (GNN)

References

1. Alhumaidi RM., et al. “Risk of Polypharmacy and Its Outcome in Terms of Drug Interaction in an Elderly Population: A Retrospective Cross-Sectional Study”. Journal of Clinical Medicine12 (2023): 3960.
2. Mohamed M R., et al. “Association of polypharmacy and potential drug-drug interactions with adverse treatment outcomes in older adults with advanced cancer”. Cancer7 (2023): 1096-1104.
3. Rasool M F., et al. “Assessment of risk factors associated with potential drug-drug interactions among patients suffering from chronic disorders”. PloS One1 (2023): e0276277.
4. Peters LB., et al. “Evaluating drug-drug interaction information in NDF-RT and DrugBank”. Journal of Biomedical Semantics 6 (2015): 19.
5. Yan Zhao., et al. “Drug-drug interaction prediction: databases, web servers and computational models”. Briefings in Bioinformatics1 (2024).
6. Ferdousi R., et al. “Computational prediction of drug-drug interactions based on drugs functional similarities”. Journal of Biomedical Informatics 70 (2017): 54-64.
7. Mei S and Zhang K. “A machine learning framework for predicting drug-drug interactions”. Scientific Report 11 (2021): 17619.
8. Lin Xuan., et al. “KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction” (2020).
9. Abbas K., et al. “Graph neural network-based drug-drug interaction prediction”. Scientific Report 15 (2025): 30340.
10. Hu EY., et al. “Enhancing link prediction in biomedical knowledge graphs with BioPathNet”. Nature Biomedical Engineering (2026).
11. Zheng Y., et al. “DDI-PULearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions”. BMC Bioinformatics19 (2019): 661.
12. Vilar S., et al. “Similarity-based modeling in large-scale prediction of drug-drug interactions”. Nature Protocols9 (2014): 2147-2163.
13. Rao A D., et al. “Is the Combination of Sulfonylureas and Metformin Associated With an Increased Risk of Cardiovascular Disease or All-Cause Mortality?” Diabetes Care8 (2008): 1672-1678.
14. Hougen I., et al. “Safety of add-on sulfonylurea therapy in patients with type 2 diabetes using metformin: a population-based real-world study”. BMJ Open Diabetes Research and Care2 (2021): e002352.
15. Yu T., et al. “Risk of acute renal failure associated with combined use of SGLT2 inhibitors and potentially nephrotoxic drugs: an epidemiological surveillance study based on the FDA adverse event reporting system (FAERS)”. Expert Opinion on Drug Safety (2025): 1-12.
16. Singh B., et al. “ACE inhibitors. StatPearls - NCBI Bookshelf (2025).
17. Antonazzo I C., et al. “Myopathy with DPP-4 inhibitors and statins in the real world: investigating the likelihood of drug-drug interactions through the FDA adverse event reporting system”. Acta Diabetologica1 (2019): 71-80.
18. Tian B., et al. “Efficacy and safety of combination therapy with sodium-glucose cotransporter 2 inhibitors and renin-angiotensin system blockers in patients with type 2 diabetes: a systematic review and meta-analysis”. Nephrology Dialysis Transplantation4 (2021): 720-729.
19. Dawra VK., et al. “Assessment of the drug interaction potential of ertugliflozin with sitagliptin, metformin, glimepiride, or simvastatin in healthy subjects”. Clinical Pharmacology in Drug Development 3 (2018b): 314-325.

Citation

Citation: Anusha Sunder., et al.“Deducing Drug-Drug Interactions Through Graph Neural Networks". Acta Scientific Medical Sciences 10.7 (2026): 04-10.

Copyright

Copyright: © 2026 Anusha Sunder., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.