Graph Neural Network-Based Prediction of Drug-Target Interactions Using Heterogeneous Biomedical Data Integration

Authors

  • Radoslaw Drywa Department of Computer Science, University of Central Florida, Orlando, FL, USA.

Keywords:

drug-target interaction; heterogeneous graph neural networks; biomedical data integration; positive-unlabeled learning; graph attention; uncertainty calibration

Abstract

Drug-target interaction (DTI) prediction must reconcile sparse, noisy, and heterogeneous evidence ranging from chemical structure and protein sequence to pathway membership, expression context, and literature-derived associations. Many existing computational models treat DTI prediction as homogeneous link prediction or concatenate features before learning, which obscures relation-specific semantics and can propagate degree and assay biases. This manuscript develops a heterogeneous graph neural network framework for DTI prediction that represents drugs, proteins, diseases, pathways, and related biomedical entities as typed nodes and encodes known interactions and contextual relations as typed edges. Type-specific encoders map molecular fingerprints, sequence representations, and omics or knowledge-base attributes into a shared latent space; relation-aware attention aggregates evidence across heterogeneous neighborhoods; and a calibrated scoring function estimates interaction probabilities with explicit handling of positive-unlabeled bias, edge confidence, and distribution shift. The framework specifies leakage-resistant evaluation, cold-start diagnostics, uncertainty calibration, and computational strategies for sparse large-scale graphs. Analytical assessment indicates that the main gains arise not from adding data indiscriminately but from preserving relation semantics, controlling noisy or indirect edges, and separating biological mechanism from statistical association. The resulting design offers a technically grounded route to more transferable and interpretable DTI prediction and clarifies the conditions under which heterogeneous biomedical integration is likely to improve prioritization rather than merely increase model complexity.

References

1. Öztürk, H., Özgür, A., & Ozkirimli, E. (2018). DeepDTA: Deep drug–target binding affinity prediction. Bioinformatics, 34(17), i821–i829.

2. Luo, Y., Zhao, X., Zhou, J., Yang, J., Zhang, Y., Kuang, W., Peng, J., Chen, L., & Zeng, J. (2017). A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nature Communications, 8, 573.

3. Zitnik, M., Agrawal, M., & Leskovec, J. (2018). Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 34(13), i457–i466.

4. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations.

5. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. In Proceedings of the International Conference on Learning Representations.

6. Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., & Welling, M. (2018). Modeling relational data with graph convolutional networks. In The Semantic Web (ESWC 2018) (pp. 593–607). Springer.

7. Wang, X., He, X., Cao, Y., Liu, M., & Chua, T.-S. (2019). KGAT: Knowledge graph attention network for recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 950–958).

8. Zhang, C., Song, D., Huang, C., Swami, A., & Chawla, N. V. (2019). Heterogeneous graph neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 793–803).

9. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794).

10. Elkan, C., & Noto, K. (2008). Learning classifiers from only positive and unlabeled data. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 213–220).

11. Xie, X., Peng, H., Hasan, A., Huang, S., Zhao, J., Fang, H., ... & Ding, C. (2023, October). Accel-gcn: High-performance gpu accelerator design for graph convolution networks. In 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) (pp. 01-09). IEEE.

12. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations.

13. Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning (pp. 1050–1059).

14. Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. In Proceedings of the 34th International Conference on Machine Learning (pp. 1321–1330).

15. Davis, M. I., Hunt, J. P., Herrgard, S., Ciceri, P., Wodicka, L. M., Pallares, G., Hocker, M., Treiber, D. K., & Zarrinkar, P. P. (2011). Comprehensive analysis of kinase inhibitor selectivity. Nature Biotechnology, 29(11), 1046–1051.

16. Gilson, M. K., Liu, T., Baitaluk, M., Nicola, G., Hwang, L., & Chong, J. (2016). BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Research, 44(D1), D1045–D1053.

17. Wishart, D. S., Feunang, Y. D., Guo, A. C., Lo, E. J., Marcu, A., Grant, J. R., ... & Wilson, M. (2018). DrugBank 5.0: A major update to the DrugBank database for 2018. Nucleic Acids Research, 46(D1), D1074–D1082.

18. Szklarczyk, D., Gable, A. L., Nastou, K. C., Lyon, D., Kirsch, R., Pyysalo, S., ... & von Mering, C. (2021). The STRING database in 2021: Customizable protein–protein networks, and functional characterization of user-uploaded gene/measurement sets. Nucleic Acids Research, 49(D1), D605–D612.

19. Subramanian, A., Narayan, R., Corsello, S. M., Peck, D. D., Natoli, T. E., Lu, X., ... & Golub, T. R. (2017). A next generation connectivity map: L1000 platform and the first 1,000,000 profiles. Cell, 171(6), 1437–1452.e17.

20. Himmelstein, D. S., Lizee, A., Hessler, C., Brueggeman, L., Chen, S. L., Hadley, D., ... & Baranzini, S. E. (2017). Systematic integration of biomedical knowledge prioritizes drugs for repurposing. eLife, 6, e26726.

Downloads

Published

2026-10-06

How to Cite

Radoslaw Drywa. (2026). Graph Neural Network-Based Prediction of Drug-Target Interactions Using Heterogeneous Biomedical Data Integration. Bioinformatics Insights and Analytics, 4(3). Retrieved from https://bioinfia.org/index.php/home/article/view/248