Abstract
Accurately predicting Drug-Disease Associations (DDAs) is of great significance for drug repurposing and new drug development. Although existing methods have promoted the development of this field to a certain extent, most of them are still limited to single-modal data and cannot fully characterize the complex features of drugs, diseases, and genes. At the same time, many methods only focus on either local neighborhoods or global structures during feature extraction, lacking the organic combination of the two, which limits the accuracy and generalization of predictions. To address this, this paper proposes MedPathEx, a drug-disease association prediction method that combines multi-modal data integration and local-global feature learning. Specifically, we first construct a drug-gene-disease heterogeneous network and fuse multi-modal attributes such as drug chemical structures, ATC classifications, side effects, disease phenotypes and semantic information, as well as gene function annotations to generate more comprehensive node representations. Subsequently, we use graph convolutional networks to extract the attribute features of nodes themselves, capture local semantic relationships through meta-path modeling with a multi-head attention mechanism, and introduce a global attention mechanism to extract overall topological patterns, thereby achieving “micro-macro complementary” feature learning. Finally, by fusing node attributes and structural features, MedPathEx obtains a more discriminative comprehensive representation for the prediction of potential DDAs. Experimental results show that MedPathEx outperforms existing methods in key indicators such as AUC, AP, and F1. Moreover, it successfully identifies new candidate drugs in cases of coronary artery disease and hypertension, demonstrating its great potential in practical applications.
Data availability
All datasets used in this study are publicly available from their respective official sources: BioSNAP ([https://snap.stanford.edu/biodata/](https:/snap.stanford.edu/biodata)),CTD ([https://ctdbase.org/](https:/ctdbase.org)),PharmGKB ([https://www.pharmgkb.org/](https:/www.pharmgkb.org)),DrugBank([https://go.drugbank.com/](https:/go.drugbank.com)),ChEMBL([https://www.ebi.ac.uk/chembl/](https:/www.ebi.ac.uk/chembl)),SIDER(https://sideeffects.embl.de/),OMIM(https://www.omim.org/),MeSH ([https://www.ncbi.nlm.nih.gov/mesh/](https:/www.ncbi.nlm.nih.gov/mesh)),Gene Ontology Consortium (http://geneontology.org/).
Code Availability
The implementation of MedPathEx and the preprocessed data is available at https://github.com/wwiswwlucky/MedPathEx.
References
Wang, Y., Song, J., Dai, Q. & Duan, X. Hierarchical negative sampling based graph contrastive learning approach for Drug-Disease association prediction. IEEE J. Biomedical Health Inf. 28, 3146–3157 (2024).
Pasrija, P., Jha, P., Upadhyaya, P., Khan, M. S. & Chopra, M. Machine learning and artificial intelligence: A paradigm shift in big Data-Driven drug design and discovery. Curr. Top. Med. Chem. 22, 1692–1727 (2022).
Xiang, Z., Yunqiu, Z., Shaodan, S. & Liman, Z. Research on drug knowledge discovery method fusing meta-path features of heterogeneous knowledge networks: taking the prediction of drug–target relations as an example. Data Anal. Knowl. Discov. 8, 125–135 (2024).
Gu, Y., Zheng, S., Yin, Q., Jiang, R. & Li, J. R. E. D. D. A. Integrating multiple biological relations to heterogeneous graph neural network for drug-disease association prediction. Comput. Biol. Med. 150, 106127 (2022).
Jarada, T. N., Rokne, J. G. & Alhajj, R. A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions. J. Cheminform. 12, 46 (2020).
Pan, X. et al. Deep learning for drug repurposing: Methods, databases, and applications. WIREs Comput. Mol. Sci. 12, e1597 (2022).
Luo, H. et al. Biomedical data and computational models for drug repositioning: a comprehensive review. Brief. Bioinform. 22, 1604–1619 (2020).
Kim, Y. et al. Drug-Disease Association Prediction Using Heterogeneous Networks for Computational Drug Repositioning. Biomolecules 12, 1497 (2022).
Liu, H., Song, Y., Guan, J., Luo, L. & Zhuang, Z. Inferring new indications for approved drugs via random walk on drug-disease heterogenous networks. BMC Bioinform. 17, 539 (2016).
Wu, G., Liu, J. & Yue, X. Prediction of drug-disease associations based on ensemble meta paths and singular value decomposition. BMC Bioinform. 20, 134 (2019).
Jamali, A. A., Tan, Y., Kusalik, A. & Wu, F. X. NTD-DR: nonnegative tensor decomposition for drug repositioning. PLOS ONE. 17, 1–18 (2022).
Wu, P. et al. Integrating gene expression and clinical data to identify drug repurposing candidates for hyperlipidemia and hypertension. Nat. Commun. 13, 46 (2022).
Huang, S., Wang, M., Zheng, X., Chen, J. & Tang, C. Hierarchical and dynamic graph attention network for Drug-Disease association prediction. IEEE J. Biomedical Health Inf. 28, 2416–2427 (2024).
Zhang, M. L. et al. RLFDDA: a meta-path based graph representation learning model for drug–disease association prediction. BMC Bioinform. 23, 516 (2022).
Sun, X., Jia, X., Lu, Z., Tang, J. & Li, M. Drug repositioning with adaptive graph convolutional networks. Bioinformatics 40, btad748 (2024).
Zhao, B. W. et al. Fusing higher and Lower-Order biological information for drug repositioning via graph representation learning. IEEE Trans. Emerg. Top. Comput. 12, 163–176 (2024).
Muzio, G., O’Bray, L. & Borgwardt, K. Biological network analysis with deep learning. Brief. Bioinform. 22, 1515–1530 (2020).
Shi, C., Li, Y., Zhang, J., Sun, Y. & Yu, P. S. A survey of heterogeneous information network analysis. IEEE Trans. Knowl. Data Eng. 29, 17–37 (2017).
Jiao, Q. et al. Springer International Publishing,. NSAP: A neighborhood subgraph aggregation method for drug–disease association prediction. In Proceedings of the International Conference on Intelligent Computing, 79–91 (2022).
Zhou, R. et al. NEDD: a network embedding based method for predicting drug-disease associations. BMC Bioinform. 21, 387 (2020).
Fu, X., Zhang, J., Meng, Z. & King, I. M. A. G. N. N. Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding. In Proceedings of The Web Conference 2020 (WWW ’20), 2331–2341 (Association for Computing Machinery, 2020).
Zitnik, M., Sosić, R., Maheshwari, S. & Leskovec, J. BioSNAP Datasets: Stanford Biomedical Network Dataset Collection. (2018). Available at: http://snap.stanford.edu/biodata
Davis, A. P. et al. Comparative toxicogenomics database (CTD): update 2023. Nucleic Acids Res. 51, D1257–D1262 (2023).
Thorn, C. F., Klein, T. E. & Altman, R. B. PharmGKB: the pharmacogenomics knowledge base. In Pharmacogenomics (eds. Innocenti, F. & van Schaik, R.) Methods Mol. Biol. 1015, 311–320 (2013).
Mendez, D. et al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res. 47, D930–D940 (2019).
Knox, C. et al. DrugBank 6.0: the drugbank knowledgebase for 2024. Nucleic Acids Res. 52, D1265–D1275 (2024).
Jaccard, P. Nouvelles recherches Sur La distribution Florale. Bull. Soc. Vaud Sci. Nat. 44, 223–270 (1908).
Kuhn, M., Letunic, I., Jensen, L. J. & Bork, P. The SIDER database of drugs and side effects. Nucleic Acids Res. 44, D1075–D1079 (2016).
van Driel, M. A., Bruggeman, J., Vriend, G., Brunner, H. G. & Leunissen, J. A. M. A text-mining analysis of the human phenome. Eur. J. Hum. Genet. 14, 535–542 (2006).
Yu, G. Using meshes for mesh term enrichment and semantic analyses. Bioinformatics 34, 3766–3767 (2018).
Yu, G. et al. GOSemSim: an R package for measuring semantic similarity among GO terms and gene products. Bioinformatics 26, 976–978 (2010).
Zhang, S., Tong, H., Xu, J. & Maciejewski, R. Graph convolutional networks: a comprehensive review. Comput. Social Networks. 6, 1–23 (2019).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
Hearst, M. A., Dumais, S. T., Osuna, E., Platt, J. & Scholkopf, B. Support vector machines. IEEE Intell. Syst. Their Appl. 13, 18–28 (1998).
Kruse, R., Mostaghim, S., Borgelt, C., Braune, C. & Steinbrecher, M. Multi-layer perceptrons. In Computational Intelligence: A Methodological Introduction 53–124 (Springer International Publishing, 2022). https://doi.org/10.1007/978-3-030-42227-1_5.
Wang, X. et al. Heterogeneous graph attention network. In Proceedings of The Web Conference 2019 (WWW ’19), 2022–2032 (2019).
Meng, Y. et al. A weighted bilinear neural collaborative filtering approach for drug repositioning. Brief. Bioinform. 23, bbab581 (2022).
Li, Y. et al. A comparative benchmarking and evaluation framework for heterogeneous network-based drug repositioning methods. Brief. Bioinform. 25, 172 (2024).
Brown, J. C., Gerhardt, T. E. & Kwon, E. Risk factors for coronary artery disease (StatPearls [Internet]. StatPearls Publishing, 2023).
Tackling, G. & Borhade, M. B. Hypertensive heart disease. in StatPearls [Internet].StatPearls publishing (2023).
Alfaddagh, A. et al. Inflammation and cardiovascular disease: from mechanisms to therapeutics. Am. J. Prev. Cardiol. 4, 100130 (2020).
McIver, L. A. & Siddique, M. S. Atorvastatin. StatPearls [Internet]. StatPearls Publishing, Treasure Island (FL) (2024).
Pireddu, R. et al. Pyridylthiazole-based Ureas as inhibitors of Rho associated protein kinases (ROCK1 and 2). Medchemcomm 3, 699–709 (2012).
Nohria, A. et al. Rho kinase Inhibition improves endothelial function in human subjects with coronary artery disease. Circ. Res. 99, 1426–1432 (2006).
Mohri, M., Shimokawa, H., Hirakawa, Y., Masumoto, A. & Takeshita, A. Rho-kinase Inhibition with intracoronary fasudil prevents myocardial ischemia in patients with coronary microvascular spasm. J. Am. Coll. Cardiol. 41, 15–19 (2003).
Loscalzo, J. Molecular interaction networks and drug development: novel approach to drug target identification and drug repositioning. FASEB J. 37, e22660 (2023).
Panwar, V. et al. Multifaceted role of mTOR (mammalian target of rapamycin) signaling pathway in human health and disease. Signal. Transduct. Target. Ther. 8, 375 (2023).
Chanan-Khan, A. A. et al. Pomalidomide: the new Immunomodulatory agent for the treatment of multiple myeloma. Blood Cancer J. 3, e143 (2013).
Chamberlain, P. P. et al. Evolution of Cereblon-Mediated protein degradation as a therapeutic modality. ACS Med. Chem. Lett. 10, 1592–1602 (2019).
Wiysonge, C. S., Volmink, J. & Opie, L. H. Beta-blockers and the treatment of hypertension: it is time to move on. Cardiovasc. J. Afr. 18, 351–352 (2007).
Knowlton, A. A. & Lee, A. R. Estrogen and the cardiovascular system. Pharmacol. Ther. 135, 54–70 (2012).
Ni, X. et al. β–estradiol alleviates hypertension– and Concanavalin A–mediated inflammatory responses via modulation of connexins in peripheral blood lymphocytes. Mol. Med. Rep. 19, 3743–3755 (2019).
Qiu, T. et al. Comorbidity of anxiety and hypertension: common risk factors and potential mechanisms. Int. J. Hypertens. 9619388 (2023).
Acknowledgements
The authors thank the referees for suggestions that helped improve the paper substantially.
Funding
This research received no external funding.
Author information
Authors and Affiliations
Contributions
Shengnan Wu and Wen Wang produced the main ideas, and did the modeling, computation and analysis and also wrote the manuscript. Huizhi Jiao, Danhong Dong, Kexin Zhang and Xuechen Luo provided supervision and effective scientific advice and related ideas, research design guidance, and added value to the article through editing and contributing completions. All authors contributed to the article and approved the submitted version.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, S., Wang, W., Jiao, H. et al. Enhanced drug disease association prediction through multimodal data integration and meta path guided global local feature fusion. Sci Rep (2026). https://doi.org/10.1038/s41598-026-36223-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-36223-9
