Identify drug-drug interactions via deep learning: A real world study

Jingyang Li; Yanpeng Zhao; Zhenting Wang; Chunyue Lei; Lianlian Wu; Yixin Zhang; Song He; Xiaochen Bo; Jian Xiao

doi:10.1016/j.jpha.2025.101194

Volume 15 Issue 6

Jun. 2025

Turn off MathJax

Article Contents

Article Navigation > Journal of Pharmaceutical Analysis > 2025 > 15(6): 101194

Jingyang Li, Yanpeng Zhao, Zhenting Wang, Chunyue Lei, Lianlian Wu, Yixin Zhang, Song He, Xiaochen Bo, Jian Xiao. Identify drug-drug interactions via deep learning: A real world study[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101194. doi: 10.1016/j.jpha.2025.101194

Citation:

Jingyang Li, Yanpeng Zhao, Zhenting Wang, Chunyue Lei, Lianlian Wu, Yixin Zhang, Song He, Xiaochen Bo, Jian Xiao. Identify drug-drug interactions via deep learning: A real world study[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101194. doi: 10.1016/j.jpha.2025.101194

Citation:

Jingyang Li, Yanpeng Zhao, Zhenting Wang, Chunyue Lei, Lianlian Wu, Yixin Zhang, Song He, Xiaochen Bo, Jian Xiao. Identify drug-drug interactions via deep learning: A real world study[J]. Journal of Pharmaceutical Analysis, 2025, 15(6): 101194. doi: 10.1016/j.jpha.2025.101194

PDF( 4530 KB)

Identify drug-drug interactions via deep learning: A real world study

doi: 10.1016/j.jpha.2025.101194

a. Department of Pharmacy, Xiangya Hospital, Central South University, Changsha, 410008, China;
b. Academy of Military Medical Sciences, Beijing, 100850, China;
c. Department of Pharmacy, People's Hospital of Qingshen, Meishan, Sichuan, 620460, China;
d. North China University of Technology, No. 5 Jinyuonzhuang Rood, Shijingshan District, Beijing, 100144, China;
e. Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, 300072, China;
f. Institute for Rational and Safe Medication Practices, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, 410008, China

Funds:

This work was supported by the National Key R&D Program of China (Grant No.: 2023YFC2604400) and the National Natural Science Foundation of China (Grant No.: 62103436).

Received Date: Jul. 30, 2024
Accepted Date: Jan. 06, 2025
Rev Recd Date: Dec. 04, 2024
Publish Date: Jan. 08, 2025

Abstract

Abstract

Identifying drug-drug interactions (DDIs) is essential to prevent adverse effects from polypharmacy. Although deep learning has advanced DDI identification, the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits. Here, we developed a Multi-Dimensional Feature Fusion model named MDFF, which integrates one-dimensional simplified molecular input line entry system sequence features, two-dimensional molecular graph features, and three-dimensional geometric features to enhance drug representations for predicting DDIs. MDFF was trained and validated on two DDI datasets, evaluated across three distinct scenarios, and compared with advanced DDI prediction models using accuracy, precision, recall, area under the curve, and F1 score metrics. MDFF achieved state-of-the-art performance across all metrics. Ablation experiments showed that integrating multi-dimensional drug features yielded the best results. More importantly, we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs. Among 12 real-world adverse drug reaction reports, the predictions of 9 reports were supported by relevant evidence. Additionally, MDFF demonstrated the ability to explain adverse DDI mechanisms, providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.
- Drug-drug interactions,
- Deep learning,
- Health care,
- Multi-dimensional feature fusion

FullText(HTML)

References(44)

References

[1]	C. Muth, J.W. Blom, S.M. Smith, et al., Evidence supporting the best clinical management of patients with multimorbidity and polypharmacy: A systematic guideline review and expert consensus, J. Intern. Med. 285 (2019) 272-288.
[2]	G. Onder, A. Marengoni, Polypharmacy, JAMA 318 (2017), 1728.
[3]	I.A. Scott, S.N. Hilmer, E. Reeve, et al., Reducing inappropriate polypharmacy: The process of deprescribing, JAMA Intern. Med. 175 (2015) 827-834.
[4]	W.H. Lu, Y.W. Wen, L.K. Chen, et al., Effect of polypharmacy, potentially inappropriate medications and anticholinergic burden on clinical outcomes: A retrospective cohort study, CMAJ (Can. Med. Assoc. J.) 187 (2015) E130-e137.
[5]	C.S. Moura, F.A. Acurcio, N.O. Belo, Drug-drug interactions associated with length of stay and cost of hospitalization, J. Pharm. Pharmaceut. Sci. 12 (2009) 266-272.
[6]	S. Yang, Y. Wang, Y. Chen, et al., Masqc: Next generation sequencing assists third generation sequencing for quality control in N6-methyladenine DNA identification, Front. Genet. 11 (2020), 269.
[7]	Z. Yang, W. Yi, J. Tao, et al., HPVMD-C: A disease-based mutation database of human papillomavirus in China, Database 2022 (2022), baac018.
[8]	Y. Wang, Y. Xu, Z. Yang, et al., Using recursive feature selection with random forest to improve protein structural class prediction for low-similarity sequences, Comput. Math. Methods Med. 2021 (2021), 5529389.
[9]	Q. Dai, C. Bao, Y. Hai, et al., MTGIpick allows robust identification of genomic islands from a single genome, Briefings Bioinf. 19 (2018) 361-373.
[10]	X. Lin, L. Dai, Y. Zhou, et al., Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction, Briefings Bioinf. 2023. https://doi.org/10.1093/bib/bbad235.
[11]	S. Vilar, E. Uriarte, L. Santana, et al., Similarity-based modeling in large-scale prediction of drug-drug interactions, Nat. Protoc. 9 (2014) 2147-2163.
[12]	X. Li, Z. Xiong, W. Zhang, et al., Deep learning for drug-drug interaction prediction: A comprehensive review, Quant. Biol. 12 (2024) 30-52.
[13]	Y. Wang, Z. Yang, Q. Yao, Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning, Commun. Med. 4 (2024), 59.
[14]	Y. Zhang, Q. Yao, L. Yue, et al., Emerging drug interaction prediction enabled by a flow-based graph neural network with biomedical network, Nat. Comput. Sci. 3 (2023) 1023-1033.
[15]	Y. Zhong, H. Zheng, X. Chen, et al., DDI-GCN: Drug-drug interaction prediction via explainable graph convolutional networks, Artif. Intell. Med. 144 (2023), 102640.
[16]	M. Sun, F. Wang, O. Elemento, et al., Structure-based drug-drug interaction detection via expressive graph convolutional networks and deep sets (student abstract), Proc. AAAI Conf. Artif. Intell. 34 (2020) 13927-13928.
[17]	J.Y. Ryu, H.U. Kim, S.Y. Lee, Deep learning improves prediction of drug-drug and drug-food interactions, Proc. Natl. Acad. Sci. U.S.A. 115 (2018) E4304-e4311.
[18]	S. Pang, Y. Zhang, T. Song, et al., Amde: A novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction, Briefings Bioinf. 23 (2022), bbab545.
[19]	K. Huang, C. Xiao, T. Hoang, et al., Caster: Predicting drug interactions with chemical substructure representation, Proc. AAAI Conf. Artif. Intell. 34 (2020) 702-709.
[20]	H. He, G. Chen, C.Y.C. Chen, 3DGT-DDI: 3D graph and text based neural network for drug-drug interaction prediction, Briefings Bioinf. 23 (2022), bbac134.
[21]	D.S. Wishart, Y.D. Feunang, A.C. Guo, et al., DrugBank 5.0: A major update to the DrugBank database for 2018, Nucleic Acids Res. 46 (2018) D1074-d1082.
[22]	C.J. Kelly, A. Karthikesalingam, M. Suleyman, et al., Key challenges for delivering clinical impact with artificial intelligence, BMC Med. 17 (2019), 195.
[23]	M. Ghassemi, Presentation matters for AI-generated clinical advice, Nat. Human Behav. 7 (2023) 1833-1835.
[24]	Y. Deng, X. Xu, Y. Qiu, et al., A multimodal deep learning framework for predicting drug-drug interaction events, Bioinformatics 36 (2020) 4316-4322.
[25]	A. Vaswani, N. Shazeer, N. Parmar, et al., Attention is all you need, arXiv. 2017. https://doi.org/10.48550/arXiv.1706.03762.
[26]	D. Andreea, H. Yu-Hsiang, V. Petar, et al., Drug-drug adverse effect prediction with graph Co-attention, arXiv. 2019. https://doi.org/10.48550/arXiv.1905.0053.
[27]	S.A. Rizvi, N. Nguyen, H. Lyu, et al., AMPNet: Attention asmessage passing for graph neural networks, arXiv. 2022. https://doi.org/10.48550/arXiv.2210.09475.
[28]	P. Velickovic, G. Cucurull, A. Casanova, et al., Graph attention networks, arXiv. 2017. https://doi.org/10.48550/arXiv.1710.10903.
[29]	M. Ma, X. Lei, A dual graph neural network for drug-drug interactions prediction based on molecular structure and interactions, PLoS Comput. Biol. 19 (2023), e1010812.
[30]	G. Ning, Y. Sun, J. Ling, et al., BDN-DDI: A bilinear dual-view representation learning framework for drug-drug interaction prediction, Comput. Biol. Med. 165 (2023), 107340.
[31]	J. Lin, B. Hong, Z. Cai, et al., Masmddi: Multi-layer adaptive soft-mask graph neural network for drug-drug interaction prediction, Front. Pharmacol. 15 (2024), 1369403.
[32]	Y. Tian, J. Yi, N. Wang, et al., DDInter 2.0: An enhanced drug interaction resource with expanded data coverage, new interaction types, and improved user interface, Nucleic Acids Res. 2024. https://doi.org/10.1093/nar/gkae726.
[33]	M.J. Gooderham, P. Bolli, P.G. Fernandez, Concomitant digoxin toxicity and warfarin interaction in a patient receiving clarithromycin, Ann. Pharmacother. 33 (1999) 796-799.
[34]	T.J. Humphries, G.J. Merritt, Review article: Drug interactions with agents used to treat acid-related diseases, Aliment. Pharmacol. Ther. 13 (1999) 18-26.
[35]	L.S. Ramos-Bonner, T.H. Goldberg, S. Moyer, et al., Methimazole-induced cholestatic jaundice in an elderly hyperthyroid patient, Am. J. Geriatr. Pharmacother. 5 (2007) 236-240.
[36]	T. Stergiopoulou, J. Meletiadis, T. Sein, et al., Comparative pharmacodynamic interaction analysis between ciprofloxacin, moxifloxacin and levofloxacin and antifungal agents against Candida albicans and Aspergillus fumigatus, J. Antimicrob. Chemother. 63 (2009) 343-348.
[37]	C. Sun, L. Zhao, Y. Yuan, et al., Detection of drug safety signal of drug-induced neutropenia and agranulocytosis in all-aged patients using electronic medical records, Pharmacoepidemiol. Drug Saf. 32 (2023) 416-425.
[38]	J.C. Tang, H. Yang, X.Y. Song, et al., Inhibition of cytochrome P450 enzymes by rhein in rat liver microsomes, Phytother Res. 23 (2009) 159-164.
[39]	G. Vomiero, B. Carpenter, I. Robb, et al., Combination of ceftriaxone and acyclovir - an underestimated nephrotoxic potential?, Pediatr. Nephrol. 17 (2002) 633-637.
[40]	J.A. Warwick, R.J. Corrall, Serious interaction between warfarin and oral terbinafine, BMJ 316 (1998), 440.
[41]	Y.K. Yu, F. Yu, C. Ye, et al., Combination therapies of diacerein and febuxostat inhibit IL-1β responses and improve clinical symptoms in patients with refractory gout, Am. J. Therapeut. 24 (2017) e290-e297.
[42]	T. Safra, B. Waissengrin, T. Levy, et al., Weekly carboplatin and paclitaxel: A retrospective comparison with the three-weekly schedule in first-line treatment of ovarian cancer, Oncol. 26 (2021) 30-39.
[43]	H. Li, Y. Fang, D. Gu, et al., Paclitaxel and cisplatin combined with concurrent involved-field irradiation in definitive chemoradiotherapy for locally advanced esophageal squamous cell carcinoma: A phase II clinical trial, Radiat. Oncol. 17 (2022), 105.
[44]	H. Wang, T. Fu, Y. Du, et al., Scientific discovery in the age of artificial intelligence, Nature 620 (2023) 47-60.