Adverse drug reaction (ADR) represents a primary concern in global pharmacovigilance. Individual genetic variations, particularly pharmacogenomics (PGx) characteristics, are key factors contributing to the occurrence of ADR. In recent years, artificial intelligence (AI) technologies have enabled the integration of multi-omics data for accurate ADR prediction. This review summarizes AI methods for predicting ADR based on PGx. It begins by organizing commonly used multi-source heterogeneous datasets related to PGx and ADR, then highlights application examples of AI models—such as traditional machine learning (e.g., support vector machine, random forests) and deep learning (e.g., convolutional neural networks, graph neural networks)—in this field. These models enable intelligent prediction of ADR by uncovering complex non-linear relationships among genetic variations, clinical medication features, and ADR. However, the field still faces challenges, including data heterogeneity, model interpretability, and obstacles in clinical translation. Finally, the review outlines future research directions, such as multi-modal data fusion and explainable AI, aiming to advance the development of personalized medication safety and precision medicine.

1.俞镔. 药物基因组学: 指导常规用药的精准工具[J]. 中国当代儿科杂志, 2020, 22(11): 1143-1148. [Yu B. Pharmacogenomics: precision tool in routine prescription[J]. Chinese Journal of Contemporary Pediatrics, 2020, 22(11): 1143-1148.] DOI: 10.7499/j.issn.1008-8830.2006032.

2.国家药品不良反应监测中心. 国家药品不良反应监测年度报告（2024年） [R/OL]. (2025-04-07) [2025-08-20]. https://www.cdr-ADRs.org.cn/center_news/202504/t20250407_51076.html.

3.Jennings ELM, Murphy KD, Gallagher P, et al. In-hospital adverse drug reactions in older adults; prevalence, presentation and associated drugs-a systematic review and Meta-analysis[J]. Age Ageing, 2020, 49(6): 948-958. DOI: 10.1093/ageing/afaa188.

4.Cacabelos R, Cacabelos N, Carril JC. The role of pharmacogenomics in adverse drug reactions[J]. Expert Rev Clin Pharmacol, 2019, 12(5): 407-442. DOI: 10.1080/17512433.2019. 1597706.

5.Pirmohamed M. Pharmacogenomics: current status and future perspectives[J]. Nat Rev Genet, 2023, 24: 350-362. DOI: 10.1038/s41576-022-00572-8.

6.李玉娇, 初亚男, 黄晓晖, 等. 基因多态性与药物不良反应发生风险的相关性及其临床证据[J]. 药学进展, 2021, 45(2): 100-111. [Li YJ, Chu YN, Huang XH, et al. Correlation between gene polymorphism and risk of adverse drug reaction and its clinical evidence[J]. Progress in Pharmaceutical Sciences, 2021, 45(2): 100-111.] https://d.wanfangdata.com.cn/periodical/CiBQZXJpb2RpY2FsQ0hJU29scjkyMDI1MTIyNDE1NDU1NRINeXhqejIwMjEwMjAwNBoIODFveXJlYzE%3D.

7.Avram S, Bologa CG, Holmes J, et al. DrugCentral 2021 supports drug discovery and repositioning[J]. Nucleic Acids Res, 2021, 49(D1): D1160-D1169. DOI: 10.1093/nar/gkaa997.

8.Knox C, Wilson M, Klinger CM, et al. DrugBank 6.0: the DrugBank knowledgebase for 2024[J]. Nucleic Acids Res, 2024, 52(D1): D1265-D1275. DOI: 10.1093/nar/gkad976.

9.Phan L, Zhang H, Wang Q, et al. The evolution of dbSNP: 25 years of impact in genomic research[J]. Nucleic Acids Res, 2025, 53(D1): D925-D931. DOI: 10.1093/nar/gkae977.

10.Gong L, Whirl-Carrillo M, Klein TE. PharmGKB, an integrated resource of pharmacogenomic knowledge[J]. Curr Protoc, 2021, 1(8): e226. DOI: 10.1002/cpz1.226.

11.Gaedigk A, Casey ST, Whirl-Carrillo M, et al. Pharmacogene variation consortium: a global resource and repository for pharmacogene variation[J]. Clin Pharmacol Ther, 2021, 110(3): 542-545. DOI: 10.1002/cpt.2321.

12.MacDonald JR, Ziman R, Yuen RKC, et al. The database of genomic variants: a curated collection of structural variation in the human genome[J]. Nucleic Acids Res, 2014, 42(D1): D986-D992. DOI: 10.1093/nar/gkt958.

13.Jeiziner C, Wernli U, Suter K, et al. HLA‐associated adverse drug reactions-scoping review[J]. Clin Transl Sci, 2021, 14(5): 1648-1658. DOI: 10.1111/cts.13062.

14.Davis AP, Wiegers TC, Johnson RJ, et al. Comparative toxicogenomics database (CTD): update 2023[J]. Nucleic Acids Res, 2023, 51(D1): D1257-D1262. DOI: 10.1093/nar/gkac833.

15.Kanehisa M, Furumichi M, Sato Y, et al. KEGG: biological systems database as a model of the real world[J]. Nucleic Acids Res, 2025, 53(D1): D672-D677. DOI: 10.1093/nar/gkae909.

16.Hecker N, Ahmed J, Von Eichborn J, et al. SuperTarget goes quantitative: update on drug-target interactions[J]. Nucleic Acids Res, 2012, 40(D1): D1113-D1117. DOI: 10.1093/nar/gkr912.

17.Kim S, Chen J, Cheng T, et al. PubChem 2025 update[J]. Nucleic Acids Res, 2025, 53(D1): D1516-D1525. DOI: 10.1093/nar/gkae1059.

18.Wang Z, Clark NR, Ma'ayan A. Drug-induced adverse events prediction with the LINCS L1000 data[J]. Bioinformatics, 2016, 32(15): 2338-2345. DOI: 10.1093/bioinformatics/btw168.

19.Kim JA, Ceccarelli R, Lu CY. Pharmacogenomic biomarkers in US FDA-approved drug labels (2000-2020)[J]. J Pers Med, 2021, 11(3): 179. DOI: 10.3390/jpm11030179.

20.Moore TJ, Morrow RL, Dormuth CR, et al. US Food and Drug Administration safety advisories and reporting to the Adverse Event Reporting System (FAERS)[J]. Pharmaceut Med, 2020, 34(2): 135-140. DOI: 10.1007/s40290-020-00329-w.

21.Kuhn M, Letunic I, Jensen LJ, et al. The SIDER database of drugs and side effects[J]. Nucleic Acids Res, 2016, 44(D1): D1075-D1079. DOI: 10.1093/nar/gkv1075.

22.Shin H, Lee S. An OMOP-CDM based pharmacovigilance data-processing pipeline (PDP) providing active surveillance for ADR signal detection from real-world data sources[J]. BMC Med Inform Decis Mak, 2021, 21(1): 159. DOI: 10.1186/s12911-021-01520-y.

23.Wu L, Ingle T, Liu Z, et al. Study of serious adverse drug reactions using FDA-approved drug labeling and MedDRA[J]. BMC Bioinformatics, 2019, 20(Suppl 2): 97. DOI: 10.1186/s12859-019-2628-5.

24.Lipscomb CE. Medical subject headings (MeSH)[J]. Bull Med Libr Assoc, 2000, 88(3): 265-266. https://pubmed.ncbi.nlm.nih.gov/10928714/.

25.Hunter FMI, Ioannidis H, Bento AP, et al. Drug and clinical candidate drug data in ChEMBL[J]. J Med Chem, 2025,68(19):19800-19827. DOI: 10.1021/acs.jmedchem.5c00920.

26.Thirumuruganathan S, Tang N, Ouzzani M, et al. Data curation with deep learning[C]. Denmark: The 23rd International Conference on Extending Database Technology, 2020: 277-286. DOI: 10.5441/002/edbt.2020.25.

27.Pan Y, Lei X, Zhang Y. Association predictions of genomics, proteinomics, transcriptomics, microbiome, metabolomics, pathomics, radiomics, drug, symptoms, environment factor, and disease networks: a comprehensive approach[J]. Med Res Rev, 2021, 42(1): 441-461. DOI: 10.1002/med.21847.

28.Wigh D, Goodman J, Lapkin A. A review of molecular representation in the age of machine learning[J]. Wiley Interdiscip Rev Comput Mol Sci, 2022, 12(5): e1603. DOI: 10.1002/wcms.1603.

29.Wei J, Chu X, Sun X, et al. Machine learning in materials science[J]. InfoMat, 2019, 1(3): 338-358. https://doi.org/10.1002/inf2.12028.

30.匡启帆, 郭佳丽, 李益洲, 等. 基于核矩阵降维算法对药物不良反应的预测[J]. 中国科技论文, 2017, 12(24): 2845-2849. [Kuang QF, Guo JL, Li YZ, et al. Prediction of drug adverse reactions based on kernel matrix dimension reduction method[J]. China Science Paper, 2017, 12(24): 2845-2849.] DOI: 10.3969/j.issn.2095-2783.2017.24.018.

31.Hassselt J and Iyengar R. Systems pharmacology-based identification of pharmacogenomic determinants of adverse drug reactions using human iPSC-derived cell lines[J]. Curr Opin Syst Biol, 2017, 4: 9-15. https://doi.org/10.1016/j.coisb.2017.05.006.

32.刘珂. 基于生物大数据的基因与药物不良反应网络化关联分析与预测[D]. 福建厦门: 厦门大学, 2018.

33.朱嘉静. 基于机器学习的药物不良反应关键问题研究[D]. 成都: 电子科技大学, 2020. DOI: 10.27005/d.cnki.gdzku.2020. 004650.

34.杜瑶. 基于多数据源与机器学习的药物副作用预测[J]. 软件导刊, 2021, 20(5): 39-43. [Du Y. Prediction of drug side effects based on multiple data sources and machine learning [J]. Software Guide, 2021, 20(5): 39-43.] DOI: 10.11907/rjdk.201917.

35.刘佳宁, 焦强, 边太成, 等. 基于深度多核多任务学习的个性化药物不良反应预测[J]. 计算机技术与发展, 2024, 34(11): 148-156. [Liu JN, Jiao Q, Bian TC, et al. Personalized adverse drug reactions prediction based on deep multi-kernel multi-task learning[J]. Computer Technology and Development, 2024, 34(11): 148-156.] DOI: 10.20165/j.cnki.ISSN1673-629X.2024.0216.

36.尹璇, 黄睿健, 孔斯予, 等. 围手术期药物相关罕见不良反应发现的真实世界数据基础与方法学进展[J]. 药物流行病学杂志. 2025, 34(8): 917-925. [Yin X, Huang RJ, Kong SY, et al. Perioperative rare adverse reactions discovery: real-world data foundations and methodological advances[J]. Chinese Journal of Pharmacoepidemiology, 2025, 34(8): 917-925.] DOI: 10.12173/j.issn.1005-0698.202411007.

37.杨泽群. 基于深度学习的药物不良反应预测方法的研究与实现[D]. 南京: 东南大学, 2023. DOI: 10.27014/d.cnki.gdnau.2023.004124.

38.Wu Y, Liu Q, Xie L. Hierarchical multi-omics data integration and modeling predict cell-specific chemical proteomics and drug responses [J]. Cell Rep Methods, 2023, 3(4): 100452. DOI: 10.1016/j.crmeth.2023.100452.

39.Krix S, DeLong LN, Madan S, et al. MultiGML: multimodal graph machine learning for prediction of adverse drug events [J]. Heliyon, 2023, 9(9): e19441. DOI: 10.1016/j.heliyon.2023.e19441.

40.Dafniet B, Taboureau O. Prediction of adverse drug reactions due to genetic predisposition using deep neural networks[J]. Mol Inform, 2024, 43: e202400021. DOI: 10.1002/minf.202400021.

41.Son A, Park J, Kim W, et al. Recent advances in omics, computational models, and advanced screening methods for drug safety and efficacy[J]. Toxics, 2024, 12(11): 822. DOI: 10.3390/toxics12110822.

42.He M, Shi Y, Han F, et al. Prediction of adverse drug reactions based on pharmacogenomics combination features: a preliminary study[J]. Front Pharmacol, 2025, 16: 1448106. DOI: 10.3389/fphar.2025.1448106.

43.司书成, 吴柳柳, 王聪慧, 等. 大语言模型助力药物流行病学研究[J]. 药物流行病学杂志, 2025, 34(9): 1074-1083. [Si SC, Wu LL, Wang CH, et al. Large language models empowering pharmacoepidemiology research[J]. Chinese Journal of Pharmacoepidemiology, 2025, 34(9): 1074-1083.] DOI: 10.12173/j.issn.1005-0698.202504033.

44.Ong JCL, Chen MH, Ng N, et al. A scoping review on generative AI and large language models in mitigating medication related harm[J]. NPJ Digit Med, 2025, 8(1): 182. DOI: 10.1038/s41746-025-01565-7.

45.Zitu MM, Owen D, Manne A, et al. Large language models for adverse drug events: a clinical perspective[J]. J Clin Med, 2025, 14(15): 5490. DOI: 10.3390/jcm14155490.

46.Guo D, Choo KKR. Applications of federated large language model for adverse drug reactions prediction: scoping review[J]. J Med Internet Res, 2025, 27: e68291. DOI: 10.2196/68291.

47.Zou H, Wang Y, Xiang K, et al. Knowledge-augmented large language model-based framework for adverse drug reactions analysis[J]. Appl Soft Comput, 2025, 185:114025. https://doi.org/10.1016/j.asoc.2025.114025.

48.Tian L, Wang Q, Zhou Z, et al. Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network[J]. BMC Bioinformatics, 2025, 26(1): 16. DOI: 10.1186/s12859-024-06028-6.

49.Zack M, Stupichev DN, Moore AJ, et al. Artificial intelligence and multi-omics in pharmacogenomics: a new era of precision medicine[J]. Mayo Clin Proc Digit Health, 2025, 3(3): 100246. DOI: 10.1016/j.mcpdig.2025.100246.