中国医药导刊 ›› 2025, Vol. 27 ›› Issue (4): 331-337.
人工智能在药品开发及监管中的应用
徐莉, 李敏, 何伍*
收稿日期:2025-02-26
修回日期:2025-04-11
出版日期:2025-04-28
发布日期:2025-04-28
The Application of Artificial Intelligence in Drug Development and Regulation
Received:2025-02-26
Revised:2025-04-11
Online:2025-04-28
Published:2025-04-28
摘要:
人工智能(AI)技术已广泛应用于药物开发及药品监管中,在提升药品开发速度并提高成功率,以及促进药品监管科学的发展方面产生深远影响。全球药品监管机构已通过立法、政策引导及技术合作生态构建,积极支持AI在药品生命周期中的应用。本研究系统探讨了AI在药物发现(包括靶点识别与选择、药物筛选与设计)、非临床研究、临床研究(包括方案设计、临床试验开展及数据收集与处理)、药品智能制造、药品上市后监测及药品监管6个方面的应用,同时重点分析中国、美国及欧盟等国家和地区对AI监管的法规政策、行业规范、发展计划以及技术指南等,概述目前AI在药品监管机构的落地应用现状,并基于以上内容,从政策设计、监管体系构建与监管思路,以及技术要求、当下面临的挑战及应对策略等方面提出思考,旨在为医药行业提供“技术-监管”协同发展的策略参考,助力实现从药物发现到患者用药安全的全链条智能升级,促进医药创新与发展。
中图分类号:
徐莉, 李敏, 何伍.
人工智能在药品开发及监管中的应用 [J]. 中国医药导刊, 2025, 27(4): 331-337.
XU Li, LI Min, HE Wu.
The Application of Artificial Intelligence in Drug Development and Regulation [J]. CHINESE JOURNAL OF MEDICINAL GUIDE, 2025, 27(4): 331-337.
| [1] FDA. Artificial intelligence in drug manufacturing[EB/OL]. (2023) [2025-02-08]. https://www.FDA.gov/media/165743/download?attachment. [2] Luo R, Sun L, Xia Y, et al. BioGPT: generative pre-trained transformer for biomedical text generation and mining[J].Brief Bioinform,2022,23(6):bbac409. [3] Chen H, King FJ, Zhou B, et al. Drug target prediction through deep learning functional representation of gene signatures[J].Nat Commun,2024,15(1):1853. [4] Liu R, Wei L, Zhang P. A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data[J].Nat Mach Intell,2021,3(1):68-75. [5] Ren F, Aliper A, Chen J, et al. A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models[J].Nat Biotechnol, 2025,43(1):63-75. [6] Olawade DB, Teke J, Fapohunda O, et al. Leveraging artificial intelligence in vaccine development: a narrative review[J].J Microbiol Methods,2024,224:106998. [7] McCaffrey P. Artificial intelligence for vaccine design[J].Methods Mol Biol,2022,2412:3-13. [8] Ozger ZB. A robust protein language model for SARS-CoV-2 protein-protein interaction network prediction[J].Artif Intell Med,2023,142:102574. [9] Steiner MC, Gibson KM, Crandall KA. Drug resistance prediction using deep learning techniques on HIV-1 sequence data[J].Viruses,2020,12(5):560. [10] Levi R, Zerhouni EG, Altuvia S. Predicting the spread of SARS-CoV-2 variants: an artificial intelligence enabled early detection[J].PNAS Nexus,2024,3(1):pgad424. [11] Thadani NN, Gurev S, Notin P, et al. Learning from prepandemic data to forecast viral escape[J].Nature,2023,622(7984):818-825. [12] Ma E, Guo X, Hu M, et al. A predictive language model for SARS-CoV-2 evolution[J].Signal Transduct Target Ther,2024,9(1):353. [13] Gangwal A, Ansari A, Ahmad I, et al. Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities[J].Front Pharmacol,2024,15:1331062. [14] Zhang K, Yang X, Wang Y, et al. Artificial intelligence in drug development[J].Nat Med,2025,31(1):45-59. [15] Tingle BI, Tang KG, Castanon M, et al. ZINC-22—a free multi-billion-scale database of tangible compounds for ligand discovery[J].J Chem Inf Model,2023,63(4):1166-1176. [16] Zhang X, Zhang O, Shen C, et al. Efficient and accurate large library ligand docking with KarmaDock[J].Nat Comput Sci,2023,3(9):789-804. [17] Tran-Nguyen VK, Junaid M, Simeon S, et al. A practical guide to machine-learning scoring for structure-based virtual screening[J].Nat Protoc,2023,18(11):3460-3511. [18] Chenthamarakshan V, Hoffman SC, Owen CD, et al. Accelerating drug target inhibitor discovery with a deep generative foundation model[J].Sci Adv,2023,9(25):eadg7865. [19] Zheng S, Tan Y, Wang Z,et al. Accelerated rational PROTAC design via deep learning and molecular simulations[J].Nature Machine Intelligence,2022,4:739-748. [20] Szymczak P, Mozejko M, Grzegorzek T, et al. Discovering highly potent antimicrobial peptides with deep generative model HydrAMP[J].Nat Commun,2023,14(1):1453. [21] Pandi A, Adam D, Zare A, et al. Cell-free biosynthesis combined with deep learning accelerates de novo-development of antimicrobial peptides[J].Nat Commun,2023,14(1):7197. [22] Vazquez Torres S, Leung PJY, Venkatesh P, et al. De novo design of high-affinity binders of bioactive helical peptides[J].Nature,2024,626(7998):435-442. [23] Notin P, Rollins N, Gal Y, et al. Machine learning for functional protein design[J]. Nat Biotechnol,2024,42(2):216-228. [24] Kim YA, Mousavi K, Yazdi A, et al. Computational design of mRNA vaccines[J]. Vaccine,2024,42(7):1831-1840. [25] Sesterhenn F, Yang C, Bonet J, et al. De novo protein design enables the precise induction of RSV-neutralizing antibodies[J].Science,2020,368(6492):eaay5051. [26] Cheng Y, Hu H, Dong X, et al. Exploring transformer model in longitudinal pharmacokinetic/pharmacodynamic analyses and comparing with alternative natural language processing models[J].J Pharm Sci,2024,113(5):1368-1375. [27] Wu K, Li X, Zhou Z, et al. Predicting pharmacodynamic effects through early drug discovery with artificial intelligence—physiologically based pharmacokinetic (AI-PBPK) modelling[J].Front Pharmacol,2024,15:1330855. [28] Joseph X, Akhil V, Arathi A, et al. Comprehensive development in organ-on-a-chip technology[J].J Pharm Sci,2022,111(1):18-31. [29] FDA. FDA's ISTAND Pilot Program accepts submission of first artificial intelligence-based and digital health technology for neuroscience[EB/OL]. (2024-01-13) [2025-02-16]. https://www.fda.gov/drugs/drug-safety-and-availability/fdas-istand-pilot-program-accepts-submission-first-artificial-intelligence-based-and-digital-health. [30] Pappalardo F, Russo G, Tshinanu FM, et al. In silico clinical trials: concepts and early adoptions[J].Brief Bioinform,2019,20(5):1699-1708. [31] Liu X, Liu C, Huang R, et al. Long short-term memory recurrent neural network for pharmacokinetic-pharmacodynamic modeling[J].Int J Clin Pharmacol Ther,2021,59(2):138-146. [32] Barrett JS, Goyal RK, Gobburu J, et al. An AI approach to generating MIDD assets across the drug development continuum[J].AAPS J,2023,25(4):70. [33] Grieb N, Schmierer L, Kim HU, et al. A digital twin model for evidence-based clinical decision support in multiple myeloma treatment[J].Front Digit Health,2023,5:1324453. [34] Laubenbacher R, Sluka JP, Glazier JA. Using digital twins in viral infection[J].Science,2021,371(6534):1105-1106. [35] Bordukova M, Makarov N, Rodriguez-Esteban R, et al. Generative artificial intelligence empowers digital twins in drug discovery and clinical trials[J].Expert Opin Drug Discov,2024,19(1):33-42. [36] Zou KH, Vigna C, Talwai A, et al. The next horizon of drug development: external control arms and innovative tools to enrich clinical trial data[J].Ther Innov Regul Sci,2024,58(3):443-455. [37] Harrer S, Shah P, Antony B, et al. Artificial intelligence for clinical trial design[J].Trends Pharmacol Sci,2019,40(8):577-591. [38] Zhang B, Zhang L, Chen Q, et al. Harnessing artificial intelligence to improve clinical trial design[J].Commun Med (Lond),2023,3(1):191. [39] Jin Q, Wang Z, Floudas CS, et al. Matching patients to clinical trials with large language models[J].Nat Commun,2024,15(1):9074. [40] Wang Y, Carter BZ, Li Z, et al. Application of machine learning methods in clinical trials for precision medicine[J].JAMIA Open,2022,5(1):ooab107. [41] Mason M, Cho Y, Rayo J, et al. Technologies for medication adherence monitoring and technology assessment criteria: narrative review[J]. JMIR Mhealth Uhealth,2022,10(3):e35157. [42] Weissler EH, Naumann T, Andersson T, et al. The role of machine learning in clinical research: transforming the future of evidence generation[J].Trials,2021,22(1):537. [43] Stehlik J, Schmalfuss C, Bozkurt B, et al. Continuous wearable monitoring analytics predict heart failure hospitalization: the LINK-HF multicenter study[J].Circ Heart Fail,2020,13(3):e006513. [44] Avram R, Olgin JE, Kuhar P, et al. A digital biomarker of diabetes from smartphone-based vascular signals[J].Nat Med,2020,26(10):1576-1582. [45] Eguia H, Sanchez-Bocanegra CL, Vinciarelli F, et al. Clinical decision support and natural language processing in medicine: systematic literature review[J].J Med Internet Res,2024,26:e55315. [46] Zhang X, Yan C, Gao C, et al. Predicting missing values in medical data via XGBoost regression[J].J Healthc Inform Res,2020,4(4):383-394. [47] WHO. WHO points to consider in continuous manufacturing of pharmaceutical products[EB/OL]. (2025-01-07)[2025-02-09]. https://cdn.who.int/media/docs/default-source/medicines/norms-and-standards/current-projects/qas24.957_continuous_manufacturing.pdf?sfvrsn=babd612a_1. [48] Huang J, O'connor T, Ahmed K, et al. AIChE PD2M advanced process control workshop-moving APC forward in the pharmaceutical industry[J]. Journal of Advanced Manufacturing and Processing, 2021, 3(1):e10071. [49] Patil RS, Kulkarni SB, Gaikwad VL. Artificial intelligence in pharmaceutical regulatory affairs[J].Drug Discov Today,2023,28(9):103700. [50] Lievano-Martínez FA, Fernández-Ledesma JD, Burgos D, et al. Intelligent process automation: an application in manufacturing industry[J].Sustainability,2022,14(14):8804. [51] Kreimeyer K, Menschik D, Winiecki S, et al. Using probabilistic record linkage of structured and unstructured data to identify duplicate cases in spontaneous adverse event reporting systems[J].Drug Saf,2017,40(7):571-582. [52] Salas M, Petracek J, Yalamanchili P, et al. The use of artificial intelligence in pharmacovigilance: a systematic review of the literature [J].Pharmaceut Med,2022,36(5):295-306. [53] Chavhan A, Uplenchwar PM. AI-driven signal detection in pharmacovigilance: advancements, challenges, and future directions[J].Int J Pharm Pharm Res,2024,30:99-119. [54] Shamim MA, Shamim MA, Arora P, et al. Artificial intelligence and big data for pharmacovigilance and patient safety[J].J Med Surg Public Health,2024,3:100139. [55] FDA. CBER biologics effectiveness and safety (BEST) system[EB/OL]. (2022-03-14) [2025-02-16]. https://www.fda.gov/vaccines-blood-biologics/safety-availability-biologics/cber-biologics-effectiveness-and-safety-best-system#:~:text=The%20Biologics%20Effectiveness%20and%20Safety%20%28BEST%29%20System%20was,and%20infrastructure%20to%20conduct%20surveillance%20and%20epidemiologic%20studies. [56] Ball R, Dal Pan G. "Artificial intelligence" for pharmacovigilance: ready for prime time?[J].Drug Saf,2022,45(5):429-438. [57] Kreimeyer K, Dang O, Spiker J, et al. Feature engineering and machine learning for causality assessment in pharmacovigilance: lessons learned from application to the FDA adverse event reporting system[J].Comput Biol Med,2021,135:104517. [58] Sorbello A ,Hasan R, Francis H, et al. A novel natural language processing and machine learning classifier that streamlines extracting drug-adverse event data from literature reports[EB/OL].[2025-02-15].https://www.fda.gov/media/142029/download. [59] 中华人民共和国国家互联网信息办公室.中华人民共和国网络安全法[EB/OL]. (2016-11-07) [2025-02-15].https://www.cac.gov.cn/2016-11/07/c_1119867116.htm. [60] 中华人民共和国国家互联网信息办公室.中华人民共和国数据安全法[EB/OL]. (2021-06-11) [2025-02-15].https://www.cac.gov.cn/2021-06/11/c_1624994566919140.htm. [61] 中华人民共和国国家互联网信息办公室.生成式人工智能服务管理暂行办法[EB/OL]. (2023-07-13) [2025-02-15].https://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm. [62] 中华人民共和国科学技术部.《新一代人工智能伦理规范》发布[EB/OL]. (2021-09-26) [2025-02-15].https://www.most.gov.cn/kjbgz/202109/t20210926_177063.html?ref=salesforce-research. [63] 国家药品监督管理局.国家药监局启动中国药品监管科学行动计划[EB/OL].(2019-04-30)[2025-02-15].https://www.nmpa.gov.cn/yaowen/ypjgyw/zhyw/20190430213401392.html. [64] 国家药品监督管理局.国家药监局关于印发《国家药品监督管理局关于加快推进药品智慧监管的行动计划》的通知[EB/OL].(2019-05-24) [2025-02-15].https://www.nmpa.gov.cn/xxgk/fgwj/gzwj/gzwjzh/20190524 175201644.html. [65] 国家药品监督管理局.“十四五”国家药品安全及促进高质量发展规划印发[EB/OL]. (2021-12-30) [2025-02-15]. https://www.nmpa.gov.cn/yaowen/ypjgyw/zhyw/20211230145247117.html. [66] 国家药品监督管理局. 国家药监局关于印发《药品监管网络安全与信息化建设“十四五”规划》的通知[EB/OL]. (2022-05-11) [2025-02-15].https://www.nmpa.gov.cn/xxgk/fgwj/gzwj/gzwjzh/20220511110329171.html. [67] 国家药品监督管理局.国家药监局综合司关于印发药品监管人工智能典型应用场景清单的通知[EB/OL]. (2024-06-18) [2025-02-15].https://www.nmpa.gov.cn/xxgk/fgwj/gzwj/gzwjzh/20240618144318144.html. [68] FDA. FDA’s technology modernization action plan[EB/OL]. (2019-09-17) [2025-02-16].https://www.fda.gov/about-fda/reports/fdas-technology-modernization-action-plan. [69] FDA. Data modernization action plan[EB/OL]. (2021-03-03) [2025-02-16]. https://www.fda.gov/about-fda/reports/data-modernization-action-plan. [70] FDA. Considerations for the use of artificial intelligence to support regulatory decision-making for drug and biological products[EB/OL]. (2025-01-06) [2025-02-16].https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological. [71] Ahluwalia K, Abernathy MJ, Beierle J, et al. The future of CMC regulatory submissions: streamlining activities using structured content and data management[J].J Pharm Sci,2022,111(5):1232-1244. [72] Yu LX, Raw A, Wu L, et al. FDA's new pharmaceutical quality initiative: knowledge-aided assessment & structured applications[J].Int J Pharm X,2019,1:100010. [73] Wu L, Gray M, Dang O, et al. RxBERT: Enhancing drug labeling text mining and analysis with AI language modeling[J]. Exp Biol Med (Maywood),2023,248(21):1937-1943. [74] EMA. Multi-annual AI workplan 2023-2028[EB/OL]. (2023-11) [2025-02-09]. https://www.ema.europa.eu/system/files/documents/work-programme/2023-12_ai-multiannual-workplan_a4_en.pdf. [75] EMA. Reflection paper on the use of Artificial Intelligence (AI) in medicinal product lifecycle[EB/OL]. (2024-09-09) [2025-02-09]. https://www.ema.europa.eu/system/files/documents/scientific-guideline/reflection-paper-use-artificial-intelligence-ai-medicinal-product-lifecycle-en.pdf. [76] EMA. Preliminary QIG considerations regarding pharmaceutical process models [EB/OL]. (2024-02-22) [2025-02-09]. https://www.ema.europa.eu/en/documents/scientific-guideline/preliminary-qig-considerations-regarding-pharmaceutical-process-models_en.pdf. [77] EMA. Guiding principles on the use of large language models in regulatory science and for medicines regulatory activities[EB/OL]. (2024-08-29) [2025-02-09]. https://www.ema.europa.eu/en/documents/other/guiding-principles-use-large-language-models-regulatory-science-medicines-regulatory-activities_en.pdf. [78] EMA. AI and digitalisation at EMA[EB/OL]. [2025-02-09]. https://www.ema.europa.eu/en/documents/presentation/presentation-artificial-intelligence-and-digitalisation-ema-joaquim-jornet-florence-butlen_en.pdf. [79] EMA. HMA-EMA joint big data taskforce phase Ⅱreport: ‘Evolving Data-Driven Regulation’[EB/OL]. (2023-09-23) [2025-02-09]. https://www.ema.europa.eu/en/documents/other/hma-ema-joint-big-data-taskforce-phase-ii-report-evolving-data-driven-regulation_en.pdf. |
| [1] | 骆实, 曹凤朝, 韩亮. 全球药品监管机构药品AI应用监管法规框架 [J]. 中国医药导刊, 2025, 27(2): 109-116. |
| [2] | 骆实, 曹凤朝, 韩亮. 全球药品监管机构药品AI应用监管策略与方法 [J]. 中国医药导刊, 2025, 27(2): 128-134. |
| [3] | 田雅轩, 陆颖. 药品监管电子证照应用发展研究与探析 [J]. 中国医药导刊, 2025, 27(2): 123-127. |
| [4] | 宋元林, 蒋维芃, 胡洁, 白春学, . 医学新质生产力研究进展及展望 [J]. 中国医药导刊, 2025, 27(2): 135-141. |
| [5] | 张皖晋, 黄曼, 董正龙. 信息化管理在上海市药物临床试验监管的探索和发展 [J]. 中国医药导刊, 2025, 27(2): 196-200. |
| [6] | 陈锋, 吴欣然. 药品监管领域大语言模型(LLM)一体化建设策略研究 [J]. 中国医药导刊, 2025, 27(1): 1-6. |
| [7] | 唐凌, 艾星, 宋媛媛, 杨志敏. 患者参与在药品监管中的作用——美欧日药品监管机构经验启示 [J]. 中国医药导刊, 2025, 27(1): 7-13. |
| [8] | 赵宝龙, 华坚, 张长风. 基于CRISPR的细胞产品的临床应用及监管挑战 [J]. 中国医药导刊, 2025, 27(1): 101-108. |
| [9] | 徐仁恩, 熊海燕, 宋东杰, 饶龙. 大数据和AI技术在江西省药品智慧监管中的探索和应用 [J]. 中国医药导刊, 2024, 26(7): 637-642. |
| [10] | 唐竹, 刘勤, 缪锦辉, 丛薇, 方东来, 马馥娟, 李劲. 远程监管在药品监管和企业管理的作用与实践 [J]. 中国医药导刊, 2024, 26(7): 643-649. |
| [11] | 刘涛, 张钰, 李钻, 种璟, 靳泽宇, 杨东, 肖楠, 孙玲. 人工智能在药品审评中的应用展望 [J]. 中国医药导刊, 2024, 26(5): 504-510. |
| [12] | 徐子涵a, 赵志霞ab, 刘丽宏ab. 美欧药品智能监管服务平台建设及对我国的启示 [J]. 中国医药导刊, 2024, 26(11): 1065-1070. |
| [13] | 周怡a, 夏天雨b, 尤翀, 周晓华ab, 国家重点研发计划“面向药品现代化监管的智能化服务平台”项目团队. 面向药品现代化监管的智能化服务平台的建设、应用与思考 [J]. 中国医药导刊, 2024, 26(11): 1075-1079. |
| [14] | 冀亦默, 林琳, 徐平洋. “一云多池”架构下药监数据备份方案与流程研究 [J]. 中国医药导刊, 2024, 26(10): 1060-1064. |
| [15] | 田蕊, 郭亮, 徐匡根, . 完善新时代药品执法体系机制思考[J]. 中国医药导刊, 2023, 25(7): 714-722. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||