人工智能在药学教学中的应用与思考^*

Application and Reflection of Artificial Intelligence in Pharmacy Education

摘要

虽然人工智能（AI）与药学学科全方位、多层次、宽领域的交叉融合极大地推动了药学学科的发展，但是绝大部分药学人才对AI在药学中的应用仍知之甚少。尤其是近年来，以大语言模型为代表的生成式人工智能技术快速发展，为药学知识获取、药物信息挖掘与智能化教学带来了新的范式。与此同时，“AI+药学”的复合型人才在新药开发过程中发挥着至关重要且不可替代的作用。面对这一现状，药学教育工作者应当秉持“AI赋能，教育先行”的核心理念，积极传播人工智能前沿思想，大力发展交叉学科优势，以应对传统药学教学中的难题。“AI+药学”创新人才培养的核心目标是培养具备扎实药学专业知识、良好计算与数据思维、能够在真实科研与应用场景中综合运用人工智能技术解决复杂问题的复合型药学人才。为此，本文提出以“教学重构、科研反哺、师资保障”为三大支柱的“AI+药学”创新人才培养模式，旨在系统推动药学教育从课程体系、教学实践到师资建设的全方位改革，逐步构建并持续优化符合时代需求的复合型药学人才培养新范式，从而为药学学科的整体发展与新药研发提供可持续的人才支撑与创新动力。

Abstract

Although the comprehensive, multi-level, and wide-ranging integration of artificial intelligence (AI) with pharmaceutical science has greatly advanced the development of the discipline, the majority of pharmaceutical professionals still have limited knowledge about the applications of AI in pharmacy. Particularly in recent years, the rapid development of generative AI technologies represented by large language models has introduced new paradigms for pharmaceutical knowledge acquisition, drug information mining, and intelligent education. Simultaneously, interdisciplinary talents in "AI + Pharmacy" play a crucial and irreplaceable role in the new drug development process. Faced with this reality, pharmaceutical educators should uphold the core philosophy of "AI empowerment, education first," actively disseminate cutting-edge AI concepts, and vigorously develop interdisciplinary advantages to address challenges in traditional pharmaceutical education. The core goal of cultivating innovative talents in "AI + Pharmacy" is to nurture interdisciplinary professionals with solid pharmaceutical expertise, strong computational and data-driven thinking, and the ability to comprehensively apply AI technologies to solve complex problems in real-world research and application scenarios. To this end, this paper proposes a three-pillar "AI + Pharmacy" innovative talent cultivation model centered on "teaching restructuring, research-driven feedback, and faculty support," aiming to systematically promote comprehensive reforms in pharmaceutical education-from curriculum systems and teaching practices to faculty development. This approach seeks to gradually establish and continuously optimize a new paradigm for interdisciplinary pharmaceutical talent cultivation that aligns with contemporary demands, thereby providing sustainable talent support and innovative momentum for the overall advancement of pharmaceutical science and new drug development.

关键词

人工智能 / 药学教学 / 交叉学科 / 复合型人才

Key words

Artificial intelligence / Pharmacy education / Interdisciplinary / Comprehensive talents

参考文献

[1] 黄奇帆. 伟大复兴的关键阶段-学习《中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要》的认识和体会. 人民论坛, 2021(15): 6-10. doi: 10.3969/j.issn.1004-3381.2021.15.001.

[2] 凌曦, 赵志刚, 李新刚. 人工智能技术在药学领域的应用-基于Web of Science的文献可视化分析. 中国药房, 2019, 30(4): 433-438. doi: 10.6039/j.issn.1001-0408.2019.04.01.

[3] LING X, ZHAO Z G, LI X G. Application of artificial intelligence technology in pharmacy field: visual analysis of literature based on Web of Science. China Pharm, 2019, 30(4): 433-438. doi: 10.6039/j.issn.1001-0408.2019.04.01.

[4] LEE P, BUBECK S, PETRO J. Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N Engl J Med, 2023, 388(13): 1233-1239. doi: 10.1056/NEJMsr2214184.

[5] LEE J, YOON W, KIM S, et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 2020, 36(4): 1234-1240. doi: 10.1093/bioinformatics/btz682.

[6] IPATHI S, GABRIEL K, TRIPATHI P K, et al. Large language models reshaping molecular biology and drug development. Chem Biol Drug Des, 2024, 103(6): e14231. doi: 10.1111/cbdd.14568.

[7] SCHILLING-WILHELMI M, RÍOS-GARCÍA M, SHABIH S, et al. From text to insight: large language models for chemical data extraction. Chem Soc Rev, 2025, 54(3): 1125-1150. doi: 10.1039/D4CS00913D.

[8] SRINIVASAN A, BERKOWITZ J, FRIEDRICH N A, et al. Large language model analysis of reporting quality of randomized clinical trial articles: a systematic review. JAMA Netw Open, 2025, 8(8): e2529418. doi: 10.1001/jamanetworkopen.2025.29418.

[9] 曹铭晨, 曲海军, 李文静, 等. 全球临床药学人工智能应用现状、中国路径及变革挑战. 英国医学杂志中文版, 2025(6): 488-494. doi: 10.3760/cma.j.cn101909-20250831-00155.

[10] CAO M C, QU H J, LI W J, et al. Current status of AI applications in clinical pharmacy in the world, China's pathway, and transformational challenges. Digit Med Health, 2025(6): 488-494. doi: 10.3760/cma.j.cn101909-20250831-00155.

[11] 丁伯祥, 胡健, 王继芳. 人工智能在药物研发中的应用进展. 山东化工, 2019, 48(22): 70-73. doi: 10.19319/j.cnki.issn.1008-021x.2019.22.025.

[12] DING B X, HU J, WANG J F. Progress in the application of artificial intelligence in drug development. Shandong Chem Ind, 2019, 48(22): 70-73. doi: 10.19319/j.cnki.issn.1008-021x.2019.22.025.

[13] 唐谦, 陈柔棻, 沈哲远, 等. 基于人工智能的小分子生成模型在药物发现中的研究进展. 中国药科大学学报, 2024, 55(3): 295-305. doi: 10.11665/j.issn.1000-5048.2024031501.

[14] TANG Q, CHEN R F, SHEN Z Y, et al. Research progress of artificial intelligence-based small molecule generation models in drug discovery. J China Pharm Univ, 2024, 55(3): 295-305. doi: 10.11665/j.issn.1000-5048.2024031501.

[15] 杜晗, 吴羿霏, 杜新. 人工智能在新药研发中的应用进展. 药学进展, 2022, 46(11): 875-882. doi: 10.20053/j.issn1001-5094.2022.11.009.

[16] DU H, WU Y F, DU X. Advances in application of artificial intelligence in new drug research and development. Prog Pharm Sci, 2022, 46(11): 875-882. doi: 10.20053/j.issn1001-5094.2022.11.009.

[17] 李风雷, 胡乔宇, 熊若凡, 等. 基于深度学习的药物设计方法. 自然杂志, 2021, 43(5): 383-390. doi: 10.3969/j.issn.0253-9608.2021.05.009.

[18] LI F L, HU Q Y, XIONG R F, et al. Computational drug design methods by deep learning algorithms. Chin J Nat, 2021, 43(5): 383-390. doi: 10.3969/j.issn.0253-9608.2021.05.009.

[19] 祝智庭, 魏非. 教育信息化2.0: 智能教育启程, 智慧教育领航. 电化教育研究, 2018, 39(9): 5-16. doi: 10.13811/j.cnki.eer.2018.09.001.

[20] ZHU Z T, WEI F. Educational informatization 2.0: starting on a journey of intelligence education guided by smart education. E-Educ Res, 2018, 39(9): 5-16. doi: 10.13811/j.cnki.eer.2018.09.001.

[21] 杨龙华, 单丽红, 张恩, 等. 人工智能在计算机辅助药物设计模块教学中的应用与思考. 药学教育, 2025, 41(5): 33-36. doi: 10.12147/j.cnki.1671-5216.2025.05.008.

[22] YANG L H, SHAN L H, ZHANG E, et al. Application and reflection of artificial intelligence in the teaching of computer-aided drug design modules. Pharm Educ, 2025, 41(5): 33-36. doi: 10.12147/j.cnki.1671-5216.2025.05.008.

[23] 卢宇, 余京蕾, 陈鹏鹤, 等. 生成式人工智能的教育应用与展望-以ChatGPT系统为例. 中国远程教育, 2023, 43(4): 24-31. doi: 10.13541/j.cnki.chinade.20230301.001.

[24] LU Y, YU J L, CHEN P H, et al. Educational application and prospect of generative artificial intelligence: taking ChatGPT system as an example. Chin J Distance Educ, 2023, 43(4): 24-31. doi: 10.13541/j.cnki.chinade.20230301.001.

[25] TURING A M. Computing machinery and intelligence. Mind, 1950, 59(236): 433-460. doi: 10.1093/mind/LIX.236.433.

[26] 沙明瑞. 人工智能算法在化学反应预测中的应用. 当代化工, 2025, 54(7): 1710-1715. doi: 10.3969/j.issn.1671-0460.2025.07.038.

[27] SHA M R. Application of artificial intelligence algorithms in chemical reaction prediction. Contemp Chem Ind, 2025, 54(7): 1710-1715. doi: 10.3969/j.issn.1671-0460.2025.07.038.

[28] 周成卓, 谢召军. 人工智能预测模型在有机化学实验教学中的应用初探. 大学化学, 2025, 40(2): 320-331. doi: 10.12461/PKU.DXHX202405090.

[29] ZHOU C Z, XIE Z J. Exploring the application of artificial intelligence prediction models in organic chemistry laboratory teaching: a preliminary study. Univ Chem, 2025, 40(2): 320-331. doi: 10.12461/PKU.DXHX202405090.

[30] 李帅鑫, 李子昊, 孙婕, 等. 深度学习在化学分子逆向合成路线规划中的应用进展. 宁夏大学学报(自然科学版), 2024, 45(1): 44-50. doi: 10.3969/j.issn.0253-2328.2024.01.007.

[31] LI S X, LI Z H, SUN J, et al. Recent advances in application of deep learning for the retrosynthetic planning of chemical molecules. J Ningxia Univ (Nat Sci Ed), 2024, 45(1): 44-50. doi: 10.3969/j.issn.0253-2328.2024.01.007.

[32] 许建耘. 自主合成机器人利用人工智能加速分子的化学发现. 石油炼制与化工, 2024, 55(6): 60. doi: 10.3969/j.issn.1005-2399.2024.06.013.

[33] 李添添, 王俊杰. 基于深度学习的“药物-靶点”亲和力预测方法设计. 中华医学图书情报杂志, 2022, 31(3): 34-39. doi: 10.3969/j.issn.1671-3982.2022.03.004.

[34] LI T T, WANG J J. Drug-target affinity prediction based on deep learning. Chin J Med Libr Inf Sci, 2022, 31(3): 34-39. doi: 10.3969/j.issn.1671-3982.2022.03.004.

[35] HUANG K, FU T, GLASS L M, et al. DeepPurpose: a deep learning library for drug-target interaction prediction. Bioinformatics, 2020, 36(22/23): 5545-5547. doi: 10.1093/bioinformatics/btaa1005.

[36] JIA Y J, GAO B, TAN J X, et al. Deep contrastive learning enables genome-wide virtual screening. Science, 2026, 391(6781): eads9530. doi: 10.1126/science.ads9530.

[37] HOUSSEIN E H, MOHAMED R E, ALI A A. Machine learning techniques for biomedical natural language processing: a comprehensive review. IEEE Access, 2021, 9: 140628-140653. doi: 10.1109/ACCESS.2021.3119621.

[38] CHEN H Y, MARTIN B, DAIMON C M, et al. Effective use of latent semantic indexing and computational linguistics in biological and biomedical applications. Front Physiol, 2013, 4: 8. doi: 10.3389/fphys.2013.00008.

[39] OIKONOMOU E D, KARVELIS P, GIANNAKEAS N, et al. How natural language processing derived techniques are used on biological data: a systematic review. Netw Model Anal Health Inform Bioinform, 2024, 13(1): 23. doi: 10.1007/s13721-024-00458-1.

[40] 刘明, 吴忠明, 廖剑, 等. 大语言模型的教育应用: 原理、现状与挑战-从轻量级BERT到对话式ChatGPT. 现代教育技术, 2023, 33(8): 19-28. doi: 10.3969/j.issn.1009-8097.2023.08.003.

[41] LIU M, WU Z M, LIAO J, et al. Educational applications of large language models: principles, status and challenges-from light-weighted BERT to conversational ChatGPT. Mod Educ Technol, 2023, 33(8): 19-28. doi: 10.3969/j.issn.1009-8097.2023.08.003.

[42] 张颖慧, 刘洋, 那顺乌力吉, 等. “新工科”背景下人工智能专业建设与教学改革探索. 工业和信息化教育, 2021(8): 27-31. doi: 10.3969/j.issn.2095-5065.2021.08.008.

[43] 刘泓泽, 王耀国, 唐圣晟, 等. 医学大语言模型的应用现状与发展趋势研究. 中国数字医学, 2024, 19(8): 1-7. doi: 10.3969/j.issn.1673-7571.2024.08.001.

[44] LIU H Z, WANG Y G, TANG S S, et al. Research on the current application and development trend of medical large language model. Chin Digit Med, 2024, 19(8): 1-7. doi: 10.3969/j.issn.1673-7571.2024.08.001.

[45] XIONG G L, WU Z X, YI J C, et al. ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties. Nucleic Acids Res, 2021, 49(W1): W5-W14. doi: 10.1093/nar/gkab255.

[46] 袁菁, 侯跃芳, 韩玙蔓, 等. 基于多组学数据融合挖掘的药物重定位研究. 医学信息学杂志, 2025, 46(11): 67-73. doi: 10.3969/j.issn.1673-6036.2025.11.010.

[47] YUAN J, HOU Y F, HAN Y M, et al. Study on drug repositioning based on multi-omics data mining. J Med Inform, 2025, 46(11): 67-73. doi: 10.3969/j.issn.1673-6036.2025.11.010.

[48] 教育部, 财政部, 发展改革委. 关于高等学校加快“双一流”建设的指导意见. 中华人民共和国国务院公报, 2019(1): 69-76.

[49] JUMPER J, EVANS R, PRITZEL A, et al. Highly accurate protein structure prediction with AlphaFold. Nature, 2021, 596(7873): 583-589. doi: 10.1038/s41586-021-03819-2.

[50] OLIVECRONA M, BLASCHKE T, ENGKVIST O, et al. Molecular de-novo design through deep reinforcement learning. J Cheminform, 2017, 9(1): 48. doi: 10.1186/s13321-017-0235-x.

[51] PENG X G, GUO R H, GUO F L, et al. Unified modeling of 3D molecular generation via atomic interactions with PocketXMol. Cell, 2026, 189(7): 1904-1922.e28. doi: 10.1016/j.cell.2026.01.003.

[52] ROSS J, BELGODERE B, CHEN V, et al. Large-scale chemical language representations capture molecular structure and properties. Nat Mach Intell, 2022, 4(12): 1256-1264. doi: 10.1038/s42256-022-00580-7.

[53] ZHANG Y, HAN Y, CHEN S, et al. Large language models to accelerate organic chemistry synthesis. Nat Mach Intell, 2025, 7(7): 1010-1022. doi: 10.1038/s42256-025-01066-y.

[54] VALIZADEHASLANI T, SHI Y, REN P, et al. PharmBERT: a domain-specific BERT model for drug labels. Brief Bioinform, 2023, 24(4): bbad226. doi: 10.1093/bib/bbad226.

基金资助

*教育部产学合作协同育人项目(202102144022)

四川大学教学改革重点项目(GSSCU2021044)