智能反应优化：深度学习与优化算法驱动的乙酰水杨酸合成

引用本文: 郑健强, 黄泳斌, 明文灿, 刘英菊. 智能反应优化：深度学习与优化算法驱动的乙酰水杨酸合成[J]. 大学化学, 2025, 40(9): 87-98. doi: 10.12461/PKU.DXHX202411062 shu

Citation: Jianqiang Zheng, Yongbin Huang, Wencan Ming, Yingju Liu. Intelligent Reaction Optimization: Synthesis of Acetylsalicylic Acid Driven by Deep Learning and Optimization Algorithms[J]. University Chemistry, 2025, 40(9): 87-98. doi: 10.12461/PKU.DXHX202411062 shu

智能反应优化：深度学习与优化算法驱动的乙酰水杨酸合成

华南农业大学材料与能源学院, 广州 510642

通讯作者: 刘英菊,E-mail:yingjuliu@scau.edu.cn

基金项目:
无机及分析化学广东省课程思政示范团队(粤教高函[2024]27号)；应用化学国家一流本科专业建设点(教高厅函[2019]46号)；广东省一流课程-无机及分析化学(粤教高函[2020]16号)；华南农业大学课程思政示范团队和示范课程-无机及分析化学(华南农教[2023]1号)

摘要: 在本科实验设计中，需要经过大量的试错实验来寻找最优的反应条件，这一过程需要消耗大量的时间和成本。为了简化复杂的实验设计过程，同时激发学生对先进技术和跨学科领域的兴趣，培养多学科交叉的创新型人才，本研究创新性地提出了智能反应优化的模型框架以预测最优产率下的反应条件组合，并将这一模块加入到本科有机实验乙酰水杨酸的合成中。本研究收集了1054个符合这一反应机理的反应数据作为模型的训练数据，主要包括了产物、反应物、催化剂、溶剂、主要反应试剂、反应温度和产率。首先预训练了一个基于化学多模态的产率预测模型，作为后续反应优化的目标函数；接着采用贝叶斯优化算法，以最小化产率的负值(即最大化产率)为目标，确定最优的反应条件组合；最后将模型预测的产率和实际产率进行了实验验证，在100次模型测试下的预测产率都完美地落在了实际产率范围内，效果优异的同时还给出了产率高达90.1%的反应试剂组合，为这一本科实验提供了多样化的实验方案。

关键词:

English

Intelligent Reaction Optimization: Synthesis of Acetylsalicylic Acid Driven by Deep Learning and Optimization Algorithms

College of Materials and Energy, South China Agricultural University, Guangzhou 510642, China

Corresponding author: Yingju Liu, yingjuliu@scau.edu.cn

Received Date: 19 November 2024
Accepted Date: 14 February 2025
Available Online: 23 April 2025

Abstract: Undergraduate experimental design typically requires extensive trial-and-error experimentation to identify optimal reaction conditions, a process that demands considerable time and resources. To simplify this complex experimental design process and to enhance students’ interest in advanced technologies and interdisciplinary fields, an intelligent reaction optimization model framework was introduced. This model is designed to predict the optimal combination of reaction conditions for achieving the highest yield, and this framework has been integrated into the undergraduate organic chemistry curriculum, specifically for the synthesis of acetylsalicylic acid. Herein, 1054 reaction data points were collected conforming to this reaction mechanism as training data for the model, mainly including product, reactant, catalyst, solvent, the main reaction reagents, reaction temperature and yield. Initially, a yield prediction model was pre-trained based on a chemical multi-modal transformer, which served as the objective function for subsequent reaction optimization. Then the Bayesian optimization algorithm was utilized to ascertain the optimal combination of reaction conditions, with the aim of minimizing the negative value of the yield (the maximizing yield). Finally, the model-predicted yields were experimentally validated against the actual yields, and in 100 model tests, the predicted yields consistently fell within the range of the actual yields, demonstrating the model’s excellent performance. The model also identified a reaction reagent combination that yielded up to 90.1%, providing a variety of experimental options for this undergraduate experiment.

Key words:

1. [1]
  Shields, B. J.; Stevens, J.; Li, J.; Parasram, M.; Damani, F.; Alvarado Martinez, J. I.; Janey, J. M.; Adams, R. P.; Doyle, A. G. Nature 2021, 590 (7844), 89.Shields, B. J.; Stevens, J.; Li, J.; Parasram, M.; Damani, F.; Alvarado Martinez, J. I.; Janey, J. M.; Adams, R. P.; Doyle, A. G. Nature 2021, 590 (7844), 89.
2. [2]
  Luo, Y.; Bag, S.; Zaremba, O.; Cierpka, A.; Andreo, J.; Wuttke, S.; Friederich, P.; Tsotsalas, M. Angew. Chem. Int. Ed. 2022, 61 (19), e202200242.Luo, Y.; Bag, S.; Zaremba, O.; Cierpka, A.; Andreo, J.; Wuttke, S.; Friederich, P.; Tsotsalas, M. Angew. Chem. Int. Ed. 2022, 61 (19), e202200242.
3. [3]
  Wang, J. Y.; Stevens, J. M.; Kariofillis, S. K.; Tom, M. J.; Golden, D. L.; Li, J.; Tabora, J. E.; Parasram, M.; Shields, B. J.; Primer, D. N.; et al. Nature 2024, 626 (8001), 1025.Wang, J. Y.; Stevens, J. M.; Kariofillis, S. K.; Tom, M. J.; Golden, D. L.; Li, J.; Tabora, J. E.; Parasram, M.; Shields, B. J.; Primer, D. N.; et al. Nature 2024, 626 (8001), 1025.
4. [4]
  朱俊杰, 薛永飞, 周国雄, 郑志安. 实验室研究与探索, 2024, 43 (10), 142.
5. [5]
  唐嘉屿, 庞继川, 肖少华, 许新华, 吴梅芬. 大学化学, 2024, 39 (5), 193.
6. [6]
  魏玉萍, 王佚婷, 姜佳良, 邓锦轩, 张宏, 马骁飞, 李俊杰. 大学化学, 2024, 39 (10), 261.
7. [7]
  董天乐, 王永森, 杨露辉, 魏建业. 化学教育(中英文), 2024, 45 (19), 89.
8. [8]
  温霞, 徐琦, 王海军, 杜钦之, 张明晓, 陈时洪. 化学教育(中英文), 2024, 45 (19), 83.
9. [9]
  SciFinder. [2024-08-15]. https://www.cas.org/SciFinder. [2024-08-15]. https://www.cas.org/
10. [10]
  Reaxy. [2024-08-16]. https://www.reaxys.com/Reaxy. [2024-08-16]. https://www.reaxys.com/
11. [11]
  周成卓, 谢召军. 大学化学, 2025, 40 (2), 320.
12. [12]
  赖自成, 张玉萍, 马燕. 计算机应用, 2021, 41 (10), 3070.
13. [13]
  Li, S. W.; Xu, L. C.; Zhang, C.; Zhang, S. Q.; Hong, X. Nat Commun. 2023, 14 (1), 3569.Li, S. W.; Xu, L. C.; Zhang, C.; Zhang, S. Q.; Hong, X. Nat Commun. 2023, 14 (1), 3569.
14. [14]
  Coley, C. W.; Thomas D. A.; Lummiss, J. A. M.; Jaworski, J. N.; Breen, C. P.; Schultz, V.; Hart, T.; Fishman, J. S.; Rogers, L.; Gao, H.; et al. Science 2019, 365 (6453), eaax1566.Coley, C. W.; Thomas D. A.; Lummiss, J. A. M.; Jaworski, J. N.; Breen, C. P.; Schultz, V.; Hart, T.; Fishman, J. S.; Rogers, L.; Gao, H.; et al. Science 2019, 365 (6453), eaax1566.
15. [15]
  张淑婷, 杨卓鸿. 有机化学实验. 北京: 中国农业出版社, 2017: 94-96.
16. [16]
  Lowe, D. M.; Corbett, P. T.; Murray-Rust, P.; Glen, R. C. J. Chem. Inf. Model. 2011, 51 (3), 739.Lowe, D. M.; Corbett, P. T.; Murray-Rust, P.; Glen, R. C. J. Chem. Inf. Model. 2011, 51 (3), 739.
17. [17]
  Brochu, E.; Cora, V. M.; Freitas, N. D. 2010, arXiv:1012.2599. [2025-08-29]. https://doi.org/10.48550/arXiv.1012.2599Brochu, E.; Cora, V. M.; Freitas, N. D. 2010, arXiv:1012.2599. [2025-08-29]. https://doi.org/10.48550/arXiv.1012.2599
18. [18]
  Goh, G. B.; Hodas, N. O.; Siegel, C.; Vishnu, A. 2017, arXiv:1712.02034. [2025-08-29]. https://doi.org/10.48550/arXiv.1712.02034Goh, G. B.; Hodas, N. O.; Siegel, C.; Vishnu, A. 2017, arXiv:1712.02034. [2025-08-29]. https://doi.org/10.48550/arXiv.1712.02034
19. [19]
  Durant, J. L.; Leland, B. A.; Henry, D. R.; Nourse, J. G. J. Chem. Inf. Comput. Sci. 2002, 42 (6), 1273.Durant, J. L.; Leland, B. A.; Henry, D. R.; Nourse, J. G. J. Chem. Inf. Comput. Sci. 2002, 42 (6), 1273.
20. [20]
  Gedeck, P.; Rohde, B.; Bartels, C. J. Chem. Inf. Model. 2006, 46 (5), 1924.Gedeck, P.; Rohde, B.; Bartels, C. J. Chem. Inf. Model. 2006, 46 (5), 1924.
21. [21]
  Rogers, D.; Hahn, M. J. Chem. Inf. Model. 2010, 50 (5), 742.Rogers, D.; Hahn, M. J. Chem. Inf. Model. 2010, 50 (5), 742.
22. [22]
  Watson, P. J. Chem. Inf. Model. 2008, 48 (1), 166.Watson, P. J. Chem. Inf. Model. 2008, 48 (1), 166.
23. [23]
  David, W. J. Chem. Inf. Comput. Sci. 1988, 28 (1), 31.David, W. J. Chem. Inf. Comput. Sci. 1988, 28 (1), 31.
24. [24]
  RDKit: Open-source cheminformatics. [2025-08-29]. https://www.rdkit.orgRDKit: Open-source cheminformatics. [2025-08-29]. https://www.rdkit.org
25. [25]
  Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. 2019, arXiv:1912.01703. [2025-08-29]. https://doi.org/10.48550/arXiv.1912.01703Paszke, A.; Gross, S.; Massa, F.; Lerer, A.; Bradbury, J.; Chanan, G.; Killeen, T.; Lin, Z.; Gimelshein, N.; Antiga, L.; et al. 2019, arXiv:1912.01703. [2025-08-29]. https://doi.org/10.48550/arXiv.1912.01703
26. [26]
  Veličković, P.; Cucurull, G.; Casanova, A.; Romero, A.; Liò, P.; Bengio, Y. 2017, arXiv:1710.10903. [2025-08-29]. https://doi.org/10.48550/arXiv.1710.10903Veličković, P.; Cucurull, G.; Casanova, A.; Romero, A.; Liò, P.; Bengio, Y. 2017, arXiv:1710.10903. [2025-08-29]. https://doi.org/10.48550/arXiv.1710.10903
27. [27]
  Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; Polosukhin, I. 2017, arXiv:1706.03762. [2025-08-29]. https://doi.org/10.48550/arXiv.1706.03762Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; Polosukhin, I. 2017, arXiv:1706.03762. [2025-08-29]. https://doi.org/10.48550/arXiv.1706.03762
28. [28]
  Huang, Z.; Zeng, Z.; Liu, B.; Fu, D.; Fu, J. 2020, arXiv:2004.00849. [2025-08-29]. https://doi.org/10.48550/arXiv.2004.00849Huang, Z.; Zeng, Z.; Liu, B.; Fu, D.; Fu, J. 2020, arXiv:2004.00849. [2025-08-29]. https://doi.org/10.48550/arXiv.2004.00849
29. [29]
  Kingma, D. P.; Ba, J. 2014, arXiv:1412.6980. [2025-08-29]. https://doi.org/10.48550/arXiv.1412.6980Kingma, D. P.; Ba, J. 2014, arXiv:1412.6980. [2025-08-29]. https://doi.org/10.48550/arXiv.1412.6980

扫一扫看文章

计量

PDF下载量: 0
文章访问数: 37
HTML全文浏览量: 6

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

智能反应优化：深度学习与优化算法驱动的乙酰水杨酸合成

通讯作者: 刘英菊,E-mail:yingjuliu@scau.edu.cn

English

Intelligent Reaction Optimization: Synthesis of Acetylsalicylic Acid Driven by Deep Learning and Optimization Algorithms

Corresponding author: Yingju Liu, yingjuliu@scau.edu.cn

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

智能反应优化：深度学习与优化算法驱动的乙酰水杨酸合成

通讯作者: 刘英菊,E-mail:yingjuliu@scau.edu.cn

English

Intelligent Reaction Optimization: Synthesis of Acetylsalicylic Acid Driven by Deep Learning and Optimization Algorithms

Corresponding author: Yingju Liu, yingjuliu@scau.edu.cn

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs