机器学习辅助高分子合成研究进展  

Machine learning-assisted investigations toward polymer synthesis

作　　者：张泽熙 蔡展翔 张文彬[2] 吕华[2] 陈茂 Zexi Zhang;Zhanxiang Cai;Wenbin Zhang;Hua Lu;Mao Chen(Department of Macromolecular Science,State Key Laboratory of Molecular Engineering of Polymers,Fudan University,Shanghai 200433,China;Beijing National Laboratory for Molecular Sciences,Key Laboratory of Polymer Chemistry and Physics of Ministry of Education,Center for Soft Matter Science and Engineering,College of Chemistry and Molecular Engineering,Peking University,Beijing 100871,China)

机构地区：[1]聚合物分子工程国家重点实验室,复旦大学高分子科学系,上海200433 [2]北京分子科学国家研究中心,高分子化学与物理教育部重点实验室,软物质科学与工程中心,北京大学化学与分子工程学院,北京100871

出　　处：《科学通报》2025年第4期471-480,共10页Chinese Science Bulletin

摘　　要：聚合物为人类社会生活发展提供了不可或缺的物质基础.在研发聚合物材料的过程中,庞大的结构空间、复杂的聚合机制为建立聚合物材料的构效关系带来重大挑战.机器学习有望突破高分子合成研究的传统范式,推进新型聚合物材料的化学创制,近年来成为了高分子化学家关注的前沿领域.机器学习技术实现了反应条件、化学结构、材料性能之间潜在关联的发掘,提高了对聚合反应空间的研究效率,为反应条件优化、链结构设计提供了系统性指导.数据驱动的生物大分子结构解析是多领域关注的焦点,机器学习助力实现了蛋白质结构预测的跨越式进步,迈入了生物大分子研究的新阶段.在此基础上,结合自动化技术,发展数智化合成,进一步降低试错成本,加速聚合物材料研发,推动理论知识发展.本文对机器学习在预测聚合物性能、设计聚合物结构与合成条件、生物大分子研究中取得的重要进展进行简要介绍与讨论.目前,机器学习辅助的高分子合成研究仍面临聚合物结构表示方法有限、高质量数据稀缺、自动化技术落地合成生产困难等挑战,亟须加大研究投入,深入开展跨学科研究,发展人工智能赋能的高分子合成,推动高端材料创新.Polymers are ubiquitous in human life, with applications ranging from commodity plastics to high-tech products. The synthesis ofnovel structured polymers lays the foundation for developing high-performance polymeric materials crucial for meeting greatinterest in various fields across aerospace, biomedicine, and electronics, among many others. However, the vast chemical space ofpolymer structures, coupled with the complexities inherent in polymerization progress, which makes it nearly impossible toexplore the entire space via conventional trial-and-error method, poses substantial challenges in predicting the polymerperformances with varied structures and in tailoring polymer structures and polymerization conditions as to achieve desiredproperties (e.g., mechanical properties, dielectric performance, and biological functions). Recently, machine Learning (ML)techniques have emerged as illuminating avenues toward revolutionizing polymer chemistry, demonstrating significant potentialin effectively navigating through the enormous landscape. Data-driven approaches could not only unveil intricate relationshipsamong variables (e.g., polymer structures, reaction conditions, and polymer properties) but also offer unintuitive mechanisticinsights that enable a deeper understanding of the polymerization process, which was previously unavailable via traditionalanalytical methods. To actually realize the aforementioned ideal visions, chemists employ outcomes from experiments and/orsimulations as the initial database, whose quantity and quality largely determine the accuracy and reliability of subsequentmodeling with delicately selected ML algorithms. Then, ML models are capable of efficiently mapping the linkage betweenconditions, structures, and properties from inputted data, facilitating property prediction with unprecedented efficiency andproviding systematical guides for polymer structure or condition parameter optimization. Furthermore, researchers believe thattransforming conventional manual operations into autonomous synt

关 键 词：高分子合成 机器学习 人工智能 聚合物 生物大分子 

分 类 号：O631[理学—高分子化学] TP181[理学—化学]