应用化学 ›› 2023, Vol. 40 ›› Issue (3): 360-373.DOI: 10.19894/j.issn.1000-0518.220229

• 综合评述 • 上一篇    下一篇

深度学习在化学信息学中的应用研究进展

刘振邦1, 张硕2, 包宇2(), 马英明2, 梁蔚淇2, 王伟2, 何颖2, 牛利2   

  1. 1.广州大学计算机科学与网络工程学院,广州 510006
    2.广州大学化学化工学院分析科学技术研究中心,广州 510006
  • 收稿日期:2022-07-01 接受日期:2022-11-10 出版日期:2023-03-01 发布日期:2023-03-27
  • 通讯作者: 包宇

Progress of Application Research on Cheminformatics in Deep Learning

Zhen-Bang LIU1, Shuo ZHANG2, Yu BAO2(), Ying-Ming MA2, Wei-Qi LIANG2, Wei WANG2, Ying HE2, Li NIU2   

  1. 1.School of Computer Science and Cyber Engineering,Guangzhou University,Guangzhou 510006,China
    2.Center for Advanced Analytical Science,School of Chemistry and Chemical Engineering,Guangzhou University,Guangzhou 510006,China
  • Received:2022-07-01 Accepted:2022-11-10 Published:2023-03-01 Online:2023-03-27
  • Contact: Yu BAO
  • About author:baoyu@gzhu.edu.cn

摘要:

在知识、数据、算法与算力的多重驱动下,深度学习不仅在计算机视觉、自然语言处理等研究领域取得了突破,并随着各学科间的迁移应用于交叉融合,逐渐衍生出多个新兴研究方向。化学信息学作为以应用信息学方法以解决化学问题的学科,深度学习技术凭借其强大的非线性学习能力,通过深度学习模型可以从数据集中对其进行筛选预测,再基于理论计算对结果可行性进行理论验证,最后通过实验表征结果,缩短了实验周期、降低了人力成本、加速了化学信息学智能化。本文简要介绍了深度学习发展历史及主要网络模型架构,介绍了近年来深度学习在在化合物合成路线规划、化合物结构活性与性质及催化剂设计的最新研究和应用现状,并对未来的发展方向进行讨论与展望。

关键词: 深度学习, 化学信息学, 构效关系, 合成路线, 催化化学

Abstract:

Deep learning has gone through breakthroughs in many research fields including computer vision, natural language processing, etc. due to multiple driving factors such as knowledge, data, algorithms and computing power. In addition, it has gradually spawned a number of new research directions with the migration and application as well as cross-integration among various disciplines. Cheminformatics is a discipline that solves chemical problems with the applied informatics methods, and deep learning can be useful since it is very powerful in nonlinear learning. Deep learning model can be used to screen and predict in the data set, and then verify the feasibility of the results based on theoretical calculation. Finally, the results are represented by experiments, which shortens the experimental period, reduces the labor cost and accelerates the intelligence of cheminformatics. This paper briefly introduces the development history and main network model architecture of deep learning as well as the latest research and application status of deep learning in synthesis planning, compound structure-activity relation and catalyst design in recent years, and also discusses and expects the future development direction.

Key words: Deep learning, Cheminformatics, Structure-activity relationship, Synthesis planning, Catalysis chemistry

中图分类号: