有机化学 ›› 2020, Vol. 40 ›› Issue (11): 3812-3827.DOI: 10.6023/cjoc202006051 上一篇    下一篇

综述与进展

机器学习在有机化学中的应用

刘伊迪, 杨骐, 李遥, 张龙, 罗三中   

  1. 清华大学化学系 基础分子科学中心 北京 100084
  • 收稿日期:2020-06-24 修回日期:2020-07-22 发布日期:2020-08-06
  • 通讯作者: 张龙, 罗三中 E-mail:luosz@tsinghua.edu.cn;zhanglong@tsinghua.edu.cn
  • 基金资助:
    科技部基础资源调查项目(No.2018FY201200)、清华大学理科双创项目(No.2019Z07L01005)和国家自然科学基金(Nos.22031006,21672217,21933008)资助项目.

Application of Machine Learning in Organic Chemistry

Liu Yidi, Yang Qi, Li Yao, Zhang Long, Luo Sanzhong   

  1. Center for Basic Molecular Science, Department of Chemistry, Tsinghua University, Beijing 100084
  • Received:2020-06-24 Revised:2020-07-22 Published:2020-08-06
  • Supported by:
    Project supported by the National Science & Technology Fundamental Resource Investigation Program of China (No. 2018FY201200), the Tsinghua University Initiative Scientific Research Program (No. 2019Z07L01005) and the Natural Science Foundation of China (Nos. 22031006, 21672217, 21933008).

近年来,由于计算能力、大数据和算法的不断进步,人工智能(Artificial intelligence,AI)重新兴起,已成为诸多研究领域变革性发展背后的重要推动力.机器学习(Machine learning,ML)是人工智能一个重要的研究领域.随着化学信息学的发展,机器学习在化学领域展现出巨大的发展潜力,也为有机化学的发展带来了新的机遇.为帮助有机化学家了解这一新兴领域,对如何将机器学习策略应用于有机化学研究做简单介绍,同时,概括总结了机器学习在化合物性质预测、分子从头设计、化学反应预测、逆合成分析和智能合成机器方面的应用实例,分析讨论了当前机器学习在有机化学领域面临的挑战和难题.

关键词: 机器学习, 分子描述符, 算法, 化学性质预测, 分子从头设计, 化学反应预测, 逆合成分析

Driven by nowadays’ computing power, big data technology as well as learning algorithm, artificial intelligence (AI) has gained trenmendous attentions and become a transformative approach in many research areas. One of the most extensively explored AI approaches in chemistry is (deep) machine learning, which provides new twists in the fields of organic chemistry. The workflow of machine learning (ML) study in organic chemistry is briefly introduced. Meanwhile, the application of ML in the accurate prediction of chemical properties, molecular de novo design, chemical reaction prediction, retrosynthetic analysis and artificial intelligence synthetic machine are also summarized. In the end, the current challenges in this field are analyzed and discussed.

Key words: machine learning, molecular descriptor, algorithm, chemical property prediction, de novo design, chemical reaction prediction, retrosynthesis analysis