Chinese Journal of Organic Chemistry ›› 2021, Vol. 41 ›› Issue (7): 2666-2675.DOI: 10.6023/cjoc202012037 Previous Articles     Next Articles



谭胖a,b, 刘旭红a,c, 谌彤童d, 秦智慧a,b, 杨涛a, 刘晓彤a,e,f,g, 刘秀磊a,b,*()   

  1. a 北京信息科技大学 北京材料基因工程高精尖创新中心 北京 100101
    b 北京信息科技大学 数据与科学情报分析实验室 北京 100101
    c 北京信息科技大学 网络文化与数字传播北京市重点实验室 北京 100192
    d 北京跟踪与通信技术研究所 北京 100094
    e 中国科学院煤炭化学研究所 煤转化国家重点实验室 太原 030001
    f 中科合成油技术有限公司 国家能源煤基液体燃料研发中心 北京 101400
    g 中国科学院大学 北京 100049
  • 收稿日期:2020-12-22 修回日期:2021-02-08 发布日期:2021-03-04
  • 通讯作者: 刘秀磊
  • 基金资助:
    北京信息科技大学“勤信人才”培育计划; 北京信息科技大学促进高校内涵发展; 北京市教育委员会科技计划一般项目(KM202111232003); 北京市自然科学基金(4204100)

Research Progress on New Organic Molecules Design via Machine Learning

Pang Tana,b, Xuhong Liua,c, Tongtong Chend, Zhihui Qina,b, Tao Yanga, Xiaotong Liua,e,f,g, Xiulei Liua,b()   

  1. a Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Information Science and Technology University, Beijing 100101
    b Laboratory of Data Science and Information Studies, Beijing Information Science and Technology University, Beijing 100101
    c Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science and Technology University, Beijing 100192
    d Beijing Institute of Tracking and Telecommunications Technology, Beijing 100094
    e State Key Laboratory of Coal Conversion, Institute of Coal Chemistry, Chinese Academy of Sciences, Taiyuan 030001
    f National Energy Center for Coal to Liquids, Synfuels China Co., Ltd, Beijing 101400
    g University of Chinese Academy of Sciences, Beijing 100049
  • Received:2020-12-22 Revised:2021-02-08 Published:2021-03-04
  • Contact: Xiulei Liu
  • Supported by:
    Qin Xin Talents Cultivation Program of Beijing Information Science & Technology University; Beijing University of Information Science and Technology to Promote the Development of the Connotation of Colleges and Universities; Beijing Education Commission for General Project of Science and Technology Plan(KM202111232003); Beijing Municipal Natural Science Foundation(4204100)

Low-cost and high-performance materials have become more and more important in past decades. It exhibits the technology level of a country. Chemists used to find the candidate material according to property regression and quantitative structure activity relationship (QSAR). Traditional methods focus on finding new molecule from prior knowledge with trial and error experiments. They are time-consuming and low efficiency on screening molecules. The appearance of machine learning (ML) changes this embarrassing situation in two ways. One is accelerating the property prediction process to prevent wasting time on worse candidates. The other is inverse molecule design which expands the imagination of human. Lots of researches show promising results using different inverse design method such as, variational auto-encoder (VAE), generative adversarial networks (GAN), reinforcement learning (RL), and recurrent neural network (RNN). They introduce uncertainty from different level to generate new structure candidates. In any method, molecule descriptor has a great impact on the result. The descriptor converts the 3D structures in real world to a vector or a notation string to feed into all kinds of ML models. Large number of descriptors have been developed in cheminformatic, bioinformatic, quantum chemistry and natural language process (NLP). Some classical descriptors are Coulomb matrix (CM), smooth overlap of atomic positions (SOAP), weighted graph (WG), simplified molecular input line entry specification (SMILES). They show different advantages and solving problems from different aspects. CM has clear definition and good result on energy regression. SOAP is good at reflecting local environment features of an atom. However, they are easy to encode but hard to decode. That is a reason why people prefer WG and SMILES in the structure inverse design tasks. WG and SMILES express structure as a graph (an atom as a node and a bond as an edge) or string to apply massive mature GNN or NLP algorithm on them. Nowadays, most of the ML applications on chemistry and molecule science are focus on developing new model to regress properties. However, it is thought that there is still large improving space on inverse design methods and traditional descriptors. In this paper, WG and SMILES are briefly introduced firstly. Then, four generative models are presented, including VAE, GAN, RL and RNN. Further, the current progress and challenges of inverse design methods are summarized case by case. Finally, some of the author՚s understanding and explorations are given out. It is proved that SMILES with BASE64 preprocessed shows some advantages on molecular reconstruction and worth to study deeply in future.

Key words: machine learning, generative model, inverse molecule design, molecule description, BASE64 encoding