Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

被引:347
作者
Liu, Bowen [1 ]
Ramsundar, Bharath [2 ]
Kawthekar, Prasad [2 ]
Shi, Jade [1 ]
Gomes, Joseph [1 ]
Quang Luu Nguyen [1 ]
Ho, Stephen [1 ]
Sloane, Jack [1 ]
Wender, Paul [1 ,3 ]
Pande, Vijay [1 ,2 ,4 ]
机构
[1] Stanford Univ, Dept Chem, Stanford, CA 94305 USA
[2] Stanford Univ, Dept Comp Sci, Stanford, CA 94305 USA
[3] Stanford Univ, Dept Chem & Syst Biol, Stanford, CA 94305 USA
[4] Stanford Univ, Dept Biol Struct, Stanford, CA 94305 USA
基金
美国国家科学基金会;
关键词
ORGANIC-CHEMISTRY; AUTOMATED DISCOVERY; SYNTHETIC ANALYSIS; CHEMICAL-REACTIONS; KNOWLEDGE-BASE; COMPUTER; DESIGN; LANGUAGE; SYSTEM; METHODOLOGY;
D O I
10.1021/acscentsci.7b00303
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
We describe a fully data driven model that learns to perform a retrosynthetic reaction prediction task, which is treated as a sequence-to-sequence mapping problem. The end-to-end trained model has an encoder-decoder architecture that consists of two recurrent neural networks, which has previously shown great success in solving other sequence-to-sequence prediction tasks such as machine translation. The model is trained on 50,000 experimental reaction examples from the United States patent literature, which span 10 broad reaction types that are commonly used by medicinal chemists. We find that our model performs comparably with a rule-based expert system baseline model, and also overcomes certain limitations associated with rule-based expert systems and with any machine learning approach that contains a rule-based expert system component. Our model provides an important first step toward solving the challenging problem of computational retrosynthetic analysis.
引用
收藏
页码:1103 / 1113
页数:11
相关论文
共 58 条
  • [31] Route Designer: A Retrosynthetic Analysis Tool Utilizing Automated Retrosynthetic Rule Generation
    Law, James
    Zsoldos, Zsolt
    Simon, Aniko
    Reid, Darryl
    Liu, Yang
    Khew, Sing Yoon
    Johnson, A. Peter
    Major, Sarah
    Wade, Robert A.
    Ando, Howard Y.
    [J]. JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2009, 49 (03) : 593 - 602
  • [32] Organic Synthesis: March of the Machines
    Ley, Steven V.
    Fitzpatrick, Daniel E.
    Ingham, Richard. J.
    Myers, Rebecca M.
    [J]. ANGEWANDTE CHEMIE-INTERNATIONAL EDITION, 2015, 54 (11) : 3449 - 3464
  • [33] Lowe D. M, 2012, Extraction of Chemical Structures and Reactions from the Literature
  • [34] Ab Initio Reactive Computer Aided Molecular Design
    Martinez, Todd J.
    [J]. ACCOUNTS OF CHEMICAL RESEARCH, 2017, 50 (03) : 652 - 656
  • [35] Nam J., 161209529 ARXIV
  • [36] Pensak D. A., 1977, COMPUTER ASSISTED OR, V61, P1, DOI [DOI 10.1021/BK-1977-0061.CH001, 10.1021/bk-1977-0061.ch001]
  • [37] Complex Chemical Reaction Networks from Heuristics-Aided Quantum Chemistry
    Rappoport, Dmitrij
    Galvin, Cooper J.
    Zubarev, Dmitry Yu.
    Aspuru-Guzik, Alan
    [J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2014, 10 (03) : 897 - 907
  • [38] COMPUTER-ASSISTED MECHANISTIC EVALUATION OF ORGANIC-REACTIONS .1. OVERVIEW
    SALATIN, TD
    JORGENSEN, WL
    [J]. JOURNAL OF ORGANIC CHEMISTRY, 1980, 45 (11) : 2043 - 2051
  • [39] Santoro A., 160506065 ARXIV
  • [40] SOPHIA, A KNOWLEDGE BASE-GUIDED REACTION PREDICTION SYSTEM - UTILIZATION OF A KNOWLEDGE-BASE DERIVED FROM A REACTION DATABASE
    SATOH, H
    FUNATSU, K
    [J]. JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1995, 35 (01): : 34 - 44