4.8 Article

A generalized-template-based graph neural network for accurate organic reactivity prediction

期刊

NATURE MACHINE INTELLIGENCE
卷 4, 期 9, 页码 772-780

出版社

NATURE PORTFOLIO
DOI: 10.1038/s42256-022-00526-z

关键词

-

资金

  1. Technology Innovation Program [20015850]
  2. Ministry of Trade, Industry and Energy (MOTIE, Korea)
  3. National Research Foundation of Korea [2019M3D3A1A01069099, 2019M3D1A1079303]
  4. National Research Foundation of Korea [2019M3D3A1A01069099, 2019M3D1A1079303] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)

向作者/读者索取更多资源

This study introduces a chemistry-inspired graph neural network that accurately predicts organic reaction products by learning generalized reaction templates, thereby significantly simplifying reaction rules and exhibiting high accuracy. Despite being simplified, the generalized reaction templates are shown to represent a large percentage of existing reactions.
The reliable prediction of chemical reactivity remains in the realm of knowledgeable synthetic chemists. Automating this process by using artificial intelligence could accelerate synthesis design in future digital laboratories. While several machine learning approaches have demonstrated promising results, most current models deviate from how human chemists analyse and predict reactions based on electronic changes. Here, we propose a chemistry-motivated graph neural network called LocalTransform, which learns organic reactivity based on generalized reaction templates to describe the net changes in electron configuration between the reactants and products. The proposed concept dramatically reduces the number of reaction rules and exhibits state-of-the-art product prediction accuracy. In addition to the built-in interpretability of the generalized reaction templates, the high score-accuracy correlation of the model allows users to assess the uncertainty of the machine predictions. To understand reactions in organic chemistry, ideally simple rules would help us predict the outcome of new reactions, but in reality such rules are not easily identified. Chen and Jung extract generalized reaction templates from data and show that they can be used in graph neural networks to predict the outcome of reactions and, despite simplification, still represent a high percentage of existing reactions.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据