Download file (3.68MB)
Download as zip (3.37MB)

コレクション

引用

説明:

In the past decade, machine learning has emerged as a powerful tool to predict reaction outcomes. However, mechanistic interpretability of the constructed machine learning models remains limited due to the use of domain-specific and often arbitrary descriptors. Herein we demonstrate that an energy descriptor comprising the energies of the possible intermediates in the reaction system serves as a physically motivated representation for constructing interpretable regression models that provide mechanistic insight. The energy descriptor was calculated using the single-component artificial force induced reaction (SC-AFIR) method, which autonomously and comprehensively searches for intermediates of a target reaction, and subsequently used to train regression models for reaction yield prediction. Linear models with regularization showed good predictions for the hold-out samples (RMSE < 7% yield) and the coefficients of the models provided information on how the energies of the intermediates relate to the reaction outcome. This work highlights the utility of energy descriptors in constructing mechanistically interpretable regression models for predictive tasks in chemistry.

権利情報:

• Creative Commons BY-NC Attribution-NonCommercial 4.0 International
  

  This document is the unedited Author’s version of a Submitted Manuscript subsequently accepted for publication in Journal of the American Chemical Society, copyright © 2026 American Chemical Society. To access the final published article, see https://doi.org/10.1021/jacs.6c05203.

キーワード: Automated Reaction Path Exploration, Interpretable Machine Learning, Reaction Yield Prediction, Reaction Mechanism Elucidation, Quantum Chemical Calculations

刊行年月日: 2026-07-01

出版者: American Chemical Society (ACS)

掲載誌:

• Journal of the American Chemical Society (ISSN: 15205126) vol. 148 issue. 25 p. 26150-26160

研究助成金:

• Japan Society for the Promotion of Science 22KJ0043
• Japan Society for the Promotion of Science 23B203
• Japan Science and Technology Agency JPMJER1903
• Japan Science and Technology Agency JPMJFR2221

原稿種別: 査読前原稿 (Author's original)

MDR DOI:

公開URL: https://doi.org/10.1021/jacs.6c05203

関連資料:

その他の識別子:

連絡先:

更新時刻: 2026-11-02 15:10:20 +0900

MDRでの公開時刻: 2026-11-02 16:34:12 +0900