Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates
Chemical Physics Reviews · 01.09.2026 · 7 (3)
DOI: 10.1063/5.0335684 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemical Physics Reviews, online erschienen am 20.07.2026. Verfasst von Toshifumi Mori und 3 weiteren Autor:innen. Die Arbeit nennt 167 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science, Fugaku Supercomputing, Data-Driven Material Research.
Abstract (Originalsprache)
In complex molecular systems, the reaction coordinate (RC) that characterizes transition pathways is essential to understand underlying molecular mechanisms. This review surveys a framework for identifying the RC by applying deep learning to the committor, which provides the most reliable measure of the progress along a transition path. The inputs to the neural network are collective variables (CVs) expressed as functions of atomic coordinates of the system, and the corresponding RC is predicted as the output by training the network on the committor as the learning target. Because deep-learning models typically operate in a black-box manner, it is difficult to determine which input variables govern the predictions. The incorporation of explainable artificial intelligence techniques enables quantitative assessment of the contributions of individual input variables to the predictions. This approach allows the identification of CVs that play dominant roles and demonstrates that the committor distribution on the surface using important CVs is separated by well-defined boundaries. The framework provides an explainable deep learning strategy for assigning a molecular mechanism from the RC and is applicable to a wide range of complex molecular systems.
Förderung
- Japan Society for the Promotion of Science
- Fugaku Supercomputing
- Data-Driven Material Research
- National Institutes of Natural Sciences
Zitieren
APA
Mori, T., Okazaki, K., Kim, K., & Matubayasi, N. (2026). Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates. Chemical Physics Reviews, 7(3). https://doi.org/10.1063/5.0335684
Vancouver
Mori T, Okazaki K, Kim K, Matubayasi N. Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates. Chemical Physics Reviews. 2026;7(3). doi:10.1063/5.0335684
BibTeX
@article{Mori2026,
author = {Mori, Toshifumi and Okazaki, Kei-ichi and Kim, Kang and Matubayasi, Nobuyuki},
title = {Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates},
journal = {Chemical Physics Reviews},
year = {2026},
volume = {7},
number = {3},
doi = {10.1063/5.0335684}
}
EUVIMED