Substituting density functional theory in reaction barrier calculations for hydrogen atom transfer in proteins.
| Autor: | Riedmiller K; Heidelberg Institute for Theoretical Studies Heidelberg Germany frauke.graeter@h-its.org., Reiser P; Institute of Theoretical Informatics, Karlsruhe Institute of Technology Engler-Bunte-Ring 8 Karlsruhe 76131 Germany pascal.friederich@kit.edu.; Institute of Nanotechnology, Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1: 76344 Eggenstein-Leopoldshafen Germany., Bobkova E; Heidelberg Institute for Theoretical Studies Heidelberg Germany frauke.graeter@h-its.org., Maltsev K; Heidelberg Institute for Theoretical Studies Heidelberg Germany frauke.graeter@h-its.org., Gryn'ova G; Heidelberg Institute for Theoretical Studies Heidelberg Germany frauke.graeter@h-its.org.; Interdisciplinary Center for Scientific Computing, Heidelberg University Heidelberg Germany., Friederich P; Institute of Theoretical Informatics, Karlsruhe Institute of Technology Engler-Bunte-Ring 8 Karlsruhe 76131 Germany pascal.friederich@kit.edu.; Institute of Nanotechnology, Karlsruhe Institute of Technology Hermann-von-Helmholtz-Platz 1: 76344 Eggenstein-Leopoldshafen Germany., Gräter F; Heidelberg Institute for Theoretical Studies Heidelberg Germany frauke.graeter@h-its.org.; Interdisciplinary Center for Scientific Computing, Heidelberg University Heidelberg Germany. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Chemical science [Chem Sci] 2024 Jan 16; Vol. 15 (7), pp. 2518-2527. Date of Electronic Publication: 2024 Jan 16 (Print Publication: 2024). |
| DOI: | 10.1039/d3sc03922f |
| Abstrakt: | Hydrogen atom transfer (HAT) reactions are important in many biological systems. As these reactions are hard to observe experimentally, it is of high interest to shed light on them using simulations. Here, we present a machine learning model based on graph neural networks for the prediction of energy barriers of HAT reactions in proteins. As input, the model uses exclusively non-optimized structures as obtained from classical simulations. It was trained on more than 17 000 energy barriers calculated using hybrid density functional theory. We built and evaluated the model in the context of HAT in collagen, but we show that the same workflow can easily be applied to HAT reactions in other biological or synthetic polymers. We obtain for relevant reactions (small reaction distances) a model with good predictive power ( R 2 ∼ 0.9 and mean absolute error of <3 kcal mol -1 ). As the inference speed is high, this model enables evaluations of dozens of chemical situations within seconds. When combined with molecular dynamics in a kinetic Monte-Carlo scheme, the model paves the way toward reactive simulations. Competing Interests: There are no conflicts to declare. (This journal is © The Royal Society of Chemistry.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|