Buchumschlag

Predicting reaction barriers of hydrogen atom transfer in proteins

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 activ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Riedmiller, Kai (Verfasst von) , Reiser, Patrick (Verfasst von) , Bobkova, Elizaveta (Verfasst von) , Maltsev, Kiril (Verfasst von) , Gryn’ova, Ganna (Verfasst von) , Friederich, Pascal (Verfasst von) , Gräter, Frauke (Verfasst von)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: Feb 13, 2023
Ausgabe:Version 1
In: ChemRxiv
Year: 2023, Pages: 1-8
DOI:10.26434/chemrxiv-2023-7hntk
Online-Zugang:Resolving-System, kostenfrei, Volltext: https://doi.org/10.26434/chemrxiv-2023-7hntk
Verlag, kostenfrei, Volltext: https://chemrxiv.org/engage/chemrxiv/article-details/63e60790fcfb27a31f87e9c0
Volltext
Verfasserangaben:Kai Riedmiller, Patrick Reiser, Elizaveta Bobkova, Kiril Maltsev, Ganna Gryn'ova, Pascal Friederich, Frauke Gräter
Beschreibung
Zusammenfassung: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 activation energies of HAT reactions in proteins. It is 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 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 (R2 <0.9 and mean absolute error of <3 kcal/mol). As the inference speed is high, this model enables evaluations of many chemical situations in rapid succession. When combined with molecular dynamics in a kinetic Monte-Carlo scheme, the model paves the way toward reactive simulations.
Beschreibung:Gesehen am 14.02.2023
Beschreibung:Online Resource
DOI:10.26434/chemrxiv-2023-7hntk

Ähnliche Einträge