A protein dynamics–based deep learning model enhances predictions of fitness and epistasis
Proceedings of the National Academy of Sciences · 2025
DOI: 10.1073/pnas.2502444122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, 2025. Verfasst von Ngoc Huynh und 5 weiteren Autor:innen. Beteiligte Einrichtung: Center for Biological Physics, Arizona State University, Tempe, AZ 85287. Hauptthemen laut MEDLINE: Deep Learning, Epistasis, Genetic, beta-Lactamases, Proteins. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, Gordon and Betty Moore Foundation (GBMF), NSF (NSF).
Abstract (Originalsprache)
Deep learning has advanced our ability to assess the effects that individual mutations have on protein function; however, predicting the complex interplay between two or more mutations remains challenging. Here, we seek to address this challenge by building a deep learning framework that incorporates information related to protein dynamics. Namely, we build a neural network architecture using a physics-based metric called the Asymmetric Dynamic Coupling Index (DCI asym ), which quantifies the degree to which each member of a pair of residues influences the flexibility of the other. DCI asym enables us to train models through an allosteric Graph Neural Network (GNN) in which each residue is linked to its distant dynamic influencers. Despite not being trained on experimental epistasis data, our GNN consistently outperforms existing approaches on deep mutational scanning datasets across four distinct proteins, highlighting its enhanced capacity to model epistatic interactions. Our GNN model was then challenged to predict the functions of 37 novel, computationally designed TEM-1 β-lactamase variants of unknown function, and it demonstrated excellent predictive accuracy for these variants. Thus, our GNN provides a pathway for better assessing the impact of multiple mutations on protein function, including epistatic relationships and mutations that have profound effects on activity despite being spatially far from the active site.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Center for Biological Physics, Arizona State University, Tempe, AZ 85287.
- School of Molecular Sciences, Arizona State University, Tempe, AZ 85287.
- The Biodesign Center for Molecular Design and Biomimetics, Arizona State University, Tempe, AZ 85287.
- Department of Physics, Arizona State University, Tempe, AZ 85287.
ORCID-Profile: Ngoc Huynh, I Can Kazan, Jeremy H Mills, S Banu Ozkan
Förderung
- NIGMS NIH HHS
- Gordon and Betty Moore Foundation (GBMF)
- NSF (NSF)
Zitieren
APA
Huynh, N., Kazan, I. C., Lu, J., Kolbaba-Kartchner, B., Mills, J. H., & Ozkan, S. B. (2025). A protein dynamics–based deep learning model enhances predictions of fitness and epistasis. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2502444122
Vancouver
Huynh N, Kazan IC, Lu J, Kolbaba-Kartchner B, Mills JH, Ozkan SB. A protein dynamics–based deep learning model enhances predictions of fitness and epistasis. Proceedings of the National Academy of Sciences. 2025. doi:10.1073/pnas.2502444122
BibTeX
@article{Huynh2025,
author = {Huynh, Ngoc and Kazan, I Can and Lu, Jin and Kolbaba-Kartchner, Bethany and Mills, Jeremy H and Ozkan, S Banu},
title = {A protein dynamics–based deep learning model enhances predictions of fitness and epistasis},
journal = {Proceedings of the National Academy of Sciences},
year = {2025},
doi = {10.1073/pnas.2502444122}
}
EUVIMED