Scalable deep learning reconstruction for accelerated multidimensional nuclear magnetic resonance spectroscopy of proteins
Science Advances · 2025
DOI: 10.1126/sciadv.adw8122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, 2025. Verfasst von Yihui Huang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen University-Neusoft Med…. Hauptthemen laut MEDLINE: Deep Learning, Proteins, Nuclear Magnetic Resonance, Biomolecular. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
High-dimensional nuclear magnetic resonance (NMR) spectroscopy can assist in determining protein structure, but it requires time-consuming acquisition. Deep learning enables ultrafast reconstruction but is limited to spectra of up to three dimensions and cannot provide faithful reconstruction under unseen acceleration factors. Extending deep learning to handle higher-dimensional spectra and varying acceleration factors is desirable. However, scalability requires complex networks and more data, seriously hindering applications. To address this, we designed a network to learn data in one dimension (1D). First, time-domain signals were modeled as the outer product of 1D exponentials. Then, each 1D exponential was approximated with a rank-one Hankel matrix. Last, reconstruction error was corrected with a neural network. Here, we demonstrate robust 3D NMR reconstruction across acceleration factors (2 to 33) using one trained network. In addition, we find that reconstruction of 4D NMR is possible with artificial intelligence. This work opens an avenue for accelerating arbitrarily high-dimensional NMR.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University, Xiamen University-Neusoft Medical Magnetic Resonance Imaging Joint Research and Development Center,…
- Department of Molecular Sciences, Swedish University of Agricultural Sciences, Uppsala, Sweden.
- Department of Chemistry and Molecular Biology, University of Gothenburg, Gothenburg, Sweden.
- Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA, USA.
- Department of Electronic Science, State Key Laboratory for Physical Chemistry of Solid Surfaces, Xiamen University, Xiamen, China.
- School of Computer and Information Engineering, Fujian Engineering Research Center for Medical Data Mining and Application, Xiamen University of Technology, Xiamen, China.
ORCID-Profile: Yihui Huang, Yuncheng Gao, Zhangren Tu, Tatiana Agback, Vladislav Orekhov, Sven G Hyberts, Gerhard Wagner, Yanqin Lin, Zhong Chen, Di Guo, Xiaobo Qu
Zitieren
APA
Huang, Y., Gao, Y., Tu, Z., Agback, T., Orekhov, V., Hyberts, S. G., Wagner, G., Lin, Y., Chen, Z., Guo, D., & Qu, X. (2025). Scalable deep learning reconstruction for accelerated multidimensional nuclear magnetic resonance spectroscopy of proteins. Science Advances. https://doi.org/10.1126/sciadv.adw8122
Vancouver
Huang Y, Gao Y, Tu Z, Agback T, Orekhov V, Hyberts SG, et al. Scalable deep learning reconstruction for accelerated multidimensional nuclear magnetic resonance spectroscopy of proteins. Science Advances. 2025. doi:10.1126/sciadv.adw8122
BibTeX
@article{Huang2025,
author = {Huang, Yihui and Gao, Yuncheng and Tu, Zhangren and Agback, Tatiana and Orekhov, Vladislav and Hyberts, Sven G and Wagner, Gerhard and Lin, Yanqin and Chen, Zhong and Guo, Di and Qu, Xiaobo},
title = {Scalable deep learning reconstruction for accelerated multidimensional nuclear magnetic resonance spectroscopy of proteins},
journal = {Science Advances},
year = {2025},
doi = {10.1126/sciadv.adw8122}
}
EUVIMED