Sammanfattning

A new deep neural network based on the WaveNet architecture (WNN) is presented, which is designed to grasp specific patterns in the NMR spectra. When trained at a fixed non-uniform sampling (NUS) schedule, the WNN benefits from pattern recognition of the corresponding point spread function (PSF) pattern produced by each spectral peak resulting in the highest quality and robust reconstruction of the NUS spectra as demonstrated in simulations and exemplified in this work on 2D 1H-15N correlation spectra of three representative globular proteins with different sizes: Ubiquitin (8.6 kDa), Azurin (14 kDa), and Malt1 (44 kDa). The pattern recognition by WNN is also demonstrated for successful virtual homodecoupling in a 2D methyl 1H-13C - HMQC spectrum of MALT1. We demonstrate using WNN that prior knowledge about the NUS schedule, which so far was not been fully exploited, can be used for designing new powerful NMR processing techniques that surpass the existing algorithmic methods. (c) 2022 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

Nyckelord

Nuclear magnetic resonance; Non-uniform sampling; DNN; CNN; Wave-net

Publicerad i

Journal of Magnetic Resonance
2023, Volym: 346, artikelnummer: 107342
Utgivare: ACADEMIC PRESS INC ELSEVIER SCIENCE

SLU författare

• Agback, Tatiana

  • Institutionen för molekylära vetenskaper, Sveriges lantbruksuniversitet
    

• Agback, Peter

  • Institutionen för molekylära vetenskaper, Sveriges lantbruksuniversitet
    

UKÄ forskningsämne

Datavetenskap (datalogi)
Biokemi och molekylärbiologi


Publikationens identifierare

DOI: https://doi.org/10.1016/j.jmr.2022.107342

Permanent länk till denna sida (URI)

https://res.slu.se/id/publ/122152