Two-dimensional NMR from a Single Pulse: Reconstructing Heteronuclear 2D spectra via off-resonance decoupling and Deep Neural Networks

Abstract

Nuclear Magnetic Resonance (NMR) spectroscopy is ubiquitous in many areas of science, including chemistry, material science, biophysics and structural biology. Heteronuclear two-dimensional (2D) NMR experiments form the basis of several NMR based investigations, especially those involving biomolecules like proteins. However, in solution, as the molecule of interest becomes larger, transverse relaxation times of the spins of interest become shorter. This makes it difficult to record 2D 1H-13C or 1H-15N correlation maps of large protein molecules using standard Fourier-transform based experiments as they contain transfer delays that are long compared to the short relaxation times. Herein, we explore the possibility of leveraging deep neural networks (DNNs) to obtain 2D correlation maps of proteins while eliminating transfer delays from experiments. In this study, we show that 2D methyl 1H-13C correlation maps can be obtained from experiments containing only a single 1H excitation pulse followed by off-resonance 13C continuous-wave decoupling. A DNN was successfully trained to reconstruct the 2D 1H-13C correlation map from datasets recorded with two 13C decoupling fields using protein samples enriched with (ILV) 13CHD2 methyl groups in a 2H background. The efficacy of this strategy is demonstrated by using the DNN to reconstruct methyl 1H-13C correlation maps of the [~]8 kDa FF domain from human HYPA/FBP11, the [~]18 kDa T4 phage lysozyme, as well as on the [~]360 kDa 77 particle from the Thermoplasma acidophilum proteasome. This study illustrates the potential for improving the sensitivity and resolution of NMR spectra using new experiments tailored for use with DNNs. Significance statementMultidimensional heteronuclear solution state nuclear magnetic resonance (NMR) spectroscopy underpins studies of protein dynamics and interactions. However, the experiments have thus far required magnetization-transfer periods and evolution delays, both of which rapidly erode the signal arising from large biomolecules. We introduce here a single-pulse strategy wherein these delays are replaced by off-resonance continuous-wave decoupling so that the two-dimensional correlation map can be reconstructed from the off-resonance decoupling data using a deep neural network. The approach yields high-quality methyl correlation spectra for proteins spanning [~]8-360 kDa. The co-design of NMR experiments along with deep neural networks establishes a general framework to acquire multidimensional NMR spectra using nontraditional strategies that can be extended to other spin systems and higher-dimensional experiments.