Towards Ultimate NMR Resolution with Deep Learning

TL;DR

This paper introduces a deep learning approach called MR-Ai that enhances multidimensional NMR spectral resolution by generating probabilistic peak representations, improving analysis especially with sparse data.

Contribution

The paper presents a novel deep learning architecture, MR-Ai, that maps spectra to peak probability representations and enables multi-spectral coprocessing for improved resolution.

Findings

MR-Ai effectively enhances spectral quality on synthetic and real protein data.

The $P^3$ representation provides a probabilistic peak map that improves peak detection.

Multi-spectral coprocessing boosts spectral resolution in sparse sampling scenarios.

Abstract

In multidimensional NMR spectroscopy, practical resolution is defined as the ability to distinguish and accurately determine signal positions against a background of overlapping peaks, thermal noise, and spectral artifacts. In the pursuit of ultimate resolution, we introduce Peak Probability Presentations ($P^3$)- a statistical spectral representation that assigns a probability to each spectral point, indicating the likelihood of a peak maximum occurring at that location. The mapping between the spectrum and $P^3$ is achieved using MR-Ai, a physics-inspired deep learning neural network architecture, designed to handle multidimensional NMR spectra. Furthermore, we demonstrate that MR-Ai enables coprocessing of multiple spectra, facilitating direct information exchange between datasets. This feature significantly enhances spectral quality, particularly in cases of highly sparse sampling. Performance of MR-Ai and high value of the $P^3$ are demonstrated on the synthetic data and spectra of Tau, MATL1, Calmodulin, and several other proteins.