Pure Isotropic Proton NMR Spectra in Solids using Deep Learning

被引：15

作者：

Cordova, Manuel ^{[1
,2
]}

Moutzouri, Pinelopi ^{[1
]}

de Almeida, Bruno Simoes ^{[1
]}

Torodii, Daria ^{[1
]}

Emsley, Lyndon ^{[1
,2
]}

机构：

[1] Ecole Polytech Fed Lausanne EPFL, Inst Sci & Ingenierie Chim, CH-1015 Lausanne, Switzerland

[2] Ecole Polytech Fed Lausanne EPFL, Natl Ctr Computat Design & Discovery Novel Mat MAR, CH-1015 Lausanne, Switzerland

来源：

ANGEWANDTE CHEMIE-INTERNATIONAL EDITION | 2023年 / 62卷 / 08期

基金：

瑞士国家科学基金会;

关键词：

Machine Learning; NMR Spectroscopy; Solid-State Structures; CARBON-CARBON CONNECTIVITIES; STATE NMR; SPECTROSCOPY; SYSTEMS;

D O I：

10.1002/anie.202216607

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

The resolution of proton solid-state NMR spectra is usually limited by broadening arising from dipolar interactions between spins. Magic-angle spinning alleviates this broadening by inducing coherent averaging. However, even the highest spinning rates experimentally accessible today are not able to completely remove dipolar interactions. Here, we introduce a deep learning approach to determine pure isotropic proton spectra from a two-dimensional set of magic-angle spinning spectra acquired at different spinning rates. Applying the model to 8 organic solids yields high-resolution H-1 solid-state NMR spectra with isotropic linewidths in the 50-400 Hz range.

引用

页数：8