A deep learning model for chemical shieldings in molecular organic solids including anisotropy

TL;DR

This paper introduces ShiftML3.0, a deep learning model that accurately predicts chemical shieldings and anisotropy in molecular solids, approaching the precision of DFT calculations and aiding NMR-based structure elucidation.

Contribution

The paper presents a novel deep learning model that improves the accuracy of chemical shielding predictions, including anisotropy, for molecular solids, surpassing previous ML models.

Findings

RMSEs close to DFT for $^{1}$H, $^{13}$C, and $^{15}$N shieldings

Predicts full shielding tensor including anisotropy

Achieves high accuracy on experimental benchmark sets

Abstract

Nuclear Magnetic Resonance (NMR) chemical shifts are powerful probes of local atomic and electronic structure that can be used to resolve the structures of powdered or amorphous molecular solids. Chemical shift driven structure elucidation depends critically on accurate and fast predictions of chemical shieldings, and machine learning (ML) models for shielding predictions are increasingly used as scalable and efficient surrogates for demanding ab initio calculations. However, the prediction accuracies of current ML models still lag behind those of the DFT reference methods they approximate, especially for nuclei such as $^{13}$C and $^{15}$N. Here, we introduce ShiftML3.0, a deep-learning model that improves the accuracy of predictions of isotropic chemical shieldings in molecular solids, and does so while also predicting the full shielding tensor. On experimental benchmark sets, we find root-mean-squared errors with respect to experiment for ShiftML3.0 that approach those of DFT reference calculations, with RMSEs of 0.53 ppm for $^{1}$H, 2.4 ppm for $^{13}$C, and 7.2 ppm for $^{15}$N, compared to DFT values of 0.49 ppm, 2.3 ppm, and 5.8 ppm, respectively.