Cordova Manuel, Engel Edgar A, Stefaniuk Artur, Paruzzo Federico, Hofstetter Albert, Ceriotti Michele, Emsley Lyndon
Laboratory of Magnetic Resonance, Institute of Chemical Sciences and Engineering, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.
National Centre for Computational Design and Discovery of Novel Materials MARVEL, Ecole Polytechnique Fédérale de Lausanne, Lausanne CH-1015, Switzerland.
J Phys Chem C Nanomater Interfaces. 2022 Oct 6;126(39):16710-16720. doi: 10.1021/acs.jpcc.2c03854. Epub 2022 Sep 23.
Nuclear magnetic resonance (NMR) chemical shifts are a direct probe of local atomic environments and can be used to determine the structure of solid materials. However, the substantial computational cost required to predict accurate chemical shifts is a key bottleneck for NMR crystallography. We recently introduced ShiftML, a machine-learning model of chemical shifts in molecular solids, trained on minimum-energy geometries of materials composed of C, H, N, O, and S that provides rapid chemical shift predictions with density functional theory (DFT) accuracy. Here, we extend the capabilities of ShiftML to predict chemical shifts for both finite temperature structures and more chemically diverse compounds, while retaining the same speed and accuracy. For a benchmark set of 13 molecular solids, we find a root-mean-squared error of 0.47 ppm with respect to experiment for H shift predictions (compared to 0.35 ppm for explicit DFT calculations), while reducing the computational cost by over four orders of magnitude.
核磁共振（NMR）化学位移是局部原子环境的直接探针，可用于确定固体材料的结构。然而，预测精确化学位移所需的巨大计算成本是NMR晶体学的一个关键瓶颈。我们最近推出了ShiftML，这是一种分子固体化学位移的机器学习模型，它基于由C、H、N、O和S组成的材料的最低能量几何结构进行训练，能够以密度泛函理论（DFT）的精度快速预测化学位移。在这里，我们扩展了ShiftML的功能，以预测有限温度结构和化学性质更多样化的化合物的化学位移，同时保持相同的速度和精度。对于一组包含13种分子固体的基准测试，我们发现H位移预测相对于实验的均方根误差为0.47 ppm（相比之下，显式DFT计算的均方根误差为0.35 ppm），同时将计算成本降低了四个数量级以上。
