A Machine Learning Model of Chemical Shifts for Chemically
and Structurally Diverse Molecular Solids
Posted on 23.09.2022 - 07:09
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 1H shift predictions (compared to 0.35 ppm for explicit DFT calculations), while reducing the computational cost by over four orders of magnitude.
CITE THIS COLLECTION
Cordova, Manuel; Engel, Edgar A.; Stefaniuk, Artur; Paruzzo, Federico; Hofstetter, Albert; Ceriotti, Michele; et al. (2022): A Machine Learning Model of Chemical Shifts for Chemically and Structurally Diverse Molecular Solids. ACS Publications. Collection. https://doi.org/10.1021/acs.jpcc.2c03854
Select your citation style and then place your mouse over the citation text to select it.
Read the peer-reviewed publication
Edgar A. Engel
local atomic environmentsfinite temperature structuresdensity functional theoryrecently introduced shiftmlpredict chemical shiftsh shift predictionschemically diverse compounds13 molecular solids1 </ supmachine learning modelmolecular solidslearning modelchemical shiftssquared errorsolid materialsmaterials composedkey bottleneckfour ordersenergy geometriesdirect probecomputational costbenchmark set47 ppm35 ppm