Rapid prediction of NMR spectral properties with quantified uncertainty

Accurate calculation of specific spectral properties for NMR is an important step for molecular structure elucidation. Here we report the development of a novel machine learning technique for accurately predicting chemical shifts of both H-1 and C-13 nuclei which exceeds DFT-accessible accuracy for C-13 and H-1 for a subset of nuclei, while being orders of magnitude more performant. Our method produces estimates of uncertainty, allowing for robust and confident predictions, and suggests future avenues for improved performance.