Rapid prediction of NMR spectral properties with quantified uncertainty

Abstract

Abstract 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 $${^1\mathrm{H}}$$ 1H and $${^{13}\mathrm{C}}$$ 13C nuclei which exceeds DFT-accessible accuracy for $${^{13}\mathrm{C}}$$ 13C and $${^1\mathrm{H}}$$ 1H 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.

Keywords

• NMR
• Machine learning
• DFT