NMR shift prediction from small data quantities
This work addresses a practical challenge in chemistry for researchers dealing with limited NMR data, though it appears incremental as it adapts machine learning to a specific data-scarce scenario.
The paper tackled the problem of predicting NMR chemical shifts when only small datasets are available, such as for heteronuclei, by introducing a novel machine learning model that achieved good results with low data quantities, specifically demonstrating this for 19F and 13C NMR shifts of small molecules in specific solvents.
Prediction of chemical shift in NMR using machine learning methods is typically done with the maximum amount of data available to achieve the best results. In some cases, such large amounts of data are not available, e.g. for heteronuclei. We demonstrate a novel machine learning model which is able to achieve good results with comparatively low amounts of data. We show this by predicting 19F and 13C NMR chemical shifts of small molecules in specific solvents.