Rull Herman, Fischer Markus, Kuhn Stefan
Department of Computer Science, Tartu University, Narva mnt 18, Tartu, 51009, Tartumaa, Estonia.
Institute for Medical Physics and Biophysics, Leipzig University, Härtelstr. 16-18, 04107, Leipzig, Sachsen, Germany.
J Cheminform. 2023 Nov 27;15(1):114. doi: 10.1186/s13321-023-00785-x.
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 that is able to achieve better results than other models for relevant datasets with comparatively low amounts of data. We show this by predicting [Formula: see text] and [Formula: see text] NMR chemical shifts of small molecules in specific solvents.
使用机器学习方法预测核磁共振（NMR）中的化学位移通常会使用尽可能多的数据以获得最佳结果。在某些情况下，无法获取如此大量的数据，例如对于异核而言。我们展示了一种新颖的机器学习模型，对于数据量相对较少的相关数据集，该模型能够比其他模型取得更好的结果。我们通过预测特定溶剂中小分子的[化学式：见原文]和[化学式：见原文] NMR化学位移来证明这一点。
