Machine learning in NMR spectroscopy
Piotr Klukowski, Roland Riek, Peter Güntert
Abstract
NMR spectroscopy is a versatile technique for studies of molecular structures, dynamic processes, and intermolecular interactions across a broad range of systems, including small molecules, macromolecules, biomolecular assemblies, and materials in both solution and solid-state environments. As the complexity of NMR studies continues to pose challenges for practitioners, the integration of machine learning is recognized as a promising research direction for improving data acquisition, processing, and analysis. Here, we summarize recent findings in this area, highlighting common applications such as signal detection, chemical shift assignment, structure determination, chemical shift prediction, non-uniform sampling reconstruction, and denoising. For each of these applications, we discuss machine learning methods, design choices, and key publicly available data repositories. We conclude by identifying major trends and emerging directions at the intersection of machine learning and NMR spectroscopy that could help advance research in the field.