DiffNMR2: NMR Guided Sampling Acquisition Through Diffusion Model Uncertainty
This addresses a critical bottleneck in NMR spectroscopy for applications like drug discovery and materials science, representing a strong domain-specific advancement rather than a foundational breakthrough.
The paper tackles the bottleneck of long acquisition times in high-resolution NMR spectroscopy for complex biological samples like proteins by proposing a diffusion model-based sub-sampling strategy that uses model uncertainty to guide sampling. The method improves reconstruction accuracy by 52.9%, reduces hallucinated peaks by 55.6%, and requires 60% less time compared to state-of-the-art approaches.
Nuclear Magnetic Resonance (NMR) spectrometry uses electro-frequency pulses to probe the resonance of a compound's nucleus, which is then analyzed to determine its structure. The acquisition time of high-resolution NMR spectra remains a significant bottleneck, especially for complex biological samples such as proteins. In this study, we propose a novel and efficient sub-sampling strategy based on a diffusion model trained on protein NMR data. Our method iteratively reconstructs under-sampled spectra while using model uncertainty to guide subsequent sampling, significantly reducing acquisition time. Compared to state-of-the-art strategies, our approach improves reconstruction accuracy by 52.9\%, reduces hallucinated peaks by 55.6%, and requires 60% less time in complex NMR experiments. This advancement holds promise for many applications, from drug discovery to materials science, where rapid and high-resolution spectral analysis is critical.