DiffNMR2: NMR Guided Sampling Acquisition Through Diffusion Model Uncertainty

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.

@article{goffinet2025_2502.05230,
  title={ DiffNMR2: NMR Guided Sampling Acquisition Through Diffusion Model Uncertainty },
  author={ Etienne Goffinet and Sen Yan and Fabrizio Gabellieri and Laurence Jennings and Lydia Gkoura and Filippo Castiglione and Ryan Young and Idir Malki and Ankita Singh and Thomas Launey },
  journal={arXiv preprint arXiv:2502.05230},
  year={ 2025 }
}