DiffNMR2: NMR Guided Sampling Acquisition Through Diffusion Model Uncertainty

2025-02-06

AI Summary

To address the prohibitively long acquisition time for high-resolution protein NMR spectra, this paper proposes a diffusion-model uncertainty-guided iterative undersampling reconstruction framework. The method introduces a novel closed-loop optimization paradigm that dynamically adapts k-space sampling and reconstruction by leveraging the predictive variance of a conditional diffusion model as a data-driven confidence signal—marking the first such use in NMR. It jointly integrates a protein-NMR-specific conditional diffusion prior, uncertainty quantification, iterative reconstruction, and active sampling update. Evaluated on real protein datasets, the approach achieves a 52.9% improvement in PSNR and a 55.6% reduction in spurious peaks compared to the state-of-the-art, while reducing total acquisition time for complex multidimensional experiments by 60%. These advances significantly enhance both the throughput and reliability of NMR-based protein structure determination.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• Reduces NMR acquisition time
• Improves spectral reconstruction accuracy
• Decreases hallucinated peaks in NMR

Innovation

• Diffusion model guides NMR sampling
• Reduces NMR acquisition time significantly
• Improves reconstruction accuracy and reduces errors