NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization

2025-08-30

AI Summary

Structural elucidation of unknown organic molecules from NMR spectra remains heavily reliant on expert interpretation, while existing computational approaches are hindered by algorithmic limitations and scarcity of high-quality labeled spectral data. Method: We propose a physics-guided, interpretable AI framework that synergistically integrates large-scale spectral matching with atom-level NMR chemical shift–driven fragment optimization, jointly embedding deep learning and quantum-chemical constraints. Contribution/Results: The method enables end-to-end structural prediction from ¹H/¹³C NMR spectra alone. It demonstrates strong generalization and robustness across synthetic benchmarks, literature-reported cases, and real experimental datasets. Notably, it significantly improves automation accuracy and reliability for complex and novel molecules—particularly in challenging inverse-structure problems—thereby establishing a new paradigm for data-efficient, physically grounded molecular structure determination.

Technology Category

• Machine Learning: Structured Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Nuclear Magnetic Resonance (NMR) spectroscopy is one of the most powerful and widely used tools for molecular structure elucidation in organic chemistry. However, the interpretation of NMR spectra to determine unknown molecular structures remains a labor-intensive and expertise-dependent process, particularly for complex or novel compounds. Although recent methods have been proposed for molecular structure elucidation, they often underperform in real-world applications due to inherent algorithmic limitations and limited high-quality data. Here, we present NMR-Solver, a practical and interpretable framework for the automated determination of small organic molecule structures from $^1$H and $^{13}$C NMR spectra. Our method introduces an automated framework for molecular structure elucidation, integrating large-scale spectral matching with physics-guided fragment-based optimization that exploits atomic-level structure-spectrum relationships in NMR. We evaluate NMR-Solver on simulated benchmarks, curated experimental data from the literature, and real-world experiments, demonstrating its strong generalization, robustness, and practical utility in challenging, real-life scenarios. NMR-Solver unifies computational NMR analysis, deep learning, and interpretable chemical reasoning into a coherent system. By incorporating the physical principles of NMR into molecular optimization, it enables scalable, automated, and chemically meaningful molecular identification, establishing a generalizable paradigm for solving inverse problems in molecular science.

Problem

• Automating molecular structure determination from NMR spectra
• Overcoming labor-intensive expert-dependent spectral interpretation
• Integrating spectral matching with physics-guided fragment optimization

Innovation

• Large-scale spectral matching for structure elucidation
• Physics-guided fragment optimization technique
• Atomic-level structure-spectrum relationship exploitation