Aug 2026· Analytical Chemistry· Vol 98 32, pp.
23717-23725
· 0 citations· 17 references
Medicine
TL;DR
PINS (Physics-Informed NMR Structure elucidation model), a generative framework that explicitly bridges the gap between spectral data and molecular topology by enforcing multiphysical priors, provides a trustworthy, automated strategy for decoding novel chemical structures in data-scarce regimes.
Abstract
1D Nuclear Magnetic Resonance (NMR) spectra offer a rapid and accessible alternative to time-consuming 2D experiments, making them ideal for high-throughput structure elucidation. However, reconstructing molecular topology solely from 1D NMR spectral data remains a formidable combinatorial challenge. This difficulty arises from the loss of explicit atomic connectivity information, and existing data-driven models generate chemically invalid or hallucinated structures. Here, we present PINS (Physics-Informed NMR Structure elucidation model), a generative framework that explicitly bridges the gap between spectral data and molecular topology by enforcing multiphysical priors. By constraining the generative search space within strict physical laws, PINS effectively mitigates structural hallucinations and helps resolve structural ambiguities compared with end-to-end deep learning models. PINS achieves 100% chemical validity and surpasses the state-of-the-art (SOTA) baseline by a substantial margin of 21.6 percentage points (a 68.9% relative improvement). Furthermore, PINS demonstrates robust extrapolation capabilities on novel molecular scaffolds within the specific domain of challenging new psychoactive substances (NPS), achieving an 89.7% identification rate in forensic scenarios. Our findings underscore the necessity of physical constraints in generative AI, providing a trustworthy, automated strategy for decoding novel chemical structures in data-scarce regimes.
MolDeTr addresses the spectrum-conditioned inverse problem and extracts spin-system parameters directly from measured 1D 1H NMR spectra, thereby substantially improving chemical-shift prediction precision by one to 2 orders of magnitude compared to existing structure-conditioned approaches.
N. Schmid, Marc Wanner, G. Fischetti et al.· Analytical Chemistry· 1 citation
Determining molecular structures from spectroscopic data remains fundamentally challenging because the inverse problem is intrinsically underdetermined: individual spectra are sparse, low-dimensional, and encode only partial structural evidence relative to the vast space of possible molecules. We address this challenge by formulating automated structure elucidation as a scalable hypothesis-refinement paradigm that tightly integrates spectral evidence with large-scale molecular priors. To supply structure-resolving NMR signals for multimodal learning, we construct \textbf{QM9SPIN}, a DFT-derived dataset comprising diverse 1D and 2D spectra, including J-coupling, DEPT experiments, and explicit spin--spin interactions. On this foundation, we introduce \textbf{SpectroMol}, a spectrum-to-structure model that proposes chemically valid molecular hypotheses conditioned on multimodal spectral inputs. Complementarily, we develop \textbf{MS-Mol2Mol}, a high-resolution mass-constrained molecular generator that integrates molecular formula, exact mass, and degree of unsaturation within a conditional generative prior trained on 400 million molecules, ensuring global compositional consistency and chemically realistic refinement. The integrated system achieves 93.8\% top-1 accuracy on the simulated benchmark, adapts effectively from simulated to experimental spectra with limited experimental fine-tuning, and further improves experimental predictions through mass-guided refinement, establishing a scalable route toward automated, data-driven organic structure elucidation.
Chengchun Liu, Zhiyuan Yan, Li Yuan et al.· 0 citations
Uni-XAS is presented, a unified benchmark and learning framework that reframes bidirectional XAS modeling as a cross-modal alignment and conditional generation problem, and introduces Permutation-Rectified Flow Matching, which integrates type-wise optimal transport into a continuous generative flow to provide a principled solution to ligand permutation ambiguity without relying on heavy high-order equivariant architectures.
Suyang Zhong, Yuhao Zhao, Boying Huang et al.· 0 citations
Semantics-Preserving Exploratory Sampling (SPES), which integrates Graph Laplacian Spectral Noise to respect chain connectivity and Conditional Freedom Modulation to dynamically balance exploration with fidelity, enables diversity-enhanced generation without sacrificing geometric validity under the reported structural metrics, improving the empirical exploration--fidelity trade-off.
Zhihua Tian, Jiale Zhou, Rubo Wang et al.· Proceedings of the 32nd ACM...· 0 citations
Nuclear Magnetic Resonance spectroscopy is the gold standard for molecular structure elucidation, yet interpreting complex spectra for unknown molecules remains a bottleneck reliant on human expertise, so NMRAgent establishes a new paradigm for interpretable AI in analytical chemistry.
Zheng Fang, Yang Chen, Yusen Tan et al.· arXiv.org· 0 citations
A manually verified, solvent-annotated 11B NMR data set constructed via a large language model (LLM)-assisted workflow provides a form of virtual spectral resolution, enabling the discrimination of chemically inequivalent boron sites that are difficult to resolve experimentally.
Penghui Li, Ben Gao, Shiyang Wang et al.· JACS Au· 0 citations