NMRTrans: Structure Elucidation from Experimental NMR Spectra via Set Transformers
Year: 2026
Type: conference-paper
Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is fundamental for molecular structure elucidation, yet interpreting spectra at scale remains time-consuming and highly expertise-dependent. While recent spectrum-as-language modeling and retrieval-based methods have shown promise, they rely heavily on large corpora of computed spectra and exhibit notable performance drops when applied to experimental measurements. To address these issues, we build NMRSpec, a large-scale corpus of experimental 1H and 13C NMR spectra mined from chemical literature, and propose NMRTrans, which models spectra as unordered peak sets and aligns the model's inductive bias with the physical nature of NMR. To the best of our knowledge, NMRTrans is the first NMR Transformer trained solely on large-scale experimental spectra and achieves state-of-the-art performance on experimental benchmarks, improving Top-10 Accuracy over the strongest baseline by +17.82 points (61.15% versus 43.33%), and underscoring the importance of experimental data and structure-aware architectures for reliable NMR structure elucidation. Code is released at https://github.com/little1d/NMRTrans.
Authors: Liujia Yang, Zhuo Yang, Jiaqing Xie, Yubin Wang, Ben Gao, Xingjian Wei, Jiaxing Sun, Jiang Wu, Conghui He, Yuqiang Li, Qinying Gu
Language: English
Subfield: Spectroscopy
Field: Chemistry
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7197043142