Vib2Mol: from vibrational spectra to molecular structures—a unified deep learning framework
8 affiliations
- 1State Key Laboratory of Physical Chemistry of Solid Surfaces, Collaborative Innovation Center of Chemistry for Energy Materials (iChEM), The MOE Key Laboratory of Spectrochemical Analysis & Instrumentation, College of Chemistry and Chemical Engineering, Xiamen University Xiamen 361005 China
- 2Shanghai Innovation Institute Shanghai 200030 China
- 3Tan Kah Kee Innovation Laboratory Xiamen 361005 China
- 4Institute of Artificial Intelligence, Xiamen University Xiamen 361005 China
- 5Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University Xiamen 361005 China
- 6Shanghai Artificial Intelligence Laboratory Shanghai 200000 China
- 7Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, School of Chemistry and Molecular Engineering, East China Normal University Shanghai 200062 China
- 8State Key Laboratory of Marine Environmental Science, Fujian Provincial Key Laboratory for Coastal Ecology and Environmental Studies, Center for Marine Environmental Chemistry & Toxicology, College of the Environment and Ecology, Xiamen University Xiamen Fujian 361102 China
Abstract
There will be a paradigm shift in chemical and biological research, enabled by autonomous, closed-loop, real-time self-directed decision-making experimentation. Spectrum-to-structure correlation, which is to elucidate molecular structures with spectral information, is the core step in understanding experimental results and closing the loop. Recent approaches have sought to bridge retrieval and generation to improve the accuracy of spectral annotation. However, these methods typically rely on fixed workflows that fail to accommodate the broader and more varied demands of spectrum-to-structure analysis, leaving the diverse prior knowledge provided by researchers largely underutilized. In this study, we proposed Vib2Mol, a unified deep learning framework designed to flexibly handle diverse spectrum-to-structure tasks according to the available prior knowledge. Vib2Mol not only achieves state-of-the-art performance in analyzing both theoretical and experimental infrared and Raman spectra across well-established benchmarks, but also demonstrates promising capabilities in elucidating reaction products from mixed spectra and in sequencing peptides from experimental spectra. These results position vibrational spectroscopy as a powerful guide for autonomous scientific discovery.
Related
- cboamd: A Machine Learning Molecular Dynamics Framework for Vibrational Strong Coupling
- Accuracy of Vibrational Properties of Machine-Learning Force Fields for Molecular Crystal Transformations
- Accurate and Rapid Vibrational Spectra of Molecular Crystals from Machine-Learned Interatomic Potentials
- Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
- Tip-Enhanced Vibrational Ladder Climbing in Surface Molecular System
BibTeX
@article{lu2026vib2mol,
title = {{Vib2Mol: from vibrational spectra to molecular structures—a unified deep learning framework}},
author = {Xin-Yu Lu and Hao Ma and Hui Li and Jia Li and Yi Rong and Yu-Qiang Li and Tong Zhu and Guo-Kun Liu and Bin Ren},
journal = {Chemical Science},
year = {2026},
month = sep,
doi = {10.1039/d6sc04559f},
url = {https://doi.org/10.1039/d6sc04559f},
note = {CC BY-NC 3.0},
}
RIS
TY - JOUR
TI - Vib2Mol: from vibrational spectra to molecular structures—a unified deep learning framework
AU - Xin-Yu Lu
AU - Hao Ma
AU - Hui Li
AU - Jia Li
AU - Yi Rong
AU - Yu-Qiang Li
AU - Tong Zhu
AU - Guo-Kun Liu
AU - Bin Ren
PY - 2026
DA - 2026/09/03
JO - Chemical Science
DO - 10.1039/d6sc04559f
UR - https://doi.org/10.1039/d6sc04559f
AB - There will be a paradigm shift in chemical and biological research, enabled by autonomous, closed-loop, real-time self-directed decision-making experimentation. Spectrum-to-structure correlation, which is to elucidate molecular structures with spectral information, is the core step in understanding experimental results and closing the loop. Recent approaches have sought to bridge retrieval and generation to improve the accuracy of spectral annotation. However, these methods typically rely on fixed workflows that fail to accommodate the broader and more varied demands of spectrum-to-structure analysis, leaving the diverse prior knowledge provided by researchers largely underutilized. In this study, we proposed Vib2Mol, a unified deep learning framework designed to flexibly handle diverse spectrum-to-structure tasks according to the available prior knowledge. Vib2Mol not only achieves state-of-the-art performance in analyzing both theoretical and experimental infrared and Raman spectra across well-established benchmarks, but also demonstrates promising capabilities in elucidating reaction products from mixed spectra and in sequencing peptides from experimental spectra. These results position vibrational spectroscopy as a powerful guide for autonomous scientific discovery.
SN - 2041-6520
SN - 2041-6539
ER -