DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908630750593024 |
|---|---|
| author | Wang, Liang Rong, Yu Xu, Tingyang Zhong, Zhenyi Liu, Zhiyuan Wang, Pengju Zhao, Deli Liu, Qiang Wu, Shu Wang, Liang Zhang, Yang |
| author_facet | Wang, Liang Rong, Yu Xu, Tingyang Zhong, Zhenyi Liu, Zhiyuan Wang, Pengju Zhao, Deli Liu, Qiang Wu, Shu Wang, Liang Zhang, Yang |
| contents | Molecular structure elucidation from spectra is a fundamental challenge in molecular science. Conventional approaches rely heavily on expert interpretation and lack scalability, while retrieval-based machine learning approaches remain constrained by limited reference libraries. Generative models offer a promising alternative, yet most adopt autoregressive architectures that overlook 3D geometry and struggle to integrate diverse spectral modalities. In this work, we present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process, directly inferring 2D and 3D molecular structures from multi-modal spectra using diffusion models. Its denoising network is parameterized by the Diffusion Molecule Transformer, an SE(3)-equivariant architecture for geometric modeling, conditioned by SpecFormer, a Transformer-based spectral encoder capturing multi-modal spectral dependencies. Extensive experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy. Its performance benefits substantially from 3D geometric modeling, SpecFormer pre-training, and multi-modal conditioning. To our knowledge, DiffSpectra is the first framework that unifies multi-modal spectral reasoning and joint 2D/3D generative modeling for de novo molecular structure elucidation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models Wang, Liang Rong, Yu Xu, Tingyang Zhong, Zhenyi Liu, Zhiyuan Wang, Pengju Zhao, Deli Liu, Qiang Wu, Shu Wang, Liang Zhang, Yang Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics Molecular Networks Molecular structure elucidation from spectra is a fundamental challenge in molecular science. Conventional approaches rely heavily on expert interpretation and lack scalability, while retrieval-based machine learning approaches remain constrained by limited reference libraries. Generative models offer a promising alternative, yet most adopt autoregressive architectures that overlook 3D geometry and struggle to integrate diverse spectral modalities. In this work, we present DiffSpectra, a generative framework that formulates molecular structure elucidation as a conditional generation process, directly inferring 2D and 3D molecular structures from multi-modal spectra using diffusion models. Its denoising network is parameterized by the Diffusion Molecule Transformer, an SE(3)-equivariant architecture for geometric modeling, conditioned by SpecFormer, a Transformer-based spectral encoder capturing multi-modal spectral dependencies. Extensive experiments demonstrate that DiffSpectra accurately elucidates molecular structures, achieving 40.76% top-1 and 99.49% top-10 accuracy. Its performance benefits substantially from 3D geometric modeling, SpecFormer pre-training, and multi-modal conditioning. To our knowledge, DiffSpectra is the first framework that unifies multi-modal spectral reasoning and joint 2D/3D generative modeling for de novo molecular structure elucidation. |
| title | DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics Molecular Networks |
| url | https://arxiv.org/abs/2507.06853 |