Flow-Matching Based Refiner for Molecular Conformer Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908578070134784 |
|---|---|
| author | Xu, Xiangyang Gao, Hongyang |
| author_facet | Xu, Xiangyang Gao, Hongyang |
| contents | Low-energy molecular conformers generation (MCG) is a foundational yet challenging problem in drug discovery. Denoising-based methods include diffusion and flow-matching methods that learn mappings from a simple base distribution to the molecular conformer distribution. However, these approaches often suffer from error accumulation during sampling, especially in the low SNR steps, which are hard to train. To address these challenges, we propose a flow-matching refiner for the MCG task. The proposed method initializes sampling from mixed-quality outputs produced by upstream denoising models and reschedules the noise scale to bypass the low-SNR phase, thereby improving sample quality. On the GEOM-QM9 and GEOM-Drugs benchmark datasets, the generator-refiner pipeline improves quality with fewer total denoising steps while preserving diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04878 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Flow-Matching Based Refiner for Molecular Conformer Generation Xu, Xiangyang Gao, Hongyang Machine Learning Quantitative Methods Low-energy molecular conformers generation (MCG) is a foundational yet challenging problem in drug discovery. Denoising-based methods include diffusion and flow-matching methods that learn mappings from a simple base distribution to the molecular conformer distribution. However, these approaches often suffer from error accumulation during sampling, especially in the low SNR steps, which are hard to train. To address these challenges, we propose a flow-matching refiner for the MCG task. The proposed method initializes sampling from mixed-quality outputs produced by upstream denoising models and reschedules the noise scale to bypass the low-SNR phase, thereby improving sample quality. On the GEOM-QM9 and GEOM-Drugs benchmark datasets, the generator-refiner pipeline improves quality with fewer total denoising steps while preserving diversity. |
| title | Flow-Matching Based Refiner for Molecular Conformer Generation |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2510.04878 |