EquiBoost: An Equivariant Boosting Approach to Molecular Conformation Generation
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_ | 1866912182031089664 |
|---|---|
| author | Yang, Yixuan Fang, Xingyu Cheng, Zhaowen Yan, Pengju Li, Xiaolin |
| author_facet | Yang, Yixuan Fang, Xingyu Cheng, Zhaowen Yan, Pengju Li, Xiaolin |
| contents | Molecular conformation generation plays key roles in computational drug design. Recently developed deep learning methods, particularly diffusion models have reached competitive performance over traditional cheminformatical approaches. However, these methods are often time-consuming or require extra support from traditional methods. We propose EquiBoost, a boosting model that stacks several equivariant graph transformers as weak learners, to iteratively refine 3D conformations of molecules. Without relying on diffusion techniques, EquiBoost balances accuracy and efficiency more effectively than diffusion-based methods. Notably, compared to the previous state-of-the-art diffusion method, EquiBoost improves generation quality and preserves diversity, achieving considerably better precision of Average Minimum RMSD (AMR) on the GEOM datasets. This work rejuvenates boosting and sheds light on its potential to be a robust alternative to diffusion models in certain scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05109 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EquiBoost: An Equivariant Boosting Approach to Molecular Conformation Generation Yang, Yixuan Fang, Xingyu Cheng, Zhaowen Yan, Pengju Li, Xiaolin Machine Learning Chemical Physics Biomolecules Molecular conformation generation plays key roles in computational drug design. Recently developed deep learning methods, particularly diffusion models have reached competitive performance over traditional cheminformatical approaches. However, these methods are often time-consuming or require extra support from traditional methods. We propose EquiBoost, a boosting model that stacks several equivariant graph transformers as weak learners, to iteratively refine 3D conformations of molecules. Without relying on diffusion techniques, EquiBoost balances accuracy and efficiency more effectively than diffusion-based methods. Notably, compared to the previous state-of-the-art diffusion method, EquiBoost improves generation quality and preserves diversity, achieving considerably better precision of Average Minimum RMSD (AMR) on the GEOM datasets. This work rejuvenates boosting and sheds light on its potential to be a robust alternative to diffusion models in certain scenarios. |
| title | EquiBoost: An Equivariant Boosting Approach to Molecular Conformation Generation |
| topic | Machine Learning Chemical Physics Biomolecules |
| url | https://arxiv.org/abs/2501.05109 |