DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917611855413248 |
|---|---|
| author | Guan, Jiaqi Zhou, Xiangxin Yang, Yuwei Bao, Yu Peng, Jian Ma, Jianzhu Liu, Qiang Wang, Liang Gu, Quanquan |
| author_facet | Guan, Jiaqi Zhou, Xiangxin Yang, Yuwei Bao, Yu Peng, Jian Ma, Jianzhu Liu, Qiang Wang, Liang Gu, Quanquan |
| contents | Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design and can be less efficient for exploring the large drug-like molecule space. In this paper, inspired by the convention in pharmaceutical practice, we decompose the ligand molecule into two parts, namely arms and scaffold, and propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. In order to facilitate the decomposed generation and improve the properties of the generated molecules, we incorporate both bond diffusion in the model and additional validity guidance in the sampling phase. Extensive experiments on CrossDocked2020 show that our approach achieves state-of-the-art performance in generating high-affinity molecules while maintaining proper molecular properties and conformational stability, with up to -8.39 Avg. Vina Dock score and 24.5 Success Rate. The code is provided at https://github.com/bytedance/DecompDiff |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07902 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design Guan, Jiaqi Zhou, Xiangxin Yang, Yuwei Bao, Yu Peng, Jian Ma, Jianzhu Liu, Qiang Wang, Liang Gu, Quanquan Biomolecules Machine Learning Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design and can be less efficient for exploring the large drug-like molecule space. In this paper, inspired by the convention in pharmaceutical practice, we decompose the ligand molecule into two parts, namely arms and scaffold, and propose a new diffusion model, DecompDiff, with decomposed priors over arms and scaffold. In order to facilitate the decomposed generation and improve the properties of the generated molecules, we incorporate both bond diffusion in the model and additional validity guidance in the sampling phase. Extensive experiments on CrossDocked2020 show that our approach achieves state-of-the-art performance in generating high-affinity molecules while maintaining proper molecular properties and conformational stability, with up to -8.39 Avg. Vina Dock score and 24.5 Success Rate. The code is provided at https://github.com/bytedance/DecompDiff |
| title | DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2403.07902 |