Rectified Flow For Structure Based Drug Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917853410623488 |
|---|---|
| author | Zhang, Daiheng Gong, Chengyue Liu, Qiang |
| author_facet | Zhang, Daiheng Gong, Chengyue Liu, Qiang |
| contents | Deep generative models have achieved tremendous success in structure-based drug design in recent years, especially for generating 3D ligand molecules that bind to specific protein pocket. Notably, diffusion models have transformed ligand generation by providing exceptional quality and creativity. However, traditional diffusion models are restricted by their conventional learning objectives, which limit their broader applicability. In this work, we propose a new framework FlowSBDD, which is based on rectified flow model, allows us to flexibly incorporate additional loss to optimize specific target and introduce additional condition either as an extra input condition or replacing the initial Gaussian distribution. Extensive experiments on CrossDocked2020 show that our approach could achieve state-of-the-art performance on generating high-affinity molecules while maintaining proper molecular properties without specifically designing binding site, with up to -8.50 Avg. Vina Dock score and 75.0% Diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rectified Flow For Structure Based Drug Design Zhang, Daiheng Gong, Chengyue Liu, Qiang Machine Learning Computational Engineering, Finance, and Science Deep generative models have achieved tremendous success in structure-based drug design in recent years, especially for generating 3D ligand molecules that bind to specific protein pocket. Notably, diffusion models have transformed ligand generation by providing exceptional quality and creativity. However, traditional diffusion models are restricted by their conventional learning objectives, which limit their broader applicability. In this work, we propose a new framework FlowSBDD, which is based on rectified flow model, allows us to flexibly incorporate additional loss to optimize specific target and introduce additional condition either as an extra input condition or replacing the initial Gaussian distribution. Extensive experiments on CrossDocked2020 show that our approach could achieve state-of-the-art performance on generating high-affinity molecules while maintaining proper molecular properties without specifically designing binding site, with up to -8.50 Avg. Vina Dock score and 75.0% Diversity. |
| title | Rectified Flow For Structure Based Drug Design |
| topic | Machine Learning Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2412.01174 |