PPFlow: Target-aware Peptide Design with Torsional Flow Matching
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929620265205760 |
|---|---|
| author | Lin, Haitao Zhang, Odin Zhao, Huifeng Jiang, Dejun Wu, Lirong Liu, Zicheng Huang, Yufei Li, Stan Z. |
| author_facet | Lin, Haitao Zhang, Odin Zhao, Huifeng Jiang, Dejun Wu, Lirong Liu, Zicheng Huang, Yufei Li, Stan Z. |
| contents | Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called \textsc{PPFlow}, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06642 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PPFlow: Target-aware Peptide Design with Torsional Flow Matching Lin, Haitao Zhang, Odin Zhao, Huifeng Jiang, Dejun Wu, Lirong Liu, Zicheng Huang, Yufei Li, Stan Z. Biomolecules Artificial Intelligence Machine Learning Therapeutic peptides have proven to have great pharmaceutical value and potential in recent decades. However, methods of AI-assisted peptide drug discovery are not fully explored. To fill the gap, we propose a target-aware peptide design method called \textsc{PPFlow}, based on conditional flow matching on torus manifolds, to model the internal geometries of torsion angles for the peptide structure design. Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design and to allow the training of deep learning methods. Extensive experiments show that PPFlow reaches state-of-the-art performance in tasks of peptide drug generation and optimization in comparison with baseline models, and can be generalized to other tasks including docking and side-chain packing. |
| title | PPFlow: Target-aware Peptide Design with Torsional Flow Matching |
| topic | Biomolecules Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.06642 |