Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913371200159744 |
|---|---|
| author | Stärk, Hannes Jing, Bowen Barzilay, Regina Jaakkola, Tommi |
| author_facet | Stärk, Hannes Jing, Bowen Barzilay, Regina Jaakkola, Tommi |
| contents | A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket's discrete residue types and the molecule's binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_05764 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design Stärk, Hannes Jing, Bowen Barzilay, Regina Jaakkola, Tommi Machine Learning Artificial Intelligence A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket's discrete residue types and the molecule's binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches. |
| title | Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2310.05764 |