Pi-SAGE: Permutation-invariant surface-aware graph encoder for binding affinity prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916878990966784 |
|---|---|
| author | Banerjee, Sharmi Karimi, Mostafa Yilmaz, Melih Jaakkola, Tommi Dubrov, Bella Shang, Shang Benson, Ron |
| author_facet | Banerjee, Sharmi Karimi, Mostafa Yilmaz, Melih Jaakkola, Tommi Dubrov, Bella Shang, Shang Benson, Ron |
| contents | Protein surface fingerprint encodes chemical and geometric features that govern protein-protein interactions and can be used to predict changes in binding affinity between two protein complexes. Current state-of-the-art models for predicting binding affinity change, such as GearBind, are all-atom based geometric models derived from protein structures. Although surface properties can be implicitly learned from the protein structure, we hypothesize that explicit knowledge of protein surfaces can improve a structure-based model's ability to predict changes in binding affinity. To this end, we introduce Pi-SAGE, a novel Permutation-Invariant Surface-Aware Graph Encoder. We first train Pi-SAGE to create a protein surface codebook directly from the structure and assign a token for each surface-exposed residue. Next, we augment the node features of the GearBind model with surface features from domain-adapted Pi-SAGE to predict binding affinity change on the SKEMPI dataset. We show that explicitly incorporating local, context-aware chemical properties of residues enhances the predictive power of all-atom graph neural networks in modeling binding affinity changes between wild-type and mutant proteins. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01924 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pi-SAGE: Permutation-invariant surface-aware graph encoder for binding affinity prediction Banerjee, Sharmi Karimi, Mostafa Yilmaz, Melih Jaakkola, Tommi Dubrov, Bella Shang, Shang Benson, Ron Biomolecules Protein surface fingerprint encodes chemical and geometric features that govern protein-protein interactions and can be used to predict changes in binding affinity between two protein complexes. Current state-of-the-art models for predicting binding affinity change, such as GearBind, are all-atom based geometric models derived from protein structures. Although surface properties can be implicitly learned from the protein structure, we hypothesize that explicit knowledge of protein surfaces can improve a structure-based model's ability to predict changes in binding affinity. To this end, we introduce Pi-SAGE, a novel Permutation-Invariant Surface-Aware Graph Encoder. We first train Pi-SAGE to create a protein surface codebook directly from the structure and assign a token for each surface-exposed residue. Next, we augment the node features of the GearBind model with surface features from domain-adapted Pi-SAGE to predict binding affinity change on the SKEMPI dataset. We show that explicitly incorporating local, context-aware chemical properties of residues enhances the predictive power of all-atom graph neural networks in modeling binding affinity changes between wild-type and mutant proteins. |
| title | Pi-SAGE: Permutation-invariant surface-aware graph encoder for binding affinity prediction |
| topic | Biomolecules |
| url | https://arxiv.org/abs/2508.01924 |