PPAP
A structure-aware deep learning model for high-accuracy protein-protein binding affinity prediction (Kd).
A deep learning framework that captures protein-protein binding affinity by fusing structural insights with sequence representations. By utilizing an interfacial contact-aware attention mechanism, the model focuses on critical interface residues, leveraging both ESM-based sequence features and AlphaFold-derived structural data to outperform traditional graph-based and sequence-only benchmarks.
Estimated resource cost: 0.0002945
Categories: Protein Design
Tags: Affinity Prediction Proteins
Key Capabilities
- Integrates AlphaFold structural insights with ESM sequence representations.
- Employs an interfacial contact-aware attention mechanism to prioritize interaction residues.
- Achieves high correlation (R = 0.63) on external benchmarks, outperforming sequence-based LLMs.
- Proven to enhance protein binder design enrichment by up to 10-fold compared to AlphaFold-Multimer metrics.
Runtime Statistics
| Metric | Value |
|---|---|
| runtime_mean | 84 |
| runtime_median | 53 |
| runtime_std | 165 |
| runtime_90th_percentile | 121 |
| runtime_max | 1366 |
Similar Tools
- BindFilter
- EvoEF2
- EvoEF2 Mutant Stability Analysis
- ImaPEp Antibody-Antigen Binding Prediction
Ready to submit your job?
Review your configuration, then confirm the estimated credit cost before you run the job. Note that credit estimates are not guaranteed and runtime can vary depending on inputs and settings.
Estimated Credits: 0.0002945
Invite-only, limited-time access. Please contact ztang@getantibody.com.
Invite-only, limited-time access. Please contact ztang@getantibody.com.