Model for pdbbind_binding_affinity¶
- Description: This is a benchmark to evaluate how accurately an AI model can predict the protein-ligand binding affinity using the PDBbind dataset. The dataset contains different types of protein-ligand complexes. Here we use mean absolute error (MAE) to compare models with respect to experimental accuracy.
Reference(s): https://github.com/atomgptlab/jarvis_leaderboard, https://doi.org/10.1021/jm030580l, https://github.com/atomgptlab/alignn
Model benchmarks
| Model name | Dataset | MAE | Team name | Dataset size | Date submitted | Notes |
|---|---|---|---|---|---|---|
| alignn2_radius | pdbbind | 1.5833 | AtomGPTLab | 11889 | 07-30-2026 | CSV, JSON, run.sh, Info |
| baseline_mean | pdbbind | 1.5136 | AtomGPTLab | 11889 | 07-31-2026 | CSV, JSON, run.sh, Info |
| alignn2_knn | pdbbind | 2.7265 | AtomGPTLab | 11889 | 07-30-2026 | CSV, JSON, run.sh, Info |