PAMNet

Reported on 4 benchmarks across 4 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical3 results

Drug DiscoveryonQM9
Error ratio· 2023-11-19
0.363
SOTA
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems arXiv:2311.11228
Protein-Ligand Affinity PredictiononPDBbind
RMSE· 2023-11-19
1.263
best: 1.211 (PLAPT)
SOTA
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems arXiv:2311.11228
Atomistic DescriptiononQM9
MAE· 2023-11-19
0.136
best: 0.00467 (Uni-Mol)
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems arXiv:2311.11228

Miscellaneous1 result

Formation EnergyonQM9
MAE· 2023-11-19
0.136
best: 0.09 (TensorNet)
A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems arXiv:2311.11228