ECFP + LightGBM

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Graphs2 results

Graph RegressiononPeptides-struct
MAE· 2025-01-29
0.2432
SOTA
Molecular Fingerprints Are Strong Models for Peptide Function Prediction arXiv:2501.17901
Graph ClassificationonPeptides-func
AP· 2025-01-29
0.746
best: 0.7479 (ESA + RWSE (Edge set attention, Random Walk Structural Encoding, + validation set))
Molecular Fingerprints Are Strong Models for Peptide Function Prediction arXiv:2501.17901

Methodology1 result

ClassificationonPeptides-func
AP· 2025-01-29
0.746
best: 0.7479 (ESA + RWSE (Edge set attention, Random Walk Structural Encoding, + validation set))
Molecular Fingerprints Are Strong Models for Peptide Function Prediction arXiv:2501.17901