activity endpoints with 4 dataset strategies and 25 model settings.
TPDB Benchmark
Benchmark Overview
A peptide-focused benchmark covering classification, regression, standardized splits, and model-ready downloads.
property endpoints covering Caco-2 permeability, half-life, and PAMPA.
metrics across classification and regression for side-by-side comparison.
downloadable benchmark CSV files for reuse.
Cross-Distribution Performance and MS Training
High matched scores do not guarantee generalization
Matched0.885
→
Cross-distribution0.592
Mean ROC-AUC falls when the negative-sample construction changes.
More consistent performance with MS training
0.826MS mean ROC-AUC
Mixed-source training shows less variation across the three test schemes.