A protein-ligand binding benchmark dataset derived from the Papyrus bioactivity database, augmented with property-matched decoy molecules for evaluating virtual screening and binding prediction models.
This dataset pairs known protein-ligand binders (actives) with synthetically selected decoy molecules — compounds that are physicochemically similar to the actives but are assumed to be non-binders. This setup enables… See the full description on the dataset page:
https://huggingface.co/datasets/Leash-Biosciences/papyrus-decoy-eval.
