HEDGEHOG: Hierarchical Evaluation of Drug Generators Through Rigorous Filtration

תקציר מקורי באנגליתarXiv:2607.13155v2 Announce Type: replace Abstract: Generative molecular models can support early drug discovery by proposing new candidate compounds de novo. In practice, useful candidates must balance target-relevant activity, physicochemical properties, and other multiparameter design constraints. However, standard metrics commonly used to evaluate molecular generators only weakly reflect whether the generated compounds are medicinally plausible and suitable for downstream computation. This can produce an incomplete view of model performance and inefficient use of computational resources. We introduce HEDGEHOG, a unified six-stage filtration benchmark that is constructed as a hit identification workflow: (i) preprocessing; (ii) physicochemical descriptor screening; (iii) structural aler