Hello organizers, Could you clarify how many distinct chemical series (per the Kruger et al. definition used for evaluation) the ~245 validation-set hits span in total? Knowing whether the hits are concentrated in a small number of series or spread across many would help participants understand whether low N_clusters reflects limited selection diversity or the underlying distribution of the hit set itself. Thank you, Mohamed Mahmoud

Created by Mohamed Mahmoud mohamed1313
Hello @mohamed1313, both the validation set and the test set contain more than 50 chemical series or individual hits not assigned to any larger chemical series (each hit represents its own chemical series). A submission could theoretically include 50 different chemical series. Luca

Number of distinct chemical series among validation set hits page is loading…