Fig. 6From: GNINA 1.0: molecular docking with deep learningComparing the Default CNN Ensemble for use in only rescoring of the poses output by the Monte Carlo chains or the refinement of the poses followed by a rescoring of the poses. The “refine” option has nearly the same docking performance as the “rescore” option when cross-docking. TopN is the percentage of targets ranked above or at N with a RMSD less than 2 ÅBack to article page