Fig. 8From: Explainable uncertainty quantifications for deep learning-based molecular property predictionEpistemic uncertainty distributions of QM9 testing data calculated with (A) the base model and (B) the nitrogen-ignorant model. The testing data are grouped by the number of nitrogen atoms in the molecule. The molecules without nitrogen atoms are denoted as 0Â N, molecules containing one nitrogen atom are denoted as 1Â N, and so onBack to article page