Fig. 4From: Predicting variant deleteriousness in non-human species: applying the CADD approach in mouseROC-AUC scores of mCADD models and C-scores evaluated on three different validation sets (a) Fairfield, b) Mutagenetix, c) ClinVar-ESP) lifted from mouse to human. Arabic numbers underneath the bars indicate the number of annotations used for model training. The numbers above the bars show the exact ROC-AUC of that particular model and validation set combinationBack to article page