Fig. 3
From: Machine learning-based predictions of dietary restriction associations across ageing-related genes
Summary of ML methods. A Selection of each possible {Dataset, ML algorithm} model. B Evaluation of each model through the nested-CV. Only 5 outer folds are depicted to facilitate visualization. C Comparison of the predictive power of all the {Dataset, ML algorithm} models using Gmean and AUC. D Computation of feature importance analysis in the two best performing models from different datasets. E Construction of the DR-annotations and the DR-probability vectors. F Possible DR-related inference from \(Ageing_{{{\text{NotDR}}}}\)-related genes strongly predicted as DR-related. TN, TP, FN and FP refer to True Negatives, True Positives, False Negatives and False Positives, respectively