Improvement over naïve prediction. Improvement in AUC of using an SVM for classification for cross-validated tests over Top−F1. The colors in each cell correspond to the difference in AUC between using an SVM for prediction and using the top-performing feature per source, per label. Higher values indicate cases where there is added benefit in considering multiple features via SVMs.
Cadag et al. BMC Bioinformatics 2012 13:321 doi:10.1186/1471-2105-13-321