Skip to main content
Fig. 5 | BMC Bioinformatics

Fig. 5

From: Comprehensive study of semi-supervised learning for DNA methylation-based supervised classification of central nervous system tumors

Fig. 5

ROC and threshold analysis of SETRED-SVM model for classifiable and non-classifiable methylation subclass (MC) cases. A ROC analysis of maximal raw (red) and maximal calibrated (blue) predicted scores with the area under the curve (AUC) and the corresponding specificity and sensitivity that maximized the Youden Index. B Specificity, sensitivity (recall), and precision at different thresholds using calibrated scores. The black vertical line represents the suggested threshold (≥ 0.8) at which we had the best balance between sensitivity and specificity using calibrated scores

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us