Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Proposal of supervised data analysis strategy of plasma miRNAs from hybridisation array data with an application to assess hemolysis-related deregulation

Fig. 2

Results of the second step of class prediction performed in the training set raw andratio data. ‘ROC space’ plot representing the classification performance of different models for class prediction in terms of false positive rate (FPR) and true positive rate (TPR) in the training set raw data (left panel) and ratio data (right panel). As true for the ROC curves, ideal models are those closest to the point (0,1), corresponding to 100 % sensitivity and specificity.

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us