Skip to main content


Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Fig. 2 | Source Code for Biology and Medicine

Fig. 2

From: PROPER: Performance visualization for optimizing and comparing ranking classifiers in MATLAB

Fig. 2

PROPER applied in performance visualization, optimization and comparisons of scoring classifiers on structural genomics data. a-d optimizing structure of ANN by different training algorithms: a an example of three-dimensional performance curve where each facet represents a standard two-dimensional performance curve, e.g. b precision-recall curve, c ROC curve, and d PPV-FPR curve. e-h comparing performance of three different scoring classifiers: e three-dimensional combination of performance curves where each facet represents a two-dimensional performance curve; f MCC against Accuracy; g MCC against cutoff, and h Accuracy against cutoff. According to this result, ANN is a stronger predictor with the highest MCC and accuracy. In this figure, ROC, MCC, TPR, FPR, and PPV represent Receiver Operating Characteristic, Matthews Correlation Coefficient, sensitivity, False Positive Rate, and Positive Predictive Value, respectively

Back to article page