Skip to main content
Figure 2 | BMC Bioinformatics

Figure 2

From: An improved machine learning protocol for the identification of correct Sequest search results

Figure 2

Receiver Operator Curves (ROC) (left) and Precision/Recall Curves (PRC) (right). Classifiers trained with the novel set of features have the suffix all, otherwise the suffix S+P is used (this does not apply to the curve for PeptideProphet shown in the ROC plot). The ROC shows how the TPR varies with the FPR, indicating what percentage of true hits one can expect to obtain at a given false-positive-rate. The PRC given an alternate view of the classification depicting the precision as a function of the recall (note PeptideProphet results only shown in ROC).

Back to article page