Skip to main content

Table 2 Performance comparisons on independent test dataset for the universal manifold ranking and SVM-based ranking

From: In-silico prediction of blood-secretory human proteins using a ranking algorithm

 

MR

SVM

AUC

0.6663

0.6592

  1. (Both rankings were performed with a different dataset as training set, evaluated by AUC of recall-precision curve. Parameter setting: σ = 2.7003 and α = 0.5. MR: Manifold ranking; SVM: SVM-based ranking)