Table 3 Performances of the proposed PepCNN model and the previous methods on the TE639 test set. The highest values in each column are highlighted in bold..

From: PepCNN deep learning tool for predicting peptide binding residues in proteins using sequence, structural, and language model features

Methods

Sensitivity

Specificity

Precision

MCC

AUC

PepBind13

0.317

–

0.450

0.348

0.767

PepNN-Seq15

–

–

–

0.251

0.792

PepBCL16

0.252

0.983

0.470

0.312

0.804

PepCNN (ours)

0.217

0.986

0.479

0.297

0.826