Skip to main content

Table 3 Performance of based models using individual feature and their combination, evaluated by LOOCV

From: Prediction of conformational B-cell epitopes from 3D structures by random forests with a distance-based feature

 

Bound dataset

Unbound dataset

Feature

AUC

F

ACC

SN

SP

AUC

F

ACC

SN

SP

Conservation

0.554

0.186

0.634

0.418

0.660

0.558

0.188

0.604

0.445

0.634

Composition

0.563

0.163

0.747

0.275

0.801

0.566

0.147

0.708

0.244

0.774

Secondary structure

0.510

0.161

0.627

0.297

0.733

0.531

0.167

0.642

0.372

0.690

Accessible area

0.570

0.192

0.593

0.470

0.605

0.618

0.241

0.562

0.616

0.548

ARD

0.589

0.206

0.620

0.487

0.633

0.627

0.243

0.585

0.578

0.588

Combination

0.633

0.227

0.672

0.490

0.692

0.654

0.256

0.608

0.601

0.606

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us