Skip to main content

Table 3 Performance evaluation of each method in the ACP dataset

From: DeepBP: Ensemble deep learning strategy for bioactive peptide prediction

Method

ACC

Sn

Sp

MCC

GRU

0.733

0.728

0.740

0.467

CNN

0.740

0.753

0.730

0.482

CapsuleGAN

0.750

0.753

0.749

0.501

Stacking

0.776

0.791

0.762

0.553

Voteing

0.779

0.786

0.773

0.558

  1. Bold values indicate the highest values for each respective indicator
  2. The stacking method uses CapsuleGAN, GRU, and CNN as base classifiers and CNN as meta-classifier to obtain the highest prediction value. The weight ratio of GRU, CNN, and CapsuleGAN in the voting method is 1:7:2
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us