Table 7 After SHAP performance evaluation.

From: GRUATT-AVP: leveraging a novel attention-based gated recurrent unit to advance the accuracy of antiviral peptide prediction

 

Model

AUC

ACC

MCC

Sen

Spe

Pre

F1

AUPR

Optimal subset

After SHAP

SVM54

0.979

0.925

0.850

0.940

0.910

0.911

0.925

0.977

200

XGBoost55

0.951

0.881

0.762

0.871

0.891

0.898

0.885

0.955

200

CNN56

0.925

0.925

0.851

0.933

0.918

0.923

0.928

0.945

200

ResNet5057

0.833

0.764

0.528

0.766

0.761

0.772

0.769

0.829

200

GRUATT-AVP

0.986

0.948

0.896

0.942

0.954

0.956

0.949

0.988

500

Back to article page