Skip to main content

Table 8 Performance of different machine learning algorithms for 5-CV on the FSL dataset

From: DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks

Classifier

AUC

PRC

F1_Score

Acc

Recall

Spec

Precision

KNN

0.9493

0.9377

0.8939

0.8859

0.9650

0.8062

0.8329

NB

0.8969

0.8414

0.8483

0.8256

0.9773

0.6730

0.7497

SVM

0.9724

0.9434

0.9489

0.9477

0.9758

0.9200

0.9241

LR

0.8941

0.8124

0.8587

0.8468

0.9339

0.7601

0.7967

RF

0.9890

0.9869

0.9544

0.9535

0.9778

0.9295

0.9324

DT

0.9423

0.8955

0.9438

0.9282

0.9251

0.9711

0.8800

XGB

0.9842

0.9787

0.9542

0.9534

0.9763

0.9305

0.9331

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us