Journal of Cheminformatics

Table 1 Performance comparison of different methods on KinaseDB (10-FCV, global evaluation model)

From: Meta-learning-based Inductive logistic matrix completion for prediction of kinase inhibitors

	AUC	AUPR	BA	RECALL	PRECISION	F1
SVM	0.6098	0.6655	0.6098	0.2397	0.6098	0.3738
KNN	0.817	0.7951	0.817	0.7388	0.817	0.7531
RF	0.8088	0.7989	0.8088	0.6975	0.8088	0.7469
MolTrans [29]	0.9297	0.8718	0.8603	0.7751	0.7267	0.8013
MTDNN [20]	0.9302	0.8735	0.8424	0.7708	0.8080	0.7889
ILMC(MACCS + CTD)	0.9290	0.8496	0.8304	0.7800	0.8090	0.7695
ILMC(ECFP + ProtVec)	0.9270	0.8595	0.8439	0.7795	0.8046	0.7891

The best results are shown in bold, the rank 2 score is marked by underline

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com