Journal of Cheminformatics

Table 2 Comparison of the top1 and top3 success rates for various methods using 48 bound/unbound structures

From: bSiteFinder, an improved protein-binding sites prediction server based on structural alignment: more accurate and less time-consuming

Method	Bound^a		Unbound^b
Method	Top1 (%)	Top3 (%)	Top1 (%)	Top3 (%)
bSiteFinder	93.8	98.7	85.4	95.8
LISE^c	92	96	81	92
MPK2^c	85	96	80	94
VICE^c	85	94	83	90
MPK1^c	83	96	75	90
DoGSite^c	83	92	71	92
Fpocket^c	83	92	69	94
LIGSITE^CSc	81	92	71	85
LIGSITE^CSCc	79	–	71	–
MSPocket^c	77	94	75	88
POCASA^c	77	90	75	92
Q-SiteFinder^c	75	90	52	75
PocketPicker^c	72	85	69	85
CAST^c	67	83	58	75
PASS^c	63	81	60	71
SURFNET^c	54	78	52	75

^aThe MCC scores of the Top1 and Top3 are 0.95 and 0.97 respectively with 48 bound structures
^bThe MCC scores of the Top1 and Top3 are 0.72 and 0.75 respectively with 48 unbound structures
^cThe success rates of these methods were taken from Xie and Hwang [32]

Back to article page

ISSN: 1758-2946

Contact us

Submission enquiries: journalsubmissions@springernature.com