BMC Bioinformatics

Table 1 Optimal parameter values for MARS [28], kNN [29], SVM [30], RF [31], and BRT [32] models.

From: Machine-learning scoring functions for identifying native poses of ligands docked to known and novel proteins

Model	Parameter	Feature set
		X	A	R	G	XA	XR	XG	AR	AG	RG	XAR	XAG	XRG	ARG	XARG
MARS	Degree	2	1	1	1	1	1	1	1	1	1	1	1	1	1	1
	Penalty	2	6	5	6	7	2	6	7	6	5	6	7	6	5	6
kNN	k	15	13	14	16	9	19	17	19	18	17	18	19	17	18	19
	q	1	1	1	1	1	1	1	1	1	1	1	1	1	1	1
SVM	C	2	2	1	1	1	4	1	2	2	1	1	2	2	1	2
	ε	0.5	0	0.250	0.250	0.125	0.125	0.250	0.250	0.250	0.125	0.250	0.125	0.125	0.125	0.250
	σ	1	0.25	0.125	0.250	0.250	0.031	0.031	0.031	0.125	0.031	0.125	0.031	0.031	0.031	0.031
RF	mtry	3	18	8	7	31	5	8	10	16	17	14	20	21	25	35
BRT	Interaction depth	15	17	18	16	19	15	18	19	17	16	16	20	18	17	20
	Number of trees	1114	1523	1573	1208	1371	2113	1610	2950	2181	2303	2213	2590	2854	2921	2859

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com