Disease candidate genes prediction using positive labeled and unlabeled instances

BMC Medical Genomics

Table 4 The selected parameters for each one-class learning algorithm separately for each disease

The name of the disease ↓	Algorithm →	SVDD		KNN	Robust Gaussian	ParzenWindow
The name of the disease ↓	Parameter →	ɤ⁴	kernel	³K	²Tol	¹h
Adrenal		0.14	RBF	2	e-3	1
Colon		0.14	RBF	1	0.015	1.2
Lung		0.3	RBF	2	e-3	1
Prostate		0.2	RBF	1	e-3	1
Heart Failure		0.14	RBF	2	e-3	0.9
Neurological		0.14	RBF	2	0.005	1

ISSN: 1755-8794