BMC Bioinformatics

Table 1 Data set characteristics.

From: Application of kernel functions for accurate similarity search in large chemical databases

data set	#S	#P	#N	#V	#E
PDE5	100	50	50	44.7	47.2
CDK2	100	50	50	38.4	40.6
COX2	100	50	50	37.7	39.6
FXa	100	50	50	45.75	48.03
AIA	100	50	50	48.33	50.61
AChE	183	94	89	29.1	32.0
ALF	151	61	60	23.8	25.2
EGF-R	497	250	247	24.6	27.1
HIV-P	267	135	132	43.0	46.2
HSP90	109	55	54	29.84	32.44
MAPK	336	168	168	28.0	31.1
HIV-RT	482	241	241	22.18	24.39

#S: total number of compounds, #P: number of positive compounds, #N: number of negative compounds, #V: average number of nodes, #E: average number of edges.

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com