Classifying and scoring of molecules with the NGN: new datasets, significance tests, and generalization

BMC Bioinformatics

Table 12 A summary of the real-valued ranges of activity for datasets used in regression experiments.

Dataset	Dataset Full Name	Size	Range	Units	Reference
ACE	Angiotensin Converting Enzyme	114	[2.1, 9.9]	pIC₅₀	[6][26]
AChE	Acetylcholinesterase	111	[4.3, 9.5]	pIC₅₀	[6]
AR	Androgen Receptor	146	[−3.56, 2.27]	logRBA	[18]
BZR	Benzodiazepine Receptor	163	[5.5, 8.9]	pIC₅₀	[6]
Cox2	Cyclooxygenase-2	282	[4.0, 9.0]	pIC₅₀	[6]
DHFR	Dihydrofolate Reductase	397	[3.3, 9.8]	pIC₅₀	[6]
ER	Estrogen Receptor	131	[−4.50, 2.60]	logRBA	[16][17]
GPB	Glycogen Phosphorylase B	66	[1.3, 6.8]	pK_i	[6][27]
Therm	Thermolysin	76	[0.5, 10.2]	pK_i	[6][26]
Thr	Thrombin	88	[4.4, 8.5]	pK_i	[6][28]

ISSN: 1471-2105