Determining Cutoff Point of Ensemble Trees Based on Sample Size in Predicting Clinical Dose with DNA Microarray Data

Table 1

Summary information and number of selected important genes of the real datasets.

Data/ID	Organism type	Response variable	Number of observations	Total genes	Selected genes
GSE1938	Yeast	Mannose concentration	15	8714	2
GSE12817	Rat	Glucose concentration	16	24606	5
GSE3078	Rat	Hydrogen peroxide	20	14102	6
GSE10748	Rat	D-serine dose	24	24606	7
GSE15457	Rat	Hypochlorous acid	25	27276	4
GSE8982	Yeast	Alpha mating factor pheromone	33	6191	9
GSE14954	Human	LDL-cholesterol concentrations	40	16401	10
GSE9751	Rat	Chlorpyrifos (CPF) dose	44	13429	11
GSE7955	Rat	Deltamethrin dose	48	24606	14
GSE2409	Rat	Anticancer drug dose	69	7987	16
GSE9539	Human	Copper sulfate	98	18211	21