Table 1. GSE accession number and number of samples for each phenotype.

	Dataset	Lung tissue	Microarray	Platform
1	GSE10799	3	16	Affymetrix Human Genome U133 Plus 2.0 Array
2	GSE12667	0	75	Affymetrix Human Genome U133 Plus 2.0 Array
3	GSE50081	0	181	Affymetrix Human Genome U133 Plus 2.0 Array
4	GSE31210	20	226	Affymetrix Human Genome U133 Plus 2.0 Array
5	GSE18842	45	46	Affymetrix Human Genome U133 Plus 2.0 Array
6	GSE10445	0	72	Affymetrix Human Genome U133 Plus 2.0 Array
7	GSE33356	60	60	Affymetrix Human Genome U133 Plus 2.0 Array
8	GSE19188	65	91	Affymetrix Human Genome U133 Plus 2.0 Array
9	GSE28571	0	100	Affymetrix Human Genome U133 Plus 2.0 Array
10	GSE10245	0	58	Affymetrix Human Genome U133 Plus 2.0 Array
	TOTAL	193	925	1118