Class distribution of microarray data sets after over sampling

Disease	Source	Before Over Sampling	After Over Sampling
DMD	Haslett et al. (2002)	12 DMD, 12 Control	17 DMD, 19 Control
DMD	Pescatori et al. (2007)	22 DMD, 14 Control	22 DMD, 14 Control
Leukemia	Golub et al. (1999)	47 ALL, 25 AML	47 ALL, 25 AML
Leukemia	Armstrong et al. (2002)	24 ALL, 24 AML	37 ALL, 35 AML
ALL	Yeoh et al. (2002)	15 BCR-ABL, 27 E2A-PBX1	15 BCR-ABL, 27 E2A-PBX1
ALL	Ross et al. (2004)	15 BCR-ABL, 18 E2A-PBX1	19 BCR-ABL, 23 E2A-PBX1

The “Disease” column states the disease type of the data set pairs, the “Source” column denotes the source of each data set, the “Before Over Sampling” column shows the class distribution of the data sets before oversampling, the “After Over Sampling” column shows the class distribution of the data sets after over sampling the smaller data set in the pair (cf. for Table 7 abbreviations).