Table of explored microarray data sets
| Disease | Source | Affy GeneChip | Class Distribution | DataSet Size | Probes Before Mapping | ENSEMBL IDs Before Merging | ENSEMBL IDs After Merging |
|---|---|---|---|---|---|---|---|
| DMD | Haslett et al. (2002) | HG-U95Av2 | 12 DMD, 12 Control | 24 | 12,600 | 8,987 | 8,813 |
| DMD | Pescatori et al. (2007) | HG-U133A | 22 DMD, 14 Control | 36 | 22,283 | 13,077 | 8,813 |
| Leukemia | Golub et al. (1999) | HU-6800 | 47 ALL, 25 AML | 72 | 7,129 | 5,472 | 5,145 |
| Leukemia | Armstrong et al. (2002) | HG-U95Av2 | 24 ALL, 24 AML | 48 | 12,564 | 8,967 | 5,145 |
| ALL | Yeoh et al. (2002) | HG-U95Av2 | 15 BCR-ABL, 27 E2A-PBX1 | 42 | 12,625 | 8,987 | 8,813 |
| ALL | Ross et al. (2004) | HG-U133A | 15 BCR-ABL, 18 E2A-PBX1 | 33 | 22,283 | 13,077 | 8,813 |
We explore data sets of the following two diseases: Duchenne muscular dystrophy (DMD) and leukemia. The DMD data set comprises normal and DMD samples. The leukemia data set comprises two different types of leukemia: acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML). The ALL data set comprises Acute lymphocytic leukemia samples with two different mutations: BCR-ABL and E2A-PBX1 (refer to Table 8 for the data processing methods of each data set).