Table 1.
Description of the five TCGA data sets
| Data type | BRCA | GBM | LAML | LUSC | SKCM |
|---|---|---|---|---|---|
| Clinical variables | |||||
| Number of patients | 739 | 299 | 180 | 308 | 366 |
| Overall survival (month) | (0.00, 196.97) | (0.13, 76.90) | (0, 95.37) | (0, 176.53) | (1, 362.5667) |
| Event rate | 7.58% | 88.96% | 64.44% | 35.39% | 37.98% |
| Gene expression | |||||
| Platform | Agilent 244K Custom Gene Expression G4502A_07 | Agilent 244K Custom Gene Expression G4502A_07 | Affymetrix Human Genome HG-U133_Plus_2 | Agilent 244K Custom Gene Expression G4502A_07 | Illumina HiSeq 2000 RNA Sequencing Version 2 analysis |
| Number of patients | 526 | 500 | 173 | 154 | 371 |
| Features before clean | 15 639 | 16 407 | 18 131 | 15 521 | 19 425 |
| Features after clean | 2500 | 2500 | 2500 | 2500 | 2500 |
| DNA methylation | |||||
| Platform | Illumina DNA Methylation 27/450 (combined) | Illumina DNA Methylation 27/450 (combined) | Illumina DNA Methylation 450 | Illumina DNA Methylation 27/450 (combined) | Illumina DNA Methylation 450 |
| Number of patients | 929 | 398 | 194 | 385 | 373 |
| Features before clean | 1662 | 1622 | 14 959 | 1578 | 193 |
| Features after clean | 193 | 193 | 193 | 193 | 193 |
| Copy number alteration | |||||
| Platform | Affymetrix Genome-Wide Human SNP Array 6.0 | Affymetrix Genome-Wide Human SNP Array 6.0 | Affymetrix Genome-Wide Human SNP Array 6.0 | Affymetrix Genome-Wide Human SNP Array 6.0 | Affymetrix Genome-Wide Human SNP Array 6.0 |
| Number of patients | 934 | 563 | 191 | 178 | 374 |
| Features before clean | 20 500 | 20 501 | 20 501 | 17 869 | 23 689 |
| Features after clean | 2500 | 2500 | 2500 | 2500 | 2500 |