Table 1.
Datasets composition.
| Dataset | Drivers | Passengers | Neutral | Other disease | Total |
|---|---|---|---|---|---|
| CNO | 3163 | – | 3163 | – | 6326 |
| Carcinoma | 1899 | – | 1899 | – | 3798 |
| Hematopoietic | 461 | – | 461 | – | 922 |
| Lymphoid | 441 | – | 441 | – | 882 |
| Glioma | 384 | – | 384 | – | 768 |
| Melanoma | 257 | – | 257 | – | 514 |
| CND | 3163 | – | 1581 | 1582 | 6326 |
| Synthetic | 3163 | 3163 | – | – | 6326 |
The CNO, CND and Synthetic datasets are composed by the same set of driver cancer variants and respectively only neutral polymorphisms (CNO), neutral and other disease-related variants (CND) and passenger cancer variants generated by CHASM algorithm (Synthetic). Carcinoma, Hematopoietic, Lymphoid, Glioma and Melanoma are subsets of CNO composed by driver cancer variant with primary histology description annotated in COSMIC database.