- Update to ChEMBL 33
- Removal of kinase.com as a data source
- Updated Uniprot API calls
- Both non-curated and curated CSVs are provided as well as a sample of the first 100 data points for testing
- EGFR kinase bioactivities based on the curated CSV as well as a sample of the first 100 data points for testing
Datapoints in each dataset:
| Dataset | Non-curated | Curated | Sample | EGFR Kinase | EGFR Sample |
|---|---|---|---|---|---|
| ChEMBL 27 | 217 612 | 174 238 | - | - | - |
| ChEMBL 28 | 237 336 | 186 972 | - | - | - |
| ChEMBL 29 | 242 609 | 190 634 | 100 | 6 509 | 100 |
| ChEMBL 30 | 252 191 | 197 073 | 100 | 6 733 | 100 |
| ChEMBL 33 | 272 922 | 211 607 | 100 | 7 287 | 100 |