Table 2.
Data set characteristics.
| Name | Size | Reference |
|---|---|---|
| muv-chaperone | 30 | [25] |
| muv-gpcr-1 | 30 | [25] |
| muv-gpcr-2 | 30 | [25] |
| muv-gpcr-3 | 30 | [25] |
| muv-kinase-1 | 30 | [25] |
| muv-kinase-2 | 30 | [25] |
| muv-kinase-3 | 30 | [25] |
| muv-nr-1 | 30 | [25] |
| muv-nr-2 | 30 | [25] |
| muv-ppi-1 | 30 | [25] |
| muv-ppi-2 | 30 | [25] |
| muv-ppi-3 | 30 | [25] |
| muv-protease-1 | 30 | [25] |
| muv-protease-2 | 30 | [25] |
| muv-protease-3 | 30 | [25] |
| muv-rnase | 30 | [25] |
| muv-rtk | 30 | [25] |
| nci-hiv | 415 | [23] |
| stahl-cox2 | 125 | [21] |
| stahl-estrogen | 53 | [21] |
| stahl-gelatinase | 40 | [21] |
| stahl-neuraminidase | 17 | [21] |
| stahl-p38-map-kinase | 24 | [21] |
| stahl-thrombin | 67 | [21] |
| suth-benzodiazepine | 404 | [22] |
| suth-dhfr | 722 | [22] |
| suth-estrogen | 361 | [22] |
| suth-steroid | 28 | [22] |
| wom-alr2 | 42 | [20] |
| wom-androgen | 36 | [20] |
| wom-cdk2 | 152 | [20] |
| wom-cox2 | 76 | [20] |
| wom-d2 | 334 | [20] |
| wom-egfr | 74 | [20] |
| wom-estrogen | 64 | [20] |
| wom-fxa | 107 | [20] |
| wom-hiv1rt | 99 | [20] |
| wom-impdh | 49 | [20] |
| wom-p38-map-kinase | 59 | [20] |
| wom-pde5 | 88 | [20] |
| wom-ppar-gamma | 27 | [20] |
Each data set is given an abbreviated name and is listed with the the number of molecules and its reference. In the case of the the NCI HIV screen (nci-hiv) we use only the 415 confirmed actives and discard the inactive and moderately-active compounds.