Table 1. Composition of the Reference Data Seta in Terms of Metabolism Phase and Enzyme Family.
number of metabolitesb | number of parent molecules | |
---|---|---|
phase 1, all | 1763 | 944 |
CYP | 1640 | – |
phase 2, all | 690 | 582 |
UGT | 480 | – |
SULT | 92 | – |
GST | 46 | – |
NAT | 34 | – |
MT | 17 | – |
phase 1 + phase 2 | 2453 | 1420 |
The reference data set was created by combining the DrugBank and MetXBioDB metabolism data and removing the data for all parent molecules contained in the test set.
Note that the total numbers of phase 1 and phase 2 metabolites do not equal the sum of the metabolites from the listed enzyme families, because not all metabolites in the data set correspond to these main enzyme families.