Fig. 1.

The diversity of compounds analyzed by the scaffold-based classification approach (SCA). CID means compound class ID, categories by complexity; the SCA also outputs the following structural descriptor values: (1) Cyclicity side chain value; (2) AE average electronegativity; (3) HD number of H-bond donors; (3) HA number of H-bond acceptors; (4) AB number of aromatic bonds; (5) ATMS number of non-H atoms; (6) BNDS number of non-H-involved bonds; (7) SSSRS number of the smallest set of smallest rings; (8) AZ average atomic numbers; (9) RB number of rotating bonds; (10) MW molecular weight