Table 4.

Simplified molecular input-line entry system (SMILES) attributes applied to build up a model.

SMILES Attribute	Comments
Sk	One symbol or two symbols which cannot be examined separately in SMILES, e.g., Cl, Br, etc.
SSk	A combination of two connected Sk
BOND	Descriptor reflects the presence in SMILES of the following symbols: ‘@’, ‘=’, and ‘#’ (i.e. presence of different bonds)
NOSP	Descriptor reflects the presence of the following chemical elements nitrogen (i.e., symbol ‘N’), oxygen (i.e., symbols ‘O’), Sulfur (i.e., symbol ‘S’), and phosphorus (i.e., symbol ‘P’)
HALO	Descriptor reflects the presence of fluorine (i.e., symbol ‘F’), chlorine (i.e., symbols ‘Cl’), bromine (i.e., symbols ‘Br’), and iodine (i.e., ‘I’)
PAIR	Descriptor reflects simultaneous the presence of pair of the above elements (i.e. details related to BOND, NOSP, and HALO, without any details about their places in molecular structure)