A Genetic Algorithm Based Support Vector Machine Model for Blood-Brain Barrier Penetration Prediction

Table 5

Most frequently used features for all top models (number of features range from 4 to 15).

Number	Descriptor name	Occurrence; (120 models)	Meaning
11	AbsCarboxy	84	Indicator for carboxylic acid^†
5	delta_	35	(pH 6.5) − (pH 7.4)
7	M_PSA_7.0	32	PSA at pH 7.0
1	M_	28
138	HA_dependent_HDCA-2_[Zefirov’s_PC]	27	H-donors charged surface area^#
268	ESP-FHASA_Fractional_HASA_(HASA/TMSA)_Quantum-Chemical_PC	27	H-acceptor surface area/total molecular surface area^#
6	M_PSA_6.5	25	PSA at pH 6.5
167	PPSA-1_Partial_positive_surface_area_[Quantum-Chemical_PC]	25	Partial positive surface area
101	Topographic_electronic_index_(all_bonds)_Zefirov’s_PC	23	Topological electronic index for all bonded pairs of atoms^‡
8	M_PSA_7.4	21	PSA at pH 7.4

Rows with the same symbol could be categorized into the same group.