Exploring the role of topological descriptors to predict physicochemical properties of anti-HIV drugs by using supervised machine learning algorithms

Table 2 The topological indices values for the candidate drugs

Drugs	M₁ (G)	M₂ (G)	H (G)	F (G)	SS (G)	ABC (G)	RI (G)	SC (G)	GA (G)	HZ (G)	ReZ₁ (G)	ReZ₂ (G)
a	132	151	12.13	332	29.48	20.04	12.54	12.99	27.20	334	31.31	740
b	114	141	9.533	298	25.06	16.19	9.754	10.43	22.57	580	27.60	738
c	82	96	7.266	214	17.94	12.22	7.613	7.827	16.35	406	19.21	490
d	172	200	14.50	460	37.18	25.35	15.19	15.89	33.59	860	39.88	1020
e	162	195	13.96	432	35.08	23.69	14.68	15.10	31.70	822	37.98	1028
f	248	280	23.06	622	55.39	38.25	23.97	24.66	51.26	1182	58.45	1366
g	272	318	22.81	746	58.20	40.00	24.05	24.97	52.48	1382	62.36	1670
h	236	272	20.73	614	51.84	35.31	21.55	22.48	47.34	1158	55.33	1362
i	206	256	15.20	606	42.32	28.33	16.26	17.15	36.86	1118	46.71	1436

ISSN: 2661-801X