Topological Features in Profiling the Antimalarial Activity Landscape of Anilinoquinolines: A Multipronged QSAR Study

Table 3

The CP-MLR and GA five-parameter models for antimalarial activity of anilinoquinolines (Table 2) along with statistics^a.

Eq.	Constant	Descriptor and scaled regression coefficient					𝑟^2	𝑠	𝑄^2	𝑄^2G5	𝐹	𝑟^2𝑡
CP-MLR
(1)		MATS4m	MATS7e	H-052	Mor30p	RTe+
	7.382	+0.816	−0.560	+1.440	−1.098	−0.905	0.692	0.395	0.604	0.588	19.76	0.562
(2)		MATS7e	H-052	RDF085p	Mor30p	R7m
	7.802	−0.545	+1.162	+0.990	−1.073	−0.918	0.687	0.399	0.599	0.577	19.34	0.611
(3)		MATS7e	H-052	Mor30p	E1m	R7m
	8.734	−0.633	+1.114	−0.994	−0.980	−0.885	0.684	0.400	0.6	0.607	19.08	0.632
(4)		MATS7e	H-052	Mor30p	E2m	R7m+
	7.749	−0.548	+1.309	−1.043	+0.574	−0.948	0.666	0.411	0.565	0.564	17.58	0.610
(5)		MATS7e	H-052	Mor30p	E2m	R6m
	7.805	−0.574	+1.349	−1.026	+0.951	−0.850	0.660	0.415	0.565	0.522	17.09	0.628
GA
(6)		MATS4m	MATS7e	Mor17p	R7m	R6e+
	8.238	+1.096	−0.955	−2.267	−0.777	+0.786	0.692	0.395	0.604	0.588	19.76	0.562
(7)		MATS4m	MATS7e	H-047	H-052	Mor30p
	6.635	+0.813	−0.570	+0.959	+1.890	−1.118	0.692	0.395	0.615	0.618	19.73	0.607
(8)		MATS7e	H-047	H-052	Mor30p	R7m
	7.505	−0.592	+0.922	+1.357	−0.923	−0.705	0.682	0.401	0.584	0.572	18.84	0.65
(9)		MATS7e	nNR2	H-052	Mor15m	Mor30p
	6.943	−0.596	+0.834	+1.614	+0.691	−1.090	0.673	0.407	0.576	0.581	18.08	0.634
(10)		MATS8m	MATS5e	MATS7e	Mor17p	R6e+
	9.247	−0.951	−0.579	−1.042	−2.257	+0.705	0.668	0.410	0.588	0.567	17.68	0.579

^aNumber of compounds used in regression (training set) is 50 and number of compounds used in test set is 40. The regression coefficients of the descriptors shown are from the scaled descriptor values (scaled between “0” and “1”, inclusive of both values). All regression coefficients are significant at higher than 95% confidence level. In 𝑌-randomization study (100 simulations each time) no model has shown average 𝑟²_𝑌rand greater than 0.107 and maximum 𝑟²_𝑌rand greater than 0.385. For all regression equations, 𝑟 is the multiple correlation coefficient, 𝑄² and 𝑄²_G5 are cross-validated 𝑟² from leave-one-out (LOO) and leave group of five out, respectively, 𝑠 is the standard error of the estimate, 𝐹 is the F-ratio between the variances of calculated and observed activities, and 𝑟²_𝑡 is test set 𝑟² value.