Quantitative prediction of selectivity between the A1 and A2A adenosine receptors

Table 2 Performance of selectivity classification models

Classification model	Class	MCC	Sensitivity	Specificity	PPV	NPV	ROC
QSAR 2-class	A₁AR	0.40 ± 0.13	0.62 ± 0.16	0.76 ± 0.11	0.57 ± 0.12	0.86 ± 0.07	0.87 ± 0.06
QSAR 2-class	A_2AAR	0.40 ± 0.13	0.76 ± 0.11	0.62 ± 0.16	0.86 ± 0.07	0.57 ± 0.12	0.87 ± 0.06
QSAR 3-class	A₁AR	0.22 ± 0.15	0.25 ± 0.15	0.96 ± 0.02	0.31 ± 0.14	0.93 ± 0.02	0.76 ± 0.06
	A_2AAR	0.20 ± 0.17	0.33 ± 0.16	0.88 ± 0.02	0.35 ± 0.14	0.83 ± 0.04	0.62 ± 0.09
	Dual	0.10 ± 0.09	0.81 ± 0.03	0.29 ± 0.10	0.75 ± 0.02	0.35 ± 0.08	0.58 ± 0.06
QSAR 3-class	A₁AR	0.00 ± 0.07	0.11 ± 0.05	0.88 ± 0.07	0.10 ± 0.06	0.91 ± 0.02	0.64 ± 0.09
	A_2AAR	0.36 ± 0.12	0.47 ± 0.14	0.85 ± 0.10	0.59 ± 0.11	0.85 ± 0.02	0.65 ± 0.09
	Non-binder	0.07 ± 0.13	0.67 ± 0.11	0.39 ± 0.12	0.70 ± 0.05	0.37 ± 0.12	0.50 ± 0.09
QSAR 4-class	A₁AR	0.11 ± 0.10	0.12 ± 0.09	0.97 ± 0.01	0.18 ± 0.11	0.95 ± 0.01	0.70 ± 0.07
	A_2AAR	0.25 ± 0.16	0.29 ± 0.13	0.94 ± 0.02	0.39 ± 0.16	0.90 ± 0.02	0.67 ± 0.09
	Dual	0.09 ± 0.05	0.51 ± 0.05	0.58 ± 0.08	0.50 ± 0.05	0.60 ± 0.02	0.58 ± 0.05
	Non-binder	0.15 ± 0.06	0.51 ± 0.09	0.64 ± 0.06	0.47 ± 0.04	0.68 ± 0.05	0.57 ± 0.07

Means of fivefold cross-validation with standard error of the mean (SEM). The class indicates the performance for that particular selectivity class: A₁AR-selective, A_2AAR-selective, dual (non-selective), and non-binders
MCC Matthews Correlation Coefficient, PPV positive predictive value, NPV negative predictive value, ROC receiver operating characteristic

ISSN: 1758-2946