Table 2.

Summarized statistical characteristics of ML models accessed by 5-fold cross validation.

Model	CCR	SE	SP	PPV	NPV	Coverage
P. falciparum 3D7 strain
Avalon	0.75	0.72	0.78	0.76	0.73	0.99
MACCS	0.74	0.73	0.75	0.74	0.73	1.00
Morgan	0.75	0.69	0.80	0.78	0.72	0.99
FeatMorgan	0.75	0.71	0.79	0.77	0.73	0.99
AtomPair	0.73	0.70	0.77	0.75	0.72	0.99
Consensus	0.76	0.71	0.80	0.78	0.73	1.00
Consensus rigor	0.76	0.72	0.80	0.78	0.74	0.98
P. falciparum W2 strain
Avalon	0.71	0.67	0.75	0.73	0.70	0.99
MACCS	0.70	0.70	0.70	0.70	0.70	1.00
Morgan	0.71	0.66	0.76	0.73	0.69	0.99
FeatMorgan	0.71	0.68	0.74	0.72	0.70	0.99
AtomPair	0.70	0.69	0.71	0.70	0.69	0.99
Consensus	0.72	0.68	0.76	0.74	0.70	1.00
Consensus rigor	0.72	0.68	0.76	0.74	0.70	0.98

CCR, Correct Classification Rate; SE, Sensitivity; SP, Specificity; PPV, Positive Predictive Value; NPV, Negative Predictive Value.