Skip to main content
Fig. 8 | Journal of Cheminformatics

Fig. 8

From: An automated framework for QSAR model building

Fig. 8

\(MODI\_ssR^{2}\) versus QSAR_PVE for 30 datasets. K is the number of nearest neighbors. a K = 3 and b K = 5. QSAR_PVE(IVS) is PVE score of externally validated models without feature selection (Full-model) and with selected features (SF-model). High correlation with SF-models QSAR_PVE suggests \(MODI\_ssR^{2}\) is good modelability criteria. Weaker correlation between Full-model QSAR_PVE and \(MODI\_ssR^{2}\) emphasize the importance of feature selection to obtain actual and reliable predictive performance of QSAR model

Back to article page