“…We employed genetic function approximation (GFA) and MLR QSAR (GFA-MLR-QSAR) analysis to search for an optimal QSAR equation(s). The fit values obtained by mapping representative hypotheses (56 models) against collected HNE inhibitors (1-115, Table A in Supplementary Materials) were enrolled, together with around 100 other physicochemical descriptors, as independent variables (genes) in GFA-MLR-QSAR analysis (see ''QSAR modeling'' section in experimental) (Abu Hammad and Taha, 2009;Abu Khalaf et al, 2010;Al-Masri et al, 2008;Al-Nadaf et al, 2010;AlSha'er and Taha, 2010a;Bersuker et al, 2000;Habash and Taha, 2011;Taha et al, , 2008aTaha et al, , b, 2008c. However, since it is essential to access the predictive power of the resulting QSAR models on an external set of inhibitors, we randomly selected 23 molecules and employed them as external test molecules for validating the QSAR models (r PRESS 2 ).…”