The apoptosis-inducing activity data of a series of 4-aryl-4H-chromenes based on three cell lines (human breast cancer cell line T47D, human non-smal cell lung cancer cell line H1299, and human colorectal cancer cell line DLD-1) have been subjected to quantitative structure-activity relationship (QSAR) analysis. A collection of chemometrics methods including multiple linear regression (MLR), factor analysis-based multiple linear regression (FA-MLR), principal component regression (PCR), and partial least squared combined with genetic algorithm for variable selection (GA-PLS) were employed to make connections between structural parameters and induction of apoptosis in three different cell lines. Models of high statistical qualities were obtained for each cell line using GA-PLS method. The results revealed that 2D autocorrelation descriptors and dipole moments as a quantum chemical parameter are important structural parameters that significantly influence the activity in all three types of cell lines. However, the determinant descriptors for activity of compounds in H1299 cell line were partly different from the two other cell lines, which might be deduce that the studied compounds induce apoptosis through a different mechanism of action.
© 2011 John Wiley & Sons A/S.