The AM1 semiempirical method is employed to calculate a set of molecular properties (variables) of 45 flavone compounds with antipicornavirus activity, and 9 new flavone molecules are used for an activity prediction study. Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA), Stepwise Discriminant Analysis (SDA), and K-Nearest Neighbor (KNN) are employed in order to reduce dimensionality and investigate which subset of variables should be more effective for classifying the flavone compounds according to their degree of antipicornavirus activity. The PCA, HCA, SDA, and KNN methods showed that the variables MR (molar refractivity), B(9) (bond order between C(9) and C(10) atoms), and B(25) (bond order between C(11) and R(7) atoms) are important properties for the separation between active and inactive flavone compounds, and this fact reveals that electronic and steric effects are relevant when one is trying to understand the interaction between flavone compounds with antipicornavirus activity and the biological receptor. In the activity prediction study, using the PCA, HCA, SDA, and KNN methodologies, three of the 9 new flavone compounds studied were classified as potentially active against picornaviruses.