Thus, if the discriminant function was greater than zero, a given compound was selected as a potential antileukemic agent; otherwise, it was categorized as “inactive.” The classification matrix was highly significant for the set (99.9% correct prediction for the active group, five out of five correctly classified, and 91.7% for the inactive group, 11 out of 12 correctly classified; Table 1 ).
← all excerpts
Application of Quantitative Structure-Activity Relationships in the Prediction of New Compounds with Anti-Leukemic Activity.
1
—
—