Classification of multidrug-resistance reversal agents using structure-based descriptors and linear discriminant analysis

Linear discriminant analysis is used to generate models to classify multidr ug-resistanee reversal agents based on activity. Models are generated and e valuated using multidrug-resistance reversal activity values for 609 compou nds measured using adriamycin-resistant P388 murine leukemia cells. Structu re-based descriptors numerically encode molecular features which are used i n model formation. Two types of models are generated: one type to classify compounds as inactive, moderately active, and active (three-class problem) and one type to classify compounds as inactive or active without considerin g the moderately active class (two-class problem). Two activity distributio ns are considered, where the separation between inactive and active compoun ds is different. When the separation between inactive and active classes is small, a model based on nine topological descriptors is developed that pro duces a classification rate of 83.1% correct for an external prediction set . Larger separation between active and inactive classes raises the predicti on set classification rate to 92.0% correct using a model with six topologi cal descriptors. Models are further validated through Monte Carlo experimen ts in which models are generated after class labels have been scrambled. Th e classification rates achieved demonstrate that the models developed could serve as a screening mechanism to identify potentially useful MDRR agents from large Libraries of compounds.