Exploring QSAR of Some Antitubercular Agents: Application of Multiple Validation Strategies

The in vitro vero cell cytotoxicity of 93 antitubercular compounds belonging to the classes of chiral pentaamines, bis-cyclic guanidines, bis-cyclic thioureas, bis-cyclic piperazines, and quinolylhydrazones has been modeled in the present quantitative structure-activity relationship (QSAR) study. Genetic function approximation followed by multiple linear regression (GFA-MLR) based on the mean absolute error (MAE) based criteria was used as the chemometric tool for the model development using 2D descriptors available from open source PaDEL-Descriptor. The developed model was statistically robust (Q2:0.868, R2pred:0.896). Additionally, the r2m metrics, concordance correlation coefficient (CCC) and MAE criteria for the test set validation were also tested. The models indicate importance of autocorrelation descriptors weighted by charge (ATSc3, ATSc5) and some electrotopological state atom type descriptor of fragments -NH-,-O-, >N- for cytotoxicity. The applicability domains of GFA-MLR models were also studied by applying both leverage and standardized residual approaches.