Quantitative Structure - Activity Relationships Study of Carbonic Anhydrase Inhibitors Using Logistic Regression Model

Binary Logistic Regression (BLR) has been developed as non-linear models to establish quantitative structure- activity relationships (QSAR) between structural descriptors and biochemical activity of carbonic anhydrase inhibitors. Using a training set consisted of ۲۱ compounds with known ki values, the model was trained and tested to solve two-class problems as active or inactive on the basis of the predicted value for IC۵۰. Many quantitative descriptors were generated to express the physicochemical properties of ۲۱ compounds with optimized structures. After filtration of these descriptors, ۳۹ of descriptors for carbonic anhydrase (CA, EC ۴.۲.۱.۱) isozyme IX (CAIX) and ۴۵ for isozymeXII (CAXII) remained and were selected for QSAR study. Logistic regression was then used to non-linearly select the most important descriptors and to develop a model for prediction of IC۵۰. To evaluate the performance of the established models, Jjackknife and self consistency tests were performed during implementation of the two model-building methods. The applied indices including accuracy, sensitivity, and specificity were ۸۵%, ۸۲% and ۱۰۰% for CAIX and also ۷۱%, ۶۸% and ۸۰% for CAXII respectively.The primary advantage of such an approach is the reduction of redundant variables and the consequent improvement in the efficiency of modeling.

کلیدواژه ها:

Quantitative structure-activity relationship ، Binary logistic regression ، Carbonic anhydrase inhibitors