QSAR and k-nearest neighbor classification analysis of selective cyclooxygenase-2 inhibitors using topologically-based numerical descriptors

Experimental IC50 data for 314 selective cyclooxygenase-2 (COX-2) inhibitor s are used to develop quantitation and classification models as a potential screening mechanism for larger libraries of target compounds. Experimental log(IC50) values ranged from 0.23 to greater than or equal to 5.00. Numeri cal descriptors encoding solely topological information are calculated for all structures and are used as inputs for linear regression, computational neural network, and classification analysis routines. Evolutionary optimiza tion algorithms are then used to search the descriptor space for informatio n-rich subsets which minimize the rms error of a diverse training set of co mpounds. An eight-descriptor model was identified as a robust predictor of experimental log(IC50) values, producing a root-mean-square error of 0.625 log units for an external prediction set of inhibitors which took no part i n model development. A k-nearest neighbor classification study of the data set discriminating between active and inactive members produced a nine-desc riptor model able to accurately classify 83.3% of the prediction set compou nds correctly.