Comparison of a neural net-based QSAR algorithm (PCANN) with hologram- andmultiple linear regression-based QSAR approaches: Application to 1,4-dihydropyridine-based calcium channel antagonists

A QSAR algorithm (PCANN) has been developed and applied to a set of calcium channel blockers which are of special interest because of their role in ca rdiac disease and also because many of them interact with P-glycoprotein, a membrane protein associated with multidrug resistance to anticancer agents . A database of 46 1,4-dihydropyridines with known Ca2+ channel binding aff inities was employed for the present analysis. The QSAR algorithm can be su mmarized as follows: (1) a set of 90 graph theoretic and information theore tic descriptors representing various structural and topological characteris tics was calculated for each of the 1,4-dihydropyridines and (2) principal component analysis (PCA) was used to compress these 90 into the eight best orthogonal composite descriptors for the database. These eight sufficed to explain 96% of the variance in the original descriptor set. (3) Two importa nt empirical descriptors, the Leo-Hansch lipophilic constant and the Hammet electronic parameter. were added to the list of eight. (4) The 10 resultin g descriptors were used as inputs to a back-propagation neural network whos e output was the predicted binding affinity. (5) The predictive ability of the network was assessed by cross-validation, A comparison of the present a pproach with two other QSAR approaches (multiple linear regression using th e same variables and a Hologram QSAR model) is made and shows that the PCAN N approach can yield better predictions, once the right network configurati on is identified. The present approach (PCANN) may prove useful for rapid a ssessment of the potential for biological activity when dealing with large chemical libraries.