Identification of the descriptor pharmacophores using variable selection QSAR: Applications to database mining

The pharmacophore concept is central to the rational drug design and discov ery process. Traditionally, a pharmacophore is defined as a specific three- dimensional (3D) arrangement of chemical functional groups found in active molecules, which are characteristic of a certain pharmacological class of c ompounds. Herein, by analogy with 3D pharmacophores, a more general concept of descriptor pharmacophore is introduced. The descriptor pharmacophores a re defined by the means of variable selection QSAR as a subset of molecular descriptors that afford the most statistically significant structure-activ ity correlation. The two variable selection QSAR methods developed in this laboratory are discussed; these include Genetic Algorithms - Partial Least Squares (GA-PLS) and K-Nearest Neighbors (KNN). Both methods employ multipl e topological descriptors of chemical structures such as molecular connecti vity indices or atom pairs (AP), and stochastic optimization algorithms to achieve a robust QSAR model, which is characterized by the highest value of cross-validated R-2 (q(2)). By default, the descriptor pharmacophore repre sents an invariant selection of descriptor types however, descriptor values are generally different for different molecules. We demonstrate that chemi cal similarity searches using descriptor pharmacophores as opposed to using all descriptors afford more efficient mining of chemical databases or virt ual libraries to discover compounds with a desired biological activity.