| Abstract
| - Rigorously validated quantitative structure−activity relationship (QSAR) models have beendeveloped for 48 antagonists of the dopamine D1 receptor and applied to mining chemicaldatasets to discover novel potential antagonists. Several QSAR methods have been employed,including comparative molecular field analysis (CoMFA), simulated annealing−partial leastsquares (SA-PLS), k-nearest neighbor (kNN), and support vector machines (SVM). With theexception of CoMFA, these approaches employed 2D topological descriptors generated withthe MolConnZ software package (EduSoft, LLC. MolconnZ, version 4.05; http://www.eslc.vabiotech.com/ [4.05], 2003). The original dataset was split into training and test sets to allowfor external validation of each training set model. The resulting models were characterized bycross-validated R2 (q2) for the training set and predictive R2 values for the test set of (q2/R2)0.51/0.47 for CoMFA, 0.7/0.76 for kNN, R2 for the training and test sets of 0.74/0.71 for SVM,and training set fitness and test set R2 values of 0.68/0.63 for SA-PLS. Validated QSAR modelswith R2> 0.7, (i.e., kNN and SVM) were used to mine three publicly available chemicaldatabases: the National Cancer Institute (NCI) database of ca. 250 000 compounds, theMaybridge Database of ca. 56 000 compounds, and the ChemDiv Database of ca. 450 000compounds. These searches resulted in only 54 consensus hits (i.e., predicted active by allmodels); five of them were previously characterized as dopamine D1 ligands, but were notpresent in the original dataset. A small fraction of the purported D1 ligands did not contain acatechol ring found in all known dopamine full agonist ligands, suggesting that they may benovel structural antagonist leads. This study illustrates that the combined application ofpredictive QSAR modeling and database mining may provide an important avenue for rationalcomputer-aided drug discovery.
|
