Application of similarity matrices and genetic neural networks in quantitative structure-activity relationships of 2-or 4-(4-methylpiperazino)pyrimidines: 5-HT2A receptor antagonists
T. Borowski et al., Application of similarity matrices and genetic neural networks in quantitative structure-activity relationships of 2-or 4-(4-methylpiperazino)pyrimidines: 5-HT2A receptor antagonists, J MED CHEM, 43(10), 2000, pp. 1901-1909
Antagonists of the 5-HT2A receptor are being used to treat many psychiatric
disorders. The present work focuses on a group of 27 antagonists possessin
g varying affinities toward the receptor. These are 26 title compounds and
clozapine as a reference antagonist. The active conformers of the conformat
ionally flexible ligands were proposed by using the active rigid analogue a
pproach and performing similarity calculations. The calculations involved g
enetic neural network (GNN) computations deriving QSARs from similarity mat
rices (SM) with cross-validated correlation coefficients exceeding 0.92. Th
e performance of neural networks with variety of architectures was studied.
As the computations were performed for cations and neutral molecules separ
ately, the relevance of the ligand charging is discussed.