QSAR and docking-based computational chemistry approach to novel GABA-AT inhibitors: kNN-MFA-based 3DQSAR model for phenyl-substituted analogs of β-phenylethylidene hydrazine

gamma-Amino butyric acid (GABA) is recognized as the principal inhibitory neurotransmitter in the mammalian central nervous system. Attenuation of GABA'ergic neurotransmission has been postulated as being involved in the pathophysiology of several CNS disorders. We report here k-nearest neighbor molecular field analysis (kNN-MFA)-based 3DQSAR model for phenyl-substituted analogs of beta-phenylethylidene hydrazine as potent inhibitors of GABA transaminase. Overall model classification accuracy was 81.19% (q (2) = 0.8119, representing internal validation) in training set and 67.32% (Pred_r (2) = 0.6732, representing external validation) in test set using sphere exclusion and forward-backward as a method of data selection and variable selection, respectively.