Quantitative structure-activity relationships (QSARs) represent a very well consolidated computational approach to correlate structural or property descriptors of chemical compounds with their chemical or biological activities. We have recently reported that autocorrelation Molecular Electrostatic Potential (autoMEP) vectors in combination to Partial Least-Square (PLS) analysis or to Response Surface Analysis (RSA) can represent an interesting alternative 3D-QSAR strategy. In the present paper, we would like to present how the applicability of in tandem linear and nonlinear 3D-QSAR methods (autoMEP/PLS&RSA) can help to predict binding affinity data of a new set of N-methyl-d-aspartate (Gly/NMDA) receptor antagonists.