Development of Neural Network Simulator for Structure−Activity Correlation of Molecules (NECO). Prediction of Endo/Exo Substitution of Norbornane Derivatives and of Carcinogenic Activity of PAHs from ¹³C-NMR Shifts

A perceptron type neural network simulator for structure−activity correlation of molecules has been developed with two different learning methods, i.e., back-propagation and reconstruction methods. First by use of the back-propagation method the exo/endo branching of norbornane and norbornene derivatives was correctly predicted from the set of ¹³C NMR chemical shifts for various ring carbon atoms. Then the obtained correlation was analyzed by the reconstruction learning method. It was shown in this case that the NMR shifts for two carbon atoms out of seven have strong correlation with the exo/endo branching. Further, structure−activity correlation between the ¹³C NMR chemical shifts and carcinogenicity of 11 polycyclic aromatic hydrocarbons was also analyzed using the reconstruction method. It was demonstrated that neural network analysis is suitable for the elucidation of complicated structure−activity problems where many factors are nonlinearly entangled.