PREDICTION OF INFRARED-SPECTRA FROM CHEMICAL STRUCTURES OF ORGANIC-COMPOUNDS USING NEURAL NETWORKS

Chemical constitutions of organic compounds are encoded using a previo usly described graph-theoretical approach (Clerc and Terkovics, Analyt ica Chimica Acta, 235 (1990) 93-102). Neural networks are used to map the correlations between the IR spectral properties and the structure descriptors. The correlations thus established are then used to predic t the IR spectral properties from the chemical structure. For a test s et with members from many different compound classes about 80% of the predictions were satisfactory.