INFRARED-SPECTRA SIMULATION OF SUBSTITUTED BENZENE-DERIVATIVES ON THEBASIS OF A 3D STRUCTURE REPRESENTATION

The identification of chemical compounds from their infrared spectra f aces new challenges from novel experimental techniques such as combina torial chemistry. To rapidly provide estimates for the infrared spectr a of candidate structures, an empirical approach to the modeling of th e relationships between the 3D structure of a molecule and its infrare d spectrum has been developed. This method is based on a novel 3D stru cture representation and a powerful modeling technique, a counterpropa gation neural network, A dataset of 871 mono-, di-, and trisubstitued benzene derivatives is analyzed with this approach.