A NEURAL DEVICE FOR SEARCHING DIRECT CORRELATIONS BETWEEN STRUCTURES AND PROPERTIES OF CHEMICAL-COMPOUNDS

A scheme of a neural device intended for searching direct correlations between structures and properties of organic compounds without prelim inary computation of molecular descriptors (that are invariant with re spect to renumbering atoms in a molecule) is suggested. The invariance of a property with respect to renumbering atoms in a molecule is ensu red by the architecture of the neural device, which is constructed by analogy with biological vision systems. A model software of the neural device was tested on several examples. The descriptive and predictive performances of the device are shown to be comparable and even overco me the performances of using molecular descriptors, such as topologica l indexes and substructural descriptors, especially for analyzing hete rogeneous data sets including inorganic compounds. The neural device c an be advantageously used in the cases when more traditional approache s fail to work or ''good'' molecular descriptors have not been devised yet.