Application of cascade correlation networks for structures to chemistry

We present the application of Cascade Correlation for structures to QSPR (q uantitative structure-property relationships) and QSAR (quantitative struct ure-activity relationships) analysis. Cascade Correlation for structures is a neural network model recently proposed for the processing of structured data. This allows the direct treatment of chemical compounds as labeled tre es, which constitutes a novel approach to QSPR/QSAR. We report the results obtained for QSPR on Alkanes (predicting the boiling point) and QSAR of a c lass of Benzodiazepines. Our approach compares favorably versus the traditi onal QSAR treatment based on equations and it is competitive with 'ad hoc' MLPs for the QSPR problem.