METHODS AND ALGORITHMS FOR PREDICTING THE PROPERTIES OF CHEMICAL-COMPOUNDS BY COMMON FRAGMENTS OF MOLECULAR GRAPHS

Methods and algorithms for predicting the properties of chemical compo unds by common fragments of their molecular graphs are described. The prediction algorithms are based on determination of a measure of struc tural proximity (distance) between molecular graphs, which depends on the size of their common fragment. The prediction procedure involves t he following steps: partitioning the properly classes of the training sample compounds into subclasses of structurally similar compounds; se eking structurally typical compounds and their fragments in each subcl ass; classifying control compounds according to their distances from t he training sample compounds or fragments of classes;forming a set of essential fragments of samples potentially responsible for the propert ies exhibited by the compounds. The algorithms were successfully teste d in the BACC system for analyzing and classifying biologically active compounds designed at the Institute of Mathematics, Siberian Branch, Russian Academy of Sciences.