CLUSTER-ANALYSIS FROM MOLECULAR SIMILARITY-MATRICES USING A NONLINEARNEURAL-NETWORK

A non-linear neural network model to perform cluster analysis is prese nted. It provides an efficient parallel algorithm for solving this pat tern recognition task, consisting, from the mathematical point of view , of a combinatorial optimization problem. A new classification techni que is discussed in order to visualize clustering patterns within a mo lecular set, by means of numerical analysis of the similarity matrix. As an example of the application of the reported neural network model, a quantum molecular similarity study in the field of structure-activi ty relationships is reported. A molecular set made of eighteen quinolo nes is used as an example. The resultant cluster distribution showed a good qualitative correlation between similarity data and biological a ctivity.