Self-organizing maps and molecular similarity.

Self-organizing maps generated by Kohonen neural networks provide a method for transforming multidimensional problems into lower dimensional problems. Here, a Kohonen network is used to generate two-dimensional representations of the electrostatic potential about the ring structures of histamine H2 agonists. Previous work by J. Gasteiger and X. Li (Angew. Chem. Int. Ed. Engl. 1994, 33, 643) has shown the usefulness of such a method for classifying molecules as muscarinic or nicotinic agonists. Here, the method is extended to rank histamine H2 agonists in order of biological activity.