A new method to discover similar substructures in protein binding pockets, independently of sequence and folding patterns or secondary structure elements, is introduced. The solvent-accessible surface of a binding pocket, automatically detected as a depression on the protein surface, is divided into a set of surface patches. Each surface patch is characterized by its shape as well as by its physicochemical characteristics. Wavelets defined on surfaces are used for the description of the shape, as they have the great advantage of allowing a comparison at different resolutions. The number of coefficients to describe the wavelets can be chosen with respect to the size of the considered data set. The physicochemical characteristics of the patches are described by the assignment of the exposed amino acid residues to one or more of five different properties determinant for molecular recognition. A self-organizing neural network is used to project the high-dimensional feature vectors onto a two-dimensional layer of neurons, called a map. To find similarities between the binding pockets, in both geometrical and physicochemical features, a clustering of the projected feature vector is performed using an automatic distance- and density-based clustering algorithm. The method was validated with a small training data set of 109 binding cavities originating from a set of enzymes covering 12 different EC numbers. A second test data set of 1378 binding cavities, extracted from enzymes of 13 different EC numbers, was then used to prove the discriminating power of the algorithm and to demonstrate its applicability to large scale analyses. In all cases, members of the data set with the same EC number were placed into coherent regions on the map, with small distances between them. Different EC numbers are separated by large distances between the feature vectors. A third data set comprising three subfamilies of endopeptidases is used to demonstrate the ability of the algorithm to detect similar substructures between functionally related active sites. The algorithm can also be used to predict the function of novel proteins not considered in training data set.

This paper presents a new algorithm to compare substructural epitopes in protein binding cavities. Through the comparison of binding cavities accommodating well characterized ligands with cavities whose actual guests are yet unknown, it is possible to draw some conclusions on the required shape of a putative ligand likely to bind to the latter cavities. To detect functional relationships among proteins, their binding-site exposed physicochemical characteristics are described by assigning generic pseudocenters to the functional groups of the amino acids flanking the particular active site. The cavities are divided into small local regions of four pseudocenters having the shape of a pyramid with triangular basis. To find similar local regions, an emergent self-organizing map is used for clustering. Two local regions within the same cluster are similar and form the basis for the superpositioning of the corresponding cavities to score this match. First results show that the similarities between enzymes with the same EC number can be found correctly. Enzymes with different EC numbers are detected to have no common substructures. These results indicate the benefit of this method and motivate further studies.

A new method has been developed to find similar substructures in protein binding cavities. It is based on the idea that protein function is intimately related to the recognition and subsequent response to the binding of an endogenous ligand in a well-characterized binding pocket. It can therefore be assumed that proteins having similar binding cavities also bind similar ligands and exhibit related function. For the comparison of the binding cavities, the binding-site exposed physicochemical characteristics are described by assigning generic pseudocenters to the functional groups of the amino acids flanking a particular active site. These pseudocenters are assembled into small substructures. To find substructures with spatial similarity and appropriate chemical properties, an emergent self-organizing map is used for clustering. Two substructures which are found to be similar form the basis for an expanded comparison of the complete cavities. Preliminary results with four pairs of binding cavities show that similarities are detected correctly and motivate further studies.

Abstract. The molecular function of a protein is coupled to the binding of a substrate or an endogenous ligand to a well defined binding cavity. To detect functional relationships among proteins, their binding-site exposed physicochemical characteristics were described by assigning generic pseudocenters to the functional groups of the amino acids flanking a particular active site. These pseudocenters were assembled into small substructures and their spatial similarity with appropriate chemical properties was examined. If two substructures of two binding cavities are found to be similar, they form the basis for an expanded comparison of the complete cavities. Preliminary tests indicate the benefit of this method and motivate further studies.