Image based system for surface matching in macromolecular screening

Computer vision technologies of structure matching based on surface representation have demonstrated their effectiveness in many research fields. In particular they can be successfully applied to in silico studies of molecular biology. Protein activities, in fact, are driven by their external characteristics, therefore the ability to match surfaces allows one to quickly infer information about possible interactions and functions of biological components. In this work we present a surface matching algorithm which is able to screen possible macromolecular interactions in terms of surface complementarities. The main characteristics of the algorithm is the exploitation of an intermediate level of data representation for 3D surfaces based on images of local description. This approach enables the matching of small pieces of surfaces, which is a crucial aspect when working in the biological context.