Protein Classification by Matching and Clustering Surface Graphs M.A. Lozano, F. Escolano ∗ Departamento de Ciencia de la Computaci´ on e Inteligencia Artificial, Universidad de Alicante, E-03080, Alicante, Spain Abstract In this paper we address the problem of comparing and classifying protein surfaces with graph-based methods. Comparison relies on matching surface graphs, extracted from the surfaces by considering concave and convex patches, through a kernelized version of the Softassign graph-matching algorithm. On the other hand, classifica- tion is performed by clustering the surface graphs with an EM-like algorithm, also relying on kernelized Softassign, and then calculating the distance of an input sur- face graph to the closest prototype. We present experiments showing the suitability of kernelized Softassign for both comparing and classifying surface graphs. Key words: protein classification, graph matching, energy minimization, graph clustering, EM-algorithms PACS: 89.80.+h, 42.30.Sy, 42.30.Tz, 87.10.+e ∗ Corresponding author. Fax +34-965-903902 Email address: sco@dccia.ua.es (F. Escolano). Preprint submitted to Elsevier Science 9th August 2005