Discrimination of Native Folds Using Network Properties of Protein Structures

Graph theoretic properties of proteins can be used to perceive the differences between correctly folded proteins and well designed decoy sets. 3D protein structures of proteins are represented with graphs. We used two different graph representations: Delaunay tessellations of proteins and contact map graphs. Graph theoretic properties for both graph types showed high classification accuracy for protein discrimination. Fisher, linear, quadratic, neural network, and support vector classifiers were used for the classification of the protein structures. The best classifier accuracy was over 98%. Results showed that characteristic features of graph theoretic properties can be used in the detection of native folds.