Structural pattern detection and domain recognition for protein function prediction

Official URL: http://192.168.1.20/record=b1293847 (Table of Contents)

Proteins are essential players of the cell that control and affect all functions. In proteins, structural patterns consist of a few amino acids which assemble in a specific arrangement. Due to their specific structures, they are recognized as the functionally important sites of the proteins, and conserved even in distantly related proteins. Moreover, several structural patterns merge and form domains which are also associated with the proteins function. In this work, we introduced a method for finding structure patterns common to a protein pair by using graphlet mappings. We presented protein structures with graphs, and then generate graphlets. Local alignments are produced by mapping the generated graphlets from protein pairs. Moreover, by merging these local alignments, we tried to recognize functionally important domains. These common domains are very useful in protein function prediction, fold classification and homology relationship detection. In this work, our algorithm was first applied to fold classification problem and 80% accuracy was observed. Furthermore, our algorithm was also used for protein function prediction and 97% accuracy was observed.