Protein secondary structure estimation with tree frowing up algorithm

There is interest in the methods were inspired by the natural processing systems at aim of solving NP type problems, recently. Genetic algorithms, ant colony algorithms, artificial neural Networks, particle swarm optimization, and artificial immune systems are used for optimization.In this thesis, tree growing up algorithm which was developed with respect to inspiring by growing up of trees, was used. Tree growing up algorithm consists of local and global search together, and it is a new method.Approximation method was used in this study, since the interactions amongs the amino acids are not known, analytically.In this study, we used amino acid primary structure chains. The angles of centre carbons in amino acids sequence in two dimensions were used by grouping centre carbons three by three. In order to accomplish this study, we used the actual angle values obtained from data bank for training of tree growing up algorithm. The proteins 1a9a, 1a89, 1bbe were used for testing process and angles? classes were determined for estimation of secondary structure of proteins.