New evolutionary approaches to protein structure prediction

Abstract

The problem of Protein Structure Prediction (PSP) is one of the principal topics in Bioinformatics. Multiple approaches have been developed in order to predict the protein structure of a protein. Determining the three dimensional structure of proteins is necessary to understand the functions of molecular protein level. An useful, and commonly used, representation for protein 3D structure is the protein contact map, which represents binary proximities (contact or non-contact) between each pair of amino acids of a protein. This thesis work, includes a compilation of the soft computing techniques for the protein structure prediction problem (secondary and tertiary structures). A novel evolutionary secondary structure predictor is also widely described in this work. Results obtained confirm the validity of our proposal. Furthermore, we also propose a multi-objective evolutionary approach for contact map prediction based on physico-chemical properties of amino acids. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. The rules obtained by the algorithm impose a set of conditions based on amino acid properties in order to predict contacts. Results obtained by our approach on four different protein data sets are also presented. Finally, a statistical study was performed to extract valid conclusions from the set of prediction rules generated by our algorithm.