Interest in protein structure prediction is wide-spread, and has been previously addressed using evolutionary algorithms. In this study we report results of a modified fmGA, which is found to be good at finding semi-optimal solutions in reasonable time. Our study focuses on tuning this fmGA in an attempt to improve the effectiveness and efficiency of the algorithm in solving a protein structure and in finding better ways to identify secondary structures. Problem definition, protein model representation, mapping to algorithm domain, tool selection modifications and conducted experiments are discussed