We describe a large-scale, stochastic-perturbation global optimization algorithm used for determining the structure of proteins. The method incorporates secondary structure predictions (which describe the more basic elements of the protein structure) into the starting structures, and thereafter minimizes using a purely physics-based energy model. We have tested our approach in CASP competition, where many research groups compete in prediction of structures that have just been experimentally determined. Results show our method to be particularly successful on protein targets where structural information from similar proteins is unavailable, i.e., the most difficult targets for most protein structure prediction methods.