Accurate knowledge of protein structures is important for predicting protein function, and structure-based drug design for therapeutics. The gap between the number of experimentally determined structures and the number of known sequences continues to increase at a rapid rate. Hence, there is an urgent need for accurate and computationally efficient methods for protein structure prediction. The National Institutes of Health has awarded a 3-year, $744,725 grant to a team of researchers from Biochemistry, Biophysics, and Molecular Biology (Andrzej Kloczkowski , Robert Jernigan) Chemistry (Mark Gordon),Computer Science (Vasant Honavar), and Mathematics (Zhijun Wu) from Iowa State University in the United States and Janusz Bujnicki, Krzysztof Ginalski and Andrzej Kolinski from the International Institute of Molecular and Cell Biology and the Warsaw University in Poland to improve the accuracy of structures predicted by homology modeling, fold recognition, and de novo modeling. The resulting algorithms and software will significantly advance the current state-of-the-art in protein structure prediction.