We have developed a two-level case-based reasoning architecture for predicting protein secondary structure. The central idea is to break the problem into two levels: first, reasoning at the object (protein) level, and using the global information from this level to focus on a more restricted problem space; second, decomposing objects into pieces (segments), and reasoning at the internal structures level; finally, synthesizing the pieces back to the objects. The architecture has been implemented and tested on a commonly used data set with 69.3% predictive accuracy. It was then tested on a new data set with 67.3% accuracy. Additional experiments were conducted to determine the effects of using different similarity matrices.