Knowledge of the polyprotein cleavage sites by HIV protease will refine our understanding of its specificity and the information thus acquired is useful for designing specific and efficient HIV protease inhibitors. The pace in searching for the proper inhibitors of HIV protease will be greatly expedited if one can find an accurate and rapid method for predicting the cleavage sites in proteins by HIV protease. Various prediction models or algorithms have been developed during the past 5 years. This Review is devoted to addressing the following problems: (1) Why is it important to predict the cleavability of a peptide by HIV protease? (2) What progresses have been made in developing the prediction methods, and what merits and weakness does each of these methods carry? The attention is focused on the state-of-the-art, which is featured by a discriminant function algorithm developed very recently as well as an improved database (the program and database are available upon request) established according to new experimental results.