Computational protein chemistry has potential to contribute to the development of new therapeutic approaches in medicine in several different ways, including indirectly by increasing understanding of the disease-associated changes in protein structure that are mechanistically important, which can have diagnostic implications, as well as directly in designing peptides to counteract the patho-physiologic effects of these changes. Studies of the role of the tumor suppressor protein p53 in the carcinogenic process provide examples of both types of contribution. Computational studies of the effects of mutations in p53 on its structure have provided insights into cancer mechanisms and have served to elucidate potential new diagnostic approaches based on the identification of changes in p53 structure. Computational studies of p53 peptides have contributed to identifying and optimizing the structural characteristics that contribute to their activity in selectively killing cancer cells.