Proteins are major constituents of living cells, forming many cellular components and most enzymes. So, knowledge of 3D protein structures is essential to understand biological mechanisms. Researchers often use neural networks to predict secondary structure in proteins, but the networks can be hard to interpret. This alternative method uses an optimal and interpretable hidden Markov model to classify protein residues. These HMM models account for the transitions observed in 3D structures and allow a predictive approach. We've developed a method for finding an optimal HMM to classify residues into secondary-structure classes. HMMs both provide a probabilistic framework for sequence treatment and produce interpretable models.