Secondary structure prediction of all-helical proteins in two states

Can secondary structure prediction be improved by prediction rules that focus on a particular structural class of proteins? To help answer this question, we have assessed the accuracy of prediction for all-helical proteins, using two conceptually different methods and two levels of description. An overall two-state single-residue accuracy of approximately 80% can be obtained by a neural network, no matter whether it is trained on two states (helix and non-helix) or first trained on three states (helix, strand and loop) and then evaluated on two states. For four test proteins, this is similar to the accuracy obtained with inductive logic programming. We conclude that on the level of secondary structure, there is no practical advantage in training on two states, especially given the added margin of error in identifying the structural class of a protein. In the further development of these methods, it is increasingly important to focus on aspects of secondary structure that aid in the construction of a correct 3-D model, such as the correct placement of segments.