Predicts two-class b-turns and the individual b-turn types. To proceed, NetTurnP uses evolutionary information and predicted protein sequence features. It was tested on a dataset of 426 non-homologous protein chains. The tool has obtained Matthews correlation coefficients values of 0.36 and 0.31 for the type specific b-turn predictions, type I and II, respectively. It can predict if an amino acid is located in a Beta-turn or not.