Beta-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of beta-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class beta-turns and prediction of the individual beta-turn types by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of beta-turn and not-beta-turn. Furthermore NetTurnP shows improved performance on some of the specific beta-turn types. In the present work, neural network methods have been trained to predict beta-turn or not and individual beta-turn types from the primary amino acid sequence. The individual beta-turn types I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of beta-turn or not is a superset comprised of all beta-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC = 0.50, Qtotal
= 82.1%, sensitivity = 75.6%, PPV = 68.8% and AUC = 0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17 -0.47. For the type specific beta-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively.
The electronic version of this article is found here: download