Ensemble of Probabilistic Neural Networks for Protein Fold Recognition

Protein data contain discriminative patterns that can be used in many beneficial applications if they are defined correctly. Protein classification in terms of fold recognition plays an important role in computational protein analysis, since it can contribute to the determination of the function of a protein whose structure is unknown. In this paper, a probabilistic neural network ensemble (PNNE) model is proposed for multi-class protein folds recognition problem. For training and evaluating the proposed method we use two datasets containing 27 SCOP folds. Experimental results show that the proposed method can improve the prediction accuracy and outperform other related approaches.