Combining hydrophobicity with PSSM for protein secondary structure prediction using BP neural network

Abstract

Objective Since predicting protein secondary structure is the basis of predicting protein spacial structure, it is important to improve the prediction accuracy of secondary structure. Methods A two-stage BP neural network was constructed based on the method of combining hydrophobicity of amino acid residues with PSSM which contains evolution information. CB513 dataset was employed in our study. After excluding the protein chains containing X,B and those with sequence length shorter than 30 amino acids, 492 protein chains in the dataset were used. The results of protein secondary structure prediction of our study were compared with those from the networks using only PSSN as their inputs. Accuracy of the network was tested by 4-fold cross-validation. Results In our study, α-helix was predicted with an averaged accuracy of nearly 79%, sensitivity of 79% and specificity of 91%. Total prediction accuracy of secondary structure reached 75.96%, which was higher than that of only using PSSM as input. Conclusion The new method developed can better predict protein secondary structure, especially α-helix with a higher accuracy. Key words: Protein secondary structure; Prediction; BP neural network; Hydrophobicity; Positionspecific scoring matrix