Prediction subcellular localization of Gram-negative bacterial proteins by support vector machine using wavelet denoising and Chou's pseudo amino acid composition

- A new method (WD-SVM) to prediction protein subcellular localization.
- 2-D wavelet denoising can effectively remove redundant information in protein sequences.
- The optimal parameters of the prediction model are discussed from several aspects.
- We investigate the effect of the six prediction algorithms on the results.
- The proposed method increases the prediction performance over several methods.

Information on the subcellular localization of Gram-negative bacterial proteins is of great significance to study the pathogenesis, drug design and discovery of certain diseases. Protein subcellular localization is an important part of proteomics, while providing new opportunities and challenges for chemometrics. Since the prediction of protein subcellular localization can help to understand their function and the role played by their metabolic processes, a number of protein subcellular localization prediction methods have been developed in recent years. In this paper, we propose a novel method by combining wavelet denoising with support vector machine to predict the subcellular localization of proteins for the first time. Firstly, the features of the protein sequence are extracted by Chou's pseudo amino acid composition (PseAAC), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of the Gram-negative bacterial proteins. Quite promising predictions are obtained using the jackknife test and compared with other predictive methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of protein subcellular localization, and it can be used to predict the other attributes of proteins.