Improving prediction of protein subcellular localization using evolutionary information and sequence-order information

Subcellular location of a protein is one of the key functional characters as proteins must be localized correctly at the subcellular level to have normal biological function. In this work, a novel hybrid-classifier prediction method has been introduced, which uses evolutionary information and sequence-order information to improve prediction performance. Prediction results on different data sets show this method performs better or, at least very close to the best existing prediction methods. Further analysis indicates that this hybrid method is also a powerful tool for the prediction of eukaryotic protein subcellular localization