Predicting protein subcellular location based on improved quadratic discriminant

The location of a protein in a cell is closely correlated with its biological function. With the number of sequences entering into databanks rapidly increasing, it is highly desirable to predict a protein subcellular localization from its amino acid sequence. Here, a novel method is presented for the prediction of mouse protein subcellular location from sequence by using the increment of diversity combined with the improved quadratic discriminant analysis. The higher predictive success rates are obtained by the self-consistency test and the jackknife test. Our prediction results show that the improved quadratic discriminant analysis is very powerful to predict subcellular location of protein.