The Recognition of Subcellular Localization of Proteins Based on their N-Terminal Amino Acid Sequence

Functional annotation of unknown proteins is a major goal in proteomics. A key annotation is the prediction of a protein´s subcellular localization. We used the method of Increment of Diversity with Quadratic Discriminant analysis (IDQD) to predict subcellular localization of proteins which are recognized by the four plant categories and three non-plant and obtained accuracies at 87.4(plusmn0.5)% and 91.2(plusmn0.2)%, respectively in 5-fold cross-validation test. Our result is better than other methods currently published.