Subcellular localization prediction of eukaryotic proteins using functional domain frequency measure

Abstract

Biologically, the function of a protein is highly related to its subcellular localization. Accordingly, it is necessary to develop an automatic yet reliable method for protein subcellular localization prediction, especially when large-scale genome sequences are to be analyzed. Various methods have been proposed to perform the task. The results, however, are not satisfactory in terms of effectiveness and efficiency. The proposed functional domain frequency measure (FDFM) is considerably simple yet greatly effective for subcellular localization prediction in a supervised fashion. The experimental results demonstrate that the total accuracy for three separate datasets by the FDFM method can reach up to 89.4%, 93.5% and 89%, respectively.