Prediction of protein subcellular location based on grey dynamic model coefficients

Identifying the function of proteins is one of the major goals in cell biology and proteomics. Protein subcellular localization is a key functional characteristic of proteins and correct prediction of protein subcellular localization will greatly help in understanding its functions. Based on the concept of the pseudo amino acid composition (PseAA) by which a considerable amount of sequence-order effects can be incorporated into a set of discrete numbers, the grey dynamic model coefficients (GDMCs) are introduced. The advantage by incorporating the GDMCs as the pseudo amino acid components for a protein is that these can more effectively reflect overall sequence-order feature than the conventional correlation factors. It was demonstrated thru the jackknife test and independent dataset test that the overall success rate by the new approach was significantly higher than those by the others. It is anticipated that the concept of GDMCs composition can be also used to predict many other protein attributes, such as membrane protein type, enzyme functional class, GPCR type, protease type, among many others.