Prediction of G-Protein-Coupled Receptor Classes with Pseudo Amino Acid Composition

G-protein-coupled receptors (GPCRs), the largest family of cell surface receptors play an important role in production of therapeutic drugs. However, the functions of many of GPCRs are unknown. Hence we develop an new method for classifying the family of GPCRs. It is difficult to predict the classification of GPCRs by means of conventional sequence alignment approaches because of their highly divergent nature. In this study, based on the concept of pseudo amino acid composition (PseAA), approximate entropy (ApEn) of protein sequence as additional characteristics is used to construct PseAA. A 21-D (dimensional) PseAA is formulated to represent the sample of a protein. Fuzzy K nearest neighbors (FKNN) classifier is applied as prediction engine. The datasets in low homology are used to validate the performance of the proposed method. Compared to others' research by now, the prediction accuracies of our research is the highest. The test results indicate that ApEn can play a complimentary role to many of the existing methods, which will be a useful tool for GPCRs function prediction.