| In the protein universe, many proteins are composed of two or more polypeptide chains, generally referred to as subunits. With the number of protein sequences rapidly increasing, we are faced a challenge of predicting the protein quaternary structure:how to develop an effective approach to predict whether it is formed just as a monomer, or as a dimer, trimer, or any other oligomers. This problem is very important because the functions of proteins are closely related to their quaternary structure.To explore this problem, this paper proposed a new method called Quat-PRE. Firstly, the features are adopted for the protein sequence based on the pseudo amino acid composition. Then the redundant features are removed by feature selection based on mRMR and wrapper. In the end, the results are obtained using SVM by5-fold cross validation from the training datasets.The results show that Quat-PRE has higher accuracy on the benchmark. And comparing with QSE software, which is develop by Robert Garian for classifying homodimer and non-homodimer, Quat-PRE is better than his QSE. |
