A prediction system for the classification of protein quaternary structure. QuaBingo is designed by three layers of classifiers that can categorize quaternary structural attributes of monomer, homooligomer, and heterooligomer. The first layer classifier identifies the structure type of the unknown protein sequence which is. Then, the result of the first layer of each class serves as input for the second layer classifier, which is used to integrate different features, considering different protein features in the predictive ability of the corresponding advantages and disadvantages to enhance the accuracy of prediction. The third layer classifier determines the structure type of the query protein. QuaBingo can overcome the problems of feature extraction encountered by functional domain composition: (i) some proteins may not contain any other known functional domains; and (ii) corresponding known functional domains are too few to represent proteins.
Department of Bioinformatics, Chung-Hua University, Taiwan; Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan; Department of Computer Science, Universiti Tunku Abdul Rahman, Jalan Universiti, Kampar, Malaysia; Biotechnology Center, Agricultural Biotechnology Center, Institute of Molecular Biology, Graduate Institute of Biotechnology, National Chung Hsing University, Taichung, Taiwan