| Institution: | 1.School of Computer Science and Technology, Tianjin University,Tianjin,People’s Republic of China;2.Tianjin University Institute of Computational Biology,Tianjin,People’s Republic of China;3.School of Chemical Engineering and Technology, Tianjin University,Tianjin,People’s Republic of China;4.Department of Computer Science and Engineering, University of South Carolina,Columbia,USA;5.School of Information Engineering, Taiyuan University of Technology,Taiyuan,People’s Republic of China |
| Abstract: | BackgroundIdentifying complexes from PPI networks has become a key problem to elucidate protein functions and identify signal and biological processes in a cell. Proteins binding as complexes are important roles of life activity. Accurate determination of complexes in PPI networks is crucial for understanding principles of cellular organization.ResultsWe propose a novel method to identify complexes on PPI networks, based on different co-expression information. First, we use Markov Cluster Algorithm with an edge-weighting scheme to calculate complexes on PPI networks. Then, we propose some significant features, such as graph information and gene expression analysis, to filter and modify complexes predicted by Markov Cluster Algorithm. To evaluate our method, we test on two experimental yeast PPI networks.ConclusionsOn DIP network, our method has Precision and F-Measure values of 0.6004 and 0.5528. On MIPS network, our method has F-Measure and S n values of 0.3774 and 0.3453. Comparing to existing methods, our method improves Precision value by at least 0.1752, F-Measure value by at least 0.0448, S n value by at least 0.0771. Experiments show that our method achieves better results than some state-of-the-art methods for identifying complexes on PPI networks, with the prediction quality improved in terms of evaluation criteria. |
