Semi-supervised learning protein complexes from protein interaction networks

New technological advances in large-scale proteinprotein interaction (PPI) detection provide researchers a valuable source for elucidating the bimolecular mechanism in the cell. In this paper, we investigate the problem of protein complex detection from noisy protein interaction data, i.e., finding the subsets of proteins that are closely coupled via protein interactions. Many people try to solve the problem by finding dense subgraphs in protein interaction networks with unsupervised methods. Here, we stand from a different point of view, redefining the properties and features for protein complexes and designing a “semi-supervised” method to analyze the problem. First we select some representative topological features and biological features to represent the protein complexes and then utilize the training data to build a multi-layer neural network model and finally detect hidden protein complexes in the protein-protein interaction networks with the obtained model. Experiments show the desirable properties of our proposed algorithm and the effectiveness of our approach.