Overlapping Protein Complexes Detection Based on Multi-level Topological Similarities

Protein complex detection is an important issue in the field of system biology, which is crucial to understanding the cellular organization and inferring protein functions. In recent years, various computational methods have been proposed to detect protein complexes from protein-protein interaction (PPI) networks. Unfortunately, most of these methods only use the local information of PPI networks and treat protein complexes as dense subgraphs, ignoring the global topology information of PPI networks. To address these limitations, we propose a new method, named OPCMTS, to detect overlapping protein complexes by simultaneously considering the local topological information and global topological information of PPI network. First, a local similarity matrix is constructed via calculating the Jaccard coefficients between proteins in the original PPI network. Then, we adopt a hierarchical compressing strategy to get multiple levels of gradually compressed smaller networks from the original PPI network and apply a network embedding model to learn protein embeddings from the compressed networks at multiple levels. The protein embeddings from these networks are concatenated and a dimensionality reduction strategy is adopted to remove the redundancy of the concatenated embeddings to generate the final embeddings. Further, a global similarity matrix is constructed by calculating the cosine similarity of the final embeddings. Finally, a core-attachment strategy is used to detect overlapping protein complexes based on the local and global similarity matrices. The experimental results prove that the proposed OPCMTS method outperforms other five state-of-the-art methods in terms of F-measure on two yeast datasets.