Community Detection in Large-Scale Bipartite Biological Networks

Abstract

Networks are useful tools to represent and analyze interactions on a large, or genome-wide scale and have therefore been widely used in biology. Many biological networks-such as those that represent regulatory interactions, drug-gene, or gene-disease associations-are of a bipartite nature, meaning they consist of two different types of nodes, with connections only forming between the different node sets. Analysis of such networks requires methodologies that are specifically designed to handle their bipartite nature. Community structure detection is a method used to identify clusters of nodes in a network. This approach is especially helpful in large-scale biological network analysis, as it can find structure in networks that often resemble a "hairball" of interactions in visualizations. Often, the communities identified in biological networks are enriched for specific biological processes and thus allow one to assign drugs, regulatory molecules, or diseases to such processes. In addition, comparison of community structures between different biological conditions can help to identify how network rewiring may lead to tissue development or disease, for example. In this mini review, we give a theoretical basis of different methods that can be applied to detect communities in bipartite biological networks. We introduce and discuss different scores that can be used to assess the quality of these community structures. We then apply a wide range of methods to a drug-gene interaction network to highlight the strengths and weaknesses of these methods in their application to large-scale, bipartite biological networks.

Keywords: biological network analysis; biological network clustering; community detection algorithms; community detection analysis; genomic data analysis; genomic networks; network analysis; networks.

Figure 1

Schematic visualization of bipartite community detection and its applications to large-scale biological networks. (A) An example of two communities (C1 and C2) detected in a bipartite network. (B) Possible applications of bipartite community detection in the analysis of large-scale biological networks. This includes pathway enrichment in communities, enrichment analysis of other biological properties by testing against external data, identification of “local hub” genes that are central to their community, node similarity detection, and community structure comparison between, for example,networks modeled on disease and control samples.

Figure 2

(A) Modularity, runtime of the method with default settings on a high-performance computing server (128 Intel Haswell cores, 1 Tb RAM), and number of communities obtained with running different community detection methods on the gene-drug interaction network. *Number of communities with more than four members/total number of communities in the gene node set. (B) Example “shell plot” of the ten largest communities detected in the drug-gene network using CONDOR. Communities are indicated with different colors.