Multi-Domain Networks Association for Biological Data Using Block Signed Graph Clustering

Abstract

Multi-domain biological network association and clustering have attracted a lot of attention in biological data integration and understanding. In many problems, different domains may have different cluster structures. Due to growth of data collection from different sources, some domains may be strongly or weakly associated with the other domains. A key challenge is how to determine the degree of association among different domains, and to achieve accurate clustering results by data integration. In this paper, we propose an unsupervised learning approach for multi-domain network association by using block signed graph clustering. In particular, with consistency weights calculation, the proposed algorithm automatically identify domains relevant to each other strongly (or weakly) by assigning them larger (or smaller) weights. This approach not only significantly improve clustering accuracy but also understand multi-domain networks association. In each iteration of the proposed algorithm, we update consistency weights based on cluster structure of each domain, and then make use of different sets of eigenvectors to obtain different cluster structures in each domain. Experimental results on both synthetic data sets and real data sets (neuron activity data and gene expression data) empirically demonstrate the effectiveness of the proposed algorithm in clustering performance and in domain association capability.

A Graph Entropy Measure From Urelement to Higher-Order Graphlets for Network Analysis

“…T HERE are ubiquitous graph structures in various realworld complex systems, which call for trustworthy and effective graph characterization paradigms for more accurate and ultimately more useful representations. During the past decades, dozens of graph representation methods have been proposed for many networks, including communication networks [1], [2], social networks [3], [4], and biological networks [5], [6], etc. Generally, representation learning for networks is widely considered as a promising yet more challenging task, which This work was supported in part by the National Natural Science Foundation of China under Grant 61673178 and 61922063; in part by the Natural Science Foundation of Shanghai under Grant 20ZR1413800; in part by the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 824019 and 101022280.…”