MuDCoD: Multi-Subject Community Detection in Personalized Dynamic Gene Networks from Single Cell RNA Sequencing

Developments in single-cell RNA sequencing (scRNA-seq) advanced our understanding of transcriptional programs of different cell types and cellular stages at the individual cell level. Single-cell RNA-seq datasets across multiple individuals and time points are now routinely generated for different conditions. Analysis of personalized dynamic gene networks constructed from these datasets could unravel subject-specific network-level variation critical for phenotypic differences. While there have been developments in the gene module discovery methods on networks estimated from scRNA-seq data, these have mostly focused on static gene networks. In this work, we develop MuDCoD to cluster genes in personalized dynamic gene networks and identify gene modules that vary not only across time but also among subjects. To this end, MuDCoD extends the global spectral clustering framework of the previously developed method, PisCES, to promote information sharing among the subject as well as the time domain. Our computational experiments across a wide variety of settings indicate that, when present, MuDCoD leverages shared signals among networks of the subjects, and performs robustly when subjects do not share any apparent information. An application to human-induced pluripotent stem cell scRNA-seq data during dopaminergic neuron differentiation indicates that MuDCoD enables robust inference for identifying time-varying personalized gene modules. Our results illustrate how personalized dynamic community detection can aid the exploration of subject-specific biological processes that vary across time.

A Novel Emerging Topic Identification and Evolution Discovery Method on Time-Evolving and Heterogeneous Online Social Networks

With the fast development of web 2.0, information generation and propagation among online users become deeply interweaved. How to effectively and immediately discover the new emerging topic and further how to uncover its evolution law are still wide open and urgently needed by both research and practical fields. This paper proposed a novel early emerging topic detection and its evolution law identification framework based on dynamic community detection method on time-evolving and scalable heterogeneous social networks. The framework is composed of three major steps. Firstly, a time-evolving and scalable complex network denoted as KeyGraph is built up by deeply analyzing the text features of all kinds of data crawled from heterogeneous online social network platforms; secondly, a novel dynamic community detection method is proposed by which the new emerging topic is detected on the modeled time-evolving and scalable KeyGraph network; thirdly, a unified directional topic propagation network modeled by a great number of short texts including microblogs and news titles is set up, and the topic evolution law of the previously detected early emerging topic is identified by fully utilizing local network variations and modularity optimization of the “time-evolving” and directional topic propagation network. Our method is proved to yield preferable results on both a huge amount of computer-generated test data and a great amount of real online network data crawled from mainstream heterogeneous social networks.

Intelligent Link Prediction Management Based on Community Discovery and User Behavior Preference in Online Social Networks

Link prediction in online social networks intends to predict users who are yet to establish their network of friends, with the motivation of offering friend recommendation based on the current network structure and the attributes of nodes. However, many existing link prediction methods do not consider important information such as community characteristics, text information, and growth mechanism. In this paper, we propose an intelligent data management mechanism based on relationship strength according to the characteristics of social networks for achieving a reliable prediction in online social networks. Secondly, by considering the network structure attributes and interest preference of users as important factors affecting the link prediction process in online social networks, we propose further improvements in the prediction process by designing a friend recommendation model with a novel incorporation of the relationship information and interest preference characteristics of users into the community detection algorithm. Finally, extensive experiments conducted on a Twitter dataset demonstrate the effectiveness of our proposed models in both dynamic community detection and link prediction.

Dynamic Community Structure in Online Social Groups

One of the main ideas about the Internet is to rethink its services in a user-centric fashion. This fact translates to having human-scale services with devices that will become smarter and make decisions in place of their respective owners. Online Social Networks and, in particular, Online Social Groups, such as Facebook Groups, will be at the epicentre of this revolution because of their great relevance in the current society. Despite the vast number of studies on human behaviour in Online Social Media, the characteristics of Online Social Groups are still unknown. In this paper, we propose a dynamic community detection driven study of the structure of users inside Facebook Groups. The communities are extracted considering the interactions among the members of a group and it aims at searching dense communication groups of users, and the evolution of the communication groups over time, in order to discover social properties of Online Social Groups. The analysis is carried out considering the activity of 17 Facebook Groups, using 8 community detection algorithms and considering 2 possible interaction lifespans. Results show that interaction communities in OSGs are very fragmented but community detection tools are capable of uncovering relevant structures. The study of the community quality gives important insights about the community structure and increasing the interaction lifespan does not necessarily result in more clusterized or bigger communities.