Prioritizing network communities

By Marinka Zitnik, Rok Sosic, Jure Leskovec. 2018

78 citations recorded by the source corpus.

Uncovering modular structure in networks is fundamental for systems in biology, physics, and engineering. Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory. Only a few communities can typically be validated, and it is thus important to prioritize which communities to select for downstream experimentation. Here we develop CRank, a mathematically principled approach for prioritizing network communities. CRank efficiently evaluates robustness and magnitude of structural features of each community and then combines these features into the community prioritization. CRank can be used with any community detection method. It needs only information provided by the network structure and does not require any additional metadata or labels. However, when available, CRank can incorporate domain-specific information to further boost performance. Experiments on many large networks show that CRank effectively prioritizes communities, yielding a nearly 50-fold improvement in community prioritization. Community detection allows one to decompose a network into its building blocks. While communities can be identified with a variety of methods, their relative importance can’t be easily derived. Here the authors introduce an algorithm to identify modules which are most promising for further analysis.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics, Network Science & Complex Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Statistical and Nonlinear Physics

In Network Science & Complex Systems

Citations in the corpus

Strategies for Pre-training Graph Neural Networks (2019, background): “This problem is exacerbated in important graph datasets from scientiﬁc domains, such as chemistry and biology, where data labeling ( e.g. , biological experiments in a wet laboratory) is resource-and time-intensive (Zitnik et al., 2018).”
Nine quick tips for analyzing network data (2019, background): “New kinds of networks are still emerging (for instance, cell–cell similarity networks [2], Hi-C networks, and image similarity networks [3]).”
Hierarchical cooperation of transcription factors from integration analysis of DNA sequences, ChIP-Seq and ChIA-PET data (2019, background): “A community of PPI is a candidate functional module [29, 30].”
Network medicine framework for identifying drug-repurposing opportunities for COVID-19 (2020, methodology): “As the optimal outcome, called the Kemeny consensus (29), is NP-hard to compute, we implemented three heuristic rank aggregation algorithms that approximate the Kemeny consensus: Borda’s count (30), the Dowdall method (31), and CRank (16).”
Graph Contrastive Learning with Augmentations (2020, background): “…labels can be extremely scarce for graph datasets (e.g. in biology and chemistry labeling through wet-lab experiments is often resource-and time-intensive) [15, 9], and pre-training can be a promising technique to mitigate the issue, as it does in convolutional neural networks (CNNs) [16, 17, 18].”
Exploration of prognosis-related microRNA and transcription factor co-regulatory networks across cancer types (2019, background): “Networks present modular structure, and decomposition of the network is beneficial for the elucidation of complex systems [38].”