Hypergraph clustering based on modularity feature projection for high-order relationship community detection of...

Area of Science:

• Microbiology
• Computational Biology
• Ecology

Background:

• Microbial communities are crucial for ecosystem health and stability.
• Understanding microbial interactions, especially higher-order ones, is key to unlocking their functional potential.
• Current methods often focus on pairwise interactions, potentially missing complex community dynamics.

Purpose of the Study:

• To develop a novel method for detecting microbial communities within higher-order interaction networks.
• To improve the analysis of complex microbial community structures and functions.
• To provide a tool for ecological restoration, disease treatment, and drug development.

Main Methods:

• A hypergraph clustering method based on modularity feature projection (HCMFP) was proposed.
• Information entropy was utilized to mine higher-order logical relationships among microbes.
• A hypergraph learning model was constructed for microbial community detection.

Main Results:

• HCMFP demonstrated superior clustering performance compared to existing methods.
• The proposed method exhibited reliable convergence speed.
• HCMFP proved effective in identifying higher-order organizations within microbial interaction networks.

Conclusions:

• HCMFP is an effective tool for analyzing higher-order microbial interactions.
• This approach enhances our understanding of microbial community complexity and function.
• The method holds promise for applications in ecological restoration and medical treatments.