Microbial community pattern detection in human body habitats via ensemble clustering framework — ASN Events
  1. Schedule
  2. Welcome Reception & Poster Viewing 1
  3. Microbial community pattern detection in human body habitats via ensemble clustering framework

Microbial community pattern detection in human body habitats via ensemble clustering framework (#207)

PENG YANG 1 , Xiaoquan Su 2 , Le Ouyang 3 , Hon-Nian Chua 1 , Kang Ning 2 , Xiao-Li Li 1
  1. Institute for Infocomm Research, A*STAR, Singapore
  2. Qingdao Institute of Bioenergy and Bioprocess Technology, Qingdao, China
  3. Sun Yat-Sen University, Guangzhou, China

Background

The human habitat is a host where microbial species evolve, function, and continue to evolve. Elucidating how microbial community responds to human habitats is a fundamental and critical task, as establishing baselines of human microbiome is essential in understanding its role in disease and health. Recent studies on healthy human microbiome focus on particular body habitats, assuming that microbiome develop similar structural pattern to perform similar ecosystem function under same environmental conditions. However, current studies usually overlook a complex and interconnected landscape of human microbiome and limit the ability in particular body habitats with leaning models of specific criterion. Therefore, these methods could not capture the underlying microbial pattern efficiently.

Results

To obtain a comprehensive view, we propose a novel ensemble clustering framework to structure microbial community pattern on large-scale metagenomic data. We first build a microbial similarity network via integrating 1920 metagenomic samples from three body habitats of healthy adults. Then a novel symmetric Nonnegative Matrix Factorization (NMF) based ensemble model is proposed on the network to detect clustering pattern. Experiments are conducted to evaluate the effectiveness of our model on deriving microbial community with respect to body habitat and host gender. From clustering results, body habitat exhibits a strong bound but non-unique microbial structural pattern. Meanwhile, human microbiome reveals different degree of structural variation over body habitat and host gender.

Conclusions

In summary, our ensemble clustering framework could efficiently explore integrated clustering results to identify accurate microbial communities. The clustering results indicate that structure of human microbiome is varied systematically across body habitats and host genders. Such trends depict an integrated biography of microbial communities, which offer a new insight towards uncovering pathogenic model of human microbiome.