Association rule mining of the human gut microbiome

Abstract

The human gut carries a vast and diverse microbial community that is essential for human health. Understanding the structure of this complex community is a crucial step toward comprehending human-microbiome interactions. Traditional co-occurrence and correlation analyses typically focus on pairwise relationships and ignore higher-order relationships. Association rule mining (ARM) is a well-developed technique in data mining and has been applied to human microbiome data to identify higher-order relationships. Yet, existing attempts suffer from small sample sizes and low taxonomic resolution. We developed an advanced ARM framework and systematically investigated the interactions between microbial species using a public large-scale uniformly processed human microbiome data from the curatedMetagenomicData (CMD) together with ARM. First, we inferred association rules in the gut microbiome samples of healthy individuals (n=2,815) in CMD. Then we compared those rules with those inferred from the individuals with different diseases: inflammatory bowel disease (IBD, n=768), colorectal cancer (CRC, n=368), impaired glucose tolerance (IGT, n=199), and type 2 diabetes (T2D, n=164). Finally, we demonstrated that ARM is an efficient feature selection tool that can improve the performance of microbiome-based disease classification. Together, this study illustrates the higher-order microbial relationships in the human gut microbiome and highlights the critical importance of incorporating association rules in microbiome-based disease classification.

Keywords: gut microbiome; high-order associations; machine learning.