Abstract
Lifestyle and physiological variables on human disease risk have been revealed to be mediated by gut microbiota. Low concordance between case-control studies for detecting disease-associated microbe existed due to limited sample size and population-wide bias in lifestyle and physiological variables. To infer gut microbiota-disease associations accurately, we propose to build machine learning models by including both human variables and gut microbiota. When the model’s performance with both gut microbiota and human variables is better than the model with just human variables, the independent gut microbiota -disease associations will be confirmed. By building models on the American Gut Project dataset, we found that gut microbiota showed distinct association strengths with different diseases. Adding gut microbiota into human variables enhanced the classification performance of IBD significantly; independent associations between occurrence information of gut microbiota and irritable bowel syndrome, C. difficile infection, and unhealthy status were found; adding gut microbiota showed no improvement on models’ performance for diabetes, small intestinal bacterial overgrowth, lactose intolerance, cardiovascular disease. Our results suggested that although gut microbiota was reported to be associated with many diseases, a considerable proportion of these associations may be very weak. We proposed a list of microbes as biomarkers to classify IBD and unhealthy status. Further functional investigations of these microbes will improve understanding of the molecular mechanism of human diseases.
Highlights
The human intestines are home to a dense microbial community, collectively known as the gut microbiota [1]
We focus on determining whether the whole gut microbiota is independently associated with human diseases by eliminating the influence of lifestyle factors using machine learning (ML) methods
By comparing the performance of models with only model using human variable data only (Meta) and models with both human variables and operational taxonomic units (OTUs) information (Meta-OTU abundance only (OTUab) and Meta-OTU occurrence only (OTUoc)), all diseases were classified into three categories: adding gut microbiota a) could improve, b) didn’t affect or c) reduced disease classification performance
Summary
The human intestines are home to a dense microbial community, collectively known as the gut microbiota [1]. Over the last few years, many case-control studies have been conducted to collect microbial 16S rRNA gene datasets from human fecal samples to explore the associations among the gut microbial community and human diseases to reveal diseasespecific microbial biomarkers [10, 11]. Gut microbiota reported by multiple studies of which abundance is differential between obese and lean individuals is inconsistent [12]. Sze and Schloss [13] comprehensively analyzed the results of several obesity-related studies. They found that the statistical detection power of a small-sample study was insufficient, and the ratio of abundance of Bacteroidetes and Firmicutes was not associated with obesity. Recent construction of a large dataset from the Swedish population did not reveal an apparent microbial signature associated with irritable bowel syndrome (IBS) as previously reported in the literature, and the heterogeneity of the microbial community among IBS patients was higher than that among healthy individuals [14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
