Predictive Metagenomic Analysis of Autoimmune Disease Identifies Robust Autoimmunity and Disease Specific Microbial Signatures

Abstract

Within the last decade, numerous studies have demonstrated changes in the gut microbiome associated with specific autoimmune diseases. Due to differences in study design, data quality control, analysis and statistical methods, the results of these studies are inconsistent and incomparable. To better understand the relationship between the intestinal microbiome and autoimmunity, we have completed a comprehensive re-analysis of 29 studies focusing on the gut microbiome in nine autoimmune diseases to identify a specific microbial signature predictive of autoimmune disease using both 16S rRNA sequencing data and shotgun metagenomics data. Despite the heterogeneity of our data set, our approach has allowed us to build robust predictive models for general autoimmunity, as well as models for individual autoimmune diseases. Through this, we identified a number of common features predictive of autoimmune diseases including deficiency in Alistipes and Lachnobacterium, in addition to 9 inflammatory bowel disease, 7 multiple sclerosis and 7 rheumatoid disease predictive taxa consistently identified across multiple cohort comparison machine learning models. Lastly, we assessed potential metabolomic alterations based on metagenomic/metabolomic correlation analysis, identifying 114 metabolites associated with autoimmunity-predictive taxa.

Gut Microbiome in Progressive Multiple Sclerosis

“…This could reflect additional strain and species level variation in Akkermansia in RRMS, which we were able to identify through use of a new taxonomic reference database from EzBioCloud 30 . We and others have previously observed elevated levels of Akkermansia in RRMS, 9–11,18 and elevated Akkermansia in MS is also observed in a recent meta‐analysis of microbiota alterations in autoimmunity 65 . Of note, Akkermansia has been reported to have a beneficial role in multiple diseases 66,67 .…”

“…30 We and others have previously observed elevated levels of Akkermansia in RRMS, [9][10][11]18 and elevated Akkermansia in MS is also observed in a recent meta-analysis of microbiota alterations in autoimmunity. 65 Of note, Akkermansia has been reported to have a beneficial role in multiple diseases. 66,67 Akkermansia improves metabolism in obese and diabetic mice, 66,68 improves cancer check point immunotherapy, 69 is associated with the antiseizure effects of a ketogenic diet, 70 and improves disease in an animal model of amyotrophic lateral sclerosis.…”

Artificial Intelligence in Rheumatoid Arthritis: Current Status and Future Perspectives: A State-of-the-Art Review

“…However, in a recently published meta-analysis, Volkova and colleagues found specific features in the gut microbiome distinguishing RA from healthy controls and other autoimmune diseases using random forest algorithms. They found that increased levels of Clostridiaceae Clostridium and Lachnospiraceae and reduced abundance of Erysipelotrichaceae were the most distinctive features in RA compared to other autoimmune diseases [62]. In addition to the gut microbiome, assessment of the oral microbiome using ML approaches may also provide promising diagnostic biomarkers [63].…”

Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn’s disease with a publicly available untargeted metabolomics dataset

“…Additional cholates were identified from this knockoff filtering method, including additional taurine conjugates [32]. Carboxylates, such as 1,2,3,4-tetrahydro-beta-carboline-1,3-dicarboxylate, were elevated, and these metabolites significantly correlate with disease prediction [46]. Dodecanedioate was also identified as important [47].…”