Vernon, S. D. | Search bioRxiv

bioRxiv2024

BioMapAI: Artificial Intelligence Multi-Omics Framework Modeling of Myalgic Encephalomyelitis / Chronic Fatigue Syndrome

Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS) is a chronic illness with a multifactorial etiology and heterogeneous symptomatology, posing major challenges for diagnosis and treatment. Here, we present BioMapAI, a supervised deep neural network trained on a four-year, longitudinal, multi-omics dataset from 249 participants, which integrates gut metagenomics, plasma metabolomics, immune cell profiling, blood laboratory data, and detailed clinical symptoms. By simultaneously modeling these diverse data types to predict clinical severity, BioMapAI identifies disease- and symptom-specific biomarkers and robustly classifies ME/CFS in both held-out and independent external cohorts. Using an explainable AI approach, we construct the first connectivity map spanning the microbiome, immune system, and plasma metabolome in health and ME/CFS, adjusted for age, gender, and additional clinical factors. This map uncovers disrupted associations between microbial metabolism (e.g., short-chain fatty acids, branched-chain amino acids, tryptophan, benzoate), plasma lipids and bile acids, and heightened inflammatory responses in mucosal and inflammatory T cell subsets (MAIT, {gamma}{delta}T) secreting IFN{gamma} and GzA. Overall, BioMapAI provides unprecedented systems-level insights into ME/CFS, refining existing hypotheses and hypothesizing new pathways associated to the diseases heterogeneous symptoms.

bioinformatics↗

bioRxiv2019

Perturbation of effector and regulatory T cell subsets in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome (ME/CFS)

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating disorder of unknown etiology, and diagnosis of the disease is largely based on clinical symptoms. We hypothesized that immunological disruption is the major driver of this disease and analyzed a large cohort of ME/CFS patient or control blood samples for differences in T cell subset frequencies and functions. We found that the ratio of CD4+ to CD8+ T cells and the proportion of CD8+ effector memory T cells were increased, whereas NK cells were reduced in ME/CFS patients younger than 50 years old compared to a healthy control group. Remarkably, major differences were observed in Th1, Th2, Th17 and mucosal-associated invariant T (MAIT) T cell subset functions across all ages of patients compared to healthy subjects. While CCR6+ Th17 cells in ME/CFS secreted less IL-17 compared to controls, their overall frequency was higher. Similarly, MAIT cells from patients secreted lower IFN{gamma}, GranzymeA and IL-17 upon activation. Together, these findings suggest chronic stimulation of these T cell populations in ME/CFS patients. In contrast, the frequency of regulatory T cells (Tregs), which control excessive immune activation, was higher in ME/CFS patients. Finally, using a machine learning algorithm called random forest, we determined that the set of T cell parameters analyzed could identify more than 90% of the subjects in the ME/CFS cohort as patients (93% true positive rate or sensitivity). In conclusion, these multiple and major perturbations or dysfunctions in T cell subsets in ME/CFS patients suggest potential chronic infections or microbiome dysbiosis. These findings also have implications for development of ME/CFS specific immune biomarkers and reveal potential targets for novel therapeutic interventions.

immunology↗