Dysbiosis signatures of gut microbiota and the progression of type 2 diabetes: a machine learning approach in a Mexican cohort

Abstract

IntroductionThe gut microbiota (GM) dysbiosis is one of the causal factors for the progression of different chronic metabolic diseases, including type 2 diabetes mellitus (T2D). Understanding the basis that laid this association may lead to developing new therapeutic strategies for preventing and treating T2D, such as probiotics, prebiotics, and fecal microbiota transplants. It may also help identify potential early detection biomarkers and develop personalized interventions based on an individual’s gut microbiota profile. Here, we explore how supervised Machine Learning (ML) methods help to distinguish taxa for individuals with prediabetes (prediabetes) or T2D.MethodsTo this aim, we analyzed the GM profile (16s rRNA gene sequencing) in a cohort of 410 Mexican naïve patients stratified into normoglycemic, prediabetes, and T2D individuals. Then, we compared six different ML algorithms and found that Random Forest had the highest predictive performance in classifying T2D and prediabetes patients versus controls.ResultsWe identified a set of taxa for predicting patients with T2D compared to normoglycemic individuals, including Allisonella, Slackia, Ruminococus_2, Megaspgaera, Escherichia/Shigella, and Prevotella, among them. Besides, we concluded that Anaerostipes, Intestinibacter, Prevotella_9, Blautia, Granulicatella, and Veillonella were the relevant genus in patients with prediabetes compared to normoglycemic subjects.DiscussionThese findings allow us to postulate that GM is a distinctive signature in prediabetes and T2D patients during the development and progression of the disease. Our study highlights the role of GM and opens a window toward the rational design of new preventive and personalized strategies against the control of this disease.

Association between gut microbiota and pan-dermatological diseases: a bidirectional Mendelian randomization research

“…Despite growing evidence of significant differences in gut microbiota composition and metabolic function in patients with urticaria compared to healthy populations ( Lu et al., 2019 ; Wang et al., 2021 ; Zhang et al., 2021 ), our study showed for the first time a significant correlation between increased abundance of the genus Intestinibacter and the risk of urticaria development, which was statistically significant even after FDR correction. There is limited research on this flora constituent, and studies have reported that the abundance of Intestinibacter is associated with type 2 diabetes mellitus ( Neri-Rosario et al., 2023 ), Crohn’s disease ( Forbes et al., 2018 ), prenatal depression ( Fang et al., 2023 ), and osteoporosis ( Akinsuyi and Roesch, 2023 ) and is also influenced by the HLA genotype ( Forbes et al., 2018 ), but its definitive role remains unknown. Functional analysis of Intestinibacter has shown that it is able to degrade fucose, suggesting an indirect involvement in intestinal mucus degradation ( Mueller et al., 2021 ), leading to a compromised intestinal barrier that allows microbes and toxins to infiltrate the body’s circulation and skin, triggering an immune response; however, whether there is a link between this activity and the development of urticaria remains to be investigated.…”

Microbiota Profiles of Hen Eggs from the Different Seasons and Different Sectors of Shanghai, China

“…Escherichia/shigella has been widely detected and described in gut microbiota and is a negative indicator for human diseases [31,32]. Recently, it has been reported as pathogenic or spoilage bacteria that appears on eggshell surfaces as well as in feces [7].…”

Oral administration of lysozyme protects against injury of ileum via modulating gut microbiota dysbiosis after severe traumatic brain injury

“…The difference between different groups was analyzed based on the nonmetric multidimensional scaling (NMDS) with Anosim. Random forest analysis is an ensemble method (combination of multiple classifiers) based on generating a set of uncorrelated decision trees to make a prediction, making it robust and suitable for complex data patterns ( Neri-Rosario et al., 2023 ). We used random forest as a machine-learning method to predicting the landmark bacteria.…”