Characteristics of Fecal Microbiota and Machine Learning Strategy for Fecal Invasive Biomarkers in Pediatric Inflammatory Bowel Disease

Machine learning and artificial intelligence within pediatric autoimmune diseases: applications, challenges, future perspective

INTRODUCTION

Autoimmune disorders affect 4.5% to 9.4% of children, significantly reducing their quality of life. The diagnosis and prognosis of autoimmune diseases are uncertain because of the variety of onset and development. Machine learning can identify clinically relevant patterns from vast amounts of data. Hence, its introduction has been beneficial in the diagnosis and management of patients.

AREAS COVERED

This narrative review was conducted through searching various electronic databases, including PubMed, Scopus, and Web of Science. This study thoroughly explores the current knowledge and identifies the remaining gaps in the applications of machine learning specifically in the context of pediatric autoimmune and related diseases.

EXPERT OPINION

Machine learning algorithms have the potential to completely change how pediatric autoimmune disorders are identified, treated, and managed. Machine learning can assist physicians in making more precise and fast judgments, identifying new biomarkers and therapeutic targets, and personalizing treatment strategies for each patient by utilizing massive datasets and powerful analytics.

Inflammatory bowel disease genomics, transcriptomics, proteomics and metagenomics meet artificial intelligence

Various extrinsic and intrinsic factors such as drug exposures, antibiotic treatments, smoking, lifestyle, genetics, immune responses, and the gut microbiome characterize ulcerative colitis and Crohn's disease, collectively called inflammatory bowel disease (IBD). All these factors contribute to the complexity and heterogeneity of the disease etiology and pathogenesis leading to major challenges for the scientific community in improving management, medical treatments, genetic risk, and exposome impact. Understanding the interaction(s) among these factors and their effects on the immune system in IBD patients has prompted advances in multi-omics research, the development of new tools as part of system biology, and more recently, artificial intelligence (AI) approaches. These innovative approaches, supported by the availability of big data and large volumes of digital medical datasets, hold promise in better understanding the natural histories, predictors of disease development, severity, complications and treatment outcomes in complex diseases, providing decision support to doctors, and promising to bring us closer to the realization of the "precision medicine" paradigm. This review aims to provide an overview of current IBD omics based on both individual (genomics, transcriptomics, proteomics, metagenomics) and multi-omics levels, highlighting how AI can facilitate the integration of heterogeneous data to summarize our current understanding of the disease and to identify current gaps in knowledge to inform upcoming research in this field.

Huaier Polysaccharide Alleviates Dextran Sulphate Sodium Salt-Induced Colitis by Inhibiting Inflammation and Oxidative Stress, Maintaining the Intestinal Barrier, and Modulating Gut Microbiota

The incidence of ulcerative colitis (UC) is increasing annually, and UC has a serious impact on patients' lives. Polysaccharides have gained attention as potential drug candidates for treating ulcerative colitis (UC) in recent years. Huaier (Trametes robiniophila Murr) is a fungus that has been used clinically for more than 1000 years, and its bioactive polysaccharide components have been reported to possess immunomodulatory effects, antitumour potential, and renoprotective effects. In this study, we aimed to examine the protective effects and mechanisms of Huaier polysaccharide (HP) against UC. Based on the H2O2-induced oxidative stress model in HT-29 cells and the dextran sulphate sodium salt (DSS)-induced UC model, we demonstrated that Huaier polysaccharides significantly alleviated DSS-induced colitis (weight loss, elevated disease activity index (DAI) scores, and colonic shortening). In addition, HP inhibited oxidative stress and inflammation and alleviated DSS-induced intestinal barrier damage. It also significantly promoted the expression of the mucin Muc2. Furthermore, HP reduced the abundance of harmful bacteria Escherichia-Shigella and promoted the abundance of beneficial bacteria Muribaculaceae_unclassified, Anaerotruncus, and Ruminococcaceae_unclassified to regulate the intestinal flora disturbance caused by DSS. Nontargeted metabolomics revealed that HP intervention would modulate metabolism by promoting levels of 3-hydroxybutyric acid, phosphatidylcholine (PC), and phosphatidylethanolamine (PE). These results demonstrated that HP had the ability to mitigate DSS-induced UC by suppressing oxidative stress and inflammation, maintaining the intestinal barrier, and modulating the intestinal flora. These findings will expand our knowledge of how HP functions and offer a theoretical foundation for using HP as a potential prebiotic to prevent UC.

The intestinal microbial metabolite acetyl l-carnitine improves gut inflammation and immune homeostasis via CADM2

Intestinal symbiotic bacteria play a key role in the regulation of immune tolerance in inflammatory bowel disease (IBD) hosts. However, the bacterial strains directly involved in this regulation and their related metabolites are largely unknown. We sought to investigate the effects of intestinal microbial metabolites on intestinal epithelium and to elucidate their therapeutic potential in regulating intestinal mucosal inflammation and immune homeostasis. Here, we used metagenomic data from Crohn's disease (CD) patients to analyze the composition of intestinal flora and identify metabolite profiles associated with disease behavior, and used the mouse model of dextran sodium sulfate (DSS)-induced colitis to characterize the therapeutic effects of the flora metabolite acetyl l-carnitine (ALC) on DSS-induced colitis. We found that intraperitoneal injection of ALC treatment could significantly alleviate the symptoms of DSS-induced colitis in mice, including prevention of weight loss, reduction in disease activity index (DAI) scores, increasing of colonic length, reduction in histological scores, and improvement in intestinal barrier function. Further, transcriptome sequencing analysis and gene silencing experiments revealed that the absence of CADM2 abolished the inhibitory effect of ALC on the TLR-MyD88 pathway in colonic epithelial cells, thereby reducing the release of inflammatory factors in colon epithelial cells. And we confirmed a significant downregulation of CADM2 expression in intestinal tissues of CD patients compared to healthy people in a population cohort. In addition, we also found that ALC increased the ratio of Treg cells in colon, and decreased the ratio of Th17 cells and macrophages, thereby improving the immune tolerance of the organism. The proposed study could be a potential approach for the treatment of CD.

Proportion-based normalizations outperform compositional data transformations in machine learning applications

BACKGROUND

Normalization, as a pre-processing step, can significantly affect the resolution of machine learning analysis for microbiome studies. There are countless options for normalization scheme selection. In this study, we examined compositionally aware algorithms including the additive log ratio (alr), the centered log ratio (clr), and a recent evolution of the isometric log ratio (ilr) in the form of balance trees made with the PhILR R package. We also looked at compositionally naïve transformations such as raw counts tables and several transformations that are based on relative abundance, such as proportions, the Hellinger transformation, and a transformation based on the logarithm of proportions (which we call "lognorm").

RESULTS

In our evaluation, we used 65 metadata variables culled from four publicly available datasets at the amplicon sequence variant (ASV) level with a random forest machine learning algorithm. We found that different common pre-processing steps in the creation of the balance trees made very little difference in overall performance. Overall, we found that the compositionally aware data transformations such as alr, clr, and ilr (PhILR) performed generally slightly worse or only as well as compositionally naïve transformations. However, relative abundance-based transformations outperformed most other transformations by a small but reliably statistically significant margin.

CONCLUSIONS

Our results suggest that minimizing the complexity of transformations while correcting for read depth may be a generally preferable strategy in preparing data for machine learning compared to more sophisticated, but more complex, transformations that attempt to better correct for compositionality. Video Abstract.

Methodology for biomarker discovery with reproducibility in microbiome data using machine learning

BACKGROUND

In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on the discovery for potential biomarkers in the human microbiome using machine learning tools has produced positive outcomes. Despite the promising results, several issues can still be found in these studies such as datasets with small number of samples, inconsistent results, lack of uniform processing and methodologies, and other additional factors lead to lack of reproducibility in biomedical research. In this work, we propose a methodology that combines the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) in multiple datasets to increase reproducibility and obtain robust and reliable results in biomedical research.

RESULTS

Three experiments were performed analyzing microbiome data from patients/cases in Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). In each experiment, we found a biomarker signature in one dataset and applied to 2 other as further validation. The effectiveness of the proposed methodology was compared with other feature selection methods such as K-Best with F-score and random selection as a base line. The Area Under the Curve (AUC) was employed as a measure of diagnostic accuracy and used as a metric for comparing the results of the proposed methodology with other feature selection methods. Additionally, we use the Matthews Correlation Coefficient (MCC) as a metric to evaluate the performance of the methodology as well as for comparison with other feature selection methods.

CONCLUSIONS

We developed a methodology for reproducible biomarker discovery for 16s rRNA microbiome sequence analysis, addressing the issues related with data dimensionality, inconsistent results and validation across independent datasets. The findings from the three experiments, across 9 different datasets, show that the proposed methodology achieved higher accuracy compared to other feature selection methods. This methodology is a first approach to increase reproducibility, to provide robust and reliable results.

Combination of fenchone and sodium hyaluronate ameliorated constipation-predominant irritable bowel syndrome and underlying mechanisms

We sought to explore the protective effect of the combination of fenchone (FE) and sodium hyaluronate (SH) on ice water-induced IBS-C rats and the potential mechanism. The neurotransmitter levels, including substance P (SP), motilin (MTL), 5-hydroxytryptamine (5-HT), and vasoactive intestinal peptide (VIP), were determined by ELISA methods. The stem cell factors (SCF)/c-Kit signaling pathway-related protein and mRNA levels were determined by western blot and reverse transcription quantitative polymerase chain reaction (RT-qPCR) analyses, respectively. The expressions of tight ZO-1, Occludin, and Claudin-1 were also measured by western blot assay and immunofluorescence staining. The 16S rRNA gene sequence was used to measure the composition of gut microbiota. The co-administration of FE and SH improved the body weight, number of fecal pellets, fecal moisture, abdominal with drawal reflex score, and gastrointestinal transit rate in IBS-C rats. The unique efficacy of combination depended on the regulation of balance between excitatory and inhibitory neurotransmitters, enhancement of intestinal barrier function, and activation of SCF/c-Kit pathway. The gut microbiota structure was also restored. The ability of FE combined with SH to regulate SCF/c-Kit signaling pathway, enhance intestinal barrier function, and modulate gut microbiota contributes to their efficacy in managing IBS-C in rats.

Exploring the Plasticity of Diet on Gut Microbiota and Its Correlation with Gut Health

Dietary habits have been proven to help alter the composition of gut microbiota, and exploring the impact of nutritional patterns on gut microbiota changes can help protect gut health. However, few studies have focused on the dietary impact on the gut microbiota over an experimental timeframe. In this study, 16S rRNA gene sequencing was employed to investigate the gut microbiota of mice under different dietary patterns, including AIN-93G diet (Control), high protein diet (HPD), high fiber diet (HFD), and switch diet (Switch). The alpha diversity of the HPD group significantly decreased, but HFD can restore this decline. During HPD, some genera were significantly upregulated (e.g., Feacalibaculum) and downregulated (e.g., Parabacteroides). However, after receiving HFD, other genera were upregulated (e.g., Akkermansia) and downregulated (e.g., Lactobacillus). In addition, the interaction between pathogenic bacteria was more pronounced during HPD, while the main effect was probiotics during HFD. In conclusion, the plasticity exhibited by the gut microbiota was subject to dietary influences, wherein disparate dietary regimens hold pivotal significance in upholding the well-being of the host. Therefore, our findings provide new ideas and references for the relationship between diets and gut microbiota.

Barley Leaf Ameliorates Citrobacter-rodentium-Induced Colitis through Arginine Enrichment

Inflammatory bowel disease (IBD) has become a global public health challenge. Our previous study showed that barley leaf (BL) significantly reduces Citrobacter-rodentium (CR)-induced colitis, but its mechanism remains elusive. Thus, in this study, we used non-targeted metabolomics techniques to search for potentially effective metabolites. Our results demonstrated that dietary supplementation with BL significantly enriched arginine and that arginine intervention significantly ameliorated CR-induced colitis symptoms such as reduced body weight, shortened colon, wrinkled cecum, and swollen colon wall in mice; in addition, arginine intervention dramatically ameliorated CR-induced histopathological damage to the colon. The gut microbial diversity analysis showed that arginine intervention significantly decreased the relative abundance of CR and significantly increased the relative abundance of Akkermansia, Blautia, Enterorhabdus, and Lachnospiraceae, which modified the CR-induced intestinal flora disorder. Notably, arginine showed a dose-dependent effect on the improvement of colitis caused by CR.

Machine learning-based feature selection to search stable microbial biomarkers: application to inflammatory bowel disease

BACKGROUND

Biomarker discovery exploiting feature importance of machine learning has risen recently in the microbiome landscape with its high predictive performance in several disease states. To have a concrete selection among a high number of features, recursive feature elimination (RFE) has been widely used in the bioinformatics field. However, machine learning-based RFE has factors that decrease the stability of feature selection. In this article, we suggested methods to improve stability while sustaining performance.

RESULTS

We exploited the abundance matrices of the gut microbiome (283 taxa at species level and 220 at genus level) to classify between patients with inflammatory bowel disease (IBD) and healthy control (1,569 samples). We found that applying an already published data transformation before RFE improves feature stability significantly. Moreover, we performed an in-depth evaluation of different variants of the data transformation and identify those that demonstrate better improvement in stability while not sacrificing classification performance. To ensure a robust comparison, we evaluated stability using various similarity metrics, distances, the common number of features, and the ability to filter out noise features. We were able to confirm that the mapping by the Bray-Curtis similarity matrix before RFE consistently improves the stability while maintaining good performance. Multilayer perceptron algorithm exhibited the highest performance among 8 different machine learning algorithms when a large number of features (a few hundred) were considered based on the best performance across 100 bootstrapped internal test sets. Conversely, when utilizing only a limited number of biomarkers as a trade-off between optimal performance and method generalizability, the random forest algorithm demonstrated the best performance. Using the optimal pipeline we developed, we identified 14 biomarkers for IBD at the species level and analyzed their roles using Shapley additive explanations.

CONCLUSION

Taken together, our work not only showed how to improve biomarker discovery in the metataxonomic field without sacrificing classification performance but also provided useful insights for future comparative studies.

Gut microbial evidence chain in high-salt diet exacerbates intestinal aging process

Although excessive salt consumption appears to hasten intestinal aging and increases susceptibility to cardiovascular disease, the molecular mechanism is unknown. In this study, mutual validation of high salt (HS) and aging fecal microbiota transplantation (FMT) in C56BL/6 mice was used to clarify the molecular mechanism by which excessive salt consumption causes intestinal aging. Firstly, we observed HS causes vascular endothelial damage and can accelerate intestinal aging associated with decreased colon and serum expression of superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), and increased malondialdehyde (MDA); after transplantation with HS fecal microbiota in mice, vascular endothelial damage and intestinal aging can also occur. Secondly, we also found intestinal aging and vascular endothelial damage in older mice aged 14 months; and after transplantation of the older mice fecal microbiota, the same effect was observed in mice aged 6–8 weeks. Meanwhile, HS and aging significantly changed gut microbial diversity and composition, which was transferable by FMT. Eventually, based on the core genera both in HS and the aging gut microbiota network, a machine learning model was constructed which could predict HS susceptibility to intestinal aging. Further investigation revealed that the process of HS-related intestinal aging was highly linked to the signal transduction mediated by various bacteria. In conclusion, the present study provides an experimental basis of potential microbial evidence in the process of HS related intestinal aging. Even, avoiding excessive salt consumption and actively intervening in gut microbiota alteration may assist to delay the aging state that drives HS-related intestinal aging in clinical practice.

Dietary Oyster (Crassostrea gigas) Extract Ameliorates Dextran Sulfate Sodium-Induced Chronic Experimental Colitis by Improving the Composition of Gut Microbiota in Mice

Previously, we have reported that the intake of oyster extract (OE), prepared from Pacific oysters (Crassostrea gigas), can attenuate symptoms of dextran sulfate sodium (DSS)-induced acute experimental colitis in mice. Herein, we aimed to evaluate whether OE intake ameliorates chronic experimental colitis induced by repeated DSS administration in mice. Male C57BL/6J (4-week-old) mice were fed either the standard diet AIN93G (control diet) or the control diet containing 5.0% (w/w) OE (OE diet). After 21 days of diet feeding, chronic experimental colitis was induced by three cycles of 2.0% (w/w) DSS solution administration (5 days), followed by distilled water (5 days). Mice fed OE alleviated the shortened colonic length, increased the relative weight of the spleen, colonic histopathological score (regeneration), and blood in the stool score compared with mice fed control diet. A tendency to improve the α-diversity of fecal microbiota, which was exacerbated by colitis, was observed in mice fed OE. Correlation analysis suggested that the anti-colitis effect of OE intake could be related to the valeric acid content and relative abundances of Ruminococcus and Enterococcus in the feces. In conclusion, OE could ameliorate DSS-induced chronic experimental colitis by improving the gut environment, including the microbiota community and SCFA composition.