Usefulness of Machine Learning-Based Gut Microbiome Analysis for Identifying Patients with Irritable Bowels Syndrome

Changes in Fecal Short-Chain Fatty Acids in IBS Patients and Effects of Different Interventions: A Systematic Review and Meta-Analysis

CONTEXT

Short-chain fatty acids (SCFAs) have been reported to be associated with the pathogenesis of irritable bowel syndrome (IBS), but the results are conflicting.

OBJECTIVE

Here, a systematic review of case-control studies detecting fecal SCFAs in IBS patients compared with healthy controls (HCs) and self-controlled studies or randomized controlled trials (RCTs) investigating fecal SCFA alterations after interventions were identified from several databases.

DATA SOURCES

A systematic search of databases (PubMed, Web of Science, and Embase) identified 21 studies published before 24 February 2023. Data extractions: Three independent reviewers completed the relevant data extraction.

DATA ANALYSIS

It was found that the fecal propionate concentration in IBS patients was significantly higher than that in HCs, while the acetate proportion was significantly lower. Low-FODMAP diets significantly reduced the fecal propionate concentration in the IBS patients while fecal microbiota transplantation and probiotic administration did not significantly change the fecal propionate concentration or acetate proportion.

CONCLUSIONS

The results suggested that the fecal propionate concentration and acetate proportion could be used as biomarkers for IBS diagnosis. A low-FODMAP diet intervention could potentially serve as a treatment for IBS while FMT and probiotic administration need more robust trials.

Temporal and fertilizer-dependent dynamics of soil bacterial communities in buckwheat fields under long-term management

This study integrated bacterial community and soil chemicals to characterize the soil ecosystem in an open upland field managed by six controlled fertilizer programs using the minimum amount of pesticides. Amplicon sequencing the 16S rRNA gene revealed that inorganic nitrogen fertilizer and compost altered the diversity and structure of the soil bacterial community throughout buckwheat (Fagopyrum esculentum Moench 'Hitachiakisoba') cultivation. The bacterial community comprised three clusters that contained bacteria that are prevalent in soils fertilized with nitrogen (cluster 1, 340 taxa), without nitrogen and compost (cluster 2, 234 taxa), and with compost-fertilized (cluster 3, 296 taxa). Cluster 2 contained more taxa in Actinobacteriota and less in Acidobacteriota, and cluster 3 contained more taxa in Gemmatimonadota compared with the other clusters. The most frequent taxa in cluster 1 were within the Chloroflexi phylum. The bacterial community structure correlated with soil chemical properties including pH, total organic carbon, SO42-, soluble Ca2+. A co-occurrence network of bacterial taxa and chemicals identified key bacterial groups comprising the center of a community network that determined topology and dynamics of the network. Temporal dynamics of the bacterial community structure indicated that Burkholderiales were associated with buckwheat ripening, indicating plant-bacteria interaction in the ecosystem.

A Systematic Review: Fecal Bacterial Profile in Patients with Irritable Bowel Syndrome Analyzed with the GA-Map Dysbiosis Test Based on the 16S rRNA Gene of Bacterial Species or Groups

Purpose

The diagnosis of irritable bowel syndrome (IBS) is based on symptom-based criteria due to lack of reliable disease-specific biomarkers. Gut microbiota is perturbed in IBS and when comparing different methods used to analyze gut microbiota, the results might be obscured. Therefore, in this systematic review we aimed to investigate the profile of fecal bacterial markers and dysbiosis index (DI) in patients with IBS and IBS subgroups compared to healthy controls (HCs) conducted by the same method (GA-map Dysbiosis Test based on16S rRNA sequencing).

Material and Method

We searched PubMed, EMBASE (Ovid) and Cochrane Library for case-control studies comparing fecal gut microbiota analyzed with the GA-map® Dysbiosis Test (Oslo, Norway) in patients with IBS and HCs. Our outcomes were the difference in fecal bacterial markers and DI in patients with IBS and IBS subgroups compared to HCs.

Results

The search identified 28 citations; five articles were included. Most studies evaluated fecal bacterial markers and DI in patients with diarrhea-predominant IBS (IBS-D). Results of fecal bacteria profile in IBS and IBS subgroups compared to HCs are inconsistent, however, two studies showed increased levels of Ruminococcus gnavus in IBS-D compared to HCs and results of DI indicated IBS and IBS subgroups (especially IBS-D) having higher DI compared to HCs.

Conclusion

This systematic review revealed inconsistent findings in respect to differences in bacterial markers between IBS and IBS subgroups with HCs in studies using the GA-map Dysbiosis Test based on 16S rRNA sequencing. However, the test is quite novel, and few studies have used the method so far. More research comparing fecal microbiota profile differences in IBS and IBS subgroups compared to HCs utilizing the same method of analysis is needed to give us further insight into the gut bacteria profile in IBS and the clinical consequences of intestinal dysbiosis.

Multi-omics approaches to studying gastrointestinal microbiome in the context of precision medicine and machine learning

The human gastrointestinal (gut) microbiome plays a critical role in maintaining host health and has been increasingly recognized as an important factor in precision medicine. High-throughput sequencing technologies have revolutionized -omics data generation, facilitating the characterization of the human gut microbiome with exceptional resolution. The analysis of various -omics data, including metatranscriptomics, metagenomics, glycomics, and metabolomics, holds potential for personalized therapies by revealing information about functional genes, microbial composition, glycans, and metabolites. This multi-omics approach has not only provided insights into the role of the gut microbiome in various diseases but has also facilitated the identification of microbial biomarkers for diagnosis, prognosis, and treatment. Machine learning algorithms have emerged as powerful tools for extracting meaningful insights from complex datasets, and more recently have been applied to metagenomics data via efficiently identifying microbial signatures, predicting disease states, and determining potential therapeutic targets. Despite these rapid advancements, several challenges remain, such as key knowledge gaps, algorithm selection, and bioinformatics software parametrization. In this mini-review, our primary focus is metagenomics, while recognizing that other -omics can enhance our understanding of the functional diversity of organisms and how they interact with the host. We aim to explore the current intersection of multi-omics, precision medicine, and machine learning in advancing our understanding of the gut microbiome. A multidisciplinary approach holds promise for improving patient outcomes in the era of precision medicine, as we unravel the intricate interactions between the microbiome and human health.

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.

The Potential Use of Artificial Intelligence in Irritable Bowel Syndrome Management

Irritable bowel syndrome (IBS) has a global prevalence of around 4.1% and is associated with a low quality of life and increased healthcare costs. Current guidelines recommend that IBS is diagnosed using the symptom-based Rome IV criteria. Despite this, when patients seek medical attention, they are usually over-investigated. This issue might be resolved by novel technologies in medicine, such as the use of Artificial Intelligence (AI). In this context, this paper aims to review AI applications in IBS. AI in colonoscopy proved to be useful in organic lesion detection and diagnosis and in objectively assessing the quality of the procedure. Only a recently published study talked about the potential of AI-colonoscopy in IBS. AI was also used to study biofilm characteristics in the large bowel and establish a potential relationship with IBS. Moreover, an AI algorithm was developed in order to correlate specific bowel sounds with IBS. In addition to that, AI-based smartphone applications have been developed to facilitate the monitoring of IBS symptoms. From a therapeutic standpoint, an AI system was created to recommend specific diets based on an individual's microbiota. In conclusion, future IBS diagnosis and treatment may benefit from AI.

Machine learning: a powerful tool for identifying key microbial agents associated with specific cancer types

Machine learning (ML) includes a broad class of computer programs that improve with experience and shows unique strengths in performing tasks such as clustering, classification and regression. Over the past decade, microbial communities have been implicated in influencing the onset, progression, metastasis, and therapeutic response of multiple cancers. Host-microbe interaction may be a physiological pathway contributing to cancer development. With the accumulation of a large number of high-throughput data, ML has been successfully applied to the study of human cancer microbiomics in an attempt to reveal the complex mechanism behind cancer. In this review, we begin with a brief overview of the data sources included in cancer microbiomics studies. Then, the characteristics of the ML algorithm are briefly introduced. Secondly, the application progress of ML in cancer microbiomics is also reviewed. Finally, we highlight the challenges and future prospects facing ML in cancer microbiomics. On this basis, we conclude that the development of cancer microbiomics can not be achieved without ML, and that ML can be used to develop tumor-targeting microbial therapies, ultimately contributing to personalized and precision medicine.

Frailty-Preventing Effect of an Intervention Program Using a Novel Complete Nutritional "COMB-FP Meal": A Pilot Randomized Control Trial

Frailty is a huge concern for the aging population, and dietary nutrition is considered a key factor in the prevention of aging. To solve the problem of frailty in the aging population, we developed a novel dietary intervention program using a novel COMpletely Balanced for Frailty Prevention (COMB-FP) meal, based on the Dietary Reference Intake for Japanese; in addition, we conducted a pilot randomized control trial comparing an exercise program only (control group) with exercise plus the COMB-FP meal program (test group). We included 110 male and female healthy volunteers with pre-frailty or frailty; the trial lasted for 12 weeks. Two daily meals were replaced with the COMB-FP meals during the trial in the test group. Walking speed and cognitive function were significantly improved in the test group compared with the control group. We observed a similar pattern in other frailty-related outcomes, such as occupancy of the microbiome, World Health Organization well-being index (WHO-5), and oxidative stress. Our study might indicate the importance of a well-balanced intake of nutrients for frailty prevention.

Overview of data preprocessing for machine learning applications in human microbiome research

Although metagenomic sequencing is now the preferred technique to study microbiome-host interactions, analyzing and interpreting microbiome sequencing data presents challenges primarily attributed to the statistical specificities of the data (e.g., sparse, over-dispersed, compositional, inter-variable dependency). This mini review explores preprocessing and transformation methods applied in recent human microbiome studies to address microbiome data analysis challenges. Our results indicate a limited adoption of transformation methods targeting the statistical characteristics of microbiome sequencing data. Instead, there is a prevalent usage of relative and normalization-based transformations that do not specifically account for the specific attributes of microbiome data. The information on preprocessing and transformations applied to the data before analysis was incomplete or missing in many publications, leading to reproducibility concerns, comparability issues, and questionable results. We hope this mini review will provide researchers and newcomers to the field of human microbiome research with an up-to-date point of reference for various data transformation tools and assist them in choosing the most suitable transformation method based on their research questions, objectives, and data characteristics.

A protease activity-based machine-learning approach as a complementary tool for conventional diagnosis of diarrhea-predominant irritable bowel syndrome

Irritable bowel syndrome (IBS) has no clinically accepted biomarkers even though it affects a large number of individuals worldwide. To address this lack of understanding, we evaluated peptidase activity in fecal samples from 35 patients with diarrheal IBS without symptom exacerbation (IBS-n) and 35 healthy subjects using a library of 384 fluorescent enzymatic substrate probes. IBS-n patients had high trypsin-like peptidase activity for cleavage of C-terminal lysine and arginine residues and low elastase-like activity for cleavage of C-terminal serine and glycine residues. These fluorescent probe library data, together with diagnostic machine-learning techniques, were able to accurately predict IBS-n. This approach can be used to diagnose diseases where no clinically accepted biomarkers exist, in which fecal enzyme activity is altered and also suggests that the development of new therapies targeting enzyme activities is possible.

Effect of Bifidobacterium bifidum G9-1 on the Intestinal Environment and Diarrhea-Predominant Irritable Bowel Syndrome (IBS-D)-like Symptoms in Patients with Quiescent Crohn's Disease: A Prospective Pilot Study

Diarrhea-predominant irritable bowel syndrome (IBS-D)-like symptoms are distressing for patients with quiescent Crohn's disease (qCD) and worsen their quality of life. In the present study, we assessed the effect of the probiotic Bifidobacterium bifidum G9-1 (BBG9-1) on the intestinal environment and clinical features in patients with qCD. Eleven patients with qCD, who met the Rome III diagnostic criteria for IBS-D, received BBG9-1 (24 mg) orally three times daily for 4 weeks. Indices of the intestinal environment (fecal calprotectin level and gut microbiome) and clinical features (CD/IBS-related symptoms, quality of life and stool irregularities) were evaluated before and after treatment. Treatment with BBG9-1 tended to reduce the IBS severity index in the studied patients (p = 0.07). Among gastrointestinal symptoms, abdominal pain and dyspepsia tended to be improved by the BBG9-1 treatment (p = 0.07 and p = 0.07, respectively), and IBD-related QOL showed a significant improvement (p = 0.007). With regard to mental status, the patient anxiety score was significantly lower at the endpoint of BBG9-1 treatment than at the baseline (p = 0.03). Although BBG9-1 treatment did not affect the fecal calprotectin level, it suppressed the serum MCP-1 level significantly and increased the abundance of intestinal Bacteroides in the study patients. The probiotic BBG9-1 is able to improve IBD-related QOL with a reduction of anxiety score in patients with quiescent CD and IBS-D-like symptoms.

Diarrhea-predominant Irritable Bowel Syndrome-like Symptoms in Patients With Quiescent Crohn's Disease: Comprehensive Analysis of Clinical Features and Intestinal Environment Including the Gut Microbiome, Organic Acids, and Intestinal Permeability

Background/Aims

Diarrhea-predominant irritable bowel syndrome (IBS-D)-like symptoms frequently occur in patients with quiescent Crohn's disease (CD). To investigate the factors underlying IBS-D-like symptoms in patients with quiescent CD, we performed a comprehensive analysis of the clinical features and intestinal environment in those patients.

Methods

We performed a prospective observational study of 27 patients with quiescent CD (CD activity index [CDAI] ≤ 150; C-reactive protein ≤ 0.3 mg/dL). The presence and severity of IBS-D-like symptoms, health-related quality of life, disease-specific quality of life, and status of depression and anxiety were evaluated. The level of intestinal permeability, fecal calprotectin and organic acids and the profiles of gut microbiome were analyzed.

Results

Twelve of the 27 patients with quiescent CD (44.4%) had IBS-like symptoms, and these patients showed a significantly higher CDAI, IBS severity index and anxiety score than those without. The inflammatory bowel disease questionnaire score was significantly lower in the patients with IBS-D-like symptoms. There were no significant differences in small intestinal/colonic permeability or the levels of organic acids between the patients with and without IBS-D-like symptoms. Fusicatenibacter was significantly less abundant in the patients with IBS-D-like symptoms whereas their fecal calprotectin level was significantly higher (384.8 ± 310.6 mg/kg) than in patients without (161.0 ± 251.0 mg/kg). The receiver operating characteristic curve constructed to predict IBS-D-like symptoms in patients with quiescent CD using the fecal calprotectin level (cutoff, 125 mg/kg) showed a sensitivity and specificity of 73.3% and 91.7%, respectively.

Conclusion

Minimal inflammation is closely associated with the development of IBS-D-like symptoms in patients with quiescent CD.

Bifico relieves irritable bowel syndrome by regulating gut microbiota dysbiosis and inflammatory cytokines

PURPOSE

Gut microbiota dysbiosis, a core pathophysiology of irritable bowel syndrome (IBS), is closely related to immunological and metabolic functions. Gut microbiota-based therapeutics have been recently explored in several studies. Bifico is a probiotic cocktail widely used in gastrointestinal disorders which relate to the imbalance of gut microbiota. However, the efficacy and potential mechanisms of Bifico treatment in IBS remains incompletely understood.

METHODS

Adopting a wrap restraint stress (WRS) -induced IBS mice model. Protective effect of Bifico in IBS mice was examined through abdominal withdrawal reflex (AWR) scores. 16S rDNA, ¹H nuclear magnetic resonance (¹H-NMR) and western blot assays were performed to analyze alterations of gut microbiota, microbiome metabolites and inflammatory cytokines, respectively.

RESULTS

Bifico could decrease intestinal visceral hypersensitivity. Although gut microbiota diversity did not increase, composition of gut microbiota was changed after treatment of Bifico, which were characterized by an increase of Proteobacteria phylum and Actinobacteria phylum, Muribaculum genus, Bifidobacterium genus and a decrease of Parabacteroides genus, Sutterella genus and Lactobacillus genus. Moreover, Bifico elevated the concentration of short-chain fatty acids (SCFAs) and reduced protein levels of interleukin-6 (IL-6) and tumor necrosis factor-α (TNF-α). From further Spearman's correlation analysis, Bifidobacterium genus were positively correlated with SCFAs including propionate, butyrate, valerate and negatively correlated with IL-6 and TNF-α.

CONCLUSION

Bifico could alleviate symptoms of IBS mice through regulation of the gut microbiota, elevating production of SCFAs and reducing the colonic inflammatory response.

The diagnostic potential and barriers of microbiome based therapeutics

High throughput technological innovations in the past decade have accelerated research into the trillions of commensal microbes in the gut. The 'omics' technologies used for microbiome analysis are constantly evolving, and large-scale datasets are being produced. Despite of the fact that much of the research is still in its early stages, specific microbial signatures have been associated with the promotion of cancer, as well as other diseases such as inflammatory bowel disease, neurogenerative diareses etc. It has been also reported that the diversity of the gut microbiome influences the safety and efficacy of medicines. The availability and declining sequencing costs has rendered the employment of RNA-based diagnostics more common in the microbiome field necessitating improved data-analytical techniques so as to fully exploit all the resulting rich biological datasets, while accounting for their unique characteristics, such as their compositional nature as well their heterogeneity and sparsity. As a result, the gut microbiome is increasingly being demonstrating as an important component of personalised medicine since it not only plays a role in inter-individual variability in health and disease, but it also represents a potentially modifiable entity or feature that may be addressed by treatments in a personalised way. In this context, machine learning and artificial intelligence-based methods may be able to unveil new insights into biomedical analyses through the generation of models that may be used to predict category labels, and continuous values. Furthermore, diagnostic aspects will add value in the identification of the non invasive markers in the critical diseases like cancer.

Differential analysis of microbiomes in mucus and tissues obtained from colorectal cancer patients

The outer mucus layer of the colorectal epithelium is easily removable and colonized by commensal microbiota, while the inner mucus layer is firmly attached to the epithelium and devoid of bacteria. Although the specific bacteria penetrating the inner mucus layer can contact epithelial cells and trigger cancer development, most studies ignore the degree of mucus adhesion at sampling. Therefore, we evaluated whether bacteria adhering to tissues could be identified by removing the outer mucus layer. Our 16S rRNA gene sequencing analysis of 18 surgical specimens of human colorectal cancer revealed that Sutterella (P = 0.045) and Enterobacteriaceae (P = 0.045) were significantly enriched in the mucus covering the mucosa relative to the mucosa. Rikenellaceae (P = 0.026) was significantly enriched in the mucus covering cancer tissues compared with those same cancer tissues. Ruminococcaceae (P = 0.015), Enterobacteriaceae (P = 0.030), and Erysipelotrichaceae (P = 0.028) were significantly enriched in the mucus covering the mucosa compared with the mucus covering cancers. Fusobacterium (P = 0.038) was significantly enriched in the mucus covering cancers compared with the mucus covering the mucosa. Comparing the microbiomes of mucus and tissues with mucus removed may facilitate identifying bacteria that genuinely invade tissues and affect tumorigenesis.

Precision Medicine Approaches with Metabolomics and Artificial Intelligence

Recent technological innovations in the field of mass spectrometry have supported the use of metabolomics analysis for precision medicine. This growth has been allowed also by the application of algorithms to data analysis, including multivariate and machine learning methods, which are fundamental to managing large number of variables and samples. In the present review, we reported and discussed the application of artificial intelligence (AI) strategies for metabolomics data analysis. Particularly, we focused on widely used non-linear machine learning classifiers, such as ANN, random forest, and support vector machine (SVM) algorithms. A discussion of recent studies and research focused on disease classification, biomarker identification and early diagnosis is presented. Challenges in the implementation of metabolomics–AI systems, limitations thereof and recent tools were also discussed.

Metagenomic Predictions: A Review 10 years on

Metagenomic predictions use variation in the metagenome (microbiome profile) to predict the unknown phenotype of the associated host. Metagenomic predictions were first developed 10 years ago, where they were used to predict which cattle would produce high or low levels of enteric methane. Since then, the approach has been applied to several traits and species including residual feed intake in cattle, and carcass traits, body mass index and disease state in pigs. Additionally, the method has been extended to include predictions based on other multi-dimensional data such as the metabolome, as well to combine genomic and metagenomic information. While there is still substantial optimisation required, the use of metagenomic predictions is expanding as DNA sequencing costs continue to fall and shows great promise particularly for traits heavily influenced by the microbiome such as feed efficiency and methane emissions.

Explainable Machine Learning for Longitudinal Multi-Omic Microbiome

Over the years, research studies have shown there is a key connection between the microbial community in the gut, genes, and immune system. Understanding this association may help discover the cause of complex chronic idiopathic disorders such as inflammatory bowel disease. Even though important efforts have been put into the field, the functions, dynamics, and causation of dysbiosis state performed by the microbial community remains unclear. Machine learning models can help elucidate important connections and relationships between microbes in the human host. Our study aims to extend the current knowledge of associations between the human microbiome and health and disease through the application of dynamic Bayesian networks to describe the temporal variation of the gut microbiota and dynamic relationships between taxonomic entities and clinical variables. We develop a set of preprocessing steps to clean, filter, select, integrate, and model informative metagenomics, metatranscriptomics, and metabolomics longitudinal data from the Human Microbiome Project. This study accomplishes novel network models with satisfactory predictive performance (accuracy = 0.648) for each inflammatory bowel disease state, validating Bayesian networks as a framework for developing interpretable models to help understand the basic ways the different biological entities (taxa, genes, metabolites) interact with each other in a given environment (human gut) over time. These findings can serve as a starting point to advance the discovery of novel therapeutic approaches and new biomarkers for precision medicine.

Metagenomics and artificial intelligence in the context of human health

Human microbiome is ubiquitous, dynamic, and site-specific consortia of microbial communities. The pathogenic nature of microorganisms within human tissues has led to an increase in microbial studies. Characterization of genera, like Streptococcus, Cutibacterium, Staphylococcus, Bifidobacterium, Lactococcus and Lactobacillus through culture-dependent and culture-independent techniques has been reported. However, due to the unique environment within human tissues, it is difficult to culture these microorganisms making their molecular studies strenuous. MGs offer a gateway to explore and characterize hidden microbial communities through a culture-independent mode by direct DNA isolation. By function and sequence-based MGs, Scientists can explore the mechanistic details of numerous microbes and their interaction with the niche. Since the data generated from MGs studies is highly complex and multi-dimensional, it requires accurate analytical tools to evaluate and interpret the data. Artificial intelligence (AI) provides the luxury to automatically learn the data dimensionality and ease its complexity that makes the disease diagnosis and disease response easy, accurate and timely. This review provides insight into the human microbiota and its exploration and expansion through MG studies. The review elucidates the significance of MGs in studying the changing microbiota during disease conditions besides highlighting the role of AI in computational analysis of MG data.

Host Genome-Metagenome Analyses Using Combinatorial Network Methods Reveal Key Metagenomic and Host Genetic Features for Methane Emission and Feed Efficiency in Cattle

Cattle production is one of the key contributors to global warming due to methane emission, which is a by-product of converting feed stuff into milk and meat for human consumption. Rumen hosts numerous microbial communities that are involved in the digestive process, leading to notable amounts of methane emission. The key factors underlying differences in methane emission between individual animals are due to, among other factors, both specific enrichments of certain microbial communities and host genetic factors that influence the microbial abundances. The detection of such factors involves various biostatistical and bioinformatics methods. In this study, our main objective was to reanalyze a publicly available data set using our proprietary Synomics Insights platform that is based on novel combinatorial network and machine learning methods to detect key metagenomic and host genetic features for methane emission and residual feed intake (RFI) in dairy cattle. The other objective was to compare the results with publicly available standard tools, such as those found in the microbiome bioinformatics platform QIIME2 and classic GWAS analysis. The data set used was publicly available and comprised 1,016 dairy cows with 16S short read sequencing data from two dairy cow breeds: Holstein and Nordic Reds. Host genomic data consisted of both 50 k and 150 k SNP arrays. Although several traits were analyzed by the original authors, here, we considered only methane emission as key phenotype for associating microbial communities and host genetic factors. The Synomics Insights platform is based on combinatorial methods that can identify taxa that are differentially abundant between animals showing high or low methane emission or RFI. Focusing exclusively on enriched taxa, for methane emission, the study identified 26 order-level taxa that combinatorial networks reported as significantly enriched either in high or low emitters. Additionally, a Z-test on proportions found 21/26 (81%) of these taxa were differentially enriched between high and low emitters (p value <.05). In particular, the phylum of Proteobacteria and the order Desulfovibrionales were found enriched in high emitters while the order Veillonellales was found to be more abundant in low emitters as previously reported for cattle (Wallace et al., 2015). In comparison, using the publicly available tool ANCOM only the order Methanosarcinales could be identified as differentially abundant between the two groups. We also investigated a link between host genome and rumen microbiome by applying our Synomics Insights platform and comparing it with an industry standard GWAS method. This resulted in the identification of genetic determinants in cows that are associated with changes in heritable components of the rumen microbiome. Only four key SNPs were found by both our platform and GWAS, whereas the Synomics Insights platform identified 1,290 significant SNPs that were not found by GWAS. Gene Ontology (GO) analysis found transcription factor as the dominant biological function. We estimated heritability of a core 73 taxa from the original set of 150 core order-level taxonomies and showed that some species are medium to highly heritable (0.25–0.62), paving the way for selective breeding of animals with desirable core microbiome characteristics. We identified a set of 113 key SNPs associated with >90% of these core heritable taxonomies. Finally, we have characterized a small set (<10) of SNPs strongly associated with key heritable bacterial orders with known role in methanogenesis, such as Desulfobacterales and Methanobacteriales.

Modeling approaches for probing cross-feeding interactions in the human gut microbiome

Microbial communities perform emergent activities that are essentially different from those carried by their individual members. The gut microbiome and its metabolites have a significant impact on the host, contributing to homeostasis or disease. Food molecules shape this community, being fermented through cross-feeding interactions of metabolites such as lactate, acetate, and amino acids, or products derived from macromolecule degradation. Mathematical and experimental approaches have been applied to understand and predict the interactions between microorganisms in complex communities such as the gut microbiota. Rational and mechanistic understanding of microbial interactions is essential to exploit their metabolic activities and identify keystone taxa and metabolites. The latter could be used in turn to modulate or replicate the metabolic behavior of the community in different contexts. This review aims to highlight recent experimental and modeling approaches for studying cross-feeding interactions within the gut microbiome. We focus on short-chain fatty acid production and fiber fermentation, which are fundamental processes in human health and disease. Special attention is paid to modeling approaches, particularly kinetic and genome-scale stoichiometric models of metabolism, to integrate experimental data under different diet and health conditions. Finally, we discuss limitations and challenges for the broad application of these modeling approaches and their experimental verification for improving our understanding of the mechanisms of microbial interactions.

Over-feeding the gut microbiome: A scoping review on health implications and therapeutic perspectives

The human gut microbiome has gained increasing attention over the past two decades. Several findings have shown that this complex and dynamic microbial ecosystem can contribute to the maintenance of host health or, when subject to imbalances, to the pathogenesis of various enteric and non-enteric diseases. This scoping review summarizes the current knowledge on how the gut microbiota and microbially-derived compounds affect host metabolism, especially in the context of obesity and related disorders. Examples of microbiome-based targeted intervention strategies that aim to restore and maintain an eubiotic layout are then discussed. Adjuvant therapeutic interventions to alleviate obesity and associated comorbidities are traditionally based on diet modulation and the supplementation of prebiotics, probiotics and synbiotics. However, these approaches have shown only moderate ability to induce sustained changes in the gut microbial ecosystem, making the development of innovative and tailored microbiome-based intervention strategies of utmost importance in clinical practice. In this regard, the administration of next-generation probiotics and engineered microbiomes has shown promising results, together with more radical intervention strategies based on the replacement of the dysbiotic ecosystem by means of fecal microbiota transplantation from healthy donors or with the introduction of synthetic communities specifically designed to achieve the desired therapeutic outcome. Finally, we provide a perspective for future translational investigations through the implementation of bioinformatics approaches, including machine and deep learning, to predict health risks and therapeutic outcomes.

Alterations in Gut Microbiome Composition and Function in Irritable Bowel Syndrome and Increased Probiotic Abundance with Daily Supplementation

Irritable bowel syndrome (IBS) is characterized by abdominal discomfort and irregular bowel movements and stool consistency. As such, the gut microbiome has been posited as being influential for the syndrome. However, identifying microbial features associated with IBS symptom heterogeneity is difficult without large cohorts. Our aim was to identify microbial features associated with IBS and IBS subtypes compared to healthy controls and to determine if a synbiotic supplementation intervention could decrease the proportion of those microbial features. Stool samples from 490 individuals with IBS (including all dominant subtypes) and 122 individuals without IBS were analyzed with metagenomic sequencing. One hundred thirty-four IBS subjects were followed over time while receiving daily synbiotic supplementation, the composition of which varied between participants. IBS participants had significantly lower alpha diversity, an enrichment in Gram-negative bacteria, and a reduction in pathways associated with short-chain fatty acid and vitamin synthesis. Shigella species were significantly associated with IBS, while Eubacterium rectale and Faecalibacterium prausnitzii were associated with healthy controls. Random forest identified unique and overlapping microbial features associated with each IBS subtype. Longitudinal assessment of 134 IBS subjects receiving synbiotic supplements demonstrated a significant difference in microbial features and an increase in probiotic abundance across time. We identified microbial features that differentiate healthy and IBS subtypes. Synbiotic supplementation in IBS subjects did not result in alpha diversity change in the microbiome but did demonstrate changes in microbial features. Future work is needed to determine if the observed microbiome changes are associated with IBS symptom improvement. IMPORTANCE An estimated 35 million people in the United States and 11.5% of the population globally are affected by IBS. Immunity, genetics, environment, diet, small intestinal bacterial overgrowth (SIBO), and the gut microbiome are all factors that contribute to the onset or triggers of IBS. With strong supporting evidence that the gut microbiome may influence symptoms associated with IBS, elucidating the important microbes that contribute to the symptoms and severity is important to make decisions for targeted treatment. As probiotics have become more common in treating IBS symptoms, identifying effective probiotics may help inform future studies and treatment.

A New Dawn for the Use of Artificial Intelligence in Gastroenterology, Hepatology and Pancreatology

Artificial intelligence (AI) is rapidly becoming an essential tool in the medical field as well as in daily life. Recent developments in deep learning, a subfield of AI, have brought remarkable advances in image recognition, which facilitates improvement in the early detection of cancer by endoscopy, ultrasonography, and computed tomography. In addition, AI-assisted big data analysis represents a great step forward for precision medicine. This review provides an overview of AI technology, particularly for gastroenterology, hepatology, and pancreatology, to help clinicians utilize AI in the near future.

Key Technologies for Progressing Discovery of Microbiome-Based Medicines

A growing number of experimental and computational approaches are illuminating the “microbial dark matter” and uncovering the integral role of commensal microbes in human health. Through this work, it is now clear that the human microbiome presents great potential as a therapeutic target for a plethora of diseases, including inflammatory bowel disease, diabetes and obesity. The development of more efficacious and targeted treatments relies on identification of causal links between the microbiome and disease; with future progress dependent on effective links between state-of-the-art sequencing approaches, computational analyses and experimental assays. We argue determining causation is essential, which can be attained by generating hypotheses using multi-omic functional analyses and validating these hypotheses in complex, biologically relevant experimental models. In this review we discuss existing analysis and validation methods, and propose best-practice approaches required to enable the next phase of microbiome research.

Profiling of host genetic alterations and intra-tumor microbiomes in colorectal cancer

Some bacteria are symbiotic in tumor tissues, and metabolites of several bacterial species have been found to cause DNA damage. However, to date, the association between bacteria and host genetic alterations in colorectal cancer (CRC) has not been fully investigated. We evaluated the association between the intra-tumor microbiome and host genetic alterations in 29 Japanese CRC patients. The tumor and non-tumor tissues were extracted from the patients, and 16S rRNA genes were sequenced for each sample. We identified enriched bacteria in tumor and non-tumor tissues. Some bacteria, such as Fusobacterium, which is already known to be enriched in CRC, were found to be enriched in tumor tissues. Interestingly, Bacteroides, which is also known to be enriched in CRC, was enriched in non-tumor tissues. Furthermore, it was shown that certain bacteria that often coexist within tumor tissue were enriched in the presence of a mutated gene or signal pathway with mutated genes in the host cells. Fusobacterium was associated with many mutated genes, as well as cell cycle-related pathways including mutated genes. In addition, the patients with a high abundance of Campylobacter were suggested to be associated with mutational signature 3 indicating failure of double-strand DNA break repairs. These results suggest that CRC development may be partly caused by DNA damage caused by substances released by bacterial infection. Taken together, the identification of distinct gut microbiome patterns and their host specific genetic alterations might facilitate targeted interventions, such as modulation of the microbiome in addition to anticancer agents or immunotherapy.

Probiotic Bifidobacterium bifidum G9-1 Has a Preventive Effect on the Acceleration of Colonic Permeability and M1 Macrophage Population in Maternally Separated Rats

Although probiotics may be useful for the treatment of irritable bowel syndrome (IBS), it is unclear how probiotics play a role in colonic mucosal integrity and immunity. Here, we aimed to investigate the effect of Bifidobacterium bifidum G9-1 (BBG9-1) on colonic mucosal integrity and macrophage behavior in rats subjected to maternal separation (MS) as a model of IBS. MS pups were individually separated from their mother rats, and a proportion of the MS rats were orally administered BBG9-1. The colonic mucosal permeability was evaluated by Ussing chamber assay. The expression of tight junction proteins and cytokines and the population of CD80-positive cells was examined in the colonic tissues by real-time reverse transcription-polymerase chain reaction (RT-PCR) and immunohistochemistry. Caco2 cells were stimulated with cytokines and the transepithelial electric resistance (TEER) was measured. MS rats showed significantly higher colonic permeability and lower claudin 4 expression in the colonic epithelium relative to controls. The number of CD80-positive macrophages was significantly increased in the colonic mucosa of MS rats, accompanied by the increase of IL-6 and IFN-γ expression. BBG9-1 treatment ameliorated the increase of M1 macrophage and IL-6/IFN-γ expression in the colonic tissue of MS rats. Simultaneously, BBG9-1 treatment improved the enhanced mucosal permeability and the decreased claudin 4 expression in the colon of MS rats. IL-6 and IFN-γ, whose expression is enhanced in the colon of MS rats, significantly decreased TEER in Caco2 cells in vitro. Probiotic BBG9-1 has a preventive effect on the acceleration of colonic permeability and M1 macrophage population in maternally separated rats.

A Machine Learning Approach to Study Glycosidase Activities from Bifidobacterium

This study aimed to recover metagenome-assembled genomes (MAGs) from human fecal samples to characterize the glycosidase profiles of Bifidobacterium species exposed to different prebiotic oligosaccharides (galacto-oligosaccharides, fructo-oligosaccharides and human milk oligosaccharides, HMOs) as well as high-fiber diets. A total of 1806 MAGs were recovered from 487 infant and adult metagenomes. Unsupervised and supervised classification of glycosidases codified in MAGs using machine-learning algorithms allowed establishing characteristic hydrolytic profiles for B. adolescentis, B. bifidum, B. breve, B. longum and B. pseudocatenulatum, yielding classification rates above 90%. Glycosidase families GH5 44, GH32, and GH110 were characteristic of B. bifidum. The presence or absence of GH1, GH2, GH5 and GH20 was characteristic of B. adolescentis, B. breve and B. pseudocatenulatum, while families GH1 and GH30 were relevant in MAGs from B. longum. These characteristic profiles allowed discriminating bifidobacteria regardless of prebiotic exposure. Correlation analysis of glycosidase activities suggests strong associations between glycosidase families comprising HMOs-degrading enzymes, which are often found in MAGs from the same species. Mathematical models here proposed may contribute to a better understanding of the carbohydrate metabolism of some common bifidobacteria species and could be extrapolated to other microorganisms of interest in future studies.

Applications of Machine Learning in Human Microbiome Studies: A Review on Feature Selection, Biomarker Identification, Disease Prediction and Treatment

The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach.