Machine learning framework for gut microbiome biomarkers discovery and modulation analysis in large-scale obese population

Effect of time-restricted eating regimen on weight loss is mediated by gut microbiome

Time-restricted eating (TRE) is a promising obesity management strategy, but weight-loss efficacy varies among participants, and the underlying mechanism is unclear. The study aimed to investigate the role of gut microbiota in weight-loss response during long-term TRE intervention. We analyzed data from 51 obese adults in a 12-month TRE program, categorizing them into distinct weight loss groups (DG) and moderate weight loss groups (MG) based on their TRE responses. Shotgun metagenomic sequencing analysis revealed a significant increase in species closely associated with weight loss effectiveness and metabolic parameter changes in the DG group. Pathways related to fatty acid biosynthesis, glycogen biosynthesis, and nucleotide metabolism were reduced in the DG group and enhanced in the MG group. Next, we identified nine specific species at baseline that contributed better responses to TRE intervention and significant weight loss. Collectively, gut microbiota contributes to responsiveness heterogeneity in TRE and can predict weight-loss effectiveness.

Progress on network modeling and analysis of gut microecology: a review

The gut microecological network is a complex microbial community within the human body that plays a key role in linking dietary nutrition and host physiology. To understand the complex relationships among microbes and their functions within this community, network analysis has emerged as a powerful tool. By representing the interactions between microbes and their associated omics data as a network, we can gain a comprehensive understanding of the ecological mechanisms that drive the human gut microbiota. In addition, the network-based approach provides a more intuitive analysis of the gut microbiota, simplifying the study of its complex dynamics and interdependencies. This review provides a comprehensive overview of the methods used to construct and analyze networks in the context of gut microecological background. We discuss various types of network modeling approaches, including co-occurrence networks, causal networks, dynamic networks, and multi-omics networks, and describe the analytical techniques used to identify important network properties. We also highlight the challenges and limitations of network modeling in this area, such as data scarcity and heterogeneity, and provide future research directions to overcome these limitations. By exploring these network-based methods, researchers can gain valuable insights into the intricate relationships and functional roles of microbial communities within the gut, ultimately advancing our understanding of the gut microbiota's impact on human health.

Dysregulation of Microbiota in Patients With First-Episode Psychosis Is Associated With Symptom Severity and Treatment Response

BACKGROUND

The gut microbiome has been implicated in the pathogenesis of mental disorders where the gut-brain axis acts as a bidirectional communication network.

METHODS

Herein, we investigated the compositional and functional differences of gut microbiome between patients with first-episode psychosis (FEP) (n = 26) and healthy control participants (n = 22) using whole-genome shotgun sequencing. In addition, we assessed the oral microbiome in patients with FEP (n = 13) and listed their taxonomic diversity.

RESULTS

Our findings suggest that there is a dysbiosis of gut microbiota in patients with FEP. Relative abundance of Bifidobacterium adolescentis, Prevotella copri, and Turicibacter sanguinis was markedly increased (linear discriminant analysis scores [log10] > 1, and Mann-Whitney U test; false discovery rate-adjusted p values < .05) in the FEP group compared with the healthy control participants. Pathway analysis indicated that several metabolic pathways, particularly deoxyribonucleotide biosynthesis, branched-chain amino acid biosynthesis, tricarboxylic acid cycle, and fatty acid elongation and biosynthesis, were dysregulated in the FEP group compared with the healthy control group. In addition, this preliminary study was able to identify specific gut microbes (at baseline) that were predictive of weight gain in the FEP group at a 1-year follow-up. Bacteroides dorei, Bifidobacterium adolescentis, Turicibacter sanguinis, Roseburia spp., and Ruminococcus lactaris were positively associated (eXtreme gradient boosting, XGBoost regression model, Shapley additive explanations, R2 = 0.82) with weight gain.

CONCLUSIONS

Our findings may suggest the involvement of gut microbiota in the pathogenesis of psychosis. The benefit of modulation of the gut microbiome in the treatment of psychotic disorders should be explored further.

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.

From hype to hope: Considerations in conducting robust microbiome science

Microbiome science has been one of the most exciting and rapidly evolving research fields in the past two decades. Breakthroughs in technologies including DNA sequencing have meant that the trillions of microbes (particularly bacteria) inhabiting human biological niches (particularly the gut) can be profiled and analysed in exquisite detail. This microbiome profiling has profound impacts across many fields of research, especially biomedical science, with implications for how we understand and ultimately treat a wide range of human disorders. However, like many great scientific frontiers in human history, the pioneering nature of microbiome research comes with a multitude of challenges and potential pitfalls. These include the reproducibility and robustness of microbiome science, especially in its applications to human health outcomes. In this article, we address the enormous promise of microbiome science and its many challenges, proposing constructive solutions to enhance the reproducibility and robustness of research in this nascent field. The optimisation of microbiome science spans research design, implementation and analysis, and we discuss specific aspects such as the importance of ecological principals and functionality, challenges with microbiome-modulating therapies and the consideration of confounding, alternative options for microbiome sequencing, and the potential of machine learning and computational science to advance the field. The power of microbiome science promises to revolutionise our understanding of many diseases and provide new approaches to prevention, early diagnosis, and treatment.

GDmicro: classifying host disease status with GCN and deep adaptation network based on the human gut microbiome data

MOTIVATION

With advances in metagenomic sequencing technologies, there are accumulating studies revealing the associations between the human gut microbiome and some human diseases. These associations shed light on using gut microbiome data to distinguish case and control samples of a specific disease, which is also called host disease status classification. Importantly, using learning-based models to distinguish the disease and control samples is expected to identify important biomarkers more accurately than abundance-based statistical analysis. However, available tools have not fully addressed two challenges associated with this task: limited labeled microbiome data and decreased accuracy in cross-studies. The confounding factors, such as the diet, technical biases in sample collection/sequencing across different studies/cohorts often jeopardize the generalization of the learning model.

RESULTS

To address these challenges, we develop a new tool GDmicro, which combines semi-supervised learning and domain adaptation to achieve a more generalized model using limited labeled samples. We evaluated GDmicro on human gut microbiome data from 11 cohorts covering 5 different diseases. The results show that GDmicro has better performance and robustness than state-of-the-art tools. In particular, it improves the AUC from 0.783 to 0.949 in identifying inflammatory bowel disease. Furthermore, GDmicro can identify potential biomarkers with greater accuracy than abundance-based statistical analysis methods. It also reveals the contribution of these biomarkers to the host's disease status.

AVAILABILITY AND IMPLEMENTATION

https://github.com/liaoherui/GDmicro.

Human Genes Involved in the Interaction between Host and Gut Microbiome: Regulation and Pathogenic Mechanisms

Introduction: The umbrella term “human gut microbiota” describes the complex ecosystem harboring our gut. It includes bacteria, viruses, protozoa, archaea, fungi, and yeasts. This taxonomic classification does not describe its functions, which encompass nutrients digestion and absorption, immune system regulation, and host metabolism. “Gut microbiome” indicates instead the genome belonging to these “microbes” actively involved in these functions. However, the interaction between the host genome and the microbial ones determines the fine functioning of our organism. Methods: We reviewed the data available in the scientific literature on the definition of gut microbiota, gut microbiome, and the data on human genes involved in the interaction with the latter. We consulted the main medical databases using the following keywords, acronyms, and their associations: gut microbiota, gut microbiome, human genes, immune function, and metabolism. Results: Candidate human genes encoding enzymes, inflammatory cytokines, and proteins show similarity with those included in the gut microbiome. These findings have become available through newer artificial intelligence (AI) algorithms allowing big data analysis. From an evolutionary point of view, these pieces of evidence explain the strict and sophisticated interaction at the basis of human metabolism and immunity regulation in humans. They unravel more and more physiopathologic pathways included in human health and disease. Discussion: Several lines of evidence also obtained through big data analysis support the bi-directional role of gut microbiome and human genome in host metabolism and immune system regulation.