MiMeNet: Exploring microbiome-metabolome relationships using neural networks

Connecting metabolome and phenotype: recent advances in functional metabolomics tools for the identification of bioactive natural products

Covering: 1995 to 2023Advances in bioanalytical methods, particularly mass spectrometry, have provided valuable molecular insights into the mechanisms of life. Non-targeted metabolomics aims to detect and (relatively) quantify all observable small molecules present in a biological system. By comparing small molecule abundances between different conditions or timepoints in a biological system, researchers can generate new hypotheses and begin to understand causes of observed phenotypes. Functional metabolomics aims to investigate the functional roles of metabolites at the scale of the metabolome. However, most functional metabolomics studies rely on indirect measurements and correlation analyses, which leads to ambiguity in the precise definition of functional metabolomics. In contrast, the field of natural products has a history of identifying the structures and bioactivities of primary and specialized metabolites. Here, we propose to expand and reframe functional metabolomics by integrating concepts from the fields of natural products and chemical biology. We highlight emerging functional metabolomics approaches that shift the focus from correlation to physical interactions, and we discuss how this allows researchers to uncover causal relationships between molecules and phenotypes.

Integrating biological knowledge for mechanistic inference in the host-associated microbiome

Advances in high-throughput technologies have enhanced our ability to describe microbial communities as they relate to human health and disease. Alongside the growth in sequencing data has come an influx of resources that synthesize knowledge surrounding microbial traits, functions, and metabolic potential with knowledge of how they may impact host pathways to influence disease phenotypes. These knowledge bases can enable the development of mechanistic explanations that may underlie correlations detected between microbial communities and disease. In this review, we survey existing resources and methodologies for the computational integration of broad classes of microbial and host knowledge. We evaluate these knowledge bases in their access methods, content, and source characteristics. We discuss challenges of the creation and utilization of knowledge bases including inconsistency of nomenclature assignment of taxa and metabolites across sources, whether the biological entities represented are rooted in ontologies or taxonomies, and how the structure and accessibility limit the diversity of applications and user types. We make this information available in a code and data repository at: https://github.com/lozuponelab/knowledge-source-mappings. Addressing these challenges will allow for the development of more effective tools for drawing from abundant knowledge to find new insights into microbial mechanisms in disease by fostering a systematic and unbiased exploration of existing information.

Co-Cultivated Enzyme Constraint Metabolic Network Model for Rational Guidance in Constructing Synthetic Consortia to Achieve Optimal Pathway Allocation Prediction

Synthetic consortia have emerged as a promising biosynthetic platform that offers new opportunities for biosynthesis. Genome-scale metabolic network models (GEMs) with complex constraints are extensively utilized to guide the synthesis in monocultures. However, few methods are currently available to guide the rational construction of synthetic consortia for predicting the optimal allocation strategy of synthetic pathways aimed at enhancing product synthesis. A standardized method to construct the co-cultivated Enzyme Constraint metabolic network model (CulECpy) is proposed, which integrates enzyme constraints and modular interaction scale constraints based on the research concept of "independent + global". This method is applied to construct several synthetic consortia models, which encompassed different target products, strains, synthetic pathways, and compositional structures. Analyzing the model, the optimal pathway allocation and initial inoculum ratio that enhance the synthesis of target products by synthetic consortia are predicted and verified. When comparing with the constructed co-culture synthesis system, the normalized root mean square error of all optimal theoretical yield simulations is found to be less than or equal to 0.25. The analyses and verifications demonstrate that the method CulECpy can guide the rational construction of synthetic consortia systems to facilitate biochemical synthesis.

Gut microbiome-metabolome interactions predict host condition

BACKGROUND

The effect of microbes on their human host is often mediated through changes in metabolite concentrations. As such, multiple tools have been proposed to predict metabolite concentrations from microbial taxa frequencies. Such tools typically fail to capture the dependence of the microbiome-metabolite relation on the environment.

RESULTS

We propose to treat the microbiome-metabolome relation as the equilibrium of a complex interaction and to relate the host condition to a latent representation of the interaction between the log concentration of the metabolome and the log frequencies of the microbiome. We develop LOCATE (Latent variables Of miCrobiome And meTabolites rElations), a machine learning tool to predict the metabolite concentration from the microbiome composition and produce a latent representation of the interaction. This representation is then used to predict the host condition. LOCATE's accuracy in predicting the metabolome is higher than all current predictors. The metabolite concentration prediction accuracy significantly decreases cross datasets, and cross conditions, especially in 16S data. LOCATE's latent representation predicts the host condition better than either the microbiome or the metabolome. This representation is strongly correlated with host demographics. A significant improvement in accuracy (0.793 vs. 0.724 average accuracy) is obtained even with a small number of metabolite samples ([Formula: see text]).

CONCLUSION

These results suggest that a latent representation of the microbiome-metabolome interaction leads to a better association with the host condition than any of the two separated or the simple combination of the two. Video Abstract.

Recent Trends in Non-Invasive Methods of Diagnosis and Evaluation of Inflammatory Bowel Disease: A Short Review

Inflammatory bowel diseases are a conglomerate of disorders causing inflammation of the gastrointestinal tract, which have gained a significant increase in prevalence in the 21st century. As they present a challenge in the terms of diagnosis as well as treatment, IBDs can present an overwhelming impact on the individual and can take a toll on healthcare costs. Thus, a quick and precise diagnosis is required in order to prevent the high number of complications that can arise from a late diagnosis as well as a misdiagnosis. Although endoscopy remains the primary method of evaluation for IBD, recent trends have highlighted various non-invasive methods of diagnosis as well as reevaluating previous ones. This review focused on the current non-invasive methods in the diagnosis of IBD, exploring their possible implementation in the near future, with the goal of achieving earlier, feasible, and cheap methods of diagnosis as well as prognosis in IBD.

Review on computer-assisted biosynthetic capacities elucidation to assess metabolic interactions and communication within microbial communities

Microbial communities thrive through interactions and communication, which are challenging to study as most microorganisms are not cultivable. To address this challenge, researchers focus on the extracellular space where communication events occur. Exometabolomics and interactome analysis provide insights into the molecules involved in communication and the dynamics of their interactions. Advances in sequencing technologies and computational methods enable the reconstruction of taxonomic and functional profiles of microbial communities using high-throughput multi-omics data. Network-based approaches, including community flux balance analysis, aim to model molecular interactions within and between communities. Despite these advances, challenges remain in computer-assisted biosynthetic capacities elucidation, requiring continued innovation and collaboration among diverse scientists. This review provides insights into the current state and future directions of computer-assisted biosynthetic capacities elucidation in studying microbial communities.

Astragaloside IV Alleviates Depression in Rats by Modulating Intestinal Microbiota, T-Immune Balance, and Metabolome

This study aims to explore the effects of Astragaloside IV (AS-IV) on abnormal behaviors, intestinal microbiota, intestinal T-immune balance, and fecal metabolism of a model of depression in rats. Herein, we integrally applied 16S rRNA sequencing, molecular biological techniques, and 1H NMR-based fecal metabolomics to demonstrate the antidepression activity of AS-IV. The results suggested that AS-IV regulated the depression-like behaviors of rats, which are presented by an increase of body weight, upregulation of sucrose preference rates, and a decrease of immobility time. Additionally, AS-IV increased the abundances of beneficial bacteria (Lactobacillus and Oscillospira) in a model of depression in rats. Moreover, AS-IV regulated significantly the imbalance of Th17/Treg cells, and the abnormal contents of both anti-inflammatory factors and pro-inflammatory factors. Besides, fecal metabolomics showed that AS-IV improved the abnormal levels of short-chain fatty acids and amino acids. Collectively, our research supplemented new data, supporting the potential of AS-IV as an effective diet or diet composition to improve depression-like behaviors, dysfunctions of microbiota, imbalance of T immune, and the abnormality of fecal metabolome. However, the causality of the other actions was not proven because of the experimental design and the methodology used. The current findings suggest that AS-IV could function as a promising diet or diet composition to alleviate depressed symptoms.

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.

Mass spectrometry-based analysis of gut microbial metabolites of aromatic amino acids

Small molecules derived from gut microbiota have been increasingly investigated to better understand the functional roles of the human gut microbiome. Microbial metabolites of aromatic amino acids (AAA) have been linked to many diseases, such as metabolic disorders, chronic kidney diseases, inflammatory bowel disease, diabetes, and cancer. Important microbial AAA metabolites are often discovered via global metabolite profiling of biological specimens collected from humans or animal models. Subsequent metabolite identity confirmation and absolute quantification using targeted analysis enable comparisons across different studies, which can lead to the establishment of threshold concentrations of potential metabolite biomarkers. Owing to their excellent selectivity and sensitivity, hyphenated mass spectrometry (MS) techniques are often employed to identify and quantify AAA metabolites in various biological matrices. Here, we summarize the developments over the past five years in MS-based methodology for analyzing gut microbiota-derived AAA. Sample preparation, method validation, analytical performance, and statistical methods for correlation analysis are discussed, along with future perspectives.

Choosing the Right Therapy at the Right Time for Pediatric Inflammatory Bowel Disease: Does Sequence Matter

Despite the enlarging therapeutic armamentarium, IBD is still plagued by a therapeutic ceiling. Precision medicine, with the selection of the "rights," may present a solution, and this review will discuss the critical process of pairing the right patient with right therapy at the right time. Firstly, the review will discuss the shift to and evidence behind early effective therapy. Then, it delves into promising future strategies of patient profiling to identify a patients' biological pathway(s) and prognosis. Finally, the review lays out practical considerations that drive treatment selection, particularly the impact of the therapeutic sequence.

Removal of false positives in metagenomics-based taxonomy profiling via targeting Type IIB restriction sites

Accurate species identification and abundance estimation are critical for the interpretation of whole metagenome sequencing (WMS) data. Yet, existing metagenomic profilers suffer from false-positive identifications, which can account for more than 90% of total identified species. Here, by leveraging species-specific Type IIB restriction endonuclease digestion sites as reference instead of universal markers or whole microbial genomes, we present a metagenomic profiler, MAP2B (MetAgenomic Profiler based on type IIB restriction sites), to resolve those issues. We first illustrate the pitfalls of using relative abundance as the only feature in determining false positives. We then propose a feature set to distinguish false positives from true positives, and using simulated metagenomes from CAMI2, we establish a false-positive recognition model. By benchmarking the performance in metagenomic profiling using a simulation dataset with varying sequencing depth and species richness, we illustrate the superior performance of MAP2B over existing metagenomic profilers in species identification. We further test the performance of MAP2B using real WMS data from an ATCC mock community, confirming its superior precision against sequencing depth. Finally, by leveraging WMS data from an IBD cohort, we demonstrate the taxonomic features generated by MAP2B can better discriminate IBD and predict metabolomic profiles.

Gut microbiota and fecal short chain fatty acids differ with adiposity and country of origin: the METS-microbiome study

The relationship between microbiota, short chain fatty acids (SCFAs), and obesity remains enigmatic. We employ amplicon sequencing and targeted metabolomics in a large (n = 1904) African origin cohort from Ghana, South Africa, Jamaica, Seychelles, and the US. Microbiota diversity and fecal SCFAs are greatest in Ghanaians, and lowest in Americans, representing each end of the urbanization spectrum. Obesity is significantly associated with a reduction in SCFA concentration, microbial diversity, and SCFA synthesizing bacteria, with country of origin being the strongest explanatory factor. Diabetes, glucose state, hypertension, obesity, and sex can be accurately predicted from the global microbiota, but when analyzed at the level of country, predictive accuracy is only universally maintained for sex. Diabetes, glucose, and hypertension are only predictive in certain low-income countries. Our findings suggest that adiposity-related microbiota differences differ between low-to-middle-income compared to high-income countries. Further investigation is needed to determine the factors driving this association.

Recent advances in data- and knowledge-driven approaches to explore primary microbial metabolism

With the rapid progress in metabolomics and sequencing technologies, more data on the metabolome of single microbes and their communities become available, revealing the potential of microorganisms to metabolize a broad range of chemical compounds. The analysis of microbial metabolomics datasets remains challenging since it inherits the technical challenges of metabolomics analysis, such as compound identification and annotation, while harboring challenges in data interpretation, such as distinguishing metabolite sources in mixed samples. This review outlines the recent advances in computational methods to analyze primary microbial metabolism: knowledge-based approaches that take advantage of metabolic and molecular networks and data-driven approaches that employ machine/deep learning algorithms in combination with large-scale datasets. These methods aim at improving metabolite identification and disentangling reciprocal interactions between microbes and metabolites. We also discuss the perspective of combining these approaches and further developments required to advance the investigation of primary metabolism in mixed microbial samples.

Moving beyond DNA: towards functional analysis of the vaginal microbiome by non-sequencing-based methods

Over the last two decades, sequencing-based methods have revolutionised our understanding of niche-specific microbial complexity. In the lower female reproductive tract, these approaches have enabled identification of bacterial compositional structures associated with health and disease. Application of metagenomics and metatranscriptomics strategies have provided insight into the putative function of these communities but it is increasingly clear that direct measures of microbial and host cell function are required to understand the contribution of microbe-host interactions to pathophysiology. Here we explore and discuss current methods and approaches, many of which rely upon mass-spectrometry, being used to capture functional insight into the vaginal mucosal interface. In addition to improving mechanistic understanding, these methods offer innovative solutions for the development of diagnostic and therapeutic strategies designed to improve women's health.

Gut microbiota and fecal short chain fatty acids differ with adiposity and country of origin: The METS-Microbiome Study

The relationship between gut microbiota, short chain fatty acid (SCFA) metabolism, and obesity is still not well understood. Here we investigated these associations in a large (n=1904) African origin cohort from Ghana, South Africa, Jamaica, Seychelles, and the US. Fecal microbiota diversity and SCFA concentration were greatest in Ghanaians, and lowest in the US population, representing the lowest and highest end of the epidemiologic transition spectrum, respectively. Obesity was significantly associated with a reduction in SCFA concentration, microbial diversity and SCFA synthesizing bacteria. Country of origin could be accurately predicted from the fecal microbiota (AUC=0.97), while the predictive accuracy for obesity was inversely correlated to the epidemiological transition, being greatest in Ghana (AUC = 0.57). The findings suggest that the microbiota differences between obesity and non-obesity may be larger in low-to-middle-income countries compared to high-income countries. Further investigation is needed to determine the factors driving this association.
.

Gut microbiota and fecal short chain fatty acids differ with adiposity and country of origin: The METS-Microbiome Study

The relationship between the gut microbiota, short chain fatty acid (SCFA) metabolism, and obesity remains unclear due to conflicting reports from studies with limited statistical power. Additionally, this association has rarely been explored in large scale diverse populations. Here, we investigated associations between fecal microbial composition, predicted metabolic potential, SCFA concentrations, and obesity in a large ( N = 1,934) adult cohort of African-origin spanning the epidemiologic transition, from Ghana, South Africa, Jamaica, Seychelles, and the United States (US). The greatest gut microbiota diversity and total fecal SCFA concentration was found in the Ghanaian population, while the lowest levels were found in the US population, respectively representing the lowest and the highest end of the epidemiologic transition spectrum. Country-specific bacterial taxa and predicted-functional pathways were observed, including an increased prevalence of Prevotella , Butyrivibrio , Weisella and Romboutsia in Ghana and South Africa, while Bacteroides and Parabacteroides were enriched in Jamaican and the US populations. Importantly, 'VANISH' taxa, including Butyricicoccus and Succinivibrio , were significantly enriched in the Ghanaian cohort, reflecting the participants' traditional lifestyles. Obesity was significantly associated with lower SCFA concentrations, a decrease in microbial richness, and dissimilarities in community composition, and reduction in the proportion of SCFA synthesizing bacteria including Oscillospira , Christensenella , Eubacterium , Alistipes , Clostridium and Odoribacter . Further, the predicted proportions of genes in the lipopolysaccharide (LPS) synthesis pathway were enriched in obese individuals, while genes associated with butyrate synthesis via the dominant pyruvate pathway were significantly reduced in obese individuals. Using machine learning, we identified features predictive of metabolic state and country of origin. Country of origin could accurately be predicted by the fecal microbiota (AUC = 0.97), whereas obesity could not be predicted as accurately (AUC = 0.65). Participant sex (AUC = 0.75), diabetes status (AUC = 0.63), hypertensive status (AUC = 0.65), and glucose status (AUC = 0.66) could all be predicted with different success. Interestingly, within country, the predictive accuracy of the microbiota for obesity was inversely correlated to the epidemiological transition, being greatest in Ghana (AUC = 0.57). Collectively, our findings reveal profound variation in the gut microbiota, inferred functional pathways, and SCFA synthesis as a function of country of origin. While obesity could be predicted accurately from the microbiota, the variation in accuracy in parallel with the epidemiological transition suggests that differences in the microbiota between obesity and non-obesity may be larger in low-to-middle countries compared to high-income countries. Further examination of independent study populations using multi-omic approaches will be necessary to determine the factors that drive this association.

Predicting metabolic response to dietary intervention using deep learning

Due to highly personalized biological and lifestyle characteristics, different individuals may have different metabolic responses to specific foods and nutrients. In particular, the gut microbiota, a collection of trillions of microorganisms living in our gastrointestinal tract, is highly personalized and plays a key role in our metabolic responses to foods and nutrients. Accurately predicting metabolic responses to dietary interventions based on individuals' gut microbial compositions holds great promise for precision nutrition. Existing prediction methods are typically limited to traditional machine learning models. Deep learning methods dedicated to such tasks are still lacking. Here we develop a new method McMLP (Metabolic response predictor using coupled Multilayer Perceptrons) to fill in this gap. We provide clear evidence that McMLP outperforms existing methods on both synthetic data generated by the microbial consumer-resource model and real data obtained from six dietary intervention studies. Furthermore, we perform sensitivity analysis of McMLP to infer the tripartite food-microbe-metabolite interactions, which are then validated using the ground-truth (or literature evidence) for synthetic (or real) data, respectively. The presented tool has the potential to inform the design of microbiota-based personalized dietary strategies to achieve precision nutrition.

Gut Microbes Meet Machine Learning: The Next Step towards Advancing Our Understanding of the Gut Microbiome in Health and Disease

The human gut microbiome plays a crucial role in human health and has been a focus of increasing research in recent years. Omics-based methods, such as metagenomics, metatranscriptomics, and metabolomics, are commonly used to study the gut microbiome because they provide high-throughput and high-resolution data. The vast amount of data generated by these methods has led to the development of computational methods for data processing and analysis, with machine learning becoming a powerful and widely used tool in this field. Despite the promising results of machine learning-based approaches for analyzing the association between microbiota and disease, there are several unmet challenges. Small sample sizes, disproportionate label distribution, inconsistent experimental protocols, or a lack of access to relevant metadata can all contribute to a lack of reproducibility and translational application into everyday clinical practice. These pitfalls can lead to false models, resulting in misinterpretation biases for microbe–disease correlations. Recent efforts to address these challenges include the construction of human gut microbiota data repositories, improved data transparency guidelines, and more accessible machine learning frameworks; implementation of these efforts has facilitated a shift in the field from observational association studies to experimental causal inference and clinical intervention.

Predicting metabolomic profiles from microbial composition through neural ordinary differential equations

Characterizing the metabolic profile of a microbial community is crucial for understanding its biological function and its impact on the host or environment. Metabolomics experiments directly measuring these profiles are difficult and expensive, while sequencing methods quantifying the species composition of microbial communities are well-developed and relatively cost-effective. Computational methods that are capable of predicting metabolomic profiles from microbial compositions can save considerable efforts needed for metabolomic profiling experimentally. Yet, despite existing efforts, we still lack a computational method with high prediction power, general applicability, and great interpretability. Here we develop a method - mNODE (Metabolomic profile predictor using Neural Ordinary Differential Equations), based on a state-of-the-art family of deep neural network models. We show compelling evidence that mNODE outperforms existing methods in predicting the metabolomic profiles of human microbiomes and several environmental microbiomes. Moreover, in the case of human gut microbiomes, mNODE can naturally incorporate dietary information to further enhance the prediction of metabolomic profiles. Besides, susceptibility analysis of mNODE enables us to reveal microbe-metabolite interactions, which can be validated using both synthetic and real data. The presented results demonstrate that mNODE is a powerful tool to investigate the microbiome-diet-metabolome relationship, facilitating future research on precision nutrition.

Changes in the Urine Metabolomic Profile in Patients Recovering from Severe COVID-19

Metabolomics is a relatively new research area that focuses mostly on the profiling of selected molecules and metabolites within the organism. A SARS-CoV-2 infection itself can lead to major disturbances in the metabolite profile of the infected individuals. The aim of this study was to analyze metabolomic changes in the urine of patients during the acute phase of COVID-19 and approximately one month after infection in the recovery period. We discuss the observed changes in relation to the alterations resulting from changes in the blood plasma metabolome, as described in our previous study. The metabolome analysis was performed using NMR spectroscopy from the urine of patients and controls. The urine samples were collected at three timepoints, namely upon hospital admission, during hospitalization, and after discharge from the hospital. The acute COVID-19 phase induced massive alterations in the metabolic composition of urine was linked with various changes taking place in the organism. Discriminatory analyses showed the feasibility of successful discrimination of COVID-19 patients from healthy controls based on urinary metabolite levels, with the highest significance assigned to citrate, Hippurate, and pyruvate. Our results show that the metabolomic changes persist one month after the acute phase and that the organism is not fully recovered.

Recent advances of machine learning applications in human gut microbiota study: from observational analysis toward causal inference and clinical intervention

Statistical methods, especially machine learning, learning(ML), are pivotal for the analyses of large data generated by multiomics human gut microbiota study. These analyses lead to the discovery of microbe-disease associations. Furthermore, recent efforts for more data transparency and accessible analytical tools improved data availability and study reproducibility. Our recent accumulated knowledge on microbe-disease associations brings light to the next questions: what is the role of microbes in disease progression and how can we apply our knowledge of microbiome in clinical settings? Here, we introduce recent studies that implemented ML to answer the questions of causal inference and clinical translation.

Multi-omics Data Deconvolution and Integration: New Methods, Insights, and Translational Implications

In the current era of multi-omics, new sequencing and molecular profiling technologies have facilitated our quest for a deeper and broader understanding of the variations and dynamic regulations in human genomes. However, analyzing and integrating data generated from diverse platforms, modalities, and large-scale heterogeneous samples to extract functional and clinically valuable information remains a significant challenge. Here, we first discuss recent advances in methods and algorithms for analyzing data at the genome, transcriptome, proteome, metabolome, and microbiome levels, followed by emerging methods for leveraging single-cell sequencing and spatial transcriptomic data. We also highlight the mechanistic insights that these advances can bring to the field, as well as the current challenges and outlooks relating to their translational and reproducible adoption at the population level. It is evident that novel statistical methods, which were inspired by new assays, will enable the associated molecular profiling pipelines and experimental designs to continuously improve our understanding of the human genome and the downstream consequences in the transcriptome, epigenome, proteome, metabolome, regulome, and microbiome.

Progress and opportunities in microbial community metabolomics

The metabolome lies at the interface of host-microbiome crosstalk. Previous work has established links between chemically diverse microbial metabolites and a myriad of host physiological processes and diseases. Coupled with scalable and cost-effective technologies, metabolomics is thus gaining popularity as a tool for characterization of microbial communities, particularly when combined with metagenomics as a window into microbiome function. A systematic interrogation of microbial community metabolomes can uncover key microbial compounds, metabolic capabilities of the microbiome, and also provide critical mechanistic insights into microbiome-linked host phenotypes. In this review, we discuss methods and accompanying resources that have been developed for these purposes. The accomplishments of these methods demonstrate that metabolomes can be used to functionally characterize microbial communities, and that microbial properties can be used to identify and investigate chemical compounds.

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.

Prognostication in inflammatory bowel disease

Personalized care in inflammatory bowel diseases (IBD) hinges on parsing the heterogeneity of IBD patients through prognostication of their disease course and therapeutic response to allow for tailor-made treatment and monitoring strategies to optimize care. Herein we review the currently available predictors of outcomes in IBD and those on the both near and far horizons. We additionally discuss the importance of worldwide collaborative efforts and tools to support clinical use of these prognostication tools.

Machine Learning Prediction of Nitrification From Ammonia- and Nitrite-Oxidizer Community Structure

Accurately modeling nitrification and understanding the role specific ammonia- or nitrite-oxidizing taxa play in it are of great interest and importance to microbial ecologists. In this study, we applied machine learning to 16S rRNA sequence and nitrification potential data from an experiment examining interactions between cropping systems and rhizosphere on microbial community assembly and nitrogen cycling processes. Given the high dimensionality of microbiome datasets, we only included nitrifers since only a few taxa are capable of ammonia and nitrite oxidation. We compared the performance of linear and nonlinear algorithms with and without qPCR measures of bacterial and archaea ammonia monooxygenase subunit A (amoA) gene abundance. Our feature selection process facilitated the identification of taxons that are most predictive of nitrification and to compare habitats. We found that Nitrosomonas and Nitrospirae were more frequently identified as important predictors of nitrification in conventional systems, whereas Thaumarchaeota were more important predictors in diversified systems. Our results suggest that model performance was not substantively improved by incorporating additional time-consuming and expensive qPCR data on amoA gene abundance. We also identified several clades of nitrifiers important for nitrification in different cropping systems, though we were unable to detect system- or rhizosphere-specific patterns in OTU-level biomarkers for nitrification. Finally, our results highlight the inherent risk of combining data from disparate habitats with the goal of increasing sample size to avoid overfitting models. This study represents a step toward developing machine learning approaches for microbiome research to identify nitrifier ecotypes that may be important for distinguishing ecotypes with defining roles in different habitats.

Do amino and fatty acid profiles of pollen provisions correlate with bacterial microbiomes in the mason bee Osmia bicornis?

Bee performance and well-being strongly depend on access to sufficient and appropriate resources, in particular pollen and nectar of flowers, which constitute the major basis of bee nutrition. Pollen-derived microbes appear to play an important but still little explored role in the plant pollen-bee interaction dynamics, e.g. through affecting quantities and ratios of important nutrients. To better understand how microbes in pollen collected by bees may affect larval health through nutrition, we investigated correlations between the floral, bacterial and nutritional composition of larval provisions and the gut bacterial communities of the solitary megachilid bee Osmia bicornis. Our study reveals correlations between the nutritional quality of pollen provisions and the complete bacterial community as well as individual members of both pollen provisions and bee guts. In particular pollen fatty acid profiles appear to interact with specific members of the pollen bacterial community, indicating that pollen-derived bacteria may play an important role in fatty acid provisioning. As increasing evidence suggests a strong effect of dietary fatty acids on bee performance, future work should address how the observed interactions between specific fatty acids and the bacterial community in larval provisions relate to health in O. bicornis. This article is part of the theme issue 'Natural processes influencing pollinator health: from chemistry to landscapes'.

MIMOSA2: a metabolic network-based tool for inferring mechanism-supported relationships in microbiome-metabolome data

MOTIVATION

Recent technological developments have facilitated an expansion of microbiome-metabolome studies, in which samples are assayed using both genomic and metabolomic technologies to characterize the abundances of microbial taxa and metabolites. A common goal of these studies is to identify microbial species or genes that contribute to differences in metabolite levels across samples. Previous work indicated that integrating these datasets with reference knowledge on microbial metabolic capacities may enable more precise and confident inference of microbe-metabolite links.

RESULTS

We present MIMOSA2, an R package and web application for model-based integrative analysis of microbiome-metabolome datasets. MIMOSA2 uses genomic and metabolic reference databases to construct a community metabolic model based on microbiome data and uses this model to predict differences in metabolite levels across samples. These predictions are compared with metabolomics data to identify putative microbiome-governed metabolites and taxonomic contributors to metabolite variation. MIMOSA2 supports various input data types and customization with user-defined metabolic pathways. We establish MIMOSA2's ability to identify ground truth microbial mechanisms in simulation datasets, compare its results with experimentally inferred mechanisms in honeybee microbiota, and demonstrate its application in two human studies of inflammatory bowel disease. Overall, MIMOSA2 combines reference databases, a validated statistical framework, and a user-friendly interface to facilitate modeling and evaluating relationships between members of the microbiota and their metabolic products.

AVAILABILITY AND IMPLEMENTATION

MIMOSA2 is implemented in R under the GNU General Public License v3.0 and is freely available as a web server at http://elbo-spice.cs.tau.ac.il/shiny/MIMOSA2shiny/ and as an R package from http://www.borensteinlab.com/software_MIMOSA2.html.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

It takes guts to learn: machine learning techniques for disease detection from the gut microbiome

Associations between the human gut microbiome and expression of host illness have been noted in a variety of conditions ranging from gastrointestinal dysfunctions to neurological deficits. Machine learning (ML) methods have generated promising results for disease prediction from gut metagenomic information for diseases including liver cirrhosis and irritable bowel disease, but have lacked efficacy when predicting other illnesses. Here, we review current ML methods designed for disease classification from microbiome data. We highlight the computational challenges these methods have effectively overcome and discuss the biological components that have been overlooked to offer perspectives on future work in this area.

Machine Learning Modeling from Omics Data as Prospective Tool for Improvement of Inflammatory Bowel Disease Diagnosis and Clinical Classifications

Research of inflammatory bowel disease (IBD) has identified numerous molecular players involved in the disease development. Even so, the understanding of IBD is incomplete, while disease treatment is still far from the precision medicine. Reliable diagnostic and prognostic biomarkers in IBD are limited which may reduce efficient therapeutic outcomes. High-throughput technologies and artificial intelligence emerged as powerful tools in search of unrevealed molecular patterns that could give important insights into IBD pathogenesis and help to address unmet clinical needs. Machine learning, a subtype of artificial intelligence, uses complex mathematical algorithms to learn from existing data in order to predict future outcomes. The scientific community has been increasingly employing machine learning for the prediction of IBD outcomes from comprehensive patient data-clinical records, genomic, transcriptomic, proteomic, metagenomic, and other IBD relevant omics data. This review aims to present fundamental principles behind machine learning modeling and its current application in IBD research with the focus on studies that explored genomic and transcriptomic data. We described different strategies used for dealing with omics data and outlined the best-performing methods. Before being translated into clinical settings, the developed machine learning models should be tested in independent prospective studies as well as randomized controlled trials.