Search

Background: Schizophrenia (SCZ) is a heterogeneous neuropsychiatric disorder for which current treatment has insufficient efficacy and severe adverse effects. The modifiable gut microbiome might be a potential target for intervention to improve neurobiological functions through the gut-microbiome-brain axis. Methods: In this case-control study, gut microbiota of 132 patients with SCZ and increased waist circumference were compared with gut microbiota of two age- and sex-matched control groups, composed of 132 healthy individuals and 132 individuals with metabolic syndrome. Shotgun sequencing was used to characterize fecal samples at the taxonomic and functional levels. Cognition of the patients with SCZ was evaluated using the Brief Assessment of Cognition instrument. Results: SCZ gut microbiota differed significantly from those of healthy control subjects and individuals with metabolic syndrome in terms of richness and global composition. SCZ gut microbiota were notably enriched in Flavonifractor plautii, Collinsella aerofaciens, Bilophila wadsworthia, and Sellimonas intestinalis, while depleted in Faecalibacterium prausnitzii, Ruminococcus lactaris, Ruminococcus bicirculans, and Veillonella rogosae. Functional potential of the gut microbiota accounted for 11% of cognition variability. In particular, the bacterial functional module for synthesizing tyrosine, a precursor for dopamine, was in SCZ cases positively associated with cognitive score (ρ = 0.34, q ≤ .1). Conclusions: Overall, this study shows that the gut microbiome of patients with SCZ differs greatly from that of healthy control subjects or individuals with metabolic syndrome. Cognitive function of patients with SCZ is associated with the potential for gut bacterial biosynthesis of tyrosine, a precursor for dopamine, suggesting that gut microbiota might be an intervention target for alleviation of cognitive dysfunction in SCZ.

The human microbiome has become an area of intense research due to its potential impact on human health. However, the analysis and interpretation of this data have proven to be challenging due to its complexity and high dimensionality. Machine learning (ML) algorithms can process vast amounts of data to uncover informative patterns and relationships within the data, even with limited prior knowledge. Therefore, there has been a rapid growth in the development of software specifically designed for the analysis and interpretation of microbiome data using ML techniques. These software incorporate a wide range of ML algorithms for clustering, classification, regression, or feature selection, to identify microbial patterns and relationships within the data and generate predictive models. This rapid development with a constant need for new developments and integration of new features require efforts into compile, catalog and classify these tools to create infrastructures and services with easy, transparent, and trustable standards. Here we review the state-of-the-art for ML tools applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on ML based software and framework resources currently available for the analysis of microbiome data in humans. The aim is to support microbiologists and biomedical scientists to go deeper into specialized resources that integrate ML techniques and facilitate future benchmarking to create standards for the analysis of microbiome data. The software resources are organized based on the type of analysis they were developed for and the ML techniques they implement. A description of each software with examples of usage is provided including comments about pitfalls and lacks in the usage of software based on ML methods in relation to microbiome data that need to be considered by developers and users. This review represents an extensive compilation to date, offering valuable insights and guidance for researchers interested in leveraging ML approaches for microbiome analysis.

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.

Microbiome data predictive analysis within a machine learning (ML) workflow presents numerous domain-specific challenges involving preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and the extraction of biological information from the results. To assist decision-making, we offer a set of recommendations on algorithm selection, pipeline creation and evaluation, stemming from the COST Action ML4Microbiome. We compared the suggested approaches on a multi-cohort shotgun metagenomics dataset of colorectal cancer patients, focusing on their performance in disease diagnosis and biomarker discovery. It is demonstrated that the use of compositional transformations and filtering methods as part of data preprocessing does not always improve the predictive performance of a model. In contrast, the multivariate feature selection, such as the Statistically Equivalent Signatures algorithm, was effective in reducing the classification error. When validated on a separate test dataset, this algorithm in combination with random forest modeling, provided the most accurate performance estimates. Lastly, we showed how linear modeling by logistic regression coupled with visualization techniques such as Individual Conditional Expectation (ICE) plots can yield interpretable results and offer biological insights. These findings are significant for clinicians and non-experts alike in translational applications.

The rapid development of machine learning (ML) techniques has opened up the data-dense field of microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range of disorders, which could substantially improve healthcare practices in the era of precision medicine. However, several challenges must be addressed to exploit the benefits of ML in this field fully. In particular, there is a need to establish “gold standard” protocols for conducting ML analysis experiments and improve interactions between microbiome researchers and ML experts. The Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome) COST Action CA18131 is a European network established in 2019 to promote collaboration between discovery-oriented microbiome researchers and data-driven ML experts to optimize and standardize ML approaches for microbiome analysis. This perspective paper presents the key achievements of ML4Microbiome, which include identifying predictive and discriminatory ‘omics’ features, improving repeatability and comparability, developing automation procedures, and defining priority areas for the novel development of ML methods targeting the microbiome. The insights gained from ML4Microbiome will help to maximize the potential of ML in microbiome research and pave the way for new and improved healthcare practices.

Abstract The number of indications for fecal microbiota transplantation is expected to rise, thus increasing the needs for production of readily available frozen or freeze-dried transplants. Using shotgun metagenomics, we investigated the capacity of two novel human fecal microbiota transplants prepared in maltodextrin-trehalose solutions (abbreviated MD and TR for maltodextrin:trehalose, 3:1, w/w, and trehalose:maltodextrin 3:1, w/w, respectively), to colonize a germ-free born mouse model. Gavage with frozen-thawed MD or TR suspensions gave the taxonomic profiles of mouse feces that best resembled those obtained with the fresh inoculum (Spearman correlations based on relative abundances of metagenomic species around 0.80 and 0.75 for MD and TR respectively), while engraftment capacity of defrosted NaCl transplants most diverged (Spearman correlations around 0.63). Engraftment of members of the family Lachnospiraceae and Ruminoccocaceae was the most challenging in all groups of mice, being improved with MD and TR transplants compared to NaCl, but still lower than with the fresh preparation. Improvement of engraftment of this important group in maintaining health represents a challenge that could benefit from further research on fecal microbiota transplant manufacturing.

One of the difficulties encountered in the statistical analysis of metaproteomics data is the high proportion of missing values, which are usually treated by imputation. Nevertheless, imputation methods are based on restrictive assumptions regarding missingness mechanisms, namely “at random” or “not at random”. To circumvent these limitations in the context of feature selection in a multi-class comparison, we propose a univariate selection method that combines a test of association between missingness and classes, and a test for difference of observed intensities between classes. This approach implicitly handles both missingness mechanisms. We performed a quantitative and qualitative comparison of our procedure with imputation-based feature selection methods on two experimental data sets, as well as simulated data with various scenarios regarding the missingness mechanisms and the nature of the difference of expression (differential intensity or differential presence). Whereas we observed similar performances in terms of prediction on the experimental data set, the feature ranking and selection from various imputation-based methods were strongly divergent. We showed that the combined test reaches a compromise by correlating reasonably with other methods, and remains efficient in all simulated scenarios unlike imputation-based feature selection methods.

Current studies are shifting from the use of single linear references to representation of multiple genomes organised in pangenome graphs or variation graphs. Meanwhile, in metagenomic samples, resolving strain-level abundances is a major step in microbiome studies, as associations between strain variants and phenotype are of great interest for diagnostic and therapeutic purposes. We developed StrainFLAIR with the aim of showing the feasibility of using variation graphs for indexing highly similar genomic sequences up to the strain level, and for characterizing a set of unknown sequenced genomes by querying this graph. On simulated data composed of mixtures of strains from the same bacterial species Escherichia coli, results show that StrainFLAIR was able to distinguish and estimate the abundances of close strains, as well as to highlight the presence of a new strain close to a referenced one and to estimate its abundance. On a real dataset composed of a mix of several bacterial species and several strains for the same species, results show that in a more complex configuration StrainFLAIR correctly estimates the abundance of each strain. Hence, results demonstrated how graph representation of multiple close genomes can be used as a reference to characterize a sample at the strain level.

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.

Thanks to the latest developments in mass spectrometry, software and standards, metaproteomics is emerging as the vital complement of metagenomics, to make headway in understanding the actual functioning of living and active microbial communities. Modern metaproteomics offers new possibilities in the area of clinical diagnosis. This is illustrated here, for the still highly challenging diagnosis of intestinal bowel diseases (IBDs). Using bottom-up proteomics, we analyzed the gut metaproteomes of the same twenty faecal specimens processed either fresh or after a two-month freezing period. We focused on metaproteomes of microbial cell envelopes since it is an outstanding way of capturing host and host–microbe interaction signals. The protein profiles of pairs of fresh and frozen-thawed samples were closely related, making feasible deferred analysis in a distant diagnosis centre. The taxonomic and functional landscape of microbes in diverse IBD phenotypes—active ulcerative colitis, or active Crohn’s disease either with ileo-colonic or exclusive colonic localization—differed from each other and from the controls. Based on their specific peptides, we could identify proteins that were either strictly overrepresented or underrepresented in all samples of one clinical group compared to all samples of another group, paving the road for promising additional diagnostic tool for IBDs.