Machine learning approaches in microbiome research: challenges and best practices

AI in microbiome-related healthcare

Artificial intelligence (AI) has the potential to transform clinical practice and healthcare. Following impressive advancements in fields such as computer vision and medical imaging, AI is poised to drive changes in microbiome-based healthcare while facing challenges specific to the field. This review describes the state-of-the-art use of AI in microbiome-related healthcare. It points out limitations across topics such as data handling, AI modelling and safeguarding patient privacy. Furthermore, we indicate how these current shortcomings could be overcome in the future and discuss the influence and opportunities of increasingly complex data on microbiome-based healthcare.

Microbial Therapeutics in Oncology: A Comprehensive Review of Bacterial Role in Cancer Treatment

Conventional cancer therapies, including chemotherapy, radiotherapy, and immunotherapy, have significantly advanced cancer treatment. However, these modalities often face limitations such as systemic toxicity, lack of specificity, and the emergence of resistance. Recent advancements in genetic engineering and synthetic biology have rekindled interest in using bacteria as a novel therapeutic approach in oncology. This comprehensive review explores the potential of microbial therapeutics, particularly bacterial therapies, in the treatment of cancer. Bacterial therapies offer several unique advantages, such as the ability to selectively target and colonize hypoxic and necrotic regions of tumors, areas typically resistant to conventional treatments. The review delves into the mechanisms through which bacteria exert antitumor effects, including direct tumor cell lysis, modulation of the immune response, and delivery of therapeutic agents like cytotoxins and enzymes. Various bacterial species, such as Salmonella, Clostridium, Lactobacillus, and Listeria, have shown promise in preclinical and clinical studies, demonstrating diverse mechanisms of action and therapeutic potential. Moreover, the review discusses the challenges associated with bacterial therapies, such as safety concerns, immune evasion, and the need for precise targeting, and how recent advances in genetic engineering are being used to overcome these hurdles. Current clinical trials and combination strategies with conventional therapies are also highlighted to provide a comprehensive overview of the ongoing developments in this field. In conclusion, while bacterial therapeutics present a novel and promising avenue in cancer treatment, further research and clinical validation is required to fully realize their potential. This review aims to inspire further exploration into microbial oncology, paving the way for innovative and more effective cancer therapies.

FruitSeg30_Segmentation dataset & mask annotations: A novel dataset for diverse fruit segmentation and classification

Fruits are mature ovaries of flowering plants that are integral to human diets, providing essential nutrients such as vitamins, minerals, fiber and antioxidants that are crucial for health and disease prevention. Accurate classification and segmentation of fruits are crucial in the agricultural sector for enhancing the efficiency of sorting and quality control processes, which significantly benefit automated systems by reducing labor costs and improving product consistency. This paper introduces the "FruitSeg30_Segmentation Dataset & Mask Annotations", a novel dataset designed to advance the capability of deep learning models in fruit segmentation and classification. Comprising 1969 high-quality images across 30 distinct fruit classes, this dataset provides diverse visuals essential for a robust model. Utilizing a U-Net architecture, the model trained on this dataset achieved training accuracy of 94.72 %, validation accuracy of 92.57 %, precision of 94 %, recall of 91 %, f1-score of 92.5 %, IoU score of 86 %, and maximum dice score of 0.9472, demonstrating superior performance in segmentation tasks. The FruitSeg30 dataset fills a critical gap and sets new standards in dataset quality and diversity, enhancing agricultural technology and food industry applications.

Robust prediction of colorectal cancer via gut microbiome 16S rRNA sequencing data

Introduction. The study addresses the challenge of utilizing human gut microbiome data for the early detection of colorectal cancer (CRC). The research emphasizes the potential of using machine learning techniques to analyze complex microbiome datasets, providing a non-invasive approach to identifying CRC-related microbial markers.Hypothesis/Gap Statement. The primary hypothesis is that a robust machine learning-based analysis of 16S rRNA microbiome data can identify specific microbial features that serve as effective biomarkers for CRC detection, overcoming the limitations of classical statistical models in high-dimensional settings.Aim. The primary objective of this study is to explore and validate the potential of the human microbiome, specifically in the colon, as a valuable source of biomarkers for colorectal cancer (CRC) detection and progression. The focus is on developing a classifier that effectively predicts the presence of CRC and normal samples based on the analysis of three previously published faecal 16S rRNA sequencing datasets.Methodology. To achieve the aim, various machine learning techniques are employed, including random forest (RF), recursive feature elimination (RFE) and a robust correlation-based technique known as the fuzzy forest (FF). The study utilizes these methods to analyse the three datasets, comparing their performance in predicting CRC and normal samples. The emphasis is on identifying the most relevant microbial features (taxa) associated with CRC development via partial dependence plots, i.e. a machine learning tool focused on explainability, visualizing how a feature influences the predicted outcome.Results. The analysis of the three faecal 16S rRNA sequencing datasets reveals the consistent and superior predictive performance of the FF compared to the RF and RFE. Notably, FF proves effective in addressing the correlation problem when assessing the importance of microbial taxa in explaining the development of CRC. The results highlight the potential of the human microbiome as a non-invasive means to detect CRC and underscore the significance of employing FF for improved predictive accuracy.Conclusion. In conclusion, this study underscores the limitations of classical statistical techniques in handling high-dimensional information such as human microbiome data. The research demonstrates the potential of the human microbiome, specifically in the colon, as a valuable source of biomarkers for CRC detection. Applying machine learning techniques, particularly the FF, is a promising approach for building a classifier to predict CRC and normal samples. The findings advocate for integrating FF to overcome the challenges associated with correlation when identifying crucial microbial features linked to CRC development.

MicroHDF: predicting host phenotypes with metagenomic data using a deep forest-based framework

The gut microbiota plays a vital role in human health, and significant effort has been made to predict human phenotypes, especially diseases, with the microbiota as a promising indicator or predictor with machine learning (ML) methods. However, the accuracy is impacted by a lot of factors when predicting host phenotypes with the metagenomic data, e.g. small sample size, class imbalance, high-dimensional features, etc. To address these challenges, we propose MicroHDF, an interpretable deep learning framework to predict host phenotypes, where a cascade layers of deep forest units is designed for handling sample class imbalance and high dimensional features. The experimental results show that the performance of MicroHDF is competitive with that of existing state-of-the-art methods on 13 publicly available datasets of six different diseases. In particular, it performs best with the area under the receiver operating characteristic curve of 0.9182 ± 0.0098 and 0.9469 ± 0.0076 for inflammatory bowel disease (IBD) and liver cirrhosis, respectively. Our MicroHDF also shows better performance and robustness in cross-study validation. Furthermore, MicroHDF is applied to two high-risk diseases, IBD and autism spectrum disorder, as case studies to identify potential biomarkers. In conclusion, our method provides an effective and reliable prediction of the host phenotype and discovers informative features with biological insights.

Personalized identification of autism-related bacteria in the gut microbiome using explainable artificial intelligence

Autism spectrum disorder (ASD) affects social interaction and communication. Emerging evidence links ASD to gut microbiome alterations, suggesting that microbial composition may play a role in the disorder. This study employs explainable artificial intelligence (XAI) to examine the contributions of individual microbial species to ASD. By using local explanation embeddings and unsupervised clustering, the research identifies distinct ASD subgroups, underscoring the disorder's heterogeneity. Specific microbial biomarkers associated with ASD are revealed, and the best classifiers achieved an AU-ROC of 0.965 ± 0.005 and an AU-PRC of 0.967 ± 0.008. The findings support the notion that gut microbiome composition varies significantly among individuals with ASD. This work's broader significance lies in its potential to inform personalized interventions, enhancing precision in ASD management and classification. These insights highlight the importance of individualized microbiome profiles for developing tailored therapeutic strategies for ASD.

Dermatological Health in the Light of Skin Microbiome Evolution

BACKGROUND

The complex ecosystem of the skin microbiome is essential for skin health by acting as a primary defense against infections, regulating immune responses, and maintaining barrier integrity. This literature review aims to consolidate existing information on the skin microbiome, focusing on its composition, functionality, importance, and its impact on skin aging.

METHODS

An exhaustive exploration of scholarly literature was performed utilizing electronic databases including PubMed, Google Scholar, and ResearchGate, focusing on studies published between 2011 and 2024. Keywords included "skin microbiome," "skin microbiota," and "aging skin." Studies involving human subjects that focused on the skin microbiome's relationship with skin health were included. Out of 100 initially identified studies, 70 met the inclusion criteria and were reviewed.

RESULTS

Studies showed that aging is associated with a reduction in the variety of microorganisms of the skin microbiome, leading to an increased susceptibility to skin conditions. Consequently, this underlines the interest in bacteriotherapy, mainly topical probiotics, to reinforce the skin microbiome in older adults, suggesting improvements in skin health and a reduction in age-related skin conditions. Further exploration is needed into the microbiome's role in skin health and the development of innovative, microbe-based skincare products. Biotherapeutic approaches, including the use of phages, endolysins, probiotics, prebiotics, postbiotics, and microbiome transplantation, can restore balance and enhance skin health. This article also addresses regulatory standards in the EU and the USA that ensure the safety and effectiveness of microbial skincare products.

CONCLUSION

This review underscores the need to advance research on the skin microbiome's role in cosmetic enhancements and tailored skincare solutions, highlighting a great interest in leveraging microbial communities for dermatological benefits.

MetaBakery: a Singularity implementation of bioBakery tools as a skeleton application for efficient HPC deconvolution of microbiome metagenomic sequencing data to machine learning ready information

In this study, we present MetaBakery (http://metabakery.fe.uni-lj.si), an integrated application designed as a framework for synergistically executing the bioBakery workflow and associated utilities. MetaBakery streamlines the processing of any number of paired or unpaired fastq files, or a mixture of both, with optional compression (gzip, zip, bzip2, xz, or mixed) within a single run. MetaBakery uses programs such as KneadData (https://github.com/bioBakery/kneaddata), MetaPhlAn, HUMAnN and StrainPhlAn as well as integrated utilities and extends the original functionality of bioBakery. In particular, it includes MelonnPan for the prediction of metabolites and Mothur for calculation of microbial alpha diversity. Written in Python 3 and C++ the whole pipeline was encapsulated as Singularity container for efficient execution on various computing infrastructures, including large High-Performance Computing clusters. MetaBakery facilitates crash recovery, efficient re-execution upon parameter changes, and processing of large data sets through subset handling and is offered in three editions with bioBakery ingredients versions 4, 3 and 2 as versatile, transparent and well documented within the MetaBakery Users' Manual (http://metabakery.fe.uni-lj.si/metabakery_manual.pdf). It provides automatic handling of command line parameters, file formats and comprehensive hierarchical storage of output to simplify navigation and debugging. MetaBakery filters out potential human contamination and excludes samples with low read counts. It calculates estimates of alpha diversity and represents a comprehensive and augmented re-implementation of the bioBakery workflow. The robustness and flexibility of the system enables efficient exploration of changing parameters and input datasets, increasing its utility for microbiome analysis. Furthermore, we have shown that the MetaBakery tool can be used in modern biostatistical and machine learning approaches including large-scale microbiome studies.

The salivary microbiome as a diagnostic biomarker of periodontitis: a 16S multi-batch study before and after the removal of batch effects

Introduction

Microbiome-based clinical applications that improve diagnosis related to oral health are of great interest to precision dentistry. Predictive studies on the salivary microbiome are scarce and of low methodological quality (low sample sizes, lack of biological heterogeneity, and absence of a validation process). None of them evaluates the impact of confounding factors as batch effects (BEs). This is the first 16S multi-batch study to analyze the salivary microbiome at the amplicon sequence variant (ASV) level in terms of differential abundance and machine learning models. This is done in periodontally healthy and periodontitis patients before and after removing BEs.

Methods

Saliva was collected from 124 patients (50 healthy, 74 periodontitis) in our setting. Sequencing of the V3-V4 16S rRNA gene region was performed in Illumina MiSeq. In parallel, searches were conducted on four databases to identify previous Illumina V3-V4 sequencing studies on the salivary microbiome. Investigations that met predefined criteria were included in the analysis, and the own and external sequences were processed using the same bioinformatics protocol. The statistical analysis was performed in the R-Bioconductor environment.

Results

The elimination of BEs reduced the number of ASVs with differential abundance between the groups by approximately one-third (Before=265; After=190). Before removing BEs, the model constructed using all study samples (796) comprised 16 ASVs (0.16%) and had an area under the curve (AUC) of 0.944, sensitivity of 90.73%, and specificity of 87.16%. The model built using two-thirds of the specimens (training=531) comprised 35 ASVs (0.36%) and had an AUC of 0.955, sensitivity of 86.54%, and specificity of 90.06% after being validated in the remaining one-third (test=265). After removing BEs, the models required more ASVs (all samples=200-2.03%; training=100-1.01%) to obtain slightly lower AUC (all=0.935; test=0.947), lower sensitivity (all=81.79%; test=78.85%), and similar specificity (all=91.51%; test=90.68%).

Conclusions

The removal of BEs controls false positive ASVs in the differential abundance analysis. However, their elimination implies a significantly larger number of predictor taxa to achieve optimal performance, creating less robust classifiers. As all the provided models can accurately discriminate health from periodontitis, implying good/excellent sensitivities/specificities, the salivary microbiome demonstrates potential clinical applicability as a precision diagnostic tool for periodontitis.

Explainable artificial intelligence and microbiome data for food geographical origin: the Mozzarella di Bufala Campana PDO Case of Study

Identifying the origin of a food product holds paramount importance in ensuring food safety, quality, and authenticity. Knowing where a food item comes from provides crucial information about its production methods, handling practices, and potential exposure to contaminants. Machine learning techniques play a pivotal role in this process by enabling the analysis of complex data sets to uncover patterns and associations that can reveal the geographical source of a food item. This study aims to investigate the potential use of explainable artificial intelligence for identifying the food origin. The case of study of Mozzarella di Bufala Campana PDO has been considered by examining the composition of the microbiota in each samples. Three different supervised machine learning algorithms have been compared and the best classifier model is represented by Random Forest with an Area Under the Curve (AUC) value of 0.93 and the top accuracy of 0.87. Machine learning models effectively classify origin, offering innovative ways to authenticate regional products and support local economies. Further research can explore microbiota analysis and extend applicability to diverse food products and contexts for enhanced accuracy and broader impact.

Interpretable machine learning decodes soil microbiome's response to drought stress

BACKGROUND

Extreme weather events induced by climate change, particularly droughts, have detrimental consequences for crop yields and food security. Concurrently, these conditions provoke substantial changes in the soil bacterial microbiota and affect plant health. Early recognition of soil affected by drought enables farmers to implement appropriate agricultural management practices. In this context, interpretable machine learning holds immense potential for drought stress classification of soil based on marker taxa.

RESULTS

This study demonstrates that the 16S rRNA-based metagenomic approach of Differential Abundance Analysis methods and machine learning-based Shapley Additive Explanation values provide similar information. They exhibit their potential as complementary approaches for identifying marker taxa and investigating their enrichment or depletion under drought stress in grass lineages. Additionally, the Random Forest Classifier trained on a diverse range of relative abundance data from the soil bacterial micobiome of various plant species achieves a high accuracy of 92.3 % at the genus rank for drought stress prediction. It demonstrates its generalization capacity for the lineages tested.

CONCLUSIONS

In the detection of drought stress in soil bacterial microbiota, this study emphasizes the potential of an optimized and generalized location-based ML classifier. By identifying marker taxa, this approach holds promising implications for microbe-assisted plant breeding programs and contributes to the development of sustainable agriculture practices. These findings are crucial for preserving global food security in the face of climate change.

mi-Mic: a novel multi-layer statistical test for microbiota-disease associations

mi-Mic, a novel approach for microbiome differential abundance analysis, tackles the key challenges of such statistical tests: a large number of tests, sparsity, varying abundance scales, and taxonomic relationships. mi-Mic first converts microbial counts to a cladogram of means. It then applies a priori tests on the upper levels of the cladogram to detect overall relationships. Finally, it performs a Mann-Whitney test on paths that are consistently significant along the cladogram or on the leaves. mi-Mic has much higher true to false positives ratios than existing tests, as measured by a new real-to-shuffle positive score.

Microbiome Dynamics: A Paradigm Shift in Combatting Infectious Diseases

Infectious diseases have long posed a significant threat to global health and require constant innovation in treatment approaches. However, recent groundbreaking research has shed light on a previously overlooked player in the pathogenesis of disease-the human microbiome. This review article addresses the intricate relationship between the microbiome and infectious diseases and unravels its role as a crucial mediator of host-pathogen interactions. We explore the remarkable potential of harnessing this dynamic ecosystem to develop innovative treatment strategies that could revolutionize the management of infectious diseases. By exploring the latest advances and emerging trends, this review aims to provide a new perspective on combating infectious diseases by targeting the microbiome.

Explainable artificial intelligence for microbiome data analysis in colorectal cancer biomarker identification

Background

Colorectal cancer (CRC) is a type of tumor caused by the uncontrolled growth of cells in the mucosa lining the last part of the intestine. Emerging evidence underscores an association between CRC and gut microbiome dysbiosis. The high mortality rate of this cancer has made it necessary to develop new early diagnostic methods. Machine learning (ML) techniques can represent a solution to evaluate the interaction between intestinal microbiota and host physiology. Through explained artificial intelligence (XAI) it is possible to evaluate the individual contributions of microbial taxonomic markers for each subject. Our work also implements the Shapley Method Additive Explanations (SHAP) algorithm to identify for each subject which parameters are important in the context of CRC.

Results

The proposed study aimed to implement an explainable artificial intelligence framework using both gut microbiota data and demographic information from subjects to classify a cohort of control subjects from those with CRC. Our analysis revealed an association between gut microbiota and this disease. We compared three machine learning algorithms, and the Random Forest (RF) algorithm emerged as the best classifier, with a precision of 0.729 ± 0.038 and an area under the Precision-Recall curve of 0.668 ± 0.016. Additionally, SHAP analysis highlighted the most crucial variables in the model's decision-making, facilitating the identification of specific bacteria linked to CRC. Our results confirmed the role of certain bacteria, such as Fusobacterium, Peptostreptococcus, and Parvimonas, whose abundance appears notably associated with the disease, as well as bacteria whose presence is linked to a non-diseased state.

Discussion

These findings emphasizes the potential of leveraging gut microbiota data within an explainable AI framework for CRC classification. The significant association observed aligns with existing knowledge. The precision exhibited by the RF algorithm reinforces its suitability for such classification tasks. The SHAP analysis not only enhanced interpretability but identified specific bacteria crucial in CRC determination. This approach opens avenues for targeted interventions based on microbial signatures. Further exploration is warranted to deepen our understanding of the intricate interplay between microbiota and health, providing insights for refined diagnostic and therapeutic strategies.

Unraveling the microbiome-metabolome nexus: a comprehensive study protocol for personalized management of Behçet's disease using explainable artificial intelligence

The presented study protocol outlines a comprehensive investigation into the interplay among the human microbiota, volatilome, and disease biomarkers, with a specific focus on Behçet's disease (BD) using methods based on explainable artificial intelligence. The protocol is structured in three phases. During the initial three-month clinical study, participants will be divided into control and experimental groups. The experimental groups will receive a soluble fiber-based dietary supplement alongside standard therapy. Data collection will encompass oral and fecal microbiota, breath samples, clinical characteristics, laboratory parameters, and dietary habits. The subsequent biological data analysis will involve gas chromatography, mass spectrometry, and metagenetic analysis to examine the volatilome and microbiota composition of salivary and fecal samples. Additionally, chemical characterization of breath samples will be performed. The third phase introduces Explainable Artificial Intelligence (XAI) for the analysis of the collected data. This novel approach aims to evaluate eubiosis and dysbiosis conditions, identify markers associated with BD, dietary habits, and the supplement. Primary objectives include establishing correlations between microbiota, volatilome, phenotypic BD characteristics, and identifying patient groups with shared features. The study aims to identify taxonomic units and metabolic markers predicting clinical outcomes, assess the supplement's impact, and investigate the relationship between dietary habits and patient outcomes. This protocol contributes to understanding the microbiome's role in health and disease and pioneers an XAI-driven approach for personalized BD management. With 70 recruited BD patients, XAI algorithms will analyze multi-modal clinical data, potentially revolutionizing BD management and paving the way for improved patient outcomes.

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.

Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action

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.