1
|
Yang SY, Han SM, Lee JY, Kim KS, Lee JE, Lee DW. Advancing Gut Microbiome Research: The Shift from Metagenomics to Multi-Omics and Future Perspectives. J Microbiol Biotechnol 2025; 35:e2412001. [PMID: 40223273 PMCID: PMC12010094 DOI: 10.4014/jmb.2412.12001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2024] [Revised: 02/14/2025] [Accepted: 02/24/2025] [Indexed: 04/15/2025]
Abstract
The gut microbiome, a dynamic and integral component of human health, has co-evolved with its host, playing essential roles in metabolism, immunity, and disease prevention. Traditional microbiome studies, primarily focused on microbial composition, have provided limited insights into the functional and mechanistic interactions between microbiota and their host. The advent of multi-omics technologies has transformed microbiome research by integrating genomics, transcriptomics, proteomics, and metabolomics, offering a comprehensive, systems-level understanding of microbial ecology and host-microbiome interactions. These advances have propelled innovations in personalized medicine, enabling more precise diagnostics and targeted therapeutic strategies. This review highlights recent breakthroughs in microbiome research, demonstrating how these approaches have elucidated microbial functions and their implications for health and disease. Additionally, it underscores the necessity of standardizing multi-omics methodologies, conducting large-scale cohort studies, and developing novel platforms for mechanistic studies, which are critical steps toward translating microbiome research into clinical applications and advancing precision medicine.
Collapse
Affiliation(s)
- So-Yeon Yang
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Seung Min Han
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Ji-Young Lee
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Kyoung Su Kim
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Jae-Eun Lee
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Dong-Woo Lee
- Department of Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| |
Collapse
|
2
|
Sirasani JP, Gardner C, Jung G, Lee H, Ahn TH. Bioinformatic approaches to blood and tissue microbiome analyses: challenges and perspectives. Brief Bioinform 2025; 26:bbaf176. [PMID: 40269515 PMCID: PMC12018304 DOI: 10.1093/bib/bbaf176] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2024] [Revised: 03/05/2025] [Accepted: 03/25/2025] [Indexed: 04/25/2025] Open
Abstract
Advances in next-generation sequencing have resulted in a growing understanding of the microbiome and its role in human health. Unlike traditional microbiome analysis, blood and tissue microbiome analyses focus on the detection and characterization of microbial DNA in blood and tissue, previously considered a sterile environment. In this review, we discuss the challenges and methodologies associated with analyzing these samples, particularly emphasizing blood and tissue microbiome research. Key preprocessing steps-including the removal of ribosomal RNA, host DNA, and other contaminants-are critical to reducing noise and accurately capturing microbial evidence. We also explore how taxonomic profiling tools, machine learning, and advanced normalization techniques address contamination and low microbial biomass, thereby improving reliability. While it offers the potential for identifying microbial involvement in systemic diseases previously undetectable by traditional methods, this methodology also carries risks and lacks universal acceptance due to concerns over reliability and interpretation errors. This paper critically reviews these factors, highlighting both the promise and pitfalls of using blood and tissue microbiome analyses as a tool for biomarker discovery.
Collapse
Affiliation(s)
- Jammi Prasanthi Sirasani
- Program of Bioinformatics and Computational Biology, Saint Louis University, St. Louis, MO, United States
| | - Cory Gardner
- Department of Computer Science, Saint Louis University, St. Louis, MO, United States
| | - Gihwan Jung
- Department of Computer Science, Saint Louis University, St. Louis, MO, United States
| | - Hyunju Lee
- AI Graduate School, Gwangju Institute of Science and Technology, Gwangju 61005, South Korea
| | - Tae-Hyuk Ahn
- Program of Bioinformatics and Computational Biology, Saint Louis University, St. Louis, MO, United States
- Department of Computer Science, Saint Louis University, St. Louis, MO, United States
| |
Collapse
|
3
|
Przymus P, Rykaczewski K, Martín-Segura A, Truu J, Carrillo De Santa Pau E, Kolev M, Naskinova I, Gruca A, Sampri A, Frohme M, Nechyporenko A. Deep learning in microbiome analysis: a comprehensive review of neural network models. Front Microbiol 2025; 15:1516667. [PMID: 39911715 PMCID: PMC11794229 DOI: 10.3389/fmicb.2024.1516667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2024] [Accepted: 12/16/2024] [Indexed: 02/07/2025] Open
Abstract
Microbiome research, the study of microbial communities in diverse environments, has seen significant advances due to the integration of deep learning (DL) methods. These computational techniques have become essential for addressing the inherent complexity and high-dimensionality of microbiome data, which consist of different types of omics datasets. Deep learning algorithms have shown remarkable capabilities in pattern recognition, feature extraction, and predictive modeling, enabling researchers to uncover hidden relationships within microbial ecosystems. By automating the detection of functional genes, microbial interactions, and host-microbiome dynamics, DL methods offer unprecedented precision in understanding microbiome composition and its impact on health, disease, and the environment. However, despite their potential, deep learning approaches face significant challenges in microbiome research. Additionally, the biological variability in microbiome datasets requires tailored approaches to ensure robust and generalizable outcomes. As microbiome research continues to generate vast and complex datasets, addressing these challenges will be crucial for advancing microbiological insights and translating them into practical applications with DL. This review provides an overview of different deep learning models in microbiome research, discussing their strengths, practical uses, and implications for future studies. We examine how these models are being applied to solve key problems and highlight potential pathways to overcome current limitations, emphasizing the transformative impact DL could have on the field moving forward.
Collapse
Affiliation(s)
- Piotr Przymus
- Faculty of Mathematics and Computer Science, Nicolaus Copernicus University in Toruń, Toruń, Pomeranian, Poland
| | - Krzysztof Rykaczewski
- Faculty of Mathematics and Computer Science, Nicolaus Copernicus University in Toruń, Toruń, Pomeranian, Poland
| | | | - Jaak Truu
- Institute of Molecular and Cell Biology, University of Tartu, Tartu, Estonia
| | | | - Mikhail Kolev
- Department of Mathematics, University of Architecture, Civil Engineering and Geodesy, Sofia, Bulgaria
- Department of Applied Computer Science and Mathematical Modeling, Faculty of Mathematics and Computer Science, University of Warmia and Mazury in Olsztyn, Olsztyn, Poland
| | - Irina Naskinova
- Department of Mathematics, University of Architecture, Civil Engineering and Geodesy, Sofia, Bulgaria
| | - Aleksandra Gruca
- Department of Computer Networks and Systems, Silesian University of Technology, Gliwice, Poland
| | - Alexia Sampri
- British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom
- Victor Phillip Dahdaleh Heart and Lung Research Institute, University of Cambridge, Cambridge, United Kingdom
| | - Marcus Frohme
- Molecular Biotechnology and Functional Genomics, Technical University of Applied Sciences Wildau, Wildau, Brandenburg, Germany
| | - Alina Nechyporenko
- Molecular Biotechnology and Functional Genomics, Technical University of Applied Sciences Wildau, Wildau, Brandenburg, Germany
- Department of System Engineering, Kharkiv National University of Radioelectronics, Kharkiv, Ukraine
| |
Collapse
|
4
|
Roy G, Prifti E, Belda E, Zucker JD. Deep learning methods in metagenomics: a review. Microb Genom 2024; 10:001231. [PMID: 38630611 PMCID: PMC11092122 DOI: 10.1099/mgen.0.001231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 03/27/2024] [Indexed: 04/19/2024] Open
Abstract
The ever-decreasing cost of sequencing and the growing potential applications of metagenomics have led to an unprecedented surge in data generation. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome plays a crucial role in human health, providing vital information for patient diagnosis and prognosis. However, analysing metagenomic data remains challenging due to several factors, including reference catalogues, sparsity and compositionality. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification and disease prediction. Beyond generating predictive models, a key aspect of these methods is also their interpretability. This article reviews DL approaches in metagenomics, including convolutional networks, autoencoders and attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the microbiome's key role in our health.
Collapse
Affiliation(s)
- Gaspar Roy
- IRD, Sorbonne University, UMMISCO, 32 avenue Henry Varagnat, Bondy Cedex, France
| | - Edi Prifti
- IRD, Sorbonne University, UMMISCO, 32 avenue Henry Varagnat, Bondy Cedex, France
- Sorbonne University, INSERM, Nutriomics, 91 bvd de l’hopital, 75013 Paris, France
| | - Eugeni Belda
- IRD, Sorbonne University, UMMISCO, 32 avenue Henry Varagnat, Bondy Cedex, France
- Sorbonne University, INSERM, Nutriomics, 91 bvd de l’hopital, 75013 Paris, France
| | - Jean-Daniel Zucker
- IRD, Sorbonne University, UMMISCO, 32 avenue Henry Varagnat, Bondy Cedex, France
- Sorbonne University, INSERM, Nutriomics, 91 bvd de l’hopital, 75013 Paris, France
| |
Collapse
|
5
|
Luo F, Wang X, Ye C, Sun H. Microbial Biomarkers in Liquid Biopsy for Cancer: An Overview and Future Directions. Cancer Control 2024; 31:10732748241292019. [PMID: 39431347 PMCID: PMC11500238 DOI: 10.1177/10732748241292019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2024] [Revised: 09/23/2024] [Accepted: 09/27/2024] [Indexed: 10/22/2024] Open
Abstract
In recent years, the relationship between microbes and tumors has led to a new wave of scholarly pursuits. Due to the growing awareness of the importance of microbiota, including those within tumors, for cancer onset, progression, metastasis, and treatment, researchers have come to understand that microbiota and the tumor microenvironment together form a dynamic and complex ecosystem. Liquid biopsy technology, a non-invasive and easily repeatable method for sample collection, combined with emerging multi-omics techniques, allows for a more comprehensive and in-depth exploration of microbial signals and characteristics in bodily fluids. Microbial biomarkers hold immense potential in the early diagnosis, treatment stratification, and prognosis prediction of cancer. In this review, we describe the significant potential of microbial biomarkers in liquid biopsy for clinical applications in cancer, including early diagnosis, predicting treatment responses, and prognosis. Moreover, we discuss current limitations and potential solutions related to microbial biomarkers. This review aims to provide an overview and future directions of microbial biomarkers in liquid biopsy for cancer clinical practice.
Collapse
Affiliation(s)
| | - Xinyue Wang
- Xinyue Wang, MB, Clinical Biobank Center, Microbiome Medicine Center, Department of Laboratory Medicine, Zhujiang Hospital, The Second School of Clinical Medicine, Southern Medical University, 253# Gongye Road, Guangzhou 510280, China.
| | | | - Haitao Sun
- Xinyue Wang, MB, Clinical Biobank Center, Microbiome Medicine Center, Department of Laboratory Medicine, Zhujiang Hospital, The Second School of Clinical Medicine, Southern Medical University, 253# Gongye Road, Guangzhou 510280, China.
| |
Collapse
|
6
|
Shen WX, Chen YZ. Toward ordered -omics data science: Researchers on the magic of turning metagenomic chaos into image-like patterns. PATTERNS (NEW YORK, N.Y.) 2023; 4:100673. [PMID: 36699736 PMCID: PMC9868643 DOI: 10.1016/j.patter.2022.100673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
Abstract
Wan Xiang Shen, a postdoctoral researcher at National University of Singapore, and Yu Zong Chen, the PI of the Bioinformatics and Drug Design (BIDD) group, have developed an AI pipeline for enhanced deep learning of metagenomic data. Their Patterns paper highlights the advantages of unsupervised data restructuring in microbiome-based disease prediction and biomarker discovery. They talk about their view of data science and the backstory of the article published in Patterns.
Collapse
Affiliation(s)
- Wan Xiang Shen
- Bioinformatics and Drug Design (BIDD) Group and Center for Computational Science and Engineering, Department of Pharmacy, National University of Singapore, Singapore 117559, Singapore
- Department of Chemistry, Faculty of Science, National University of Singapore, Singapore 117543, Singapore
| | - Yu Zong Chen
- Bioinformatics and Drug Design (BIDD) Group and Center for Computational Science and Engineering, Department of Pharmacy, National University of Singapore, Singapore 117559, Singapore
- The State Key Laboratory of Chemical Oncogenomics, Key Laboratory of Chemical Biology, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, PR China
| |
Collapse
|
7
|
Lee Y, Cappellato M, Di Camillo B. Machine learning-based feature selection to search stable microbial biomarkers: application to inflammatory bowel disease. Gigascience 2022; 12:giad083. [PMID: 37882604 PMCID: PMC10600917 DOI: 10.1093/gigascience/giad083] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2023] [Revised: 08/23/2023] [Accepted: 09/17/2023] [Indexed: 10/27/2023] Open
Abstract
BACKGROUND Biomarker discovery exploiting feature importance of machine learning has risen recently in the microbiome landscape with its high predictive performance in several disease states. To have a concrete selection among a high number of features, recursive feature elimination (RFE) has been widely used in the bioinformatics field. However, machine learning-based RFE has factors that decrease the stability of feature selection. In this article, we suggested methods to improve stability while sustaining performance. RESULTS We exploited the abundance matrices of the gut microbiome (283 taxa at species level and 220 at genus level) to classify between patients with inflammatory bowel disease (IBD) and healthy control (1,569 samples). We found that applying an already published data transformation before RFE improves feature stability significantly. Moreover, we performed an in-depth evaluation of different variants of the data transformation and identify those that demonstrate better improvement in stability while not sacrificing classification performance. To ensure a robust comparison, we evaluated stability using various similarity metrics, distances, the common number of features, and the ability to filter out noise features. We were able to confirm that the mapping by the Bray-Curtis similarity matrix before RFE consistently improves the stability while maintaining good performance. Multilayer perceptron algorithm exhibited the highest performance among 8 different machine learning algorithms when a large number of features (a few hundred) were considered based on the best performance across 100 bootstrapped internal test sets. Conversely, when utilizing only a limited number of biomarkers as a trade-off between optimal performance and method generalizability, the random forest algorithm demonstrated the best performance. Using the optimal pipeline we developed, we identified 14 biomarkers for IBD at the species level and analyzed their roles using Shapley additive explanations. CONCLUSION Taken together, our work not only showed how to improve biomarker discovery in the metataxonomic field without sacrificing classification performance but also provided useful insights for future comparative studies.
Collapse
Affiliation(s)
- Youngro Lee
- Department of Electrical and Computer Engineering, Seoul National University, Seoul, 08826, Korea
- Institute of Engineering Research at Seoul National University, Seoul, 08826, Korea
| | - Marco Cappellato
- Department of Information Engineering, University of Padova, Padova, 35122, Italy
| | - Barbara Di Camillo
- Department of Information Engineering, University of Padova, Padova, 35122, Italy
| |
Collapse
|