Utilizing metagenomic profiling and machine learning model to identify bacterial biomarkers for major depressive disorder

Aug 4, 2026

Upload by Riley

Major depressive disorder (MDD) shows substantial heterogeneity and its pathogenesis remains incompletely understood, despite evidence linking depression to gut flora. This research used metagenomic profiling of intestinal bacterial communities in 36 patients with MDD and 36 healthy controls, followed by a support vector machine–recursive feature elimination (SVM-RFE) strategy to discover microbial biomarkers. Eight MDD-specific taxa were associated with diagnostic performance, achieving strong accuracy in training and validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Background and relevance

Gut-brain axis and prior evidence

Methods

Study design and metagenomic profiling

Machine learning model for biomarker discovery

Results

Diversity changes in MDD

Identified bacterial biomarkers and diagnostic accuracy

Validation performance

Conclusion

TYPE Original Research PUBLISHED 18 February 2025 DOI 10.3389/fpsyt.2025.1539596 OPEN ACCESS EDITED BY Melanie Föcking, Royal College of Surgeons in Ireland, Ireland REVIEWED BY Shinsuke Hidese, Teikyo University, Japan Yanlin Tao, Fudan University, China *CORRESPONDENCE Huimin Hu [1271292800@qq.com](1271292800@qq.com) †These authors have contributed equally to this work RECEIVED 04 December 2024 ACCEPTED 31 January 2025 PUBLISHED 18 February 2025 CITATION Wang X, Cao D, Zhang H, Chen W, Sun Jand Hu H (2025) Utilizing metagenomic proﬁling and machine learning model to identify bacterial biomarkers for major depressive disorder. Front. Psychiatry 16:1539596 . doi: 10.3389/fpsyt.2025.1539596 COPYRIGHT © 2025 Wang, Cao, Zhang, Chen, Sun and Hu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Utilizing metagenomic proﬁling and machine learning model to identify bacterial biomarkers for major depressive disorder Xuan Wang 1†, Di Cao 2†, Hanlin Zhang 3, Wei Chen 1, Jiaxin Sun 1 and Huimin Hu 4* 1 Department of Dermatology, Lianyungang Municipal Oriental Hospital, Lianyungang, China, 2 Department of Dermatology, The First People’s Hospital of Lianyungang, Lianyungang, China, 3 Department of Dermatology, Jieshou City People’s Hospital, Fuyang, China, 4 Department of Dermatology, The Afﬁliated Huai’an Hospital of Xuzhou Medical University and The Second People’s Hospital of Huai’an, Huaian, China Background: Major depressive disorder (MDD) is highly heterogeneous, which provides a signiﬁcant challenge in the management of this disorder. However, the pathogenesis of major depressive disorder is not fully understood. Studies have shown that depression is highly correlated with gut ﬂora. The objective of this study was to explore the potential of microbial biomarkers in the diagnosis of major depressive disorder. Methods: In this study, we used a metagenomic approach to analyze the composition and differences of gut bacterial communities in 36 patients with major depressive disorder and 36 healthy individuals. We then applied a Support Vector Machine Recursive Feature Elimination (SVM-RFE) machine learning model to ﬁnd potential microbial markers. Results: Our results showed that the alpha diversity of the intestinal ﬂora did not differ signiﬁcantly in major depressive disorder compared to healthy populations. However, the beta diversity was signiﬁcantly altered. Machine learning identiﬁed 8 MDD-spec iﬁc bacterial biomarkers, with Alistipes, Dysosmo bacter, Actinomyces, Ruthenibacterium, and Thomasclavelia being signiﬁcantly enriched, while Faecalibacterium, Pseudobutyrivibrio, and Roseburia were signiﬁcantly reduced, demonstrating superior diagnostic accuracy (area under the curve, AUC = 0 . 919) . In addition, the gut bacteria performed satisfactorily in the validation cohort with an AUC of 0 . 800 (95% CI: 0 .6334-0. 9143) . Conclusion: This study reveals the complex relationship between gut microbiota and major depressive disorder and provides a scientiﬁc basis for the development of a microbiota-based diagnostic tool for depression. KEYWORDS major depressive disorder, gut bacteria, metagenome, machine learning, diagnosing disease Frontiers in Psychiatry 01 [frontiersin.org](frontiersin.org) Introduction Major depressive disorder (MDD) is a gradually debilitating global mental illness, more than 300 million people of all ages are suffering from depression, the prevalence of depression in China is 4.2%, and it is conservatively estimated that the number of people suffering from

FAQs

What was the main objective of the study?

To identify potential microbial biomarkers that could support the diagnosis of major depressive disorder using metagenomic profiling and machine learning.

How were biomarkers selected in this research?

Gut bacterial communities from participants were analyzed with metagenomic methods, and a SVM-RFE machine learning approach was used to select candidate microbial markers.

Which diversity aspects differed between MDD and healthy groups?

Alpha diversity showed no significant difference, while beta diversity was significantly altered between major depressive disorder and healthy populations.

Aug 4, 2026

Upload by Riley