What question did this study set out to answer?

The aim is to identify mitochondria-related gene signatures that can serve as biomarkers for tuberculosis diagnosis using machine learning techniques.

April 14, 2026Microbial Pathogenesis0 citationsOpen Access

View Full Paper

Identifying mitochondria-related signatures for tuberculosis diagnosis through machine learning on single-cell transcriptomics data and experimental verification

XZXianyi ZhangShenzhen Second People's Hospital KZKehong ZhangShenzhen Second People's Hospital YWYu WangNorthwestern Polytechnical University

Key Points

The aim is to identify mitochondria-related gene signatures that can serve as biomarkers for tuberculosis diagnosis using machine learning techniques.
Integrated analysis of microarray and single-cell RNA sequencing data from tuberculosis and healthy controls
Identification of ten differentially expressed mitochondrial genes (MitoDEGs)
Quantitative PCR validation in an infected cell model
Use of LASSO and SVM-RFE algorithms to select hub markers for diagnostic model
The SVM-based diagnostic model demonstrated robust performance with AUC values up to 0.993 across multiple cohorts
Three hub markers (STAT2, CASP1, COX7B) were prioritized for the model
Independent clinical validation confirmed the model's efficacy with an AUC of 0.909

Abstract

Tuberculosis (TB) remains a major cause of infectious disease mortality. Early diagnosis is crucial for curbing transmission and initiating timely treatment. However, the lack of reliable non-sputum-based diagnostic tools often delays prompt detection. Since mitochondrial dysregulation facilitates Mycobacterium tuberculosis (MTB) evasion, we explored mitochondria-related gene signatures as diagnostic biomarkers. By integrating microarray (GSE19491) and single-cell RNA sequencing (scRNA-seq; SRP247583) data from active tuberculosis disease (TBD), latent tuberculosis infection (TBI), and healthy controls (HC) obtained from the Gene Expression Omnibus (GEO) database, we identified ten mitochondria-related differentially expressed genes (MitoDEGs) —STAT2, CASP1, SCO2, PRELID1, COX7B, COX6A1, TSPO, IFI6, ATG3, and COX7A2— in the monocytic lineage. Enrichment analysis revealed that these ten MitoDEGs were primarily enriched in oxidative phosphorylation. Quantitative PCR (qPCR) validated the upregulation of these genes in an H37Rv-infected THP-1 cell model ( P < 0.01). Using the Least Absolute Shrinkage and Selection Operator (LASSO) and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) algorithms, we prioritized three hub markers (STAT2, CASP1 and COX7B) to construct a blood-based diagnostic model. The SVM-based model achieved robust diagnostic performance in differentiating TBD in the training ( n = 125; AUC = 0.852), validation ( n = 30; AUC = 0.885), and two testing sets: GSE54992 ( n = 15; AUC = 0.907) and GSE34608 ( n = 26; AUC = 0.993). Moreover, an independent clinical cohort further confirmed its efficacy ( n = 52; AUC = 0.909) in discriminating TBD from non-TB controls. In summary, we developed a three-MitoDEG model that shows promising diagnostic performance for TBD and was preliminarily validated, offering a scalable, non-sputum alternative for triage in resource-limited settings. • Host mitochondrial genes reflect immune responses to tuberculosis infection • Machine learning pinpoints a three-gene blood signature for tuberculosis disease • The three-gene model is validated with high accuracy in patient cohorts

Demander à l'IA

Bookmark

View Full Paper

Demander à l'IA

Bookmark

View Full Paper

Identifying mitochondria-related signatures for tuberculosis diagnosis through machine learning on single-cell transcriptomics data and experimental verification

Key Points

Abstract

Cite This Study

Also Consider

Also Consider