Related Experiment Video
Updated: Apr 14, 2026

A Microscopic Phenotypic Assay for the Quantification of Intracellular Mycobacteria Adapted for High-throughput/High-content Screening
Published on: January 17, 2014
Identifying mitochondria-related signatures for tuberculosis diagnosis through machine learning on single-cell
Xianyi Zhang1, Kehong Zhang2, Yu Wang3
1The Baoan People's Hospital of Shenzhen, The Second Affiliated Hospital of Shenzhen University, Shenzhen University, Shenzhen, 518000, China.
Researchers identified three mitochondria-related genes (STAT2, CASP1, COX7B) as biomarkers for diagnosing active tuberculosis disease (TBD). This blood-based test offers a promising, non-sputum alternative for early detection and treatment initiation.
Area of Science:
- Biomolecular analysis and diagnostics
- Genomics and transcriptomics
- Infectious disease research
Background:
- Tuberculosis (TB) causes significant mortality, with early diagnosis critical for control.
- Current diagnostic methods often rely on sputum, delaying detection and treatment.
- Mitochondrial dysregulation is implicated in Mycobacterium tuberculosis (MTB) evasion.
Purpose of the Study:
- To identify mitochondria-related gene signatures as potential biomarkers for active tuberculosis disease (TBD).
- To develop and validate a non-sputum-based diagnostic model for TBD using blood samples.
Main Methods:
- Integrated microarray and single-cell RNA sequencing data from active TB, latent TB, and healthy controls.
- Identified ten mitochondria-related differentially expressed genes (MitoDEGs) in monocytic cells.
- Utilized LASSO and SVM-RFE algorithms to select three hub markers (STAT2, CASP1, COX7B) for a diagnostic model.
Main Results:
- A three-MitoDEG (STAT2, CASP1, COX7B) blood-based diagnostic model was constructed.
- The model demonstrated robust diagnostic performance across training, validation, and independent testing sets (AUCs ranging from 0.852 to 0.993).
- An independent clinical cohort confirmed the model's efficacy in discriminating TBD from non-TB controls (AUC = 0.909).
Conclusions:
- A novel three-MitoDEG signature shows significant potential as a blood-based diagnostic tool for TBD.
- This non-sputum approach offers a scalable alternative for TB triage, especially in resource-limited settings.
- Further validation could lead to improved early diagnosis and management of tuberculosis.
Related Concept Videos
Pulmonary Tuberculosis IV
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Pulmonary Tuberculosis I
Causative Organism
The primary infectious agent causing tuberculosis is Mycobacterium tuberculosis, a slow-growing, acid-fast, aerobic rod that exhibits sensitivity to heat and ultraviolet light. Instances of Mycobacterium bovis and Mycobacterium avium contributing to the development of TB infection are rare.
Mode of...
Pulmonary Tuberculosis V
Latent tuberculosis infection occurs when TB bacteria are present in a person's body, but are not causing illness or symptoms. It is not contagious, and preventive treatment is crucial to avoid the...
Pulmonary Tuberculosis II
Here is a detailed explanation of its pathophysiology:
Transmission: The process begins when a person inhales droplet nuclei containing M. tuberculosis. These are typically released into the air when an individual with pulmonary or...

