Related Experiment Video
Updated: Aug 13, 2025
Identification of Mycobacterium Species by DNA Microarray Chip Method
Published on: June 24, 2025
A Machine Learning Approach Reveals a Microbiota Signature for Infection with Mycobacterium avium subsp.
Sang-Mok Lee1, Hong-Tae Park2, Seojoung Park1
1School of Energy and Chemical Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of Korea.
Abstract:
Although Mycobacterium avium subsp. paratuberculosis (MAP) has threatened public health and the livestock industry, the current diagnostic tools (e.g., fecal PCR and enzyme-linked immunosorbent assay [ELISA]) for MAP infection have some limitations, such as inconsistent results due to intermittent bacterial shedding or low sensitivity during the early stage of infection. Therefore, this study aimed to develop a novel biomarker focusing on elucidating the gut microbial signature of MAP-positive ruminants, since the clinical signs of MAP infection are closely related to dysbiosis. 16S rRNA-based gut microbial community analysis revealed both a decrease in microbial diversity and the emergence of several distinct taxa following MAP infection. To determine the discriminant taxa diagnostic of MAP infection, machine learning-based feature selection and predictive model construction were applied to taxon abundance data or their transformed derivatives. The selected taxa, such as Clostridioides (formerly Clostridium) difficile, were used to build models using a support vector machine, linear support vector classification, k-nearest neighbor, and random forest with 10-fold cross-validation. The receiver operating characteristic-area under the curve (ROC-AUC) analysis of the models revealed their high accuracy, up to approximately 96%. Collectively, taxonomic signatures of cattle gut microbiotas according to MAP infection status could be identified by feature selection tools and applied to establish a predictive model for the infection state. IMPORTANCE Due to the limitations, such as intermittent bacterial shedding or poor sensitivity, of the current diagnostic tools for Johne's disease, novel biomarkers are urgently needed to aid control of the disease. Here, we explored the fecal microbiota of Johne's disease-affected cattle and tried to discover distinct microbial characteristics which have the potential to be novel noninvasive biomarkers. Through 16S rRNA sequencing and machine learning approaches, a dozen taxa were selected as taxonomic signatures to discriminate the disease state. In addition, when constructing predictive models using relative abundance data of the corresponding taxa, the models showed high accuracy for classification, even including animals with subclinical infection. Thus, our study suggested novel noninvasive microbiological biomarkers that are robustly expressed regardless of subclinical infection and the applicability of machine learning for diagnosis of Johne's disease.
Insights
Novel gut microbial biomarkers can accurately diagnose Mycobacterium avium subsp. paratuberculosis (MAP) infection in cattle. Machine learning models identified specific bacterial taxa in fecal samples, offering a promising noninvasive diagnostic approach for Johne's disease.
Area of Science:
- Veterinary Microbiology
- Animal Health Diagnostics
- Gut Microbiome Research
Background:
- Current diagnostics for Mycobacterium avium subsp. paratuberculosis (MAP) infection, such as fecal PCR and ELISA, have limitations including inconsistent results and low sensitivity, especially in early or subclinical stages.
- Clinical signs of MAP infection are linked to gut dysbiosis, suggesting the gut microbial signature could serve as a diagnostic indicator.
- Johne's disease, caused by MAP, significantly impacts the livestock industry, necessitating improved diagnostic tools for effective control.
Purpose of the Study:
- To develop novel, noninvasive biomarkers for MAP infection by analyzing the gut microbial signature of infected ruminants.
- To identify specific bacterial taxa that can discriminate between MAP-positive and MAP-negative cattle.
- To construct accurate predictive models for MAP infection status using machine learning algorithms based on microbial data.
Main Methods:
- 16S rRNA gene sequencing was employed to analyze the gut microbial community structure and diversity in cattle.
- Machine learning techniques, including feature selection and predictive modeling (SVM, LC, k-NN, Random Forest), were applied to taxon abundance data.
- Cross-validation and Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) analysis were used to evaluate model performance and accuracy.
Main Results:
- MAP infection led to a decrease in gut microbial diversity and altered the abundance of specific bacterial taxa.
- Machine learning models successfully identified key discriminant taxa, such as Clostridioides difficile, with high accuracy (up to 96% ROC-AUC).
- The developed predictive models demonstrated robust classification performance, even for animals with subclinical MAP infection.
Conclusions:
- Distinct fecal microbial taxonomic signatures can serve as reliable, noninvasive biomarkers for diagnosing MAP infection in cattle.
- Machine learning approaches are highly effective in identifying microbial biomarkers and building accurate diagnostic models for Johne's disease.
- These findings offer a promising alternative to current diagnostic methods, aiding in the control and management of MAP in livestock.
