Best practices for developing microbiome-based disease diagnostic classifiers through machine learning
The human gut microbiome, crucial in various diseases, can be utilized to develop diagnostic models through machine learning (ML). The specific tools and parameters used in model construction such as data preprocessing, batch effect removal and modeling algorithms can impact model performance and ge...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Gut Microbes |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19490976.2025.2489074 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849765268295778304 |
|---|---|
| author | Peikun Li Min Li Wei-Hua Chen |
| author_facet | Peikun Li Min Li Wei-Hua Chen |
| author_sort | Peikun Li |
| collection | DOAJ |
| description | The human gut microbiome, crucial in various diseases, can be utilized to develop diagnostic models through machine learning (ML). The specific tools and parameters used in model construction such as data preprocessing, batch effect removal and modeling algorithms can impact model performance and generalizability. To establish an generally applicable workflow, we divided the ML process into three above-mentioned steps and optimized each sequentially using 83 gut microbiome cohorts across 20 diseases. We tested a total of 156 tool-parameter-algorithm combinations and benchmarked them according to internal- and external- AUCs. At the data preprocessing step, we identified four data preprocessing methods that performed well for regression-type algorithms and one method that excelled for non-regression-type algorithms. At the batch effect removal step, we identified the “ComBat” function from the sva R package as an effective batch effect removal method and compared the performance of various algorithms. Finally, at the ML algorithm selection step, we found that Ridge and Random Forest ranked the best. Our optimized work flow performed similarly comparing with previous exhaustive methods for disease-specific optimizations, thus is generally applicable and can provide a comprehensive guideline for constructing diagnostic models for a range of diseases, potentially serving as a powerful tool for future medical diagnostics. |
| format | Article |
| id | doaj-art-a5844d9eebed4aeab9fe97926edd99bf |
| institution | DOAJ |
| issn | 1949-0976 1949-0984 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Gut Microbes |
| spelling | doaj-art-a5844d9eebed4aeab9fe97926edd99bf2025-08-20T03:04:54ZengTaylor & Francis GroupGut Microbes1949-09761949-09842025-12-0117110.1080/19490976.2025.2489074Best practices for developing microbiome-based disease diagnostic classifiers through machine learningPeikun Li0Min Li1Wei-Hua Chen2Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular Imaging, Center for Artificial Intelligence Biology, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaKey Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular Imaging, Center for Artificial Intelligence Biology, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaKey Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular Imaging, Center for Artificial Intelligence Biology, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, Hubei, ChinaThe human gut microbiome, crucial in various diseases, can be utilized to develop diagnostic models through machine learning (ML). The specific tools and parameters used in model construction such as data preprocessing, batch effect removal and modeling algorithms can impact model performance and generalizability. To establish an generally applicable workflow, we divided the ML process into three above-mentioned steps and optimized each sequentially using 83 gut microbiome cohorts across 20 diseases. We tested a total of 156 tool-parameter-algorithm combinations and benchmarked them according to internal- and external- AUCs. At the data preprocessing step, we identified four data preprocessing methods that performed well for regression-type algorithms and one method that excelled for non-regression-type algorithms. At the batch effect removal step, we identified the “ComBat” function from the sva R package as an effective batch effect removal method and compared the performance of various algorithms. Finally, at the ML algorithm selection step, we found that Ridge and Random Forest ranked the best. Our optimized work flow performed similarly comparing with previous exhaustive methods for disease-specific optimizations, thus is generally applicable and can provide a comprehensive guideline for constructing diagnostic models for a range of diseases, potentially serving as a powerful tool for future medical diagnostics.https://www.tandfonline.com/doi/10.1080/19490976.2025.2489074Gut microbiomemachine learningpatient stratificationdisease diagnostic modelsoptimal model construction workflow |
| spellingShingle | Peikun Li Min Li Wei-Hua Chen Best practices for developing microbiome-based disease diagnostic classifiers through machine learning Gut Microbes Gut microbiome machine learning patient stratification disease diagnostic models optimal model construction workflow |
| title | Best practices for developing microbiome-based disease diagnostic classifiers through machine learning |
| title_full | Best practices for developing microbiome-based disease diagnostic classifiers through machine learning |
| title_fullStr | Best practices for developing microbiome-based disease diagnostic classifiers through machine learning |
| title_full_unstemmed | Best practices for developing microbiome-based disease diagnostic classifiers through machine learning |
| title_short | Best practices for developing microbiome-based disease diagnostic classifiers through machine learning |
| title_sort | best practices for developing microbiome based disease diagnostic classifiers through machine learning |
| topic | Gut microbiome machine learning patient stratification disease diagnostic models optimal model construction workflow |
| url | https://www.tandfonline.com/doi/10.1080/19490976.2025.2489074 |
| work_keys_str_mv | AT peikunli bestpracticesfordevelopingmicrobiomebaseddiseasediagnosticclassifiersthroughmachinelearning AT minli bestpracticesfordevelopingmicrobiomebaseddiseasediagnosticclassifiersthroughmachinelearning AT weihuachen bestpracticesfordevelopingmicrobiomebaseddiseasediagnosticclassifiersthroughmachinelearning |