A Machine Learning Approach for Biomarker Discovery in Microbiome
We propose to develop a robust and reproducible methodology for biomarker discovery in microbiome data using machine learning. This methodology aims to address the challenges of reproducibility and consistency in biomedical research. We plan to apply this methodology to identify potential biomarkers for diseases such as Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). Our approach will utilize the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) algorithm for feature selection across multiple datasets. We believe this approach will enhance reproducibility and yield robust results.
These are the results of the different taxa, validated in different datasets.
https://github.com/steppenwolf0/reproducibilityBiomarker
These are the Datasets used for each one.
ASD 26 Taxa
- David et al* (Discovery)
http://files.cqls.oregonstate.edu/David_Lab/ASD_study1/ - PRJNA578223
- PRJNA589343
IBD 54 Taxa
- PRJEB21504 (Discovery)
- DRA006094
- PRJNA684584
T2D 9 Taxa
- PRJNA325931 (Discovery)
- PRJNA554535
- PRJEB53017
Parkinson 84 Taxa
- PRJEB14674 (Discovery)
- PRJNA742875
- PRJEB27564
- PRJNA594156
Rojas-Velazquez, David, et al. "Matthews correlation coefficient-based feature ranking in recursive ensemble feature selection for high-dimensional and low-sample size data." Machine Learning with Applications (2025): 100757.https://www.sciencedirect.com/science/article/pii/S2666827025001409
Rojas-Velazquez, D., Kidwai, S., Liu, T. C., El-Yacoubi, M. A., Garssen, J., Tonda, A., & Lopez-Rincon, A. (2025). Understanding Parkinson's: The microbiome and machine learning approach. Maturitas, 193, Article 108185. https://doi.org/10.1016/j.maturitas.2024.108185
https://research-portal.uu.nl/ws/files/250872251/1-s2.0-S0378512224002809-main.pdf
https://research-portal.uu.nl/ws/files/250872251/1-s2.0-S0378512224002809-main.pdf
Rojas-Velazquez, D., Kidwai, S., Kraneveld, A. D., Tonda, A., Oberski, D., Garssen, J., & Lopez-Rincon, A. (2024). Methodology for biomarker discovery with reproducibility in microbiome data using machine learning. BMC Bioinformatics, 25(1), Article 26. https://doi.org/10.1186/s12859-024-05639-3 https://dspace.library.uu.nl/bitstream/handle/1874/435906/s12859-024-05639-3.pdf?sequence=1
Peralta-Marzal, L. N., Rojas-Velazquez, D., Rigters, D., Prince, N., Garssen, J., Kraneveld, A. D., Perez-Pardo, P., & Lopez-Rincon, A. (2024). A robust microbiome signature for autism spectrum disorder across different studies using machine learning. Scientific Reports, 14(1), Article 814. https://doi.org/10.1038/s41598-023-50601-7 https://dspace.library.uu.nl/bitstream/handle/1874/435328/s41598-023-50601-7.pdf?sequence=1