Machine learning approaches in microbiome research: challenges and best practices
Frontiers in Microbiology · 22.09.2023 · 14
DOI: 10.3389/fmicb.2023.1261889 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Frontiers in Microbiology, online erschienen am 22.09.2023. Verfasst von Georgios Papoutsoglou und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Crete, Heraklion, Greece. Die Arbeit wurde bisher 148-mal zitiert (Crossref) und nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Microbiome data predictive analysis within a machine learning (ML) workflow presents numerous domain-specific challenges involving preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and the extraction of biological information from the results. To assist decision-making, we offer a set of recommendations on algorithm selection, pipeline creation and evaluation, stemming from the COST Action ML4Microbiome. We compared the suggested approaches on a multi-cohort shotgun metagenomics dataset of colorectal cancer patients, focusing on their performance in disease diagnosis and biomarker discovery. It is demonstrated that the use of compositional transformations and filtering methods as part of data preprocessing does not always improve the predictive performance of a model. In contrast, the multivariate feature selection, such as the Statistically Equivalent Signatures algorithm, was effective in reducing the classification error. When validated on a separate test dataset, this algorithm in combination with random forest modeling, provided the most accurate performance estimates. Lastly, we showed how linear modeling by logistic regression coupled with visualization techniques such as Individual Conditional Expectation (ICE) plots can yield interpretable results and offer biological insights. These findings are significant for clinicians and non-experts alike in translational applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, University of Crete, Heraklion, Greece.
- JADBio Gnosis DA S.A., Science and Technology Park of Crete, Heraklion, Greece.
- Department of Applied Statistics and Operations Research and Quality, Polytechnic University of Valencia, Valencia, Spain.
- Center for Mathematics and Applications (NOVA Math), NOVA School of Science and Technology, Caparica, Portugal.
- Research and Development Unit for Mechanical and Industrial Engineering (UNIDEMI), Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Caparica, Portugal.
- Department of Ecology, Universität Innsbruck, Innsbruck, Austria.
Zitieren
APA
Papoutsoglou, G., Tarazona, S., Lopes, M. B., Klammsteiner, T., Ibrahimi, E., Eckenberger, J., Novielli, P., Tonda, A., Simeon, A., Shigdel, R., Béreux, S., Vitali, G., Tangaro, S., Lahti, L., Temko, A., Claesson, M. J., & Berland, M. (2023). Machine learning approaches in microbiome research: challenges and best practices. Frontiers in Microbiology, 14. https://doi.org/10.3389/fmicb.2023.1261889
Vancouver
Papoutsoglou G, Tarazona S, Lopes MB, Klammsteiner T, Ibrahimi E, Eckenberger J, et al. Machine learning approaches in microbiome research: challenges and best practices. Frontiers in Microbiology. 2023;14. doi:10.3389/fmicb.2023.1261889
BibTeX
@article{Papoutsoglou2023,
author = {Papoutsoglou, Georgios and Tarazona, Sonia and Lopes, Marta B and Klammsteiner, Thomas and Ibrahimi, Eliana and Eckenberger, Julia and Novielli, Pierfrancesco and Tonda, Alberto and Simeon, Andrea and Shigdel, Rajesh and Béreux, Stéphane and Vitali, Giacomo and Tangaro, Sabina and Lahti, Leo and Temko, Andriy and Claesson, Marcus J and Berland, Magali},
title = {Machine learning approaches in microbiome research: challenges and best practices},
journal = {Frontiers in Microbiology},
year = {2023},
volume = {14},
doi = {10.3389/fmicb.2023.1261889}
}
EUVIMED