EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting Host-Interaction Traits in Probiotic Bacteria Using Machine Learning and Functional Data

Gabriela de Quadros da Luz, Kristofer Stift Kappel, Rafaella Sinnott Dias, Fábio Pereira Leivas Leite, Frederico Schmitt Kremer

Journal of Genome Biotechnology and Genetics · 2026

DOI: 10.3390/jgbg1020012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Genome Biotechnology and Genetics, 2026. Verfasst von Gabriela de Quadros da Luz und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying probiotic microorganisms requires linking genomic content to experimentally reported host-interaction traits. A machine-learning framework predicted seven probiotic phenotypes (acid resistance, bile resistance, adhesion, antimicrobial activity, immunomodulation, antioxidant activity, and antiproliferative potential) from functional COG categories and biosynthetic gene cluster annotations in 1183 genomes (780 probiotic and 403 non-probiotic). CatBoost, Random Forest, XGBoost, LightGBM, and Logistic Regression were evaluated with stratified cross-validation, leave-one-out cross-validation, and an 80:20 holdout split. Antioxidant and antiproliferative models performed best, with cross-validation F1-scores of 0.92 and 0.97 and holdout F1-scores of 0.70 and 0.72. SHAP analysis identified model-derived genomic associations rather than causal mechanisms, including an inverse association between T3PKS abundance and antioxidant classification and associations between lipid transport/metabolism features and antiproliferative classification. The framework supports high-throughput in silico prioritization of candidate probiotic strains for phenotype-specific validation. Interpretation remains limited by heterogeneous source annotations, label noise, and potential false negatives in the non-probiotic dataset.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Zitieren

APA

Luz, G. D. Q. D., Kappel, K. S., Dias, R. S., Leite, F. P. L., & Kremer, F. S. (2026). Predicting Host-Interaction Traits in Probiotic Bacteria Using Machine Learning and Functional Data. Journal of Genome Biotechnology and Genetics. https://doi.org/10.3390/jgbg1020012

Vancouver

Luz GDQD, Kappel KS, Dias RS, Leite FPL, Kremer FS. Predicting Host-Interaction Traits in Probiotic Bacteria Using Machine Learning and Functional Data. Journal of Genome Biotechnology and Genetics. 2026. doi:10.3390/jgbg1020012

BibTeX
@article{Luz2026,
  author = {Luz, Gabriela de Quadros da and Kappel, Kristofer Stift and Dias, Rafaella Sinnott and Leite, Fábio Pereira Leivas and Kremer, Frederico Schmitt},
  title = {Predicting Host-Interaction Traits in Probiotic Bacteria Using Machine Learning and Functional Data},
  journal = {Journal of Genome Biotechnology and Genetics},
  year = {2026},
  doi = {10.3390/jgbg1020012}
}
Kostenlos starten →