EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicted meta-omics: A potential solution to multi-omics data scarcity in microbiome studies

Bianca-Maria Cosma iD, Stephanie Pillay, David Calderón-Franco iD, Thomas Abeel iD

PLOS One · 10.04.2026 · 21 (4) · e0345919

DOI: 10.1371/journal.pone.0345919 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 10.04.2026. Verfasst von Bianca-Maria Cosma und 3 weiteren Autor:innen. Beteiligte Einrichtung: Delft Bioinformatics Lab, Delft University of Technology, Delft, The Netherlands. Hauptthemen laut MEDLINE: Computational Biology, Models, Biological, Gastrointestinal Microbiome. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of South Africa.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imbalances in the gut microbiome have been linked to conditions such as inflammatory bowel disease, diabetes, and cancer. While metagenomics and amplicon sequencing are commonly used to study the microbiome, they do not capture all layers of microbial functions. Other meta-omics data can provide more insights, but these are more costly and laborious to procure. The growing availability of paired meta-omics data offers an opportunity to develop machine learning models that can infer connections between metagenomics data and other forms of meta-omics data, enabling the prediction of these other forms of meta-omics data from metagenomics. We evaluated several machine learning models for predicting meta-omics features from various meta-omics inputs. Simpler architectures such as elastic net regression and random forests generated reliable predictions of transcript and metabolite abundances, with correlations of up to 0.77 and 0.74, respectively, but predicting protein profiles was more challenging. We also identified a core set of well-predicted features for each meta-omics output type, and showed that multi-output regression neural networks performed similarly when trained using fewer output features. Lastly, our experiments demonstrated that predicted features can be used for the downstream task of inflammatory bowel disease classification, with performance comparable to that of experimental data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyModels, BiologicalGastrointestinal MicrobiomeMachine LearningHumans

Autor:innen und Institutionen

  • Delft Bioinformatics Lab, Delft University of Technology, Delft, The Netherlands.
  • Department of Medical Oncology, Radboundumc, Nijmegen, The Netherlands.
  • Hologenomix B.V., Delft, The Netherlands.
  • Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, Cambridge, United States of America.

ORCID-Profile: Bianca-Maria Cosma, David Calderón-Franco, Thomas Abeel

Förderung

  • National Research Foundation of South Africa

Zitieren

APA

Cosma, B. M., Pillay, S., Calderón-Franco, D., & Abeel, T. (2026). Predicted meta-omics: A potential solution to multi-omics data scarcity in microbiome studies. PLOS One, 21(4), e0345919. https://doi.org/10.1371/journal.pone.0345919

Vancouver

Cosma BM, Pillay S, Calderón-Franco D, Abeel T. Predicted meta-omics: A potential solution to multi-omics data scarcity in microbiome studies. PLOS One. 2026;21(4):e0345919. doi:10.1371/journal.pone.0345919

BibTeX
@article{Cosma2026,
  author = {Cosma, Bianca-Maria and Pillay, Stephanie and Calderón-Franco, David and Abeel, Thomas},
  title = {Predicted meta-omics: A potential solution to multi-omics data scarcity in microbiome studies},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {4},
  pages = {e0345919},
  doi = {10.1371/journal.pone.0345919}
}
Kostenlos starten →