EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

kinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters

Rana A Barghout iD, Lya Chiñas Serrano iD, Benjamin Sanchez-Lengeling iD, Radhakrishnan Mahadevan iD

PLOS Computational Biology · 06.11.2026 · 22 (11) · e1014881

DOI: 10.1371/journal.pcbi.1014881 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 06.11.2026. Verfasst von Rana A Barghout und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering & Applied Chemistry, University of Toronto, Toronto, Ontario, Canada. Hauptthemen laut MEDLINE: Deep Learning, Models, Biological, Systems Biology. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSERC, Genome Canada, Ontario Ministry of Research and Innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters ( k c a t ) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the framework’s capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Gram-positive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningModels, BiologicalSystems BiologyKineticsStochastic ProcessesComputational BiologyAnimalsProteome

Substanzen

Proteome

Autor:innen und Institutionen

  • Department of Chemical Engineering & Applied Chemistry, University of Toronto, Toronto, Ontario, Canada.
  • Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada.

ORCID-Profile: Rana A Barghout, Lya Chiñas Serrano, Benjamin Sanchez-Lengeling, Radhakrishnan Mahadevan

Förderung

  • NSERC
  • Genome Canada
  • Ontario Ministry of Research and Innovation
  • Acceleration Consortium
  • Vector Institute
  • Digital Research Alliance Canada

Zitieren

APA

A Barghout, R., Chiñas Serrano, L., Sanchez-Lengeling, B., & Mahadevan, R. (2026). kinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters. PLOS Computational Biology, 22(11), e1014881. https://doi.org/10.1371/journal.pcbi.1014881

Vancouver

A Barghout R, Chiñas Serrano L, Sanchez-Lengeling B, Mahadevan R. kinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters. PLOS Computational Biology. 2026;22(11):e1014881. doi:10.1371/journal.pcbi.1014881

BibTeX
@article{ABarghout2026,
  author = {A Barghout, Rana and Chiñas Serrano, Lya and Sanchez-Lengeling, Benjamin and Mahadevan, Radhakrishnan},
  title = {kinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {11},
  pages = {e1014881},
  doi = {10.1371/journal.pcbi.1014881}
}
Kostenlos starten →