EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Predicting membrane protein localization by deep learning on structure and chemistry

Bivek Pokhrel, Christian Munley, Miguel Pedraza, Edward Lyman iD

Protein Science · 2026

DOI: 10.1002/pro.70747 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Protein Science, 2026. Verfasst von Bivek Pokhrel und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics and Astronomy, University of Delaware, Newark, Delaware, USA. Hauptthemen laut MEDLINE: Deep Learning, Membrane Proteins. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

It has been known since at least the 1980's that the structure and chemistry of membranes and membrane proteins are matched. Exploiting this fact, a graph neural network model of proteins was trained on experimentally determined membrane protein structures to predict the native membrane environment of transmembrane domains from their structure. The algorithm, “GPSforTMDs,” learns to generalize about membrane protein structure, obtains overall performance that is competitive with sequence‐based methods, and obtains exceptional performance for some categories of membrane environment, even when training examples are few. Other categories it finds more challenging, in some cases for clear reasons (for example, compatibility of TMDs with membranes along the secretory pathway), and in other cases that are mysterious (mistaking archaeal TMDs for bacterial, and vice versa). The results motivate the need for high quality databases reporting TMD localization, and suggest that peering inside the algorithm will reveal new “rules” for membrane proteins. The code and associated database is available at https://github.com/bivekpok/GPSforTMDs .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMembrane ProteinsGraph Neural NetworksAlgorithmsDatabases, ProteinPrediction Algorithms

Stichwörter der Autor:innen

deep learning for proteinsgraph neural networksmembrane environment classificationmembrane protein localizationorganelle‐specific membrane environmentstransmembrane domains

Substanzen

Membrane Proteins

Autor:innen und Institutionen

  • Department of Physics and Astronomy, University of Delaware, Newark, Delaware, USA.
  • Institute of Bioengineering, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland.
  • Department of Chemistry and Biochemistry, University of Delaware, Newark, Delaware, USA.

ORCID-Profile: Edward Lyman

Förderung

  • NIGMS NIH HHS

Zitieren

APA

Pokhrel, B., Munley, C., Pedraza, M., & Lyman, E. (2026). Predicting membrane protein localization by deep learning on structure and chemistry. Protein Science. https://doi.org/10.1002/pro.70747

Vancouver

Pokhrel B, Munley C, Pedraza M, Lyman E. Predicting membrane protein localization by deep learning on structure and chemistry. Protein Science. 2026. doi:10.1002/pro.70747

BibTeX
@article{Pokhrel2026,
  author = {Pokhrel, Bivek and Munley, Christian and Pedraza, Miguel and Lyman, Edward},
  title = {Predicting membrane protein localization by deep learning on structure and chemistry},
  journal = {Protein Science},
  year = {2026},
  doi = {10.1002/pro.70747}
}
Kostenlos starten →