EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of Protein Ion–Ligand Binding Sites with ELECTRA

Clement Essien iD, Lei Jiang, Duolin Wang, Dong Xu iD

Molecules · 2023

DOI: 10.3390/molecules28196793 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecules, 2023. Verfasst von Clement Essien und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA. Hauptthemen laut MEDLINE: Proteins, Metals. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, US National Institutes of Health, Research Computing Support Services at the University of Missouri.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it is becoming crucial to identify ion-binding sites. The accurate identification of protein–ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion-binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46%, respectively, in the F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools, producing prediction results for a hundred sequences for a specific ion in under ten minutes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsMetalsLigandsBinding SitesProtein BindingIons

Stichwörter der Autor:innen

ELECTRAdeep learningion-binding site predictionnatural language processingsequence-based predictiontransformer

Substanzen

LigandsProteinsMetalsIons

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA.

ORCID-Profile: Clement Essien, Dong Xu

Förderung

  • NIGMS NIH HHS
  • US National Institutes of Health
  • Research Computing Support Services at the University of Missouri
  • the Pacific Northwest National Laboratory (PNNL)

Zitieren

APA

Essien, C., Jiang, L., Wang, D., & Xu, D. (2023). Prediction of Protein Ion–Ligand Binding Sites with ELECTRA. Molecules. https://doi.org/10.3390/molecules28196793

Vancouver

Essien C, Jiang L, Wang D, Xu D. Prediction of Protein Ion–Ligand Binding Sites with ELECTRA. Molecules. 2023. doi:10.3390/molecules28196793

BibTeX
@article{Essien2023,
  author = {Essien, Clement and Jiang, Lei and Wang, Duolin and Xu, Dong},
  title = {Prediction of Protein Ion–Ligand Binding Sites with ELECTRA},
  journal = {Molecules},
  year = {2023},
  doi = {10.3390/molecules28196793}
}
Kostenlos starten →