EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structure‐aware deep learning model for peptide toxicity prediction

Hossein Ebrahimikondori iD, Darcy Sutherland, Anat Yanai, Amelia Richter, Ali Salehi, Chenkai Li iD, Lauren Coombe, Monica Kotkoff, René L Warren, Inanc Birol

Protein Science · 2024-07 · 33 (7)

DOI: 10.1002/pro.5076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Protein Science, online erschienen am 22.06.2024. Verfasst von Hossein Ebrahimikondori und 9 weiteren Autor:innen. Beteiligte Einrichtung: Canada's Michael Smith Genome Sciences Centre, BC Cancer Agency, Vancouver, British Columbia, Canada. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Genome Canada, Genome BC, Investment Agriculture Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Antimicrobial resistance is a critical public health concern, necessitating the exploration of alternative treatments. While antimicrobial peptides (AMPs) show promise, assessing their toxicity using traditional wet lab methods is both time‐consuming and costly. We introduce tAMPer, a novel multi‐modal deep learning model designed to predict peptide toxicity by integrating the underlying amino acid sequence composition and the three‐dimensional structure of peptides. tAMPer adopts a graph‐based representation for peptides, encoding ColabFold‐predicted structures, where nodes represent amino acids and edges represent spatial interactions. Structural features are extracted using graph neural networks, and recurrent neural networks capture sequential dependencies. tAMPer's performance was assessed on a publicly available protein toxicity benchmark and an AMP hemolysis data we generated. On the latter, tAMPer achieves an F1‐score of 68.7%, outperforming the second‐best method by 23.4%. On the protein benchmark, tAMPer exhibited an improvement of over 3.0% in the F1‐score compared to current state‐of‐the‐art methods. We anticipate tAMPer to accelerate AMP discovery and development by reducing the reliance on laborious toxicity screening experiments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAntimicrobial PeptidesNeural Networks, ComputerHemolysis

Stichwörter der Autor:innen

3D structuresantimicrobial peptidesattention mechanismgraph neural networksmulti‐modal deep learningtAMPer

Substanzen

Antimicrobial Peptides

Autor:innen und Institutionen

  • Canada's Michael Smith Genome Sciences Centre, BC Cancer Agency, Vancouver, British Columbia, Canada.
  • Bioinformatics Graduate Program, University of British Columbia, Vancouver, British Columbia, Canada.
  • Public Health Laboratory, British Columbia Centre for Disease Control, Vancouver, British Columbia, Canada.
  • Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, British Columbia, Canada.
  • Department of Medical Genetics, University of British Columbia, Vancouver, British Columbia, Canada.

ORCID-Profile: Hossein Ebrahimikondori, Chenkai Li

Förderung

  • Genome Canada
  • Genome BC
  • Investment Agriculture Foundation
  • Genome British Columbia

Zitieren

APA

Ebrahimikondori, H., Sutherland, D., Yanai, A., Richter, A., Salehi, A., Li, C., Coombe, L., Kotkoff, M., Warren, R. L., & Birol, I. (2024). Structure‐aware deep learning model for peptide toxicity prediction. Protein Science, 33(7). https://doi.org/10.1002/pro.5076

Vancouver

Ebrahimikondori H, Sutherland D, Yanai A, Richter A, Salehi A, Li C, et al. Structure‐aware deep learning model for peptide toxicity prediction. Protein Science. 2024;33(7). doi:10.1002/pro.5076

BibTeX
@article{Ebrahimikondori2024,
  author = {Ebrahimikondori, Hossein and Sutherland, Darcy and Yanai, Anat and Richter, Amelia and Salehi, Ali and Li, Chenkai and Coombe, Lauren and Kotkoff, Monica and Warren, René L and Birol, Inanc},
  title = {Structure‐aware deep learning model for peptide toxicity prediction},
  journal = {Protein Science},
  year = {2024},
  volume = {33},
  number = {7},
  doi = {10.1002/pro.5076}
}
Kostenlos starten →