EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Utilizing protein structure graph embeddings to predict the pathogenicity of missense variants

Martin Danner, Matthias Begemann, Miriam Elbracht, Ingo Kurth, Jeremias Krause iD

NAR Genomics and Bioinformatics · 2025

DOI: 10.1093/nargab/lqaf097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Martin Danner und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Human Genetics and Genomic Medicine, Medical Faculty, Uniklinik RWTH Aachen, Pauwelsstrasse 30, Aachen 52074, North-Rhine-Westphalia, G…. Hauptthemen laut MEDLINE: Mutation, Missense, Proteins, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: START-Program of the Faculty of Medicine, Clinician-Scientist-Program of the Faculty of Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Genetic variants can impact the structure of the corresponding protein, which can have detrimental effects on protein function. While the effect of protein-truncating variants is often easier to evaluate, most genetic variants that affect the protein-coding region of the human genome are missense variants. These variants are mostly single nucleotide variants, which result in the exchange of a single amino acid. The effect on protein function of these variants can be challenging to deduce. To aid the interpretation of missense variants, a variety of bioinformatic algorithms have been developed, yet current algorithms rarely directly use the protein structure as a feature to consider. We developed a machine learning workflow that utilizes the protein-language-model ESMFold to predict the protein structure of missense variants, which is subsequently embedded using graph autoencoders. The generated embeddings are used in a classifier model, which predicts pathogenicity. We provide evidence that graph embeddings can be used for pathogenicity prediction and that they can be used to enhance the widely applied CADD score. Additionally, we explored different levels of abstraction of the graph embeddings and their influence on the classifier. Finally, we compare the utility of graph embeddings from different protein-folding models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Mutation, MissenseProteinsComputational BiologyHumansMachine LearningAlgorithmsProtein Conformation

Substanzen

Proteins

Autor:innen und Institutionen

  • Institute for Human Genetics and Genomic Medicine, Medical Faculty, Uniklinik RWTH Aachen, Pauwelsstrasse 30, Aachen 52074, North-Rhine-Westphalia, Germany.
  • scieneers GmbH, Data Science Department, Kantstraße 1a, Karlsruhe 76137, Baden-Wuerttemberg, Germany.

ORCID-Profile: Jeremias Krause

Förderung

  • START-Program of the Faculty of Medicine
  • Clinician-Scientist-Program of the Faculty of Medicine

Zitieren

APA

Danner, M., Begemann, M., Elbracht, M., Kurth, I., & Krause, J. (2025). Utilizing protein structure graph embeddings to predict the pathogenicity of missense variants. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf097

Vancouver

Danner M, Begemann M, Elbracht M, Kurth I, Krause J. Utilizing protein structure graph embeddings to predict the pathogenicity of missense variants. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf097

BibTeX
@article{Danner2025,
  author = {Danner, Martin and Begemann, Matthias and Elbracht, Miriam and Kurth, Ingo and Krause, Jeremias},
  title = {Utilizing protein structure graph embeddings to predict the pathogenicity of missense variants},
  journal = {NAR Genomics and Bioinformatics},
  year = {2025},
  doi = {10.1093/nargab/lqaf097}
}
Kostenlos starten →