EUVIMEDEUVIMED entdecken
Crossref

Accurate proteome-wide missense variant effect prediction with AlphaMissense

Jun Cheng iD, Guido Novati, Joshua Pan, Clare Bycroft iD, Akvilė Žemgulytė, Taylor Applebaum iD, Alexander Pritzel, Lai Hong Wong, Michal Zielinski iD, Tobias Sargeant iD, Rosalia G Schneider iD, Andrew W Senior iD und 4 weitere

Science · 22.09.2023 · 381 (6664)

DOI: 10.1126/science.adg7492 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, erschienen am 22.09.2023. Verfasst von Jun Cheng und 15 weiteren Autor:innen. Beteiligte Einrichtung: Google DeepMind, London, UK. Hauptthemen laut MEDLINE: Amino Acid Substitution, Disease, Mutation, Missense, Proteome. Die Arbeit wurde bisher 2494-mal zitiert (Crossref) und nennt 103 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The vast majority of missense variants observed in the human genome are of unknown clinical significance. We present AlphaMissense, an adaptation of AlphaFold fine-tuned on human and primate variant population frequency databases to predict missense variant pathogenicity. By combining structural context and evolutionary conservation, our model achieves state-of-the-art results across a wide range of genetic and experimental benchmarks, all without explicitly training on such data. The average pathogenicity score of genes is also predictive for their cell essentiality, capable of identifying short essential genes that existing statistical approaches are underpowered to detect. As a resource to the community, we provide a database of predictions for all possible human single amino acid substitutions and classify 89% of missense variants as either likely benign or likely pathogenic.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Amino Acid SubstitutionDiseaseMutation, MissenseProteomeSequence AlignmentHumansBenchmarkingConserved SequenceDatabases, GeneticGenome, HumanProtein ConformationMachine Learning

Substanzen

Proteome

Autor:innen und Institutionen

  • Google DeepMind, London, UK.

ORCID-Profile: Jun Cheng, Clare Bycroft, Taylor Applebaum, Michal Zielinski, Tobias Sargeant, Rosalia G Schneider, Andrew W Senior, John Jumper, Demis Hassabis, Pushmeet Kohli, Žiga Avsec

Zitieren

APA

Cheng, J., Novati, G., Pan, J., Bycroft, C., Žemgulytė, A., Applebaum, T., Pritzel, A., Wong, L. H., Zielinski, M., Sargeant, T., Schneider, R. G., Senior, A. W., Jumper, J., Hassabis, D., Kohli, P., & Avsec, Ž. (2023). Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science, 381(6664). https://doi.org/10.1126/science.adg7492

Vancouver

Cheng J, Novati G, Pan J, Bycroft C, Žemgulytė A, Applebaum T, et al. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science. 2023;381(6664). doi:10.1126/science.adg7492

BibTeX
@article{Cheng2023,
  author = {Cheng, Jun and Novati, Guido and Pan, Joshua and Bycroft, Clare and Žemgulytė, Akvilė and Applebaum, Taylor and Pritzel, Alexander and Wong, Lai Hong and Zielinski, Michal and Sargeant, Tobias and Schneider, Rosalia G and Senior, Andrew W and Jumper, John and Hassabis, Demis and Kohli, Pushmeet and Avsec, Žiga},
  title = {Accurate proteome-wide missense variant effect prediction with AlphaMissense},
  journal = {Science},
  year = {2023},
  volume = {381},
  number = {6664},
  doi = {10.1126/science.adg7492}
}
Kostenlos starten →