EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Updated benchmarking of variant effect predictors using deep mutational scanning

Benjamin J Livesey iD, Joseph A Marsh iD

Molecular Systems Biology · 08.08.2023 · 19 (8)

DOI: 10.15252/msb.202211474 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Molecular Systems Biology, online erschienen am 13.06.2023. Verfasst von Benjamin J Livesey und 1 weiteren Autor:innen. Beteiligte Einrichtung: MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK. Hauptthemen laut MEDLINE: Benchmarking, Mutation, Missense. Die Arbeit wurde bisher 129-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council, EC¦ERC¦HORIZON EUROPE European Research Council, Lister Institute of Preventive Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The assessment of variant effect predictor (VEP) performance is fraught with biases introduced by benchmarking against clinical observations. In this study, building on our previous work, we use independently generated measurements of protein function from deep mutational scanning (DMS) experiments for 26 human proteins to benchmark 55 different VEPs, while introducing minimal data circularity. Many top‐performing VEPs are unsupervised methods including EVE, DeepSequence and ESM‐1v, a protein language model that ranked first overall. However, the strong performance of recent supervised VEPs, in particular VARITY, shows that developers are taking data circularity and bias issues seriously. We also assess the performance of DMS and unsupervised VEPs for discriminating between known pathogenic and putatively benign missense variants. Our findings are mixed, demonstrating that some DMS datasets perform exceptionally at variant classification, while others are poor. Notably, we observe a striking correlation between VEP agreement with DMS data and performance in identifying clinically relevant variants, strongly supporting the validity of our rankings and the utility of DMS for independent benchmarking.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BenchmarkingMutation, MissenseHumansMutationProteins

Stichwörter der Autor:innen

BenchmarkCircularityDMSMAVEVEP

Substanzen

Proteins

Autor:innen und Institutionen

  • MRC Human Genetics Unit, Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK.

ORCID-Profile: Benjamin J Livesey, Joseph A Marsh

Förderung

  • Medical Research Council
  • EC¦ERC¦HORIZON EUROPE European Research Council
  • Lister Institute of Preventive Medicine
  • UKRI¦Medical Research Council

Zitieren

APA

Livesey, B. J., & Marsh, J. A. (2023). Updated benchmarking of variant effect predictors using deep mutational scanning. Molecular Systems Biology, 19(8). https://doi.org/10.15252/msb.202211474

Vancouver

Livesey BJ, Marsh JA. Updated benchmarking of variant effect predictors using deep mutational scanning. Molecular Systems Biology. 2023;19(8). doi:10.15252/msb.202211474

BibTeX
@article{Livesey2023,
  author = {Livesey, Benjamin J and Marsh, Joseph A},
  title = {Updated benchmarking of variant effect predictors using deep mutational scanning},
  journal = {Molecular Systems Biology},
  year = {2023},
  volume = {19},
  number = {8},
  doi = {10.15252/msb.202211474}
}
Kostenlos starten →