EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Variant Classification Using Proteomics‐Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery

Christopher E Gillies iD, Joelle Mbatchou, Lukas Habegger, Michael D Kessler, Suying Bao, Suganthi Balasubramanian, Olivier Delaneau, Jack A Kosmicki, Cristen J Willer, Hyun Min Kang, Aris Baras, Jeffrey G Reid und 3 weitere

Genetic Epidemiology · 2025

DOI: 10.1002/gepi.70023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Genetic Epidemiology, 2025. Verfasst von Christopher E Gillies und 14 weiteren Autor:innen. Beteiligte Einrichtung: Regeneron Genetics Center, Tarrytown, New York, USA. Hauptthemen laut MEDLINE: Proteomics, Genetic Variation, Genetic Association Studies. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rare variant association analysis, which assesses the aggregate effect of rare damaging variants within a gene, is a powerful strategy for advancing knowledge of human biology. Numerous models have been proposed to identify damaging coding variants, with the most recent ones employing deep learning and large language models (LLMs) to predict the impact of changes in coding sequences. Here, we use newly available proteomics data on 2898 proteins across 46,665 individuals to evaluate and refine LLM predictors of damaging variants. Using one of these refined models, we evaluate the association between rare damaging variants and human phenotypes at 241 positive control gene‐trait pairs. Among these gene‐trait pairs, our proteomics‐guided model outperforms an ensemble of conventional approaches including PolyPhen2, MutationTaster, SIFT, and LRT, as well as newer machine learning approaches for identifying damaging missense variants, such as CADD, ESM‐1v, ESM‐1b, and AlphaMissense. When attempting to recover known associations by correctly separating damaging singleton missense variants from other singleton variants, our approach recapitulates 36.5% of gene‐trait pairs with known associations, exceeding all the alternatives we considered. Furthermore, when we apply our model to 10 example traits from the UK Biobank, we identify 177 gene–trait associations—again exceeding all other approaches. Our results demonstrate that summary statistics from large‐scale human proteomics data enable evaluation and refinement of coding variant classification LLMs, improving discovery potential in human genetic studies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteomicsGenetic VariationGenetic Association StudiesHumansMachine LearningModels, GeneticPhenotypeGenome-Wide Association StudyDeep LearningLanguageMutation, MissenseLarge Language Models

Autor:innen und Institutionen

  • Regeneron Genetics Center, Tarrytown, New York, USA.

ORCID-Profile: Christopher E Gillies

Zitieren

APA

Gillies, C. E., Mbatchou, J., Habegger, L., Kessler, M. D., Bao, S., Balasubramanian, S., Delaneau, O., Kosmicki, J. A., Willer, C. J., Kang, H. M., Baras, A., Reid, J. G., Marchini, J., Abecasis, G. R., & Ghoussaini, M. (2025). Variant Classification Using Proteomics‐Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery. Genetic Epidemiology. https://doi.org/10.1002/gepi.70023

Vancouver

Gillies CE, Mbatchou J, Habegger L, Kessler MD, Bao S, Balasubramanian S, et al. Variant Classification Using Proteomics‐Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery. Genetic Epidemiology. 2025. doi:10.1002/gepi.70023

BibTeX
@article{Gillies2025,
  author = {Gillies, Christopher E and Mbatchou, Joelle and Habegger, Lukas and Kessler, Michael D and Bao, Suying and Balasubramanian, Suganthi and Delaneau, Olivier and Kosmicki, Jack A and Willer, Cristen J and Kang, Hyun Min and Baras, Aris and Reid, Jeffrey G and Marchini, Jonathan and Abecasis, Gonçalo R and Ghoussaini, Maya},
  title = {Variant Classification Using Proteomics‐Informed Large Language Models Increases Power of Rare Variant Association Studies and Enhances Target Discovery},
  journal = {Genetic Epidemiology},
  year = {2025},
  doi = {10.1002/gepi.70023}
}
Kostenlos starten →