EUVIMEDEUVIMED entdecken
Open Access

Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores

Stephen Hermes, Janet Cady, Steven Armentrout, James O'Connor, Sarah Carlson Holdaway, Carlos Cruchaga, Thomas Wingo, Ellen McRae Greytak, the Alzheimer’s Disease Neuroimaging Initiative

Journal of Alzheimer’s Disease · 2024

DOI: 10.3233/jad-230236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Alzheimer’s Disease, 2024. Verfasst von Stephen Hermes und 8 weiteren Autor:innen. Beteiligte Einrichtung: Parabon NanoLabs, Inc., Reston, VA, USA. Hauptthemen laut MEDLINE: Alzheimer Disease, Machine Learning, Multifactorial Inheritance, Epistasis, Genetic. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NHLBI NIH HHS, NINDS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Polygenic risk scores (PRS) are linear combinations of genetic markers weighted by effect size that are commonly used to predict disease risk. For complex heritable diseases such as late-onset Alzheimer’s disease (LOAD), PRS models fail to capture much of the heritability. Additionally, PRS models are highly dependent on the population structure of the data on which effect sizes are assessed and have poor generalizability to new data.

Objective

The goal of this study is to construct a paragenic risk score that, in addition to single genetic marker data used in PRS, incorporates epistatic interaction features and machine learning methods to predict risk for LOAD.

Methods

We construct a new state-of-the-art genetic model for risk of Alzheimer’s disease. Our approach innovates over PRS models in two ways: First, by directly incorporating epistatic interactions between SNP loci using an evolutionary algorithm guided by shared pathway information; and second, by estimating risk via an ensemble of non-linear machine learning models rather than a single linear model. We compare the paragenic model to several PRS models from the literature trained on the same dataset.

Results

The paragenic model is significantly more accurate than the PRS models under 10-fold cross-validation, obtaining an AUC of 83% and near-clinically significant matched sensitivity/specificity of 75%. It remains significantly more accurate when evaluated on an independent holdout dataset and maintains accuracy within APOE genotype strata.

Conclusions

Paragenic models show potential for improving disease risk prediction for complex heritable diseases such as LOAD over PRS models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Alzheimer DiseaseMachine LearningMultifactorial InheritanceEpistasis, GeneticGenetic Predisposition to DiseaseHumansFemaleMalePolymorphism, Single NucleotideAgedGenome-Wide Association StudyApolipoproteins EModels, GeneticGenetic Risk Score

Stichwörter der Autor:innen

Alzheimer’s diseasedata miningdeep learningepistasismachine learningpredictive genetic testing

Substanzen

Apolipoproteins E

Autor:innen und Institutionen

  • Parabon NanoLabs, Inc., Reston, VA, USA.
  • Department of Psychiatry, Washington University, St. Louis, MO, USA.
  • Hope Center Program on Protein Aggregation and Neurodegeneration, Washington University, St. Louis, MO, USA.
  • Goizueta Alzheimer's Disease Center, Emory University School of Medicine, Atlanta, GA, USA.
  • Department of Neurology, Emory University School of Medicine, Atlanta, GA, USA.
  • Department of Human Genetics, Emory University School of Medicine, Atlanta, GA, USA.

Förderung

  • NIA NIH HHS
  • NHLBI NIH HHS
  • NINDS NIH HHS

Zitieren

APA

Hermes, S., Cady, J., Armentrout, S., O'Connor, J., Holdaway, S. C., Cruchaga, C., Wingo, T., Greytak, E. M., & the Alzheimer’s Disease Neuroimaging Initiative (2024). Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores. Journal of Alzheimer’s Disease. https://doi.org/10.3233/jad-230236

Vancouver

Hermes S, Cady J, Armentrout S, O'Connor J, Holdaway SC, Cruchaga C, et al. Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores. Journal of Alzheimer’s Disease. 2024. doi:10.3233/jad-230236

BibTeX
@article{Hermes2024,
  author = {Hermes, Stephen and Cady, Janet and Armentrout, Steven and O'Connor, James and Holdaway, Sarah Carlson and Cruchaga, Carlos and Wingo, Thomas and Greytak, Ellen McRae and the Alzheimer’s Disease Neuroimaging Initiative, the Alzheimer’s Disease Neuroimaging Initiative},
  title = {Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores},
  journal = {Journal of Alzheimer’s Disease},
  year = {2024},
  doi = {10.3233/jad-230236}
}
Kostenlos starten →