EUVIMEDSkopri EUVIMED
Open access · CC BY-NC-ND 4.0

Genetic Prediction Modeling in Large Cohort Studies via Boosting Targeted Loss Functions

Hannah Klinkhammer iD, Christian Staerk, Carlo Maj, Peter M Krawitz, Andreas Mayr iD

Statistics in Medicine · 2024

DOI: 10.1002/sim.10249 ↗

At a glance

Journal article in Statistics in Medicine, 2024. Written by Hannah Klinkhammer and 4 co-authors. Institution: Institute of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Bonn, Germany. Major MEDLINE topics: Algorithms, Genome-Wide Association Study, Models, Genetic. 62 references. The full text is freely available (open access, CC BY-NC-ND 4.0).

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Polygenic risk scores (PRS) aim to predict a trait from genetic information, relying on common genetic variants with low to medium effect sizes. As genotype data are high‐dimensional in nature, it is crucial to develop methods that can be applied to large‐scale data (large and large ). Many PRS tools aggregate univariate summary statistics from genome‐wide association studies into a single score. Recent advancements allow simultaneous modeling of variant effects from individual‐level genotype data. In this context, we introduced snpboost, an algorithm that applies statistical boosting on individual‐level genotype data to estimate PRS via multivariable regression models. By processing variants iteratively in batches, snpboost can deal with large‐scale cohort data. Having solved the technical obstacles due to data dimensionality, the methodological scope can now be broadened—focusing on key objectives for the clinical application of PRS. Similar to most methods in this context, snpboost has, so far, been restricted to quantitative and binary traits. Now, we incorporate more advanced alternatives—targeted to the particular aim and outcome. Adapting the loss function extends the snpboost framework to further data situations such as time‐to‐event and count data. Furthermore, alternative loss functions for continuous outcomes allow us to focus not only on the mean of the conditional distribution but also on other aspects that may be more helpful in the risk stratification of individual patients and can quantify prediction uncertainty, for example, median or quantile regression. This work enhances PRS fitting across multiple model classes previously unfeasible for this data type.

Subjects

MeSH terms (MEDLINE)

AlgorithmsGenome-Wide Association StudyModels, GeneticHumansCohort StudiesMultifactorial InheritanceComputer SimulationPolymorphism, Single NucleotideGenotypeModels, StatisticalGenetic Predisposition to Disease

Author keywords

boostingpolygenic scorespredictionquantile regressiontime‐to‐event data

Authors and institutions

  • Institute of Medical Biometry, Informatics and Epidemiology, Medical Faculty, University of Bonn, Bonn, Germany.
  • Institute of Genomic Statistics and Bioinformatics, Medical Faculty, University of Bonn, Bonn, Germany.
  • IUF - Leibniz Research Institute for Environmental Medicine, Düsseldorf, Germany.
  • Department of Statistics, TU Dortmund University, Dortmund, Germany.
  • Center for Human Genetics, Philipps-University Marburg, Marburg, Germany.

ORCID profiles: Hannah Klinkhammer, Andreas Mayr

Cite

APA

Klinkhammer, H., Staerk, C., Maj, C., Krawitz, P. M., & Mayr, A. (2024). Genetic Prediction Modeling in Large Cohort Studies via Boosting Targeted Loss Functions. Statistics in Medicine. https://doi.org/10.1002/sim.10249

Vancouver

Klinkhammer H, Staerk C, Maj C, Krawitz PM, Mayr A. Genetic Prediction Modeling in Large Cohort Studies via Boosting Targeted Loss Functions. Statistics in Medicine. 2024. doi:10.1002/sim.10249

BibTeX
@article{Klinkhammer2024,
  author = {Klinkhammer, Hannah and Staerk, Christian and Maj, Carlo and Krawitz, Peter M and Mayr, Andreas},
  title = {Genetic Prediction Modeling in Large Cohort Studies via Boosting Targeted Loss Functions},
  journal = {Statistics in Medicine},
  year = {2024},
  doi = {10.1002/sim.10249}
}
Start for free →