Generating synthetic genotypes using diffusion models
Bioinformatics · 01.07.2025 · 41 (Supplement_1) · i484-i492
DOI: 10.1093/bioinformatics/btaf209 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.07.2025. Verfasst von Philip Kenneweg und 4 weiteren Autor:innen. Beteiligte Einrichtung: AG Machine Learning, Bielefeld University, Bielefeld, NRW 33615, Germany. Hauptthemen laut MEDLINE: Genotype, Models, Genetic. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Summary In this paper, we introduce the first diffusion model designed to generate complete synthetic human genotypes, which, by standard protocols, one can straightforwardly expand into full-length, DNA-level genomes. The synthetic genotypes mimic real human genotypes without just reproducing known genotypes, in terms of approved metrics. When training biomedically relevant classifiers with synthetic genotypes, accuracy is near-identical to the accuracy achieved when training classifiers with real data. We further demonstrate that augmenting small amounts of real with synthetically generated genotypes drastically improves performance rates. This addresses a significant challenge in translational human genetics: real human genotypes, although emerging in large volumes from genome wide association studies, are sensitive private data, which limits their public availability. Therefore, the integration of additional, insensitive data when striving for rapid sharing of biomedical knowledge of public interest appears imperative. Availability and implementation All non proprietary data and the code to replicate the experiments is available on Github.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- AG Machine Learning, Bielefeld University, Bielefeld, NRW 33615, Germany.
- AG Genome Data Science, Bielefeld University, Bielefeld, NRW 33615, Germany.
- College of Biology, Hunan University, Hunan, Hunan Province 410082, China.
ORCID-Profile: Xiao Luo, Alexander Schönhuth
Zitieren
APA
Kenneweg, P., Dandinasivara, R., Luo, X., Hammer, B., & Schönhuth, A. (2025). Generating synthetic genotypes using diffusion models. Bioinformatics, 41(Supplement_1), i484-i492. https://doi.org/10.1093/bioinformatics/btaf209
Vancouver
Kenneweg P, Dandinasivara R, Luo X, Hammer B, Schönhuth A. Generating synthetic genotypes using diffusion models. Bioinformatics. 2025;41(Supplement_1):i484-i492. doi:10.1093/bioinformatics/btaf209
BibTeX
@article{Kenneweg2025,
author = {Kenneweg, Philip and Dandinasivara, Raghuram and Luo, Xiao and Hammer, Barbara and Schönhuth, Alexander},
title = {Generating synthetic genotypes using diffusion models},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {Supplement_1},
pages = {i484--i492},
doi = {10.1093/bioinformatics/btaf209}
}
EUVIMED