15Generative models have shown breakthroughs in a wide spectrum of domains due to 16 recent advancements in machine learning algorithms and increased computational 17 power. Despite these impressive achievements, the ability of generative models to 18 create realistic synthetic data is still under-exploited in genetics and absent from 19 population genetics. 20
21Yet a known limitation of this field is the reduced access to many genetic databases 22 augmenting reference panels with AGs, (ii) scores obtained from selection tests on 30AGs and real genomes are highly correlated and (iii) AGs can inherit genotype-31 phenotype associations. AGs have the potential to become valuable assets in genetic 32 studies by providing high quality anonymous substitutes for private databases. 33 34 514 This work was supported by the European Union through the European Regional 515