Neural ADMIXTURE - datasets

Contains the datasets All-Chms, Chm-22 and Chm-22-Sim used in the experiments of the article Neural ADMIXTURE: rapid population clustering with autoencoders. If you use this data, please cite the corresponding article.

Datasets are different compilations of publicly available data (1000 Genomes Project, Simons Genome Diversity Project, Human Genome Diversity Project). Chm-22-Sim also contains synthetic data generated from existing one using a tool which will be available to the public in the near future.