HAPNEST: An efficient tool for generating large-scale genetics datasets from limited training data

In this extended abstract we present a new highly efficient software tool called HAPNEST that enables machine learning practitioners to easily generate and evaluate large synthetic datasets for human genetics applications. HAPNEST enables the generation of diverse synthetic datasets from small, publicly accessible reference datasets. We demonstrate the suitability of HAPNEST-generated data for supervised tasks such as genetic risk scoring. The HAPNEST software can be accessed at https://github.com/intervene-EU-H2020/synthetic_data .