Peer-Reviewed Publication
PLoS Genet2026;22(10):e1012321.October 1, 2026Journal Article
GPC: An expressive and tractable deep generative model for genetic variation data.
Prateek Anand1, Anji Liu2, Meihua Dang3, Boyang Fu4, Xinzhu Wei5, Guy Van den Broeck1, Sriram Sankararaman1,6,7
1Department of Computer Science, University of California, Los Angeles, Los Angeles, California, United States of America.
2Department of Computer Science, National University of Singapore, Singapore, Singapore.
3Department of Computer Science, Stanford University, Stanford, California, United States of America.
4Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts, United States of America.
5Department of Computational Biology, Cornell University, Ithaca, New York, United States of America.
6Department of Human Genetics, University of California, Los Angeles, California, United States of America.
7Department of Computational Medicine, University of California, Los Angeles, California, United States of America.
Abstract
Generative models play an important role in population genetics, being used to generate artificial genomes (AGs) that help benchmark methods, test evolutionary hypotheses, and construct reference panels for imputation while working around data-sharing restrictions. Existing generative models of genetic variation, however, struggle to faithfully express dependencies in the data while retaining trac…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans