GPC: An expressive and tractable deep generative model for genetic variation data
Open Access
- 6 October 2026
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Genetics
- Vol. 22 (10) , e1012321
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 tractability and preserving privacy. We introduce Genetic Probabilistic Circuits ( GPC ), a deep generative model for genetic variation data based on hidden Chow-Liu trees represented as probabilistic circuits. GPC generalizes traditional hidden Markov models by allowing arbitrary tree structures over latent variables, enabling it to capture long-range dependencies among SNPs. GPC is tractable, supporting exact computation of marginal and conditional probabilities that enables both AG generation and direct genotype imputation (avoiding the need for simulating AGs). We show that GPC generates AGs that accurately reproduce population structure and linkage disequilibrium patterns across a range of length scales. Compared to other deep generative approaches, GPC consistently improves imputation accuracy, with particularly strong gains for low-frequency variants and in populations that are not well-represented in public reference panels. Finally, we show that GPC better preserves privacy of the training data, thereby providing a practical framework for AG generation in settings with limited data access.Keywords
Funding Information
- National Institute of Health (R35 GM153406)
- National Science Foundation (CAREER 1943497)
- National University of Singapore (SUG 251RES250)
- National Institute of Health (R35 GM150579)
- National Science Foundation (IIS 2435801)
- DARPA ANSR (FA8750 23 2 0004)
- CODORD (HR00112590089)
- SAFRON (HR00112530141)
- National Science Foundation (IIS 1943641)
- Adobe Research
- Cisco Research
- Qualcomm
- Amazon
This publication has 40 references indexed in Scilit:
- High-coverage whole-genome sequencing of the expanded 1000 Genomes Project cohort including 602 triosCell, 2022
- Meta-imputation: An efficient method to combine genotype data after imputation with multiple reference panelsThe American Journal of Human Genetics, 2022
- Generation and evaluation of privacy preserving synthetic health dataNeurocomputing, 2020
- Developments in coalescent theory from single loci to chromosomesTheoretical Population Biology, 2020
- Coalescent Theory2019
- A One-Penny Imputed Genome from Next-Generation Reference PanelsThe American Journal of Human Genetics, 2018
- A global reference for human genetic variationNature, 2015
- Cutset Networks: A Simple, Tractable, and Scalable Approach for Improving the Accuracy of Chow-Liu Trees2014
- Recombination as a Point Process along SequencesTheoretical Population Biology, 1999
- Properties of a neutral allele model with intragenic recombinationTheoretical Population Biology, 1983