CoChat
Sign Up
PreprintCited by 22Genetic diversity and population structureForensic and Genetic ResearchEvolution and Genetic Dynamics

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

This population does not exist: learning the distribution of evolutionary histories with generative adversarial networks

Open access
Booker, William W., Ray, Dylan D., Schrider, Daniel R.·2022·Genetics
DOI 10.1101/2022.09.17.508145PMC PMC10213497

Preprint — published as 10.1093/genetics/iyad063 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Numerous studies over the last decade have demonstrated the utility of machine learning methods when applied to population genetic tasks. More recent studies show the potential of deep learning methods in particular, which allow researchers to approach problems without making prior assumptions about how the data should be summarized or manipulated, instead learning their own internal representation of the data in an attempt to maximize inferential accuracy. One type of deep neural network, called Generative Adversarial Networks (GANs), can even be used to generate new data, and this approach has been used to create individual artificial human genomes free from privacy concerns. In this study, we further explore the application of GANs in population genetics by designing and training a network to learn the statistical distribution of population genetic alignments (i.e. data sets consisting of sequences from an entire population sample) under several diverse evolutionary histories—the first GAN capable of performing this task. After testing multiple different neural network architectures, we report the results of a fully differentiable Deep-Convolutional Wasserstein GAN with gradient penalty that is capable of generating artificial examples of population genetic alignments that successfully mimic key aspects of the training data, including the site frequency spectrum, differentiation between populations, and patterns of linkage disequilibrium. We demonstrate consistent training success across various evolutionary models, including models of panmictic and subdivided populations, populations at equilibrium and experiencing changes in size, and populations experiencing either no selection or positive selection of various strengths, all without the need for extensive hyperparameter tuning. Overall, our findings highlight the ability of GANs to learn and mimic population genetic data and suggest future areas where this work can be applied in population genetics research that we discuss herein.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2022.09.17.508145

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 72

  1. Abbasnejad M. E. , Q. Shi , A. van den Hengel , and L. Liu , 2019 A generative adversarial density estimator, pp. 10774–10783 in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. · DOI
  2. 2020, Predicting the landscape of recombination using deep learning, Mol. Biol. Evol, 37, 1790, 10.1093/molbev/msaa038 · DOI
  3. Adrion J. R. , C. B. Cole , N. Dukler , J. G. Galloway , A. L. Gladstein , et al., 2020b A community-maintained standard library of population genetic models. eLife 9. https://doi.org/10.7554/eLife.54967 · DOI
  4. Arjovsky M. , S. Chintala , and L. Bottou , 2017 Wasserstein GAN. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1701.07875 · DOI · Paper page
  5. Battey C. J. , G. C. Coffing , and A. D. Kern , 2021 Visualizing population structure with variational autoencoders. G3 (Bethesda) 11. https://doi.org/10.1093/g3journal/jkaa036 · DOI
  6. Baumdicker F. , G. Bisschop , D. Goldstein , G. Gower , A. P. Ragsdale , et al., 2022 Efficient ancestry and mutation simulation with msprime 1.0. Genetics 220. https://doi.org/10.1093/genetics/iyab229 · DOI
  7. 10.1146/annurev-ecolsys-102209-144621 · DOI
  8. Benegas G. , S. S. Batra , and Y. S. Song , 2022 DNA language models are powerful zero-shot predictors of non-coding variant effects. BioRxiv. [accessed 2023 Apr 6]. https://doi.org/10.1101/2022.08.22.504706 · DOI
  9. 10.1007/s10851-014-0506-3 · DOI
  10. Bousmalis K. , N. Silberman , D. Dohan , D. Erhan , and D. Krishnan , 2017 Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks, pp. 95–104 in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. · DOI · Paper page
  11. 10.1214/ss/1009213726 · DOI · Paper page
  12. 2021, A survey on the explainability of supervised machine learning, jair, 70, 245, 10.1613/jair.1.12228 · DOI · Paper page
  13. 10.1109/MSP.2017.2765202 · DOI · Paper page
  14. 10.1093/genetics/155.3.1405 · DOI · Paper page
  15. 10.1093/molbev/msu077 · DOI
  16. 10.1093/molbev/msy224 · DOI
  17. Goodfellow I. J. , J. Pouget-Abadie , M. Mirza , B. Xu , D. Warde-Farley , et al., 2014 Generative Adversarial Networks. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1406.2661 · DOI · Paper page
  18. Gower G. , P. I. Picazo , M. Fumagalli , and F. Racimo , 2021 Detecting adaptive introgression in human evolution using convolutional neural networks. eLife 10. https://doi.org/10.7554/eLife.64669 · DOI · Paper page
  19. Gulrajani I. , F. Ahmed , M. Arjovsky , V. Dumoulin , and A. C. Courville , 2017 Improved training of wasserstein gans. Advances in neural information processing systems 30.
  20. 10.1038/s41586-020-2649-2 · DOI · Paper page
  21. He K. , X. Zhang , S. Ren , and J. Sun , 2015 Deep Residual Learning for Image Recognition. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1512.03385 · DOI · Paper page
  22. 10.1093/genetics/141.4.1605 · DOI
  23. 10.1093/bioinformatics/18.2.337 · DOI
  24. Isildak U. , A. Stella , and M. Fumagalli , 2021 Distinguishing between recent balancing selection and incomplete sweep using deep neural networks. Mol. Ecol. Resour. https://doi.org/10.1111/1755-0998.13379 · DOI
  25. Jang E. , S. Gu , and B. Poole , 2016 Categorical Reparameterization with Gumbel-Softmax. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1611.01144 · DOI · Paper page
  26. 10.1534/genetics.104.038224 · DOI
  27. 10.1093/genetics/123.4.887 · DOI · Paper page
  28. Karras T. , S. Laine , and T. Aila , 2018 A Style-Based Generator Architecture for Generative Adversarial Networks. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1812.04948 · DOI · Paper page
  29. 2021, Alias-Free Generative Adversarial Networks, Advances in Neural Information Processing Systems, 34, 852
  30. 10.1371/journal.pcbi.1004842 · DOI
  31. 10.1093/bioinformatics/btw556 · DOI
  32. 10.1534/g3.118.200262 · DOI
  33. Khan S. A. , R. Lehmann , X. Martinez-de-Morentin , A. M. Ruiz , V. Lagani , et al., 2022 scAEGAN: Unification of Single-Cell Genomics Data by Adversarial Learning of Latent Space Correspondences. BioRxiv. https://doi.org/10.1101/2022.04.19.488745 · DOI
  34. 10.1534/genetics.103.025387 · DOI
  35. Kim Y. , and J.-W. Ha , 2021 Contrastive Fine-grained Class Clustering via Generative Adversarial Networks. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.2112.14971 · DOI
  36. Kingma D. P. , and J. Ba , 2014 Adam: A Method for Stochastic Optimization. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1412.6980 · DOI · Paper page
  37. 10.1162/neco.1989.1.4.541 · DOI · Paper page
  38. 10.1109/5.726791 · DOI · Paper page
  39. 10.1038/nature14539 · DOI · Paper page
  40. 10.1038/ng.3254 · DOI
  41. 10.1186/s13059-020-02196-9 · DOI
  42. 10.1109/TIP.2022.3142527 · DOI
  43. 10.1038/nature10231 · DOI · Paper page
  44. Maddison C. J. , A. Mnih , and Y. W. Teh , 2016 The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1611.00712 · DOI
  45. 10.1073/pnas.76.10.5269 · DOI
  46. 10.1017/S0016672300033619 · DOI
  47. 2019, in Advances in Neural Information Processing Systems, 32, 8024
  48. 10.1093/bioinformatics/btv493 · DOI
  49. Radford A. , L. Metz , and S. Chintala , 2015 Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1511.06434 · DOI · Paper page
  50. Salimans T. , I. Goodfellow , W. Zaremba , V. Cheung , A. Radford , et al., 2016 Improved techniques for training gans. Advances in neural information processing systems 29.
  51. 2021, Deep learning for population size history inference: Design, comparison and combination with approximate Bayesian computation, Mol. Ecol. Resour, 21, 2645, 10.1111/1755-0998.13224 · DOI
  52. 10.1038/ng.3015 · DOI · Paper page
  53. 10.1093/gbe/evv228 · DOI
  54. 10.1371/journal.pgen.1005928 · DOI
  55. 10.1016/j.tig.2017.12.005 · DOI · Paper page
  56. Selvaraju R. R. , M. Cogswell , A. Das , R. Vedantam , D. Parikh , et al., 2017 Grad-CAM: Visual explanations from deep networks via gradient-based localization, pp. 618–626 in Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), IEEE. · DOI · Paper page
  57. 10.1093/genetics/141.1.413 · DOI · Paper page
  58. Simonyan K. , A. Vedaldi , and A. Zisserman , 2013 Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1312.6034 · DOI · Paper page
  59. 10.1017/S0016672300014634 · DOI · Paper page
  60. Smith C. C. R. , S. Tittes , P. L. Ralph , and A. D. Kern , 2022 Dispersal inference from population genetic variation using a convolutional neural network. BioRxiv. [accessed 2023 Apr 6]. https://doi.org/10.1101/2022.08.25.505329 · DOI
  61. 10.1111/mec.13288 · DOI
  62. 10.1017/S0016672300014634 · DOI · Paper page
  63. 10.1126/science.1219240 · DOI · Paper page
  64. 10.1038/ng.3748 · DOI
  65. Thanh-Tung H. , and T. Tran , 2020 Catastrophic forgetting and mode collapse in GANs, pp. 1–10 in 2020 International Joint Conference on Neural Networks (IJCNN), IEEE. · DOI
  66. 10.1371/journal.pbio.0040072 · DOI
  67. Wang Z. , J. Wang , M. Kourakos , N. Hoang , H. H. Lee , et al., 2020 Automatic inference of demographic parameters using generative adversarial networks. BioRxiv. [accessed 2023 Apr 6]. https://doi.org/10.1101/2020.08.05.237834 · DOI
  68. 10.1016/0040-5809(75)90020-9 · DOI
  69. Whitehouse L. S. , and D. R. Schrider , 2022 Timesweeper: accurately identifying selective sweeps using population genomic time series. BioRxiv. [accessed 2023 Apr 6]. https://doi.org/10.1101/2022.07.06.499052 · DOI
  70. Yale A. , S. Dash , R. Dutta , I. Guyon , A. Pavao , et al., 2019 Privacy Preserving Synthetic Health Data, in hal-02160496, Bruges, Belgium. · DOI
  71. 10.1371/journal.pgen.1009303 · DOI
  72. Zhu J.-Y. , T. Park , P. Isola , and A. A. Efros , 2017 Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. arXiv. [accessed 2023 Apr 6]. https://doi.org/10.48550/arxiv.1703.10593 · DOI · Paper page

Metadata

Authors
Booker, W. W., Ray, D. D., & Schrider, D. R.
Affiliations
University of North Carolina at Chapel Hill (US)
Corresponding author
  • Booker, William W.
  • Schrider, Daniel R.
ORCID
Venue
Genetics
Publisher
openRxiv
Published
2022-09-17
Volume
224
Issue
2
ISSN
0016-6731 (ISSN-L)
DOI
10.1101/2022.09.17.508145
PMC
PMC10213497
OpenAlex
W4366083659
Cited by
22
References
1
Citations by year
2026: 5 · 2025: 5 · 2024: 7 · 2023: 5
FWCI
3.65
Type
journal article
Language
en
Open access
Locations
  • Genetics (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Institutes of Health
  • National Human Genome Research Institute (R01HG010774)
  • National Institute of General Medical Sciences (R35GM138286)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic diversity and population structure
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Forensic and Genetic Research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Evolution and Genetic Dynamics
Keywords
generative adversarial networks, synthetic data generation, site frequency spectrum, linkage disequilibrium, genetic differentiation, positive selection, population size change, panmictic population, subpopulations
MeSH terms
Machine Learning, Biological Evolution, Humans, Linkage Disequilibrium, Genome, Human, Privacy

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review