Deep learning approach to the estimation of the ratio of reproductive modes in a partially clonal population

Genetic diversity among biological entities, including populations, species, and communities, serves as a fundamental source of information for understanding their structure and functioning. However, many ecological and evolutionary problems arise from limited and complex datasets, complicating traditional analytical approaches. In this context, our study applies a deep learning­based approach to address a crucial question in evolutionary biology: the balance  between sexual and asexual reproduction. Sexual reproduction often disrupts advantageous gene combinations favored by selection, whereas asexual reproduction allows faster proliferation without the need for males, effectively maintaining beneficial genotypes. This research focuses on exploring the coexistence patterns of sexual and asexual reproduction within a single species. We developed a convolutional neural network model specifically designed to analyze the dynamics of populations exhibiting mixed reproductive strategies within changing environments. The model developed here allows one to estimate the ratio of population members who originate from sexual reproduction to the clonal organisms produced by parthenogenetic females. This model assumes the reproductive ratio remains constant over time in populations with dual reproductive strategies and stable population sizes. The approach proposed is suitable for neutral multiallelic marker traits such as microsatellite repeats. Our results demonstrate that the model estimates the ratio of reproductive modes with an accuracy as high as 0.99, effectively handling the complexities posed by small sample sizes. When the training dataset’s dimensionality aligns with the actual data, the model converges to the minimum error much faster, highlighting the significance of dataset design in predictive performance. This work contributes to the understanding of reproductive strategy dynamics in evolutionary biology, showcasing the potential of deep learning to enhance genetic data analysis. Our findings pave the way for future research examining the nuances of genetic diversity and reproductive modes in fluctuating ecological contexts, emphasizing the importance of advanced computational methods in evolutionary studies.

1. Adiconis X., Borges-Rivera D., Satija R., DeLuca D.S., Busby M.A., Berlin A.M., Sivachenko A., Thompson D.A., Wysoker A., Fennell T., Gnirke A., Pochet N., Regev A., Levin J.Z. Comparative analysis of RNA sequencing methods for degraded or low-input samples. Nat Methods. 2013;10(7):623-629. doi 10.1038/nmeth.2483

2. Adrion J.R., Galloway J.G., Kern A.D. Predicting the landscape of recombination using deep learning. Mol Biol Evol. 2020;37(6):1790-1808. doi 10.1093/molbev/msaa038

3. Anders U., Korn O. Model selection in neural networks. Neural Netw. 1999;12(2):309-323. doi 10.1016/s0893-6080(98)00117-8

4. Avise J.C., Quattro J.M., Vrijenhoek R.C. Molecular clones within organismal clones. In: Hecht M.K., Wallace B., Macintyre R.J. (Eds) Evolutionary Biology. Vol. 26. Boston, MA: Springer, 1992;225246. doi 10.1007/978-1-4615-3336-8_6

5. Baer B. Sexual selection. In: Starr C. (Ed.) Encyclopedia of Social Insects. 2020. Springer, Cham. doi 10.1007/978-3-319-90306-4_104-1

6. Barton N.H., Charlesworth B. Why sex and recombination? Science. 1998;281(5385):1986-1990. doi 10.1126/science.281.5385.1986

7. Cohen I.R., Marron A. Evolution is driven by natural autoencoding: reframing species, interaction codes, cooperation and sexual reproduction. Proc Biol Sci. 2023;290(1994):20222409. doi 10.1098/rspb.2022.2409

8. Eğrioğlu E., Aladağ Ç.H., Günay S. A new model selection strategy in artificial neural networks. Appl Math Comput. 2008;195(2):591-597. doi 10.1016/j.amc.2007.05.005

9. Gutiérrez-Valencia J., Hughes P.W., Berdan E.L., Slotte T. The genomic architecture and evolutionary fates of supergenes. Genome Biol Evol. 2021;13(5):evab057. doi 10.1093/gbe/evab057

10. Hsiao S.J. Sources of error in molecular diagnostic analyses. In: Dasgupta A., Sepulveda J.L. (Eds) Accurate Results in the Clinical Laboratory. Elsevier, 2019;337-347. doi 10.1016/B978-0-12-8137765.00021-2

11. Janko K., Bohlen J., Lamatsch D., Flajšhans M., Epplen J.T., Ráb P., Kotlík P., Šlechtová V. The gynogenetic reproduction of diploid and triploid hybrid spined loaches (Cobitis: Teleostei), and their ability to establish successful clonal lineages – on the evolution of polyploidy in asexual vertebrates. Genetica. 2007;131(2):185-194. doi 10.1007/s10709-006-9130-5

12. Kingma D.P., Ba J. Adam: a method for stochastic optimization. arXiv. 2014. doi 10.48550/arXiv.1412.6980

13. Kircher M., Kelso J. High-throughput DNA sequencing – concepts and limitations. BioEssays. 2010;32(6):524-536. doi 10.1002/bies.200900181

14. Korfmann K., Gaggiotti O.E., Fumagalli M. Deep learning in population genetics. Genome Biol Evol. 2023;15(2):evad008. doi 10.1093/gbe/evad008

15. Levin Y., Talsania K., Tran B., Shetty J., Zhao Y., Mehta M. Optimization for sequencing and analysis of degraded FFPE-RNA samples. J Vis Exp. 2020;160:e61060. doi 10.3791/61060

16. Messer P.W. Neutral models of genetic drift and mutation. In: Kliman R.M. (Ed.) Encyclopedia of Evolutionary Biology. Academic Press, Elsevier, 2016;119-123. doi 10.1016/B978-0-12-800049-6.00031-7

17. Montinaro F., Pankratov V., Yelmen B., Pagani L., Mondal M. Revisiting the out of Africa event with a deep-learning approach. Am J Hum Genet. 2021;108(11):2037-2051. doi 10.1016/j.ajhg.2021.09.006

18. Otto S.P. Selective interference and the evolution of sex. J Hered. 2021;112(1):9-18. doi 10.1093/jhered/esaa026

19. Poroshina A., Sherbakov D. A procedure for modeling genetic diversity distortions in populations of organisms with mixed reproductive strategies. Mathematics. 2023;11(13):2985. doi 10.3390/math11132985

20. Putman A.I., Carbone I. Challenges in analysis and interpretation of microsatellite data for population genetic studies. Ecol Evol. 2014; 4(22):4399-4428. doi 10.1002/ece3.1305

21. Ratner V.A. Principles of Organization and Mechanisms of Molecular Genetic Processes. Novosibirsk: Nauka Publ., 1972 (in Russian) Rossi V., Gandolfi A., Baraldi F., Bellavere C., Menozzi P. Phylo genetic relationships of coexisting Heterocypris (Crustacea, Ostracoda) lineages with different reproductive modes from Lampedusa Island (Italy). Mol Phylogenet Evol. 2007;44(3):1273-1283. doi 10.1016/j.ympev.2007.04.013

22. Sanchez T., Cury J., Charpiat G., Jay F. Deep learning for population size history inference: design, comparison and combination with approximate Bayesian computation. Mol Ecol Resour. 2021;21(8): 2645-2660. doi 10.1111/1755-0998.13224

23. Schön I., Martens K., van Dijk P. (Eds) Lost Sex. The Evolutionary Biology of Parthenogenesis. Springer, 2009. doi 10.1007/978-90-481-2770-2

24. Schurko A.M., Neiman M., Logsdon J.M. Jr. Signs of sex: what we know and how we know it. Trends Ecol Evol. 2009;24(4):208-217. doi 10.1016/j.tree.2008.11.010

25. Tagg N., Doncaster C.P., Innes D.J. Resource competition between genetically varied and genetically uniform populations of Daph­nia pulex (Leydig): does sexual reproduction confer a short-term ecological advantage? Biol J Linn Soc. 2005;85(1):111-123. doi 10.1111/j.1095-8312.2005.00475.x

26. Thielsch A., Völker E., Kraus R.H.S., Schwenk K. Discrimination of hybrid classes using cross-species amplification of microsatellite loci: methodological challenges and solutions in Daphnia. Mol Ecol Resour. 2012;12(4):697-705. doi 10.1111/j.1755-0998.2012.03142.x

27. Zhou Z.H. Ensemble Methods: Foundations and Algorithms. CRC Press, 2025