{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:13:32Z","timestamp":1785413612435,"version":"3.56.0"},"posted":{"date-parts":[[2025,12,9]]},"group-title":"Genomics","reference-count":94,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"award":["2R35GM13826"],"award-info":[{"award-number":["2R35GM13826"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R15HG011528"],"award-info":[{"award-number":["R15HG011528"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]},{"award":["390727645"],"award-info":[{"award-number":["390727645"]}],"id":[{"id":"https:\/\/ror.org\/018mejw64","id-type":"ROR","asserted-by":"publisher"}]},{"award":["390838134"],"award-info":[{"award-number":["390838134"]}],"id":[{"id":"https:\/\/ror.org\/018mejw64","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Reinhard Frank-Stiftung"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,12,9]]},"abstract":"<jats:title>\n                  A\n                  <jats:sc>bstract<\/jats:sc>\n                <\/jats:title>\n                <jats:p>\n                  Machine learning approaches have become a powerful alternative to traditional methods in population genetics. Convolutional neural networks (CNNs) in particular have been successful in inferring natural selection, recombination rate estimation, introgression, dispersal distances, and effective population size changes. One limitation of CNNs and other deep learning methods is that they can be difficult to interpret. When they have been shown to be as or more successful than summary-statistic-based methods, what are they learning? Here we investigate CNNs from two different methods: the\n                  <jats:bold>pg-gan<\/jats:bold>\n                  discriminator for identifying real vs. simulated data, and two networks trained to detect selective sweeps. We first compute correlations between learned network features and traditional summary statistics, then assess whether summary statistics can be predicted from the learned features. To understand the learned features, we compute feature importance through SHAP values and feature groupings through dimensionality reduction. Finally we use decision trees and random forests to build an interpretable \u201cmodel-of-the-model\u201d. Our results reveal that some CNN architectures can implicitly compute summary statistics such as pairwise heterozygosity, while statistics such as the site frequency spectrum are less similar to the network\u2019s learned features. We find that long-range linkage disequilibrium is readily approximated by the networks and may be more efficiently computed by CNNs than traditional methods (which are quadratic in the number of sites). Overall, this work contributes to the interpretability of deep learning methods in population genetics by clarifying the relationships between model architecture, learned network features, established summary statistics, and predicted evolutionary parameters.\n                <\/jats:p>","DOI":"10.64898\/2025.12.04.692404","type":"posted-content","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:42Z","timestamp":1765308342000},"source":"Crossref","is-referenced-by-count":1,"title":["Interpreting Convolutional Neural Networks in Population Genetics"],"prefix":"10.64898","author":[{"given":"Huiting","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3334-2742","authenticated-orcid":false,"given":"Leon","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan D.","family":"Ray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5249-4151","authenticated-orcid":false,"given":"Daniel R.","family":"Schrider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franz","family":"Baumdicker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0484-0838","authenticated-orcid":false,"given":"Sara","family":"Mathieson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025121111000732000_2025.12.04.692404v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nature15393"},{"key":"2025121111000732000_2025.12.04.692404v1.2","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.109.104042"},{"key":"2025121111000732000_2025.12.04.692404v1.3","unstructured":"Adebayo, J. , Gilmer, J. , Muelly, M. , Goodfellow, I. , Hardt, M. , and Kim, B. 2018. Sanity checks for saliency maps. Advances in neural information processing systems, 31,."},{"key":"2025121111000732000_2025.12.04.692404v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msaa038"},{"issue":"5","key":"2025121111000732000_2025.12.04.692404v1.5","doi-asserted-by":"crossref","first-page":"msaf094","DOI":"10.1093\/molbev\/msaf094","article-title":"Efficient detection and characterization of targets of natural selection using transfer learning","volume":"42","year":"2025","journal-title":"Molecular Biology and Evolution"},{"key":"2025121111000732000_2025.12.04.692404v1.6","doi-asserted-by":"crossref","unstructured":"Arnab, S. P. , Campelo dos Santos, A. L. , Fumagalli, M. , and DeGiorgio, M. 2025. Semi-supervised detection of natural selection with positive-unlabeled learning. bioRxiv, pages 2025\u201308.","DOI":"10.1101\/2025.08.15.670602"},{"key":"2025121111000732000_2025.12.04.692404v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/nature15393"},{"issue":"4","key":"2025121111000732000_2025.12.04.692404v1.8","first-page":"2025","article-title":"Approximate bayesian computation in population genetics","volume":"162","year":"2002","journal-title":"Genetics Society of America"},{"key":"2025121111000732000_2025.12.04.692404v1.9","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-ecolsys-102209-144621"},{"issue":"2","key":"2025121111000732000_2025.12.04.692404v1.10","doi-asserted-by":"crossref","first-page":"iyad063","DOI":"10.1093\/genetics\/iyad063","article-title":"This population does not exist: learning the distribution of evolutionary histories with generative adversarial networks","volume":"224","year":"2023","journal-title":"Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.11","doi-asserted-by":"publisher","DOI":"10.1093\/gbe\/evae005"},{"key":"2025121111000732000_2025.12.04.692404v1.12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2025121111000732000_2025.12.04.692404v1.13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010407"},{"key":"2025121111000732000_2025.12.04.692404v1.14","doi-asserted-by":"crossref","unstructured":"Caldas, I. V. , Clark, A. G. , and Messer, P. W. 2022. Inference of selective sweep parameters through supervised learning. bioRxiv, pages 2022\u201307.","DOI":"10.1101\/2022.07.19.500702"},{"issue":"11","key":"2025121111000732000_2025.12.04.692404v1.15","doi-asserted-by":"crossref","first-page":"e1010979","DOI":"10.1371\/journal.pcbi.1010979","article-title":"On convolutional neural networks for selection inference: Revealing the effect of preprocessing on model learning and the capacity to discover novel patterns","volume":"19","year":"2023","journal-title":"PLoS computational biology"},{"key":"2025121111000732000_2025.12.04.692404v1.16","doi-asserted-by":"crossref","unstructured":"Chan, J. , Perrone, V. , Spence, J. , Jenkins, P. , Mathieson, S. , and Song, Y. February 2018. A likelihood-free inference framework for population genetic data using exchangeable neural networks. Neural Information Processing Systems, pages 8594\u20138605.","DOI":"10.1101\/267211"},{"issue":"7","key":"2025121111000732000_2025.12.04.692404v1.17","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1016\/j.tree.2010.04.001","article-title":"Approximate bayesian computation (abc) in practice","volume":"25","year":"2010","journal-title":"Trends in ecology & evolution"},{"key":"2025121111000732000_2025.12.04.692404v1.18","article-title":"Explainable and interpretable multimodal large language models: A comprehensive survey","year":"2024","journal-title":"arXiv preprint"},{"key":"2025121111000732000_2025.12.04.692404v1.19","doi-asserted-by":"crossref","unstructured":"Efron, B. Bootstrap methods: another look at the jackknife. In Breakthroughs in statistics: Methodology and distribution, pages 569\u2013593. Springer, 1992.","DOI":"10.1007\/978-1-4612-4380-9_41"},{"key":"2025121111000732000_2025.12.04.692404v1.20","doi-asserted-by":"crossref","unstructured":"Eneli, A. A. , Siu, P. C. , Perez, M. F. , Burt, A. , Fumagalli, M. , and Mathieson, S. 2025. On the use of generative models for evolutionary inference of malaria vectors from genomic data. bioRxiv, pages 2025\u201306.","DOI":"10.1101\/2025.06.26.661760"},{"key":"2025121111000732000_2025.12.04.692404v1.21","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq322"},{"key":"2025121111000732000_2025.12.04.692404v1.22","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/155.3.1405"},{"key":"2025121111000732000_2025.12.04.692404v1.23","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msy224"},{"key":"2025121111000732000_2025.12.04.692404v1.24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"2025121111000732000_2025.12.04.692404v1.25","doi-asserted-by":"crossref","first-page":"e1005004","DOI":"10.1371\/journal.pgen.1005004","article-title":"Recent selective sweeps in north american drosophila melanogaster show signatures of soft sweeps","volume":"11","year":"2015","journal-title":"PLoS genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.26","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.115.184002"},{"key":"2025121111000732000_2025.12.04.692404v1.27","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"2025121111000732000_2025.12.04.692404v1.28","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.64669"},{"key":"2025121111000732000_2025.12.04.692404v1.29","doi-asserted-by":"crossref","unstructured":"Gower, G. , Picazo, P. I. , Lindgren, F. , and Racimo, F. 2023. Inference of population genetics parameters using discriminator neural networks: an adversarial monte carlo approach. bioRxiv, pages 2023\u201304.","DOI":"10.1101\/2023.04.27.538386"},{"key":"2025121111000732000_2025.12.04.692404v1.30","doi-asserted-by":"crossref","unstructured":"Gower, G. , Pope, N. S. , Rodrigues, M. F. , Tittes, S. , Tran, L. N. , Alam, O. , Cavassim, M. I. A. , Fields, P. D. , Haller, B. C. , Huang, X. , et al. 2025. Accessible, realistic genome simulation with selection using stdpopsim. bioRxiv.","DOI":"10.1101\/2025.03.23.644823"},{"key":"2025121111000732000_2025.12.04.692404v1.31","doi-asserted-by":"publisher","DOI":"10.1101\/418657"},{"issue":"2","key":"2025121111000732000_2025.12.04.692404v1.32","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1111\/1755-0998.12968","article-title":"Tree-sequence recording in slim opens new horizons for forward-time simulation of whole genomes","volume":"19","year":"2019","journal-title":"Molecular ecology resources"},{"key":"2025121111000732000_2025.12.04.692404v1.33","doi-asserted-by":"crossref","unstructured":"He, K. , Zhang, X. , Ren, S. , and Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025121111000732000_2025.12.04.692404v1.34","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msab332"},{"key":"2025121111000732000_2025.12.04.692404v1.35","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.104.036947"},{"issue":"8","key":"2025121111000732000_2025.12.04.692404v1.36","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.1111\/1755-0998.13379","article-title":"Distinguishing between recent balancing selection and incomplete sweep using deep neural networks","volume":"21","year":"2021","journal-title":"Molecular Ecology Resources"},{"issue":"5","key":"2025121111000732000_2025.12.04.692404v1.37","doi-asserted-by":"crossref","first-page":"e1004842","DOI":"10.1371\/journal.pcbi.1004842","article-title":"Efficient coalescent simulation and genealogical analysis for large sample sizes","volume":"12","year":"2016","journal-title":"PLoS computational biology"},{"issue":"11","key":"2025121111000732000_2025.12.04.692404v1.38","doi-asserted-by":"crossref","first-page":"e1006581","DOI":"10.1371\/journal.pcbi.1006581","article-title":"Efficient pedigree recording for fast population genetics simulation","volume":"14","year":"2018","journal-title":"PLoS computational biology"},{"key":"2025121111000732000_2025.12.04.692404v1.39","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/146.3.1197"},{"key":"2025121111000732000_2025.12.04.692404v1.40","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw556"},{"issue":"6","key":"2025121111000732000_2025.12.04.692404v1.41","doi-asserted-by":"crossref","first-page":"1959","DOI":"10.1534\/g3.118.200262","article-title":"diplos\/hic: an updated approach to classifying selective sweeps","volume":"8","year":"2018","journal-title":"G3: Genes, Genomes, Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.42","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.103.025387"},{"key":"2025121111000732000_2025.12.04.692404v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90011-4"},{"key":"2025121111000732000_2025.12.04.692404v1.44","article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","journal-title":"arXiv preprint"},{"key":"2025121111000732000_2025.12.04.692404v1.45","doi-asserted-by":"publisher","DOI":"10.1093\/gbe\/evad008"},{"key":"2025121111000732000_2025.12.04.692404v1.46","doi-asserted-by":"publisher","DOI":"10.7554\/elife.84874"},{"issue":"1","key":"2025121111000732000_2025.12.04.692404v1.47","doi-asserted-by":"crossref","first-page":"e1011110","DOI":"10.1371\/journal.pgen.1011110","article-title":"The era of the arg: An introduction to ancestral recombination graphs and their significance in empirical evolutionary genomics","volume":"20","year":"2024","journal-title":"Plos Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.48","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msq211"},{"key":"2025121111000732000_2025.12.04.692404v1.49","unstructured":"Lundberg, S. M. and Lee, S.-I. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, 30,."},{"issue":"11","key":"2025121111000732000_2025.12.04.692404v1.50","doi-asserted-by":"crossref","first-page":"e1011032","DOI":"10.1371\/journal.pgen.1011032","article-title":"Domain-adaptive neural networks improve supervised machine learning based on simulated population genetic data","volume":"19","year":"2023","journal-title":"PLoS Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.51","unstructured":"Molnar, C. Interpretable Machine Learning. 2 edition, 2022. URL https:\/\/christophm.github.io\/interpretable-ml-book\/."},{"issue":"11","key":"2025121111000732000_2025.12.04.692404v1.52","doi-asserted-by":"crossref","first-page":"2037","DOI":"10.1016\/j.ajhg.2021.09.006","article-title":"Revisiting the out of africa event with a deep-learning approach","volume":"108","year":"2021","journal-title":"The American Journal of Human Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.53","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msad211"},{"key":"2025121111000732000_2025.12.04.692404v1.54","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-024-00772-4"},{"key":"2025121111000732000_2025.12.04.692404v1.55","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti584"},{"key":"2025121111000732000_2025.12.04.692404v1.56","unstructured":"Perron, L. and Furnon, V. 2019. Or-tools. Google. [Online]. Available: https:\/\/developers.google.com\/optimization."},{"key":"2025121111000732000_2025.12.04.692404v1.57","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbac354"},{"key":"2025121111000732000_2025.12.04.692404v1.58","doi-asserted-by":"crossref","unstructured":"Quelin, A. , Austerlitz, F. , and Jay, F. 2025. Assessing simulation-based supervised machine learning for demographic parameter inference from genomic data. Heredity, pages 1\u201310.","DOI":"10.1101\/2025.04.07.647546"},{"key":"2025121111000732000_2025.12.04.692404v1.59","doi-asserted-by":"publisher","DOI":"10.1038\/nature17439"},{"issue":"2","key":"2025121111000732000_2025.12.04.692404v1.60","doi-asserted-by":"crossref","first-page":"e1010657","DOI":"10.1371\/journal.pgen.1010657","article-title":"Introunet: identifying introgressed alleles via semantic segmentation","volume":"20","year":"2024","journal-title":"PLoS Genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.61","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/iyae024"},{"key":"2025121111000732000_2025.12.04.692404v1.62","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.113.152587"},{"key":"2025121111000732000_2025.12.04.692404v1.63","doi-asserted-by":"crossref","unstructured":"Rozemberczki, B. , Watson, L. , Bayer, P. , Yang, H.-T. , Kiss, O. , Nilsson, S. , and Sarkar, R. The shapley value in machine learning. In The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence, pages 5572\u20135579. International Joint Conferences on Artificial Intelligence Organization, 2022.","DOI":"10.24963\/ijcai.2022\/778"},{"key":"2025121111000732000_2025.12.04.692404v1.64","doi-asserted-by":"crossref","unstructured":"Sanchez, T. , Cury, J. , Charpiat, G. , and Jay, F. July 2020. Deep learning for population size history inference: design, comparison and combination with approximate bayesian computation. Molecular Ecology Resources.","DOI":"10.1101\/2020.01.20.910539"},{"key":"2025121111000732000_2025.12.04.692404v1.65","doi-asserted-by":"publisher","DOI":"10.1093\/gbe\/evv228"},{"issue":"3","key":"2025121111000732000_2025.12.04.692404v1.66","doi-asserted-by":"crossref","first-page":"e1005928","DOI":"10.1371\/journal.pgen.1005928","article-title":"S\/hic: robust identification of soft and hard sweeps using machine learning","volume":"12","year":"2016","journal-title":"PLoS genetics"},{"key":"2025121111000732000_2025.12.04.692404v1.67","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msx154"},{"key":"2025121111000732000_2025.12.04.692404v1.68","doi-asserted-by":"publisher","DOI":"10.1016\/j.tig.2017.12.005"},{"key":"2025121111000732000_2025.12.04.692404v1.69","doi-asserted-by":"crossref","unstructured":"Shapley, L. S. et al. 1953. A value for n-person games.","DOI":"10.1515\/9781400881970-018"},{"issue":"3","key":"2025121111000732000_2025.12.04.692404v1.70","first-page":"1","article-title":"Deep learning for population genetic inference","volume":"12","year":"2016","journal-title":"PLos Computational Biology"},{"key":"2025121111000732000_2025.12.04.692404v1.71","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","year":"2013","journal-title":"arXiv preprint"},{"key":"2025121111000732000_2025.12.04.692404v1.72","article-title":"Rethinking interpretability in the era of large language models","year":"2024","journal-title":"arXiv preprint"},{"key":"2025121111000732000_2025.12.04.692404v1.73","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/iyad068"},{"issue":"17","key":"2025121111000732000_2025.12.04.692404v1.74","doi-asserted-by":"crossref","first-page":"4562","DOI":"10.1111\/mec.14223","article-title":"Demographic model selection using random forests and the site frequency spectrum","volume":"26","year":"2017","journal-title":"Molecular Ecology"},{"key":"2025121111000732000_2025.12.04.692404v1.75","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-019-0484-x"},{"key":"2025121111000732000_2025.12.04.692404v1.76","doi-asserted-by":"crossref","unstructured":"Szatkownik, A. , Furtlehner, C. , Charpiat, G. , Yelmen, B. , and Jay, F. 2024. Latent generative modeling of long genetic sequences with gans. bioRxiv, pages 2024\u201308.","DOI":"10.1101\/2024.08.07.607012"},{"key":"2025121111000732000_2025.12.04.692404v1.77","unstructured":"Szatkownik, A. , Furtlehner, C. , Charpiat, G. , Yelmen, B. , and Jay, F. Towards creating longer genetic sequences with gans: Generation in principal component space. In Machine Learning in Computational Biology, pages 110\u2013122. PMLR, 2024."},{"key":"2025121111000732000_2025.12.04.692404v1.78","doi-asserted-by":"crossref","unstructured":"Szatkownik, A. , Planche, L. , Demeulle, M. , Chambe, T. , \u00c1vila-Arcos, M. C. , Huerta-Sanchez, E. , Furtlehner, C. , Charpiat, G. , Jay, F. , and Yelmen, B. 2024. Diffusion-based artificial genomes and their usefulness for local ancestry inference. bioRxiv, pages 2024\u201310.","DOI":"10.1101\/2024.10.28.620648"},{"issue":"3","key":"2025121111000732000_2025.12.04.692404v1.79","first-page":"585","article-title":"Statistical methods for testing the neutral mutation hypothesis by dna polymorphism","volume":"123","year":"1989","journal-title":"Genetics Society of America"},{"key":"2025121111000732000_2025.12.04.692404v1.80","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-2927-x"},{"issue":"10","key":"2025121111000732000_2025.12.04.692404v1.81","doi-asserted-by":"crossref","first-page":"msaf250","DOI":"10.1093\/molbev\/msaf250","article-title":"Interpreting supervised machine learning inferences in population genomics using haplotype matrix permutations","volume":"42","year":"2025","journal-title":"Molecular Biology and Evolution"},{"key":"2025121111000732000_2025.12.04.692404v1.82","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msad277"},{"issue":"1","key":"2025121111000732000_2025.12.04.692404v1.83","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s42003-025-07480-7","article-title":"Fast and accurate deep learning scans for signatures of natural selection in genomes using faster-nn","volume":"8","year":"2025","journal-title":"Communications Biology"},{"key":"2025121111000732000_2025.12.04.692404v1.84","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0040072"},{"issue":"137","key":"2025121111000732000_2025.12.04.692404v1.85","first-page":"1","article-title":"Hybrid predictive models: When an interpretable model collaborates with a black-box model","volume":"22","year":"2021","journal-title":"Journal of Machine Learning Research"},{"issue":"8","key":"2025121111000732000_2025.12.04.692404v1.86","doi-asserted-by":"crossref","first-page":"2689","DOI":"10.1111\/1755-0998.13386","article-title":"Automatic inference of demographic parameters using generative adversarial networks","volume":"21","year":"2021","journal-title":"Molecular ecology resources"},{"key":"2025121111000732000_2025.12.04.692404v1.87","doi-asserted-by":"publisher","DOI":"10.1093\/genetics\/iyad084"},{"key":"2025121111000732000_2025.12.04.692404v1.88","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msae223"},{"key":"2025121111000732000_2025.12.04.692404v1.89","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm386"},{"key":"2025121111000732000_2025.12.04.692404v1.90","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-biodatasci-020722-115651"},{"issue":"2","key":"2025121111000732000_2025.12.04.692404v1.91","doi-asserted-by":"crossref","first-page":"e1009303","DOI":"10.1371\/journal.pgen.1009303","article-title":"Creating artificial human genomes using generative neural networks","volume":"17","year":"2021","journal-title":"PLoS genetics"},{"issue":"10","key":"2025121111000732000_2025.12.04.692404v1.92","doi-asserted-by":"crossref","first-page":"e1011584","DOI":"10.1371\/journal.pcbi.1011584","article-title":"Deep convolutional and conditional neural networks for large-scale genomic data generation","volume":"19","year":"2023","journal-title":"PLOS Computational Biology"},{"key":"2025121111000732000_2025.12.04.692404v1.93","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"key":"2025121111000732000_2025.12.04.692404v1.94","doi-asserted-by":"crossref","unstructured":"Zhang, Q. , Yang, Y. , Ma, H. , and Wu, Y. N. Interpreting cnns via decision trees. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pages 6261\u20136270, 2019.","DOI":"10.1109\/CVPR.2019.00642"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2025.12.04.692404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T19:00:16Z","timestamp":1765479616000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2025.12.04.692404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":94,"URL":"https:\/\/doi.org\/10.64898\/2025.12.04.692404","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]},"subtype":"preprint"}}