{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T05:53:11Z","timestamp":1791438791291,"version":"4.3.3"},"reference-count":73,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":6,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/T008717\/1"],"award-info":[{"award-number":["BB\/T008717\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101078303"],"award-info":[{"award-number":["101078303"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006406","name":"Earth and Life Systems Alliance","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006406","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006428","name":"Bureau for Economic Growth, Education, and Environment, United States Agency for International Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Evolutionary Applications"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Forecasting extinction risk from genomic data is challenging because of interactions among environment, demography, and genomic erosion. Here, we use known outcomes from forward simulations as a proof\u2010of\u2010concept study to test whether machine\u2010learning (ML) models can discriminate relative extinction risk and recovery potential from genomic summary statistics, and identify the most informative predictors. Using individual\u2010based, forward\u2010in\u2010time simulations, we generated genomic and fitness data for 11,200 populations across 112 demographic parameter combinations (ancestral population size: 100\u201310,000, bottleneck size: 4\u201350, fecundity: 8\u201364). We evaluated populations at three time points relative to bottleneck onset: 100\u2009years before, 10\u2009years before and at onset. We then assessed their subsequent fate up to 200\u2009years after the end of the bottleneck, classifying populations as extinct or recovered. From 10 sampled individuals per population, we derived 738 predictors spanning diversity, heterozygosity, genetic\/realised\/masked load, and ROH\u2010based inbreeding (FROH). Unsupervised analyses primarily captured historical demography and did not separate outcomes. In contrast, supervised models achieved high performance at bottleneck onset, correctly predicting population fate (i.e., future extinction or recovery) from genomics alone with \u224886%\u201387% accuracy. However, extinction was harder to predict correctly than recovery because simulated extinctions were rarer. Bottleneck size and fecundity provided strong baseline predictability, with genomics adding modest but complementary information. The upper\u2010quantile ROH\/FROH summaries were consistently more informative than mean diversity or mean load. A complementary single\u2010genome analysis showed that reference\u2010genome\u2010style summaries retain useful signal when demographic information is sparse. Together, these results highlight the promise of ML\u2010informed extinction\u2010risk assessment to translate genomic indicators into more actionable, early\u2010warning signals for biodiversity conservation.<\/jats:p>","DOI":"10.1111\/eva.70331","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T05:12:43Z","timestamp":1791436363000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine\u2010Learning Models Trained on Genomic Summary Statistics Assess Extinction Risk and Recovery Potential of Bottlenecked Populations"],"prefix":"10.1111","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7509-772X","authenticated-orcid":false,"given":"Johanna C.","family":"Winder","sequence":"first","affiliation":[{"name":"School of Environmental Sciences University of East Anglia, Norwich Research Park  Norwich UK"},{"name":"Durrell Institute of Conservation and Ecology (DICE), School of Natural Sciences University of Kent  Canterbury UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8756-6124","authenticated-orcid":false,"given":"Jack N.","family":"Marsters","sequence":"additional","affiliation":[{"name":"Mansfield College University of Oxford  Oxford UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4462-9897","authenticated-orcid":false,"given":"Thomas","family":"Birley","sequence":"additional","affiliation":[{"name":"School of Environmental Sciences University of East Anglia, Norwich Research Park  Norwich UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9169-8536","authenticated-orcid":false,"given":"Jasmyn","family":"Gooding","sequence":"additional","affiliation":[{"name":"School of Computing Sciences University of East Anglia, Norwich Research Park  Norwich UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2663-2001","authenticated-orcid":false,"given":"Taoyang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing Sciences University of East Anglia, Norwich Research Park  Norwich UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6941-8187","authenticated-orcid":false,"given":"Jim J.","family":"Groombridge","sequence":"additional","affiliation":[{"name":"Durrell Institute of Conservation and Ecology (DICE), School of Natural Sciences University of Kent  Canterbury UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2964-020X","authenticated-orcid":false,"given":"Hern\u00e1n E.","family":"Morales","sequence":"additional","affiliation":[{"name":"Globe Institute University of Copenhagen  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-738X","authenticated-orcid":false,"given":"Cock","family":"van Oosterhout","sequence":"additional","affiliation":[{"name":"School of Environmental Sciences University of East Anglia, Norwich Research Park  Norwich UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.110.124560"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/eva.13701"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2019.03.002"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature09678"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2023.110414"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41576\u2010022\u201000448\u2010x"},{"key":"e_1_2_11_9_1","doi-asserted-by":"crossref","unstructured":"Birley T. andC.vanOosterhout.2026.\u201cSelection Mode Governs the Scaling of Genetic Load Diversity and Adaptation.\u201dbioRxiv: The Preprint Server for Biology.https:\/\/doi.org\/10.64898\/2026.03.04.709298.","DOI":"10.64898\/2026.03.04.709298"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42003\u2010022\u201003638\u20109"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2023.110091"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2008.03.011"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/eva.70052"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.2307\/5542"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg.2017.109"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg2526"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msx088"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","unstructured":"Chen T. andC.Guestrin.2016.\u201cXGBoost: A Scalable Tree Boosting System.\u201dIn:Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '16) 785\u2013794.https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/brv.12816"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2309455121"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1139\/facets\u20102016\u20100011"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2023.05.008"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msad256"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2018.12.008"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/mec.70088"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2005.05.002"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1365\u20102656.2001.00502.x"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010020\u201014803\u20101"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1500052"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1086\/723601"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2020.108654"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41559\u2010024\u201002533\u20102"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1619508114"},{"key":"e_1_2_11_35_1","volume-title":"IUCN Green Status of Species: A Global Standard for Measuring Species Recovery and Assessing Conservation Impact. Version 2.0","author":"IUCN","year":"2021"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/cobi.13918"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104642118"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/mec.14197"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0013996"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2110614119"},{"key":"e_1_2_11_41_1","doi-asserted-by":"crossref","unstructured":"Kyriazis C. C. S.Grosser Y.Foster et\u00a0al.2026.\u201cElevated Recessive Lethal Frequencies Drive Hatching Failure Following Near Extinction in 'Alal\u0101 the Hawaiian Crow.\u201dbioRxiv: The Preprint Server for Biology.https:\/\/doi.org\/10.64898\/2026.03.24.713968.","DOI":"10.64898\/2026.03.24.713968"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2025.06.013"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1086\/285580"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2115635118"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10592\u2010010\u20100050\u20107"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1111\/eva.13216"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature06922"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biocon.2006.05.016"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1086\/587826"},{"key":"e_1_2_11_50_1","first-page":"2825","article-title":"Scikit\u2010Learn: Machine Learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10531\u2010022\u201002456\u2010z"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10592\u2010023\u201001548\u20109"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.9735\/2229\u20103981"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature13685"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1111\/conl.12040"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gecco.2021.e01492"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1534\/g3.118.200836"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1111\/mec.17641"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tree.2014.11.009"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41893\u2010022\u201000851\u20106"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1111\/1755\u20100998.13967"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13059\u2010018\u20101520\u20103"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1038\/371065a0"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010020\u20102189\u20109"},{"key":"e_1_2_11_66_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010022\u201027980\u2010y"},{"key":"e_1_2_11_67_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41437\u2010023\u201000666\u2010x"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1111\/cobi.70360"},{"key":"e_1_2_11_69_1","doi-asserted-by":"publisher","DOI":"10.1093\/jhered\/esag011"},{"key":"e_1_2_11_70_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010019\u20100686\u20102"},{"key":"e_1_2_11_71_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12864\u2010022\u201008963\u20101"},{"key":"e_1_2_11_72_1","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msag070"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abn5856"},{"key":"e_1_2_11_74_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12915\u2010025\u201002361\u20101"}],"container-title":["Evolutionary Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eva.70331","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/eva.70331","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eva.70331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T05:12:45Z","timestamp":1791436365000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/eva.70331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":73,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1111\/eva.70331"],"URL":"https:\/\/doi.org\/10.1111\/eva.70331","archive":["Portico"],"relation":{},"ISSN":["1752-4571","1752-4571"],"issn-type":[{"value":"1752-4571","type":"print"},{"value":"1752-4571","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"2026-02-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70331"}}