{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T22:27:06Z","timestamp":1783117626483,"version":"3.54.6"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T00:00:00Z","timestamp":1713398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM127348"],"award-info":[{"award-number":["R01GM127348"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM149235"],"award-info":[{"award-number":["R35GM149235"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Inferring past demographic history of natural populations from genomic data is of central concern in many studies across research fields. Previously, our group had developed dadi, a widely used demographic history inference method based on the allele frequency spectrum (AFS) and maximum composite-likelihood optimization. However, dadi\u2019s optimization procedure can be computationally expensive. Here, we present donni (demography optimization via neural network inference), a new inference method based on dadi that is more efficient while maintaining comparable inference accuracy. For each dadi-supported demographic model, donni simulates the expected AFS for a range of model parameters then trains a set of Mean Variance Estimation neural networks using the simulated AFS. Trained networks can then be used to instantaneously infer the model parameters from future genomic data summarized by an AFS. We demonstrate that for many demographic models, donni can infer some parameters, such as population size changes, very well and other parameters, such as migration rates and times of demographic events, fairly well. Importantly, donni provides both parameter and confidence interval estimates from input AFS with accuracy comparable to parameters inferred by dadi\u2019s likelihood optimization while bypassing its long and computationally intensive evaluation process. donni\u2019s performance demonstrates that supervised machine learning algorithms may be a promising avenue for developing more sustainable and computationally efficient demographic history inference methods.<\/jats:p>","DOI":"10.1093\/molbev\/msae077","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T19:13:21Z","timestamp":1713294801000},"source":"Crossref","is-referenced-by-count":8,"title":["Computationally Efficient Demographic History Inference from Allele Frequencies with Supervised Machine Learning"],"prefix":"10.1093","volume":"41","author":[{"given":"Linh N","family":"Tran","sequence":"first","affiliation":[{"name":"Genetics Graduate Interdisciplinary Program, University of Arizona, Tucson, AZ 85721, USA"},{"name":"Department of Molecular & Cellular Biology, University of Arizona , Tucson, AZ 85721 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connie K","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Molecular & Cellular Biology, University of Arizona , Tucson, AZ 85721 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7161-5107","authenticated-orcid":false,"given":"Travis J","family":"Struck","sequence":"additional","affiliation":[{"name":"Department of Molecular & Cellular Biology, University of Arizona , Tucson, AZ 85721 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathews","family":"Sajan","sequence":"additional","affiliation":[{"name":"Department of Molecular & Cellular Biology, University of Arizona , Tucson, AZ 85721 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8659-0579","authenticated-orcid":false,"given":"Ryan N","family":"Gutenkunst","sequence":"additional","affiliation":[{"name":"Department of Molecular & Cellular Biology, University of Arizona , Tucson, AZ 85721 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,4,18]]},"reference":[{"issue":"1","key":"2024053114055211000_msae077-B1","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1534\/genetics.109.104042","article-title":"Frequency spectrum neutrality tests: one for all and all for one","volume":"183","author":"Achaz","year":"2009","journal-title":"Genetics"},{"key":"2024053114055211000_msae077-B2","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.tpb.2017.12.008","article-title":"On the decidability of population size histories from finite allele frequency spectra","volume":"120","author":"Baharian","year":"2018","journal-title":"Theor Popul Biol"},{"issue":"3","key":"2024053114055211000_msae077-B3","doi-asserted-by":"crossref","first-page":"iyab229","DOI":"10.1093\/genetics\/iyab229","article-title":"Efficient ancestry and mutation simulation with msprime 1.0","volume":"220","author":"Baumdicker","year":"2022","journal-title":"Genetics"},{"issue":"6484","key":"2024053114055211000_msae077-B4","doi-asserted-by":"crossref","first-page":"eaay5012","DOI":"10.1126\/science.aay5012","article-title":"Insights into human genetic variation and population history from 929 diverse genomes","volume":"367","author":"Bergstr\u00f6m","year":"2020","journal-title":"Science"},{"issue":"6","key":"2024053114055211000_msae077-B5","doi-asserted-by":"crossref","first-page":"2469","DOI":"10.1214\/14-AOS1264","article-title":"Descartes\u2019 rule of signs and the identifiability of population demographic models from genomic variation data","volume":"42","author":"Bhaskar","year":"2014","journal-title":"Ann Stat"},{"issue":"5","key":"2024053114055211000_msae077-B6","doi-asserted-by":"crossref","first-page":"e1000083","DOI":"10.1371\/journal.pgen.1000083","article-title":"Assessing the evolutionary impact of amino acid mutations in the human genome","volume":"4","author":"Boyko","year":"2008","journal-title":"PLoS Genet"},{"key":"2024053114055211000_msae077-B7","author":"Center","year":"2011"},{"issue":"34","key":"2024053114055211000_msae077-B8","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2205986119","article-title":"Comparative genomics uncovers the evolutionary history, demography, and molecular adaptations of South American Canids","volume":"119","author":"Chavez","year":"2022","journal-title":"Proc Natl Acad Sci USA"},{"issue":"2","key":"2024053114055211000_msae077-B9","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1093\/molbev\/msv255","article-title":"Computationally efficient composite likelihood statistics for demographic inference","volume":"33","author":"Coffman","year":"2016","journal-title":"Mol Biol Evol"},{"issue":"10","key":"2024053114055211000_msae077-B10","doi-asserted-by":"crossref","first-page":"e1003905","DOI":"10.1371\/journal.pgen.1003905","article-title":"Robust demographic inference from genomic and SNP data","volume":"9","author":"Excoffier","year":"2013","journal-title":"PLoS Genet"},{"issue":"2","key":"2024053114055211000_msae077-B11","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1093\/molbev\/msy224","article-title":"The unreasonable effectiveness of convolutional neural networks in population genetic inference","volume":"36","author":"Flagel","year":"2019","journal-title":"Mol Biol Evol"},{"issue":"8","key":"2024053114055211000_msae077-B12","doi-asserted-by":"crossref","first-page":"1852","DOI":"10.1016\/j.cub.2022.02.050","article-title":"Hunter-gatherer genomes reveal diverse demographic trajectories during the rise of farming in Eastern Africa","volume":"32","author":"Gopalan","year":"2022","journal-title":"Curr Biol"},{"issue":"5","key":"2024053114055211000_msae077-B13","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1093\/molbev\/msaa305","article-title":"Dadi. cuda: accelerating population genetics inference with graphics processing units","volume":"38","author":"Gutenkunst","year":"2021","journal-title":"Mol Biol Evol"},{"issue":"10","key":"2024053114055211000_msae077-B14","doi-asserted-by":"crossref","first-page":"e1000695","DOI":"10.1371\/journal.pgen.1000695","article-title":"Inferring the joint demographic history of multiple populations from multidimensional SNP frequency data","volume":"5","author":"Gutenkunst","year":"2009","journal-title":"PLoS Genet"},{"issue":"11","key":"2024053114055211000_msae077-B15","first-page":"2805","article-title":"Phylogeny estimation by integration over isolation with migration models","volume":"35","author":"Hey","year":"2018","journal-title":"Mol Biol Evol"},{"key":"2024053114055211000_msae077-B16","author":"Huang","year":"2023"},{"issue":"5","key":"2024053114055211000_msae077-B17","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/j.ajhg.2012.03.011","article-title":"Population demographic history can cause the appearance of recombination hotspots","volume":"90","author":"Johnston","year":"2012","journal-title":"Am J Hum Genet"},{"issue":"3","key":"2024053114055211000_msae077-B18","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1534\/genetics.117.200493","article-title":"Inferring the joint demographic history of multiple populations: beyond the diffusion approximation","volume":"206","author":"Jouganous","year":"2017","journal-title":"Genetics"},{"issue":"531","key":"2024053114055211000_msae077-B19","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1080\/01621459.2019.1635482","article-title":"Efficiently inferring the demographic history of many populations with allele count data","volume":"115","author":"Kamm","year":"2020","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"2024053114055211000_msae077-B20","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1080\/10618600.2016.1159212","article-title":"Efficient computation of the joint sample frequency spectra for multiple populations","volume":"26","author":"Kamm","year":"2017","journal-title":"J Comput Graph Stat"},{"issue":"5","key":"2024053114055211000_msae077-B21","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","author":"Kelleher","year":"2016","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"2024053114055211000_msae077-B22","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1534\/genetics.116.194019","article-title":"Exact calculation of the joint allele frequency spectrum for isolation with migration models","volume":"207","author":"Kern","year":"2017","journal-title":"Genetics"},{"issue":"9","key":"2024053114055211000_msae077-B23","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1109\/TNN.2011.2162110","article-title":"Comprehensive review of neural network-based prediction intervals and new advances","volume":"22","author":"Khosravi","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"2024053114055211000_msae077-B24","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1534\/genetics.116.197145","article-title":"Inference of the distribution of selection coefficients for new nonsynonymous mutations using large samples","volume":"206","author":"Kim","year":"2017","journal-title":"Genetics"},{"key":"2024053114055211000_msae077-B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1684-5","article-title":"Whole-genome sequence analysis of a pan African set of samples reveals archaic gene flow from an extinct basal population of modern humans into sub-saharan populations","volume":"20","author":"Lorente-Galdos","year":"2019","journal-title":"Genome Biol"},{"issue":"2","key":"2024053114055211000_msae077-B26","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1534\/genetics.112.141846","article-title":"Demographic inference using spectral methods on SNP data, with an analysis of the human out-of-Africa expansion","volume":"192","author":"Luki\u0107","year":"2012","journal-title":"Genetics"},{"issue":"6","key":"2024053114055211000_msae077-B27","doi-asserted-by":"crossref","first-page":"R276","DOI":"10.1016\/j.cub.2021.01.053","article-title":"Demographic inference","volume":"31","author":"Marchi","year":"2021","journal-title":"Curr Biol"},{"key":"2024053114055211000_msae077-B28","doi-asserted-by":"crossref","DOI":"10.1016\/j.cell.2022.04.008","article-title":"The genomic origins of the world\u015b first farmers","author":"Marchi","year":"2022","journal-title":"Cell"},{"issue":"1","key":"2024053114055211000_msae077-B29","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1534\/genetics.166.1.351","article-title":"The allele frequency spectrum in genome-wide human variation data reveals signals of differential demographic history in three large world populations","volume":"166","author":"Marth","year":"2004","journal-title":"Genetics"},{"issue":"3","key":"2024053114055211000_msae077-B30","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/ng.1074","article-title":"Differential confounding of rare and common variants in spatially structured populations","volume":"44","author":"Mathieson","year":"2012","journal-title":"Nat Genet"},{"issue":"1","key":"2024053114055211000_msae077-B31","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.cub.2017.11.021","article-title":"Genomic analysis of demographic history and ecological niche modeling in the endangered sumatran rhinoceros dicerorhinus sumatrensis","volume":"28","author":"Mays","year":"2018","journal-title":"Curr Biol"},{"issue":"1","key":"2024053114055211000_msae077-B32","doi-asserted-by":"crossref","first-page":"e1002342","DOI":"10.1371\/journal.pbio.1002342","article-title":"The iPlant collaborative: cyberinfrastructure for enabling data to discovery for the life sciences","volume":"14","author":"Merchant","year":"2016","journal-title":"PLoS Biol"},{"key":"2024053114055211000_msae077-B33","first-page":"e01457","article-title":"Demographic changes and loss of genetic diversity in two insular populations of bobcats (Lynx rufus)","volume":"26","author":"Miller-Butterworth","year":"2021","journal-title":"Glob Ecol Conserv"},{"key":"2024053114055211000_msae077-B34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-018-08089-7","article-title":"Approximate Bayesian computation with deep learning supports a third archaic introgression in Asia and Oceania","volume":"10","author":"Mondal","year":"2019","journal-title":"Nat Commun"},{"issue":"3","key":"2024053114055211000_msae077-B35","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.tpb.2008.01.001","article-title":"Can one learn history from the allelic spectrum?","volume":"73","author":"Myers","year":"2008","journal-title":"Theor Popul Biol"},{"issue":"13","key":"2024053114055211000_msae077-B36","doi-asserted-by":"crossref","first-page":"2709","DOI":"10.1111\/j.1365-294X.2011.05131.x","article-title":"Jaatha: a fast composite-likelihood approach to estimate demographic parameters","volume":"20","author":"Naduvilezhath","year":"2011","journal-title":"Mol Ecol"},{"key":"2024053114055211000_msae077-B37","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1101\/gr.4252305","article-title":"Genomic scans for selective sweeps using SNP data","volume":"15","author":"Nielsen","year":"2005","journal-title":"Genome Res"},{"key":"2024053114055211000_msae077-B38","first-page":"55","author":"Nix","year":"1994"},{"issue":"19","key":"2024053114055211000_msae077-B39","doi-asserted-by":"crossref","first-page":"5245","DOI":"10.1111\/mec.14266","article-title":"Evaluating mechanisms of diversification in a Guineo-Congolian tropical forest frog using demographic model selection","volume":"26","author":"Portik","year":"2017","journal-title":"Mol Ecol"},{"issue":"6","key":"2024053114055211000_msae077-B40","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1093\/bioinformatics\/btv684","article-title":"Reliable abc model choice via random forests","volume":"32","author":"Pudlo","year":"2016","journal-title":"Bioinformatics"},{"issue":"8","key":"2024053114055211000_msae077-B41","doi-asserted-by":"crossref","first-page":"2645","DOI":"10.1111\/1755-0998.13224","article-title":"Deep learning for population size history inference: design, comparison and combination with approximate Bayesian computation","volume":"21","author":"Sanchez","year":"2021","journal-title":"Mol Ecol Resour"},{"issue":"4","key":"2024053114055211000_msae077-B42","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1093\/genetics\/132.4.1161","article-title":"Population genetics of polymorphism and divergence","volume":"132","author":"Sawyer","year":"1992","journal-title":"Genetics"},{"issue":"4","key":"2024053114055211000_msae077-B43","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.tig.2017.12.005","article-title":"Supervised machine learning for population genetics: a new paradigm","volume":"34","author":"Schrider","year":"2018","journal-title":"Trends Genet"},{"issue":"3","key":"2024053114055211000_msae077-B44","doi-asserted-by":"crossref","first-page":"e1004845","DOI":"10.1371\/journal.pcbi.1004845","article-title":"Deep learning for population genetic inference","volume":"12","author":"Sheehan","year":"2016","journal-title":"PLoS Comput Biol"},{"key":"2024053114055211000_msae077-B45","author":"Sluijterman"},{"issue":"17","key":"2024053114055211000_msae077-B46","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","author":"Smith","year":"2017","journal-title":"Mol Ecol"},{"key":"2024053114055211000_msae077-B47","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.gde.2018.07.002","article-title":"Inference of population history using coalescent HMMs: review and outlook","volume":"53","author":"Spence","year":"2018","journal-title":"Curr Opin Genet Dev"},{"issue":"52","key":"2024053114055211000_msae077-B48","doi-asserted-by":"crossref","first-page":"2505","DOI":"10.21105\/joss.02505","article-title":"sbi: a toolkit for simulation-based inference","volume":"5","author":"Tejero-Cantero","year":"2020","journal-title":"J Open Source Softw"},{"issue":"25","key":"2024053114055211000_msae077-B49","doi-asserted-by":"crossref","first-page":"7677","DOI":"10.1073\/pnas.1503717112","article-title":"Fundamental limits on the accuracy of demographic inference based on the sample frequency spectrum","volume":"112","author":"Terhorst","year":"2015","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024053114055211000_msae077-B50","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41559-018-0735-8","article-title":"Multiple episodes of interbreeding between neanderthal and modern humans","volume":"3","author":"Villanea","year":"2019","journal-title":"Nat Ecol Evol"}],"container-title":["Molecular Biology and Evolution"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/mbe\/advance-article-pdf\/doi\/10.1093\/molbev\/msae077\/57274335\/msae077.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/mbe\/article-pdf\/41\/5\/msae077\/58027013\/msae077.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/mbe\/article-pdf\/41\/5\/msae077\/58027013\/msae077.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T17:50:59Z","timestamp":1717177859000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/mbe\/article\/doi\/10.1093\/molbev\/msae077\/7651223"}},"subtitle":[],"editor":[{"given":"Kelley","family":"Harris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,4,18]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,3]]}},"URL":"https:\/\/doi.org\/10.1093\/molbev\/msae077","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.05.24.542158","asserted-by":"object"}]},"ISSN":["0737-4038","1537-1719"],"issn-type":[{"value":"0737-4038","type":"print"},{"value":"1537-1719","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,5]]},"published":{"date-parts":[[2024,4,18]]},"article-number":"msae077"}}