@article{abf4c405af0c4229bee83cefc6b9501f,
title = "Evolutionary origins of the SARS-CoV-2 sarbecovirus lineage responsible for the COVID-19 pandemic",
abstract = "There are outstanding evolutionary questions on the recent emergence of human coronavirus SARS-CoV-2 including the role of reservoir species, the role of recombination and its time of divergence from animal viruses. We find that the sarbecoviruses—the viral subgenus containing SARS-CoV and SARS-CoV-2—undergo frequent recombination and exhibit spatially structured genetic diversity on a regional scale in China. SARS-CoV-2 itself is not a recombinant of any sarbecoviruses detected to date, and its receptor-binding motif, important for specificity to human ACE2 receptors, appears to be an ancestral trait shared with bat viruses and not one acquired recently via recombination. To employ phylogenetic dating methods, recombinant regions of a 68-genome sarbecovirus alignment were removed with three independent methods. Bayesian evolutionary rate and divergence date estimates were shown to be consistent for these three approaches and for two different prior specifications of evolutionary rates based on HCoV-OC43 and MERS-CoV. Divergence dates between SARS-CoV-2 and the bat sarbecovirus reservoir were estimated as 1948 (95% highest posterior density (HPD): 1879–1999), 1969 (95% HPD: 1930–2000) and 1982 (95% HPD: 1948–2009), indicating that the lineage giving rise to SARS-CoV-2 has been circulating unnoticed in bats for decades.",
author = "Boni, {Maciej F.} and Philippe Lemey and Xiaowei Jiang and Lam, {Tommy Tsan Yuk} and Perry, {Blair W.} and Castoe, {Todd A.} and Andrew Rambaut and Robertson, {David L.}",
note = "Funding Information: We thank all authors who have kindly deposited and shared genome data on GISAID. We thank T. Bedford for providing M.F.B. with an alignment on which an initial recombination analysis was done. We thank A. Chan and A. Irving for helpful comments on the manuscript. The research leading to these results received funding (to A.R. and P.L.) from the European Research Council under the European Union{\textquoteright}s Horizon 2020 research and innovation programme (grant agreement no. 725422-ReservoirDOCS). D.L.R. is funded by the MRC (no. MC_UU_1201412). The Artic Network receives funding from the Wellcome Trust through project no. 206298/Z/17/Z. P.L. acknowledges support by the Research Foundation—Flanders ({\textquoteleft}Fonds voor Wetenschappelijk Onderzoek—Vlaanderen{\textquoteright} (nos. G066215N, G0D5117N and G0B9317N)) and by the European Union{\textquoteright}s Horizon 2020 project MOOD (no. 874850). T.L. is funded by The National Natural Science Foundation of China Excellent Young Scientists Fund (Hong Kong and Macau; no. 31922087). We thank originating laboratories at South China Agricultural University (Y. Shen, L. Xiao and W. Chen; no. EPI_ISL_410721) and Beijing Institute of Microbiology and Epidemiology (W.-C. Cao, T.T.-Y.L., N. Jia, Y.-W. Zhang, J.-F. Jiang and B.-G. Jiang, nos. EPI_ISL_410538, EPI_ISL_410539, EPI_ISL_410540, EPI_ISL_410541 and EPI_ISL_410542) for the use of sequence data via the GISAID platform. Publisher Copyright: {\textcopyright} 2020, The Author(s), under exclusive licence to Springer Nature Limited.",
year = "2020",
month = nov,
day = "1",
doi = "10.1038/s41564-020-0771-4",
language = "English (US)",
volume = "5",
pages = "1408--1417",
journal = "Nature Microbiology",
issn = "2058-5276",
publisher = "Nature Publishing Group",
number = "11",
}