{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T03:00:27Z","timestamp":1790823627216,"version":"4.1.0"},"posted":{"date-parts":[[2026,1,5]]},"group-title":"Evolutionary Biology","reference-count":93,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"crossref","award":["R35GM133700"],"award-info":[{"award-number":["R35GM133700"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"crossref","award":["R35GM156320"],"award-info":[{"award-number":["R35GM156320"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/032atxq54","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/02xhk2825","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/052csg198","id-type":"ROR","asserted-by":"publisher"}]},{"award":["Chateaubriand Fellowship"],"award-info":[{"award-number":["Chateaubriand Fellowship"]}],"id":[{"id":"https:\/\/ror.org\/027wfea20","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"crossref","award":["ANR-24-CE45-1226"],"award-info":[{"award-number":["ANR-24-CE45-1226"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,1,5]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>\n                  Bacteria are hosts to enormous genic diversity. How new genes emerge, functionalize, and spread remain longstanding questions. Here, we explore a mechanism by which adaptive deletions fuse distant gene fragments. Unlike other gene birth mechanisms that begin with rare, neutral mutations, these \u201cdeletion-born fusions\u201d reach high frequency by hitch-hiking on the deletion. The deletion-driven proliferation of the fusion prolongs the mutational supply within these genes before loss, providing additional opportunities for neofunctionalization. We document one such gene fixing and expressing in a long-term\n                  <jats:italic>E. coli<\/jats:italic>\n                  evolution experiment, and identify additional fusion events in the\n                  <jats:italic>Mycobacterium tuberculosis-bovis<\/jats:italic>\n                  split. Finally, we develop a scalable systematic screen to detect these genes in all 2.4 million public single-isolate genomes and identify deletion-born fusions across the bacterial tree of life. These findings challenge the notion that deletions are solely destructive and highlight their role as potential catalysts for evolutionary innovation.\n                <\/jats:p>","DOI":"10.64898\/2026.01.05.697752","type":"posted-content","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T03:25:12Z","timestamp":1767669912000},"source":"Crossref","is-referenced-by-count":4,"title":["Novel genes arise from genomic deletions across the bacterial tree of life"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8382-5945","authenticated-orcid":false,"given":"Arya","family":"Kaul","sequence":"first","affiliation":[{"name":"Departments of Biomedical Informatics and Microbiology, and Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, 02115, USA"},{"name":"Inria, Irisa, Univ. Rennes, 35042 Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6481-5845","authenticated-orcid":false,"given":"Fernando","family":"Rossine","sequence":"additional","affiliation":[{"name":"Departments of Biomedical Informatics and Microbiology, and Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0200-557X","authenticated-orcid":false,"given":"Karel","family":"B\u0159inda","sequence":"additional","affiliation":[{"name":"Inria, Irisa, Univ. Rennes, 35042 Rennes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1303-5598","authenticated-orcid":false,"given":"Michael","family":"Baym","sequence":"additional","affiliation":[{"name":"Departments of Biomedical Informatics and Microbiology, and Laboratory of Systems Pharmacology, Harvard Medical School, Boston, MA, 02115, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026010702152090000_2026.01.05.697752v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nmicrobiol.2016.48"},{"key":"2026010702152090000_2026.01.05.697752v1.2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3000106"},{"key":"2026010702152090000_2026.01.05.697752v1.3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.252529799"},{"key":"2026010702152090000_2026.01.05.697752v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2019.08.012"},{"key":"2026010702152090000_2026.01.05.697752v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2021.01.005"},{"key":"2026010702152090000_2026.01.05.697752v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.01.001"},{"key":"2026010702152090000_2026.01.05.697752v1.7","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2023.1157956"},{"key":"2026010702152090000_2026.01.05.697752v1.8","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.641817"},{"key":"2026010702152090000_2026.01.05.697752v1.9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1006005"},{"key":"2026010702152090000_2026.01.05.697752v1.10","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2020.00160"},{"key":"2026010702152090000_2026.01.05.697752v1.11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0202513"},{"key":"2026010702152090000_2026.01.05.697752v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msab329"},{"key":"2026010702152090000_2026.01.05.697752v1.13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.chem-ph\/9512004"},{"key":"2026010702152090000_2026.01.05.697752v1.14","doi-asserted-by":"publisher","DOI":"10.1534\/genetics.118.301719"},{"key":"2026010702152090000_2026.01.05.697752v1.15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl135"},{"key":"2026010702152090000_2026.01.05.697752v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/ismej.2014.60"},{"key":"2026010702152090000_2026.01.05.697752v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/S0168-9525(01)02447-7"},{"key":"2026010702152090000_2026.01.05.697752v1.18","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.micro.60.080805.142300"},{"key":"2026010702152090000_2026.01.05.697752v1.19","doi-asserted-by":"publisher","DOI":"10.1002\/bies.201300037"},{"key":"2026010702152090000_2026.01.05.697752v1.20","doi-asserted-by":"publisher","DOI":"10.1126\/science.1114057"},{"key":"2026010702152090000_2026.01.05.697752v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcf.2013.04.003"},{"key":"2026010702152090000_2026.01.05.697752v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-14508-5"},{"key":"2026010702152090000_2026.01.05.697752v1.23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1002651"},{"key":"2026010702152090000_2026.01.05.697752v1.24","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.01377-14"},{"key":"2026010702152090000_2026.01.05.697752v1.25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.0010015"},{"key":"2026010702152090000_2026.01.05.697752v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.mrfmmm.2006.01.020"},{"key":"2026010702152090000_2026.01.05.697752v1.27","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msw071"},{"key":"2026010702152090000_2026.01.05.697752v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-23622-w"},{"key":"2026010702152090000_2026.01.05.697752v1.29","doi-asserted-by":"publisher","DOI":"10.1007\/s00253-008-1512-4"},{"key":"2026010702152090000_2026.01.05.697752v1.30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1514974112"},{"key":"2026010702152090000_2026.01.05.697752v1.31","doi-asserted-by":"publisher","DOI":"10.1086\/285289"},{"key":"2026010702152090000_2026.01.05.697752v1.32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3002418"},{"key":"2026010702152090000_2026.01.05.697752v1.33","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msaa007"},{"key":"2026010702152090000_2026.01.05.697752v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-017-0283-7"},{"key":"2026010702152090000_2026.01.05.697752v1.35","doi-asserted-by":"publisher","DOI":"10.1093\/nargab\/lqaa033"},{"key":"2026010702152090000_2026.01.05.697752v1.36","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2017.00072"},{"key":"2026010702152090000_2026.01.05.697752v1.37","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay4199"},{"key":"2026010702152090000_2026.01.05.697752v1.38","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3564"},{"key":"2026010702152090000_2026.01.05.697752v1.39","doi-asserted-by":"publisher","DOI":"10.1038\/nature24287"},{"key":"2026010702152090000_2026.01.05.697752v1.40","doi-asserted-by":"publisher","DOI":"10.7554\/elife.81979"},{"key":"2026010702152090000_2026.01.05.697752v1.41","doi-asserted-by":"publisher","DOI":"10.1126\/science.add1417"},{"key":"2026010702152090000_2026.01.05.697752v1.42","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac023"},{"key":"2026010702152090000_2026.01.05.697752v1.43","doi-asserted-by":"publisher","DOI":"10.3390\/microorganisms11010177"},{"key":"2026010702152090000_2026.01.05.697752v1.44","doi-asserted-by":"publisher","DOI":"10.1128\/mSphere.00535-21"},{"key":"2026010702152090000_2026.01.05.697752v1.45","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892127"},{"key":"2026010702152090000_2026.01.05.697752v1.46","doi-asserted-by":"publisher","DOI":"10.1074\/jbc.M117.805499"},{"key":"2026010702152090000_2026.01.05.697752v1.47","doi-asserted-by":"publisher","DOI":"10.1002\/jemt.1060190408"},{"key":"2026010702152090000_2026.01.05.697752v1.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.femsle.2004.09.004"},{"key":"2026010702152090000_2026.01.05.697752v1.49","doi-asserted-by":"publisher","DOI":"10.1128\/AEM.01532-10"},{"key":"2026010702152090000_2026.01.05.697752v1.50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1917820117"},{"key":"2026010702152090000_2026.01.05.697752v1.51","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2021.0243"},{"key":"2026010702152090000_2026.01.05.697752v1.52","doi-asserted-by":"publisher","DOI":"10.1038\/nrmicro.2018.8"},{"key":"2026010702152090000_2026.01.05.697752v1.53","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2021.745592"},{"key":"2026010702152090000_2026.01.05.697752v1.54","doi-asserted-by":"publisher","DOI":"10.1128\/JB.185.24.7247-7256.2003"},{"key":"2026010702152090000_2026.01.05.697752v1.55","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1316894110"},{"key":"2026010702152090000_2026.01.05.697752v1.56","doi-asserted-by":"publisher","DOI":"10.1101\/2024.03.08.584059"},{"key":"2026010702152090000_2026.01.05.697752v1.57","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000798"},{"key":"2026010702152090000_2026.01.05.697752v1.58","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0050016"},{"key":"2026010702152090000_2026.01.05.697752v1.59","doi-asserted-by":"publisher","DOI":"10.1002\/prot.10423"},{"key":"2026010702152090000_2026.01.05.697752v1.60","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2002-3-5-research0024"},{"key":"2026010702152090000_2026.01.05.697752v1.61","doi-asserted-by":"publisher","DOI":"10.1038\/nature11184"},{"key":"2026010702152090000_2026.01.05.697752v1.62","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3000862"},{"key":"2026010702152090000_2026.01.05.697752v1.63","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.genet.38.072902.091600"},{"key":"2026010702152090000_2026.01.05.697752v1.64","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaf761"},{"key":"2026010702152090000_2026.01.05.697752v1.65","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-60327-853-9_6"},{"key":"2026010702152090000_2026.01.05.697752v1.66","doi-asserted-by":"publisher","DOI":"10.1038\/s41564-025-02062-z"},{"key":"2026010702152090000_2026.01.05.697752v1.67","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30857-9"},{"key":"2026010702152090000_2026.01.05.697752v1.68","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2023.0505"},{"key":"2026010702152090000_2026.01.05.697752v1.69","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511623486"},{"key":"2026010702152090000_2026.01.05.697752v1.70","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"2026010702152090000_2026.01.05.697752v1.71","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03021"},{"key":"2026010702152090000_2026.01.05.697752v1.72","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu153"},{"key":"2026010702152090000_2026.01.05.697752v1.73","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02090-4"},{"key":"2026010702152090000_2026.01.05.697752v1.74","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-421"},{"key":"2026010702152090000_2026.01.05.697752v1.75","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaa213"},{"key":"2026010702152090000_2026.01.05.697752v1.76","doi-asserted-by":"crossref","unstructured":"BEDOPS: high-performance genomic feature operations | Bioinformatics | Oxford Academic https:\/\/academic.oup.com\/bioinformatics\/article\/28\/14\/1919\/218826.","DOI":"10.1093\/bioinformatics\/bts277"},{"key":"2026010702152090000_2026.01.05.697752v1.77","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty191"},{"key":"2026010702152090000_2026.01.05.697752v1.78","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa913"},{"key":"2026010702152090000_2026.01.05.697752v1.79","unstructured":"Eddy, Sean HMMER. http:\/\/hmmer.org\/."},{"key":"2026010702152090000_2026.01.05.697752v1.80","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2004-5-2-r12"},{"key":"2026010702152090000_2026.01.05.697752v1.81","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04296"},{"key":"2026010702152090000_2026.01.05.697752v1.82","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3988"},{"key":"2026010702152090000_2026.01.05.697752v1.83","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae311"},{"key":"2026010702152090000_2026.01.05.697752v1.84","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae268"},{"key":"2026010702152090000_2026.01.05.697752v1.85","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-025-02625-2"},{"key":"2026010702152090000_2026.01.05.697752v1.86","unstructured":"Chambers, D. (2025). d-chambers\/dbscan1d."},{"key":"2026010702152090000_2026.01.05.697752v1.87","unstructured":"B\u0159inda, K. (2025). karel-brinda\/attotree."},{"key":"2026010702152090000_2026.01.05.697752v1.88","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01762"},{"key":"2026010702152090000_2026.01.05.697752v1.89","doi-asserted-by":"publisher","DOI":"10.1093\/sysbio\/20.4.406"},{"key":"2026010702152090000_2026.01.05.697752v1.90","doi-asserted-by":"publisher","DOI":"10.1093\/jac\/dkaa390"},{"key":"2026010702152090000_2026.01.05.697752v1.91","doi-asserted-by":"publisher","DOI":"10.1186\/s40793-024-00659-1"},{"key":"2026010702152090000_2026.01.05.697752v1.92","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0022594"},{"key":"2026010702152090000_2026.01.05.697752v1.93","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/mst030"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.01.05.697752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T10:15:31Z","timestamp":1767780931000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.01.05.697752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":93,"URL":"https:\/\/doi.org\/10.64898\/2026.01.05.697752","relation":{},"subject":[],"published":{"date-parts":[[2026,1,5]]},"subtype":"preprint"}}