{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:21:07Z","timestamp":1768519267898,"version":"3.49.0"},"posted":{"date-parts":[[2024,12,20]]},"group-title":"Bioinformatics","reference-count":62,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,1,13]]},"abstract":"<jats:p>\n                  Bacterial genomes exhibit significant variation in gene content and sequence identity. Pangenome analyses explore this diversity by classifying genes into core and accessory clusters of orthologous groups (COGs). However, strict sequence identity cutoffs can misclassify divergent alleles as different genes, inflating accessory gene counts. CLARC (Connected Linkage and Alignment Redefinition of COGs) [\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/IndraGonz\/CLARC\">https:\/\/github.com\/IndraGonz\/CLARC<\/jats:ext-link>\n                  ] improves pangenome analyses by condensing accessory COGs using functional annotation and linkage information. Through this approach, orthologous groups are consolidated into more practical units of selection. Analyzing 8,000+\n                  <jats:italic>Streptococcus pneumoniae<\/jats:italic>\n                  genomes, CLARC reduced accessory gene estimates by more than 30% and improved evolutionary predictions based on accessory gene frequencies. By refining COG definitions, CLARC offers critical insights into bacterial evolution, aiding genetic studies across diverse populations.\n                <\/jats:p>","DOI":"10.1101\/2024.12.18.629228","type":"posted-content","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T15:35:18Z","timestamp":1734708918000},"source":"Crossref","is-referenced-by-count":0,"title":["Linkage-based ortholog refinement in bacterial pangenomes with CLARC"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2040-956X","authenticated-orcid":false,"given":"Indra","family":"Gonz\u00e1lez Ojeda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7849-8078","authenticated-orcid":false,"given":"Samantha G.","family":"Palace","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3607-0938","authenticated-orcid":false,"given":"Pamela P.","family":"Martinez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8611-5241","authenticated-orcid":false,"given":"Taj","family":"Azarian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lindsay R.","family":"Grant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6051-1484","authenticated-orcid":false,"given":"Laura L.","family":"Hammitt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William P.","family":"Hanage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1504-9213","authenticated-orcid":false,"given":"Marc","family":"Lipsitch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025011600151622000_2024.12.18.629228v2.1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1000344"},{"key":"2025011600151622000_2024.12.18.629228v2.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41579-020-0368-1"},{"key":"2025011600151622000_2024.12.18.629228v2.3","doi-asserted-by":"publisher","DOI":"10.1093\/femsre\/fuac031"},{"key":"2025011600151622000_2024.12.18.629228v2.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41579-021-00650-4"},{"key":"2025011600151622000_2024.12.18.629228v2.5","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.00644-19"},{"key":"2025011600151622000_2024.12.18.629228v2.6","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-021-07829-2"},{"key":"2025011600151622000_2024.12.18.629228v2.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92501-8"},{"key":"2025011600151622000_2024.12.18.629228v2.8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0506758102"},{"key":"2025011600151622000_2024.12.18.629228v2.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41396-020-00867-w"},{"key":"2025011600151622000_2024.12.18.629228v2.10","doi-asserted-by":"crossref","unstructured":"Molari, Marco and Shaw Liam P. and Neher Richard A. Evolutionary dynamics of genome structure and content among closely related bacteria, July 2024. Pages: 2024.07.08.602537 Section: New Results.","DOI":"10.1101\/2024.07.08.602537"},{"key":"2025011600151622000_2024.12.18.629228v2.11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv421"},{"key":"2025011600151622000_2024.12.18.629228v2.12","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx977"},{"key":"2025011600151622000_2024.12.18.629228v2.13","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giz119"},{"key":"2025011600151622000_2024.12.18.629228v2.14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007732"},{"key":"2025011600151622000_2024.12.18.629228v2.15","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02090-4"},{"key":"2025011600151622000_2024.12.18.629228v2.16","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx117"},{"key":"2025011600151622000_2024.12.18.629228v2.17","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-024-03312-9"},{"key":"2025011600151622000_2024.12.18.629228v2.18","unstructured":"Maximillian G. Marin , Christoph Wippel , Natalia Quinones-Olvera , Mahboobeh Behruznia , et al. Analysis of the limited M.tuberculosis accessory genome reveals potential pitfalls of pan-genome analysis approaches, March 2024. Pages: 2024.03.21.586149 Section: New Results."},{"key":"2025011600151622000_2024.12.18.629228v2.19","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-023-03089-3"},{"key":"2025011600151622000_2024.12.18.629228v2.20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1006280"},{"key":"2025011600151622000_2024.12.18.629228v2.21","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.78533"},{"key":"2025011600151622000_2024.12.18.629228v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31858-4"},{"key":"2025011600151622000_2024.12.18.629228v2.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2019.04.021"},{"key":"2025011600151622000_2024.12.18.629228v2.24","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-0997-x"},{"key":"2025011600151622000_2024.12.18.629228v2.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2020.12.004"},{"key":"2025011600151622000_2024.12.18.629228v2.26","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2010-11-10-r107"},{"key":"2025011600151622000_2024.12.18.629228v2.27","doi-asserted-by":"publisher","DOI":"10.1126\/science.add1417"},{"key":"2025011600151622000_2024.12.18.629228v2.28","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.1377"},{"key":"2025011600151622000_2024.12.18.629228v2.29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0024704"},{"key":"2025011600151622000_2024.12.18.629228v2.30","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-017-0337-x"},{"key":"2025011600151622000_2024.12.18.629228v2.31","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3000878"},{"key":"2025011600151622000_2024.12.18.629228v2.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.idc.2015.07.009"},{"key":"2025011600151622000_2024.12.18.629228v2.33","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.10327"},{"key":"2025011600151622000_2024.12.18.629228v2.34","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl158"},{"key":"2025011600151622000_2024.12.18.629228v2.35","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/30.7.1575"},{"key":"2025011600151622000_2024.12.18.629228v2.36","doi-asserted-by":"publisher","DOI":"10.1101\/gr.277733.123"},{"key":"2025011600151622000_2024.12.18.629228v2.37","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/2.1.19"},{"key":"2025011600151622000_2024.12.18.629228v2.38","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3456"},{"key":"2025011600151622000_2024.12.18.629228v2.39","doi-asserted-by":"publisher","DOI":"10.1099\/mgen.0.001021"},{"key":"2025011600151622000_2024.12.18.629228v2.40","doi-asserted-by":"crossref","unstructured":"Athina Gavriilidou , Emilian Paulitz , Christian Resl , Nadine Ziemert , et al. Goldfinder: Unraveling Networks of Gene Co-occurrence and Avoidance in Bacterial Pangenomes, May 2024. Pages: 2024.04.29.591652 Section: New Results.","DOI":"10.1101\/2024.04.29.591652"},{"key":"2025011600151622000_2024.12.18.629228v2.41","doi-asserted-by":"publisher","DOI":"10.1097\/INF.0b013e318201a154"},{"key":"2025011600151622000_2024.12.18.629228v2.42","doi-asserted-by":"publisher","DOI":"10.1099\/mgen.0.000252"},{"key":"2025011600151622000_2024.12.18.629228v2.43","doi-asserted-by":"publisher","DOI":"10.1097\/INF.0b013e3181a06303"},{"key":"2025011600151622000_2024.12.18.629228v2.44","doi-asserted-by":"publisher","DOI":"10.1097\/INF.0000000000001207"},{"key":"2025011600151622000_2024.12.18.629228v2.45","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(03)14022-6"},{"key":"2025011600151622000_2024.12.18.629228v2.46","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2895"},{"key":"2025011600151622000_2024.12.18.629228v2.47","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2015.03.012"},{"key":"2025011600151622000_2024.12.18.629228v2.48","doi-asserted-by":"publisher","DOI":"10.1128\/JCM.00744-15"},{"key":"2025011600151622000_2024.12.18.629228v2.49","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2018.10.021"},{"key":"2025011600151622000_2024.12.18.629228v2.50","doi-asserted-by":"publisher","DOI":"10.1093\/infdis\/jiv167"},{"key":"2025011600151622000_2024.12.18.629228v2.51","doi-asserted-by":"publisher","DOI":"10.1128\/mbio.03355 23"},{"key":"2025011600151622000_2024.12.18.629228v2.52","doi-asserted-by":"publisher","DOI":"10.1002\/cpbi.102"},{"key":"2025011600151622000_2024.12.18.629228v2.53","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu153"},{"key":"2025011600151622000_2024.12.18.629228v2.54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005595"},{"key":"2025011600151622000_2024.12.18.629228v2.55","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btt086"},{"key":"2025011600151622000_2024.12.18.629228v2.56","doi-asserted-by":"publisher","DOI":"10.1101\/gr.241455.118"},{"key":"2025011600151622000_2024.12.18.629228v2.57","doi-asserted-by":"publisher","DOI":"10.1006\/jmbi.1990.9999"},{"key":"2025011600151622000_2024.12.18.629228v2.58","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.33"},{"key":"2025011600151622000_2024.12.18.629228v2.59","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1085"},{"key":"2025011600151622000_2024.12.18.629228v2.60","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-016-1108-8"},{"key":"2025011600151622000_2024.12.18.629228v2.61","doi-asserted-by":"publisher","DOI":"10.1093\/molbev\/msab293"},{"key":"2025011600151622000_2024.12.18.629228v2.62","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.12.18.629228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:42:55Z","timestamp":1768462975000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2024.12.18.629228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1101\/2024.12.18.629228","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1093\/nar\/gkaf488","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,12,20]]},"subtype":"preprint"}}