@article{mbs:/content/journal/mgen/10.1099/mgen.0.000670, author = "Horesh, Gal and Taylor-Brown, Alyce and McGimpsey, Stephanie and Lassalle, Florent and Corander, Jukka and Heinz, Eva and Thomson, Nicholas R.", title = "Different evolutionary trends form the twilight zone of the bacterial pan-genome", journal= "Microbial Genomics", year = "2021", volume = "7", number = "9", pages = "", doi = "https://doi.org/10.1099/mgen.0.000670", url = "https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.000670", publisher = "Microbiology Society", issn = "2057-5858", type = "Journal Article", keywords = "pan-genome", keywords = "E. coli", keywords = "evolutionary dynamics", keywords = "HGT", eid = "000670", abstract = "The pan-genome is defined as the combined set of all genes in the gene pool of a species. Pan-genome analyses have been very useful in helping to understand different evolutionary dynamics of bacterial species: an open pan-genome often indicates a free-living lifestyle with metabolic versatility, while closed pan-genomes are linked to host-restricted, ecologically specialized bacteria. A detailed understanding of the species pan-genome has also been instrumental in tracking the phylodynamics of emerging drug resistance mechanisms and drug-resistant pathogens. However, current approaches to analyse a species’ pan-genome do not take the species population structure into account, nor do they account for the uneven sampling of different lineages, as is commonplace due to over-sampling of clinically relevant representatives. Here we present the application of a population structure-aware approach for classifying genes in a pan-genome based on within-species distribution. We demonstrate our approach on a collection of 7500 Escherichia coli genomes, one of the most-studied bacterial species and used as a model for an open pan-genome. We reveal clearly distinct groups of genes, clustered by different underlying evolutionary dynamics, and provide a more biologically informed and accurate description of the species’ pan-genome.", }