@article{torrance_burton_diop_bobay_2024, title={Evolution of homologous recombination rates across bacteria}, volume={121}, ISSN={["1091-6490"]}, url={https://doi.org/10.1073/pnas.2316302121}, DOI={10.1073/pnas.2316302121}, abstractNote={Bacteria are nonsexual organisms but are capable of exchanging DNA at diverse degrees through homologous recombination. Intriguingly, the rates of recombination vary immensely across lineages where some species have been described as purely clonal and others as "quasi-sexual." However, estimating recombination rates has proven a difficult endeavor and estimates often vary substantially across studies. It is unclear whether these variations reflect natural variations across populations or are due to differences in methodologies. Consequently, the impact of recombination on bacterial evolution has not been extensively evaluated and the evolution of recombination rate-as a trait-remains to be accurately described. Here, we developed an approach based on Approximate Bayesian Computation that integrates multiple signals of recombination to estimate recombination rates. We inferred the rate of recombination of 162 bacterial species and one archaeon and tested the robustness of our approach. Our results confirm that recombination rates vary drastically across bacteria; however, we found that recombination rate-as a trait-is conserved in several lineages but evolves rapidly in others. Although some traits are thought to be associated with recombination rate (e.g., GC-content), we found no clear association between genomic or phenotypic traits and recombination rate. Overall, our results provide an overview of recombination rate, its evolution, and its impact on bacterial evolution.}, number={11}, journal={PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA}, author={Torrance, Ellis L. and Burton, Corey and Diop, Awa and Bobay, Louis-Marie}, year={2024}, month={Mar} }
 @article{torrance_burton_diop_bobay_2024, title={Evolution of homologous recombination rates across bacteria}, volume={121}, DOI={10.1073/pnas.231630212}, number={18}, journal={Proceedings of the National Academy of Sciences}, author={Torrance, E.L. and Burton, C. and Diop, A. and Bobay, L.M.}, year={2024}, pages={e2316302121} }
 @article{torrance_diop_bobay_2024, title={Homologous Recombination Shapes the Architecture and Evolution of Bacterial Genomes}, url={https://doi.org/10.1101/2024.05.31.596828}, DOI={10.1101/2024.05.31.596828}, abstractNote={Abstract Homologous recombination is a key evolutionary force that varies considerably across bacterial species. However, how the landscape of homologous recombination varies across genes and within individual genomes has only been studied in a few species. Here, we used Approximate Bayesian Computation to estimate the recombination rate along the genomes of 145 bacterial species. Our results show that homologous recombination varies greatly along bacterial genomes and shapes many aspects of genome architecture and evolution. The genomic landscape of recombination presents several key signatures: rates are highest near the origin of replication in most species, patterns of recombination generally appear symmetrical in both replichores ( i.e. replicational halves of circular chromosomes) and most species have genomic hotpots of recombination. Furthermore, many closely related species share conserved landscapes of recombination across orthologs indicating that recombination landscapes are conserved over significant evolutionary distances. We show evidence that recombination drives the evolution of GC-content through increasing the effectiveness of selection and not through biased gene conversion, thereby contributing to an ongoing debate. Finally, we demonstrate that the rate of recombination varies across gene function and that many hotspots of recombination are associated with adaptive and mobile regions often encoding genes involved in pathogenicity.}, author={Torrance, Ellis L. and Diop, Awa and Bobay, Louis-Marie}, year={2024}, month={Jun} }
 @article{diop_bobay_2024, title={Introgression impacts the evolution of bacteria, but species borders are rarely fuzzy}, url={https://doi.org/10.1101/2024.05.09.593304}, DOI={10.1101/2024.05.09.593304}, abstractNote={Abstract Most bacteria engage in gene flow and that this may act as a force maintaining species cohesiveness like it does in sexual organisms. However, introgression (gene flow between the genomic backbone of distinct species) has been reported in bacteria and is associated with fuzzy species borders in some lineages, but its prevalence and impact on the delimitation of bacterial species has not been systematically characterized. Here, we quantified the patterns of introgression across 50 major bacterial lineages. Our results reveal that bacteria present various levels of introgression, with an average of 2% of introgressed core genes and up to 12% in Campylobacter . Furthermore, our results show that some species are more prone to introgression than others within the same genus and introgression is most frequent between highly related species. We found evidence that the various levels of introgression across lineages are likely related to ecological proximity between species. Introgression can occasionally lead to fuzzy species borders, although many of these cases are likely instances of ongoing speciation. Overall, our results indicate that introgression has substantially shaped the evolution and the diversification of bacteria, but this process does not substantially blur species borders.}, author={Diop, Awa and Bobay, Louis-Marie}, year={2024}, month={May} }
 @article{martinez-gutierrez_bobay_2024, title={Prevalence and Dynamics of Genome Rearrangements in Bacteria and Archaea}, url={https://doi.org/10.1101/2024.10.04.616710}, DOI={10.1101/2024.10.04.616710}, abstractNote={The genetic material of bacteria and archaea is organized into various structures and set-ups, attesting that genome architecture is dynamic in these organisms. However, strong selective pressures are also acting to preserve genome organization, and it remains unclear how frequently genomes experience rearrangements and what mechanisms lead to these processes. Here, we assessed the dynamics and the drivers of genomic rearrangements across 121 microbial species. We show that synteny is highly conserved within most species, although several species present exceptionally flexible genomic layouts. Our results show a rather variable pace at which genomic rearrangements occur across bacteria and archaea, pointing to different selective constraints driving the accumulation of genomic changes across species. Importantly, we found that not only inversions but also translocations are highly enriched near the origin of replication (Ori), which suggests that many rearrangements may confer an adaptive advantage to the cell through the relocation of genes that benefit from gene dosage effects. Finally, our results support the view that mobile genetic elements, in particular transposable elements, are the main drivers of genomic translocations and inversions. Overall, our study shows that microbial species present largely stable genomic layouts and identifies key patterns and drivers of genome rearrangements in prokaryotes.}, author={Martinez-Gutierrez, Carolina A. and Bobay, Louis-Marie}, year={2024}, month={Oct} }
 @article{benlaïfaoui_richard_diop_naimi_belkaid_bernet_veyrier_elkrief_bobay_routy_et al._2023, title={Tractidigestivibacter montrealensis</i> sp. nov., a new member of human gut microbiota isolated from a healthy volunteer}, volume={370}, ISSN={1574-6968}, url={http://dx.doi.org/10.1093/femsle/fnad058}, DOI={10.1093/femsle/fnad058}, abstractNote={Abstract
               Strain KD21T, isolated from the fecal sample of a healthy female volunteer, is a strictly anaerobic, non-motile, Gram-staining-positive, saccharolytic small rod that does not produce spores. Strain KD21T was able to grow in the range of temperature 28°C–37°C (optimum, 37 °C), pH 6.0–8.0 (optimum, pH 7.0), and with 0–5.0 g/l NaCl (optimum, 0 g/l NaCl). Bacteria cells reduced nitrates to nitrites. Its major fatty acids were C18:1ω9c, C16:0, C18:0, and summed in feature 8 (C18:1ω7c and/or C18:1ω6c). 16S rRNA gene phylogenetic analysis revealed that KD21T is a member of the genus Tractidigestivibacter and is distinct from any species with validly published names. The sequence showed 98.48% similarity with T. scatoligenes SK9K4T. The DNA G + C content of strain KD21T was 62.6 mol%. The DNA–DNA hybridization and OrthoANI values between strain KD21T and T. scatoligenes SK9K4T were 40.2% and 90.2%, respectively. Differences in phenotypic, phylogenetic, chemotaxonomic, and genomic characteristics indicated that strain KD21T represents a novel species within the genus Tractidigestivibacter. The name T. montrealensis sp. nov. is proposed and the type strain is KD21T (= CSUR Q8103T =  DSM 115111T).}, journal={FEMS Microbiology Letters}, publisher={Oxford University Press (OUP)}, author={Benlaïfaoui, Myriam and Richard, Corentin and Diop, Awa and Naimi, Sabrine and Belkaid, Wiam and Bernet, Eve and Veyrier, Frederic and Elkrief, Arielle and Bobay, Louis-Marie and Routy, Bertrand and et al.}, year={2023} }
 @article{diop_torrance_stott_bobay_2022, title={Gene flow and introgression are pervasive forces shaping the evolution of bacterial species}, volume={23}, ISSN={1474-760X}, url={http://dx.doi.org/10.1186/s13059-022-02809-5}, DOI={10.1186/s13059-022-02809-5}, abstractNote={Abstract
                Background
                Although originally thought to evolve clonally, studies have revealed that most bacteria exchange DNA. However, it remains unclear to what extent gene flow shapes the evolution of bacterial genomes and maintains the cohesion of species.
              
                Results
                Here, we analyze the patterns of gene flow within and between >2600 bacterial species. Our results show that fewer than 10% of bacterial species are truly clonal, indicating that purely asexual species are rare in nature. We further demonstrate that the taxonomic criterion of ~95% genome sequence identity routinely used to define bacterial species does not accurately represent a level of divergence that imposes an effective barrier to gene flow across bacterial species. Interruption of gene flow can occur at various sequence identities across lineages, generally from 90 to 98% genome identity. This likely explains why a ~95% genome sequence identity threshold has empirically been judged as a good approximation to define bacterial species. Our results support a universal mechanism where the availability of identical genomic DNA segments required to initiate homologous recombination is the primary determinant of gene flow and species boundaries in bacteria. We show that these barriers of gene flow remain porous since many distinct species maintain some level of gene flow, similar to introgression in sexual organisms.
              
                Conclusions
                Overall, bacterial evolution and speciation are likely shaped by similar forces driving the evolution of sexual organisms. Our findings support a model where the interruption of gene flow—although not necessarily the initial cause of speciation—leads to the establishment of permanent and irreversible species borders.
              }, number={1}, journal={Genome Biology}, publisher={Springer Science and Business Media LLC}, author={Diop, Awa and Torrance, Ellis L. and Stott, Caroline M. and Bobay, Louis-Marie}, year={2022}, month={Nov} }
 @article{ligaba-osena_salehin_numan_wang_choi_jima_bobay_guo_2022, title={Genome-wide transcriptome analysis of the orphan crop tef (Eragrostis tef (Zucc.) Trotter) under long-term low calcium stress}, volume={12}, ISSN={2045-2322}, url={http://dx.doi.org/10.1038/s41598-022-23844-z}, DOI={10.1038/s41598-022-23844-z}, abstractNote={AbstractCalcium (Ca2+) is one of the essential mineral nutrients for plant growth and development. However, the effects of long-term Ca2+deficiency in orphan crops such as Tef [(Eragrostis tef) (Zucc.) Trotter], which accumulate high levels of Ca in the grains, remained unknown. Tef is a staple crop for nearly 70 million people in East Africa, particularly in Ethiopia and Eritrea. It is one of the most nutrient-dense grains, and is also more resistant to marginal soils and climatic conditions than main cereals like corn, wheat, and rice. In this study, tef plants were grown in a hydroponic solution containing optimum (1 mM) or low (0.01 mM) Ca2+, and plant growth parameters and whole-genome transcriptome were analyzed. Ca+2-deficient plants exhibited leaf necrosis, leaf curling, and growth stunting symptoms. Ca2+deficiency significantly decreased root and shoot Ca, potassium (K), and copper content in both root and shoots. At the same time, it greatly increased root iron (Fe) content, suggesting the role of Ca2+in the uptake and/or translocation of these minerals. Transcriptomic analysis using RNA-seq revealed that members of Ca2+channels, including the cyclic nucleotide-gated channels and glutamate receptor-like channels, Ca2+-transporters, Ca2+-binding proteins and Ca2+-dependent protein kinases were differentially regulated by Ca+2treatment. Moreover, several Fe/metal transporters, including members of vacuolar Fe transporters, yellow stripe-like, natural resistance-associated macrophage protein, and oligo-peptide transporters, were differentially regulated between shoot and root in response to Ca2+treatment. Taken together, our findings suggest that Ca2+deficiency affects plant growth and mineral accumulation by regulating the transcriptomes of several transporters and signaling genes.}, number={1}, journal={Scientific Reports}, publisher={Springer Science and Business Media LLC}, author={Ligaba-Osena, Ayalew and Salehin, Mohammad and Numan, Muhammad and Wang, Xuegeng and Choi, Sang-Chul and Jima, Dereje and Bobay, Louis-Marie and Guo, Wanli}, year={2022}, month={Nov} }
 @article{martinez-hernandez_diop_garcia-heredia_bobay_martinez-garcia_2022, title={Correction to: Unexpected myriad of co-occurring viral strains and species in one of the most abundant and microdiverse viruses on Earth}, volume={16}, url={https://doi.org/10.1038/s41396-021-01182-8}, DOI={10.1038/s41396-021-01182-8}, number={4}, journal={The ISME Journal}, publisher={Springer Science and Business Media LLC}, author={Martinez-Hernandez, Francisco and Diop, Awa and Garcia-Heredia, Inmaculada and Bobay, Louis-Marie and Martinez-Garcia, Manuel}, year={2022}, month={Apr}, pages={1199–1199} }
 @article{buton_bobay_2021, title={Evolution of Chi motifs in Proteobacteria}, volume={11}, url={https://doi.org/10.1093/g3journal/jkaa054}, DOI={10.1093/g3journal/jkaa054}, abstractNote={Abstract
               Homologous recombination is a key pathway found in nearly all bacterial taxa. The recombination complex not only allows bacteria to repair DNA double-strand breaks but also promotes adaption through the exchange of DNA between cells. In Proteobacteria, this process is mediated by the RecBCD complex, which relies on the recognition of a DNA motif named Chi to initiate recombination. The Chi motif has been characterized in Escherichia coli and analogous sequences have been found in several other species from diverse families, suggesting that this mode of action is widespread across bacteria. However, the sequences of Chi-like motifs are known for only five bacterial species: E. coli, Haemophilus influenzae, Bacillus subtilis, Lactococcus lactis, and Staphylococcus aureus. In this study, we detected putative Chi motifs in a large dataset of Proteobacteria and identified four additional motifs sharing high sequence similarity and similar properties to the Chi motif of E. coli in 85 species of Proteobacteria. Most Chi motifs were detected in Enterobacteriaceae and this motif appears well conserved in this family. However, we did not detect Chi motifs for the majority of Proteobacteria, suggesting that different motifs are used in these species. Altogether these results substantially expand our knowledge on the evolution of Chi motifs and on the recombination process in bacteria.}, number={1}, journal={G3 Genes|Genomes|Genetics}, publisher={Oxford University Press (OUP)}, author={Buton, Angélique and Bobay, Louis-Marie}, editor={Zetka, MEditor}, year={2021}, month={Mar}, pages={1–7} }
 @article{martinez-hernandez_diop_garcia-heredia_bobay_martinez-garcia_2022, title={Unexpected myriad of co-occurring viral strains and species in one of the most abundant and microdiverse viruses on Earth}, volume={16}, ISSN={1751-7362 1751-7370}, url={http://dx.doi.org/10.1038/s41396-021-01150-2}, DOI={10.1038/s41396-021-01150-2}, abstractNote={Abstract
               Viral genetic microdiversity drives adaptation, pathogenicity, and speciation and has critical consequences for the viral-host arms race occurring at the strain and species levels, which ultimately impact microbial community structure and biogeochemical cycles. Despite the fact that most efforts have focused on viral macrodiversity, little is known about the microdiversity of ecologically important viruses on Earth. Recently, single-virus genomics discovered the putatively most abundant ocean virus in temperate and tropical waters: the uncultured dsDNA virus vSAG 37-F6 infecting Pelagibacter, the most abundant marine bacteria. In this study, we report the cooccurrence of up to ≈1,500 different viral strains (>95% nucleotide identity) and ≈30 related species (80-95% nucleotide identity) in a single oceanic sample. Viral microdiversity was maintained over space and time, and most alleles were the result of synonymous mutations without any apparent adaptive benefits to cope with host translation codon bias and efficiency. Gene flow analysis used to delimitate species according to the biological species concept (BSC) revealed the impact of recombination in shaping vSAG 37-F6 virus and Pelagibacter speciation. Data demonstrated that this large viral microdiversity somehow mirrors the host species diversity since ≈50% of the 926 analyzed Pelagibacter genomes were found to belong to independent BSC species that do not significantly engage in gene flow with one another. The host range of this evolutionarily successful virus revealed that a single viral species can infect multiple Pelagibacter BSC species, indicating that this virus crosses not only formal BSC barriers but also biomes since viral ancestors are found in freshwater.}, number={4}, journal={The ISME Journal}, publisher={Oxford University Press (OUP)}, author={Martinez-Hernandez, Francisco and Diop, Awa and Garcia-Heredia, Inmaculada and Bobay, Louis-Marie and Martinez-Garcia, Manuel}, year={2022}, pages={1025–1035} }
 @article{harris_torrance_raymann_bobay_2020, title={CoreCruncher</i>: Fast and Robust Construction of Core Genomes in Large Prokaryotic Data Sets}, volume={38}, ISSN={1537-1719}, url={http://dx.doi.org/10.1093/molbev/msaa224}, DOI={10.1093/molbev/msaa224}, abstractNote={Abstract
               The core genome represents the set of genes shared by all, or nearly all, strains of a given population or species of prokaryotes. Inferring the core genome is integral to many genomic analyses, however, most methods rely on the comparison of all the pairs of genomes; a step that is becoming increasingly difficult given the massive accumulation of genomic data. Here, we present CoreCruncher; a program that robustly and rapidly constructs core genomes across hundreds or thousands of genomes. CoreCruncher does not compute all pairwise genome comparisons and uses a heuristic based on the distributions of identity scores to classify sequences as orthologs or paralogs/xenologs. Although it is much faster than current methods, our results indicate that our approach is more conservative than other tools and less sensitive to the presence of paralogs and xenologs. CoreCruncher is freely available from: https://github.com/lbobay/CoreCruncher. CoreCruncher is written in Python 3.7 and can also run on Python 2.7 without modification. It requires the python library Numpy and either Usearch or Blast. Certain options require the programs muscle or mafft.}, number={2}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Harris, Connor D and Torrance, Ellis L and Raymann, Kasie and Bobay, Louis-Marie}, editor={Ouangraoua, AidaEditor}, year={2020}, month={Sep}, pages={727–734} }
 @article{bobay_2020, title={CoreSimul: a forward-in-time simulator of genome evolution for prokaryotes modeling homologous recombination}, volume={21}, url={https://doi.org/10.1186/s12859-020-03619-x}, DOI={10.1186/s12859-020-03619-x}, abstractNote={Abstract
                Background
                Prokaryotes are asexual, but these organisms frequently engage in homologous recombination, a process that differs from meiotic recombination in sexual organisms. Most tools developed to simulate genome evolution either assume sexual reproduction or the complete absence of DNA flux in the population. As a result, very few simulators are adapted to model prokaryotic genome evolution while accounting for recombination. Moreover, many simulators are based on the coalescent, which assumes a neutral model of genomic evolution, and those are best suited for organisms evolving under weak selective pressures, such as animals and plants. In contrast, prokaryotes are thought to be evolving under much stronger selective pressures, suggesting that forward-in-time simulators are better suited for these organisms.
              
                Results
                Here, I present CoreSimul, a forward-in-time simulator of core genome evolution for prokaryotes modeling homologous recombination. Simulations are guided by a phylogenetic tree and incorporate different substitution models, including models of codon selection.
              
                Conclusions
                CoreSimul is a flexible forward-in-time simulator that constitutes a significant addition to the limited list of available simulators applicable to prokaryote genome evolution.
              }, number={1}, journal={BMC Bioinformatics}, publisher={Springer Science and Business Media LLC}, author={Bobay, Louis-Marie}, year={2020}, month={Dec} }
 @article{buton_bobay_2020, title={Evolution of Chi motifs in Proteobacteria}, url={https://doi.org/10.1101/2020.08.13.249359}, DOI={10.1101/2020.08.13.249359}, abstractNote={AbstractHomologous recombination is a key pathway found in nearly all bacterial taxa. The recombination complex allows bacteria to repair DNA double strand breaks but also promotes adaption through the exchange of DNA between cells. In Proteobacteria, this process is mediated by the RecBCD complex, which relies on the recognition of a DNA motif named Chi to initiate recombination. The Chi motif has been characterized inEscherichia coliand analogous sequences have been found in several other species from diverse families, suggesting that this mode of action is widespread across bacteria. However, the sequences of Chi-like motifs are known for only five bacterial species:E. coli, Haemophilus influenzae,Bacillus subtilis,Lactococcus lactisandStaphylococcus aureus. In this study we detected putative Chi motifs in a large dataset of Proteobacteria and we identified four additional motifs sharing high sequence similarity and similar properties to the Chi motif ofE. coliin 85 species of Proteobacteria. Most Chi motifs were detected inEnterobacteriaceaeand this motif appears well conserved in this family. However, we did not detect Chi motifs for the majority of Proteobacteria, suggesting that different motifs are used in these species. Altogether these results substantially expand our knowledge on the evolution of Chi motifs and on the recombination process in bacteria.}, author={Buton, Angélique and Bobay, Louis-Marie}, year={2020}, month={Aug} }
 @article{stott_bobay_2020, title={Impact of homologous recombination on core genome phylogenies}, url={https://doi.org/10.21203/rs.3.rs-29898/v2}, DOI={10.21203/rs.3.rs-29898/v2}, abstractNote={Abstract
        Background. Core genome phylogenies are widely used to build the evolutionary history of individual prokaryote species. By using hundreds or thousands of shared genes, these approaches are the gold standard to reconstruct the relationships of large sets of strains. However, there is growing evidence that bacterial strains exchange DNA through homologous recombination at rates that vary widely across prokaryote species, indicating that core genome phylogenies might not be able to reconstruct true phylogenies when recombination rate is high. Few attempts have been made to evaluate the robustness of core genome phylogenies to recombination, but some analyses suggest that reconstructed trees are not always accurate.Results. In this study, we tested the robustness of core genome phylogenies to various levels of recombination rates. By analyzing simulated and empirical data, we observed that core genome phylogenies are relatively robust to recombination rates; nevertheless, our results suggest that many reconstructed trees are not completely accurate even when bootstrap supports are high. We found that some core genome phylogenies are highly robust to recombination whereas others are strongly impacted by it, and we identified that the robustness of core genome phylogenies to recombination is highly linked to the levels of selective pressures acting on a species. Stronger selective pressures lead to less accurate tree reconstructions, presumably because selective pressures more strongly bias the routes of DNA transfers, thereby causing phylogenetic artifacts. Conclusions. Overall, these results have important implications for the application of core genome phylogenies in prokaryotes.}, author={Stott, Caroline Marie and Bobay, Louis-Marie}, year={2020}, month={Dec} }
 @article{stott_bobay_2020, title={Impact of homologous recombination on core genome phylogenies}, url={https://doi.org/10.21203/rs.3.rs-29898/v1}, DOI={10.21203/rs.3.rs-29898/v1}, abstractNote={Abstract
        Background. Core genome phylogenies are widely used to build the evolutionary history of individual prokaryote species. By using hundreds or thousands of shared genes, these approaches are the gold standard to reconstruct the relationships of large sets of strains. However, there is growing evidence that bacterial strains exchange DNA through homologous recombination at rates that vary widely across prokaryote species, indicating that core genome phylogenies might not be able to reconstruct true phylogenies when recombination rate is high. Few attempts have been made to evaluate the robustness of core genome phylogenies to recombination, but some analyses suggest that reconstructed trees are not always accurate.Results. In this study, we tested the robustness of core genome phylogenies to various levels of recombination rates. By analyzing simulated and empirical data, we observed that core genome phylogenies are relatively robust to recombination rates; nevertheless, our results suggest that many reconstructed trees are not completely accurate even when bootstrap supports are high. We found that some core genome phylogenies are highly robust to recombination whereas others are strongly impacted by it, and we identified that the robustness of core genome phylogenies to recombination is highly linked to the levels of selective pressures acting on a species. Stronger selective pressures lead to less accurate tree reconstructions, presumably because selective pressures more strongly bias the routes of DNA transfers, thereby causing phylogenetic artifacts.Conclusions. Overall these results have important implications for the application of core genome phylogenies in prokaryotes.}, author={Stott, Caroline Marie and Bobay, Louis-Marie}, year={2020}, month={Jun} }
 @article{stott_bobay_2020, title={Impact of homologous recombination on core genome phylogenies}, volume={21}, ISSN={1471-2164}, url={http://dx.doi.org/10.1186/s12864-020-07262-x}, DOI={10.1186/s12864-020-07262-x}, abstractNote={AbstractBackgroundCore genome phylogenies are widely used to build the evolutionary history of individual prokaryote species. By using hundreds or thousands of shared genes, these approaches are the gold standard to reconstruct the relationships of large sets of strains. However, there is growing evidence that bacterial strains exchange DNA through homologous recombination at rates that vary widely across prokaryote species, indicating that core genome phylogenies might not be able to reconstruct true phylogenies when recombination rate is high. Few attempts have been made to evaluate the robustness of core genome phylogenies to recombination, but some analyses suggest that reconstructed trees are not always accurate.ResultsIn this study, we tested the robustness of core genome phylogenies to various levels of recombination rates. By analyzing simulated and empirical data, we observed that core genome phylogenies are relatively robust to recombination rates; nevertheless, our results suggest that many reconstructed trees are not completely accurate even when bootstrap supports are high. We found that some core genome phylogenies are highly robust to recombination whereas others are strongly impacted by it, and we identified that the robustness of core genome phylogenies to recombination is highly linked to the levels of selective pressures acting on a species. Stronger selective pressures lead to less accurate tree reconstructions, presumably because selective pressures more strongly bias the routes of DNA transfers, thereby causing phylogenetic artifacts.ConclusionsOverall, these results have important implications for the application of core genome phylogenies in prokaryotes.}, number={1}, journal={BMC Genomics}, publisher={Springer Science and Business Media LLC}, author={Stott, Caroline M. and Bobay, Louis-Marie}, year={2020}, month={Nov} }
 @article{bobay_o’donnell_ochman_2020, title={Recombination events are concentrated in the spike protein region of Betacoronaviruses}, volume={16}, url={https://doi.org/10.1371/journal.pgen.1009272}, DOI={10.1371/journal.pgen.1009272}, abstractNote={The Betacoronaviruses comprise multiple subgenera whose members have been implicated in human disease. As with SARS, MERS and now SARS-CoV-2, the origin and emergence of new variants are often attributed to events of recombination that alter host tropism or disease severity. In most cases, recombination has been detected by searches for excessively similar genomic regions in divergent strains; however, such analyses are complicated by the high mutation rates of RNA viruses, which can produce sequence similarities in distant strains by convergent mutations. By applying a genome-wide approach that examines the source of individual polymorphisms and that can be tested against null models in which recombination is absent and homoplasies can arise only by convergent mutations, we examine the extent and limits of recombination in Betacoronaviruses. We find that recombination accounts for nearly 40% of the polymorphisms circulating in populations and that gene exchange occurs almost exclusively among strains belonging to the same subgenus. Although experimental studies have shown that recombinational exchanges occur at random along the coronaviral genome, in nature, they are vastly overrepresented in regions controlling viral interaction with host cells.}, number={12}, journal={PLOS Genetics}, publisher={Public Library of Science (PLoS)}, author={Bobay, Louis-Marie and O’Donnell, Angela C. and Ochman, Howard}, editor={Tang, HuaEditor}, year={2020}, month={Dec}, pages={e1009272} }
 @article{bobay_wissel_raymann_2020, title={Strain Structure and Dynamics Revealed by Targeted Deep Sequencing of the Honey Bee Gut Microbiome}, volume={5}, ISSN={2379-5042}, url={http://dx.doi.org/10.1128/msphere.00694-20}, DOI={10.1128/msphere.00694-20}, abstractNote={The factors driving fine-scale composition and dynamics of gut microbial communities are poorly understood. In this study, we used metagenomic amplicon deep sequencing to decipher the strain dynamics of two key members of the honey bee gut microbiome. Using this high-throughput and cost-effective approach, we were able to confirm results from previous large-scale whole-genome shotgun (WGS) metagenomic sequencing studies while also gaining additional insights into the community dynamics of two core members of the honey bee gut microbiome. Moreover, we were able to show that cryptic strains are not responsible for the observed variations in microbiome composition across bees.}, number={4}, journal={mSphere}, publisher={American Society for Microbiology}, author={Bobay, Louis-Marie and Wissel, Emily F. and Raymann, Kasie}, editor={Campbell, Barbara J.Editor}, year={2020}, month={Aug} }
 @misc{bobay_2020, title={The Prokaryotic Species Concept and Challenges}, ISBN={9783030382803 9783030382810}, url={http://dx.doi.org/10.1007/978-3-030-38281-0_2}, DOI={10.1007/978-3-030-38281-0_2}, abstractNote={Abstract
Species constitute the fundamental units of taxonomy and an ideal species definition would embody groups of genetically cohesive organisms reflecting their shared history, traits, and ecology. In contrast to animals and plants, where genetic cohesion can essentially be characterized by sexual compatibility and population structure, building a biologically relevant species definition remains a challenging endeavor in prokaryotes. Indeed, the structure, ecology, and dynamics of microbial populations are still largely enigmatic, and many aspects of prokaryotic genomics deviate from sexual organisms. In this chapter, I present the main concepts and operational definitions commonly used to designate microbial species. I further emphasize how these different concepts accommodate the idiosyncrasies of prokaryotic genomics, in particular, the existence of a core- and a pangenome. Although prokaryote genomics is undoubtedly different from animals and plants, there is growing evidence that gene flow—similar to sexual reproduction—plays a significant role in shaping the genomic cohesiveness of microbial populations, suggesting that, to some extent, a species definition based on the Biological Species Concept is applicable to prokaryotes. Building a satisfying species definition remains to be accomplished, but the integration of genomic data, ecology, and bioinformatics tools has expanded our comprehension of prokaryotic populations and their dynamics.}, journal={The Pangenome}, publisher={Springer International Publishing}, author={Bobay, Louis-Marie}, year={2020}, pages={21–49} }
 @article{bobay_raymann_2019, title={Population Genetics of Host-Associated Microbiomes}, volume={5}, ISSN={2198-6428}, url={http://dx.doi.org/10.1007/s40610-019-00122-y}, DOI={10.1007/s40610-019-00122-y}, number={3}, journal={Current Molecular Biology Reports}, publisher={Springer Science and Business Media LLC}, author={Bobay, Louis-Marie and Raymann, Kasie}, year={2019}, month={Jul}, pages={128–139} }
 @article{bobay_ochman_2018, title={Biological species in the viral world}, volume={115}, url={https://doi.org/10.1073/pnas.1717593115}, DOI={10.1073/pnas.1717593115}, abstractNote={Significance
          The biological species concept (BSC) has served as the basis for defining species for over 75 years. Members of a biological species are defined by their ability to exchange genetic material, and it was originally thought that asexual lineages were not amenable to species-level classification based on the BSC since clonal individuals are reproductively isolated from one another. In this study, we demonstrate that the rates and patterns of gene exchange in acellular organisms (viruses and bacteriophages) allow the assignment of true biological species, an essential step to organizing the tree of life. Our results show that a universal species definition, based on the BSC, can be used to define biological species in all major lifeforms.}, number={23}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Bobay, Louis-Marie and Ochman, Howard}, year={2018}, month={Jun}, pages={6040–6045} }
 @article{bobay_ellis_ochman_2018, title={ConSpeciFix</i>: classifying prokaryotic species based on gene flow}, volume={34}, ISSN={1367-4803 1367-4811}, url={http://dx.doi.org/10.1093/bioinformatics/bty400}, DOI={10.1093/bioinformatics/bty400}, abstractNote={Abstract
               
                  Summary
                  Classification of prokaryotic species is usually based on sequence similarity thresholds, which are easy to apply but lack a biologically-relevant foundation. Here, we present ConSpeciFix, a program that classifies prokaryotes into species using criteria set forth by the Biological Species Concept, thereby unifying species definition in all domains of life.
               
               
                  Availability and implementation
                  ConSpeciFix’s webserver is freely available at www.conspecifix.com. The local version of the program can be freely downloaded from https://github.com/Bobay-Ochman/ConSpeciFix. ConSpeciFix is written in Python 2.7 and requires the following dependencies: Usearch, MCL, MAFFT and RAxML.
               }, number={21}, journal={Bioinformatics}, publisher={Oxford University Press (OUP)}, author={Bobay, Louis-Marie and Ellis, Brian Shin-Hua and Ochman, Howard}, editor={Hancock, JohnEditor}, year={2018}, month={May}, pages={3738–3740} }
 @article{bobay_ochman_2018, title={Factors driving effective population size and pan-genome evolution in bacteria}, volume={18}, url={https://doi.org/10.1186/s12862-018-1272-4}, DOI={10.1186/s12862-018-1272-4}, abstractNote={Knowledge of population-level processes is essential to understanding the efficacy of selection operating within a species. However, attempts at estimating effective population sizes (Ne) are particularly challenging in bacteria due to their extremely large census populations sizes, varying rates of recombination and arbitrary species boundaries. In this study, we estimated Ne for 153 species (152 bacteria and one archaeon) defined under a common framework and found that ecological lifestyle and growth rate were major predictors of Ne; and that contrary to theoretical expectations, Ne was unaffected by recombination rate. Additionally, we found that Ne shapes the evolution and diversity of total gene repertoires of prokaryotic species. Together, these results point to a new model of genome architecture evolution in prokaryotes, in which pan-genome sizes, not individual genome sizes, are governed by drift-barrier evolution.}, number={1}, journal={BMC Evolutionary Biology}, publisher={Springer Science and Business Media LLC}, author={Bobay, Louis-Marie and Ochman, Howard}, year={2018}, month={Dec} }
 @article{bobay_2018, title={Heredity: A Very Short Introduction}, volume={9}, url={https://doi.org/10.1093/jmammal/gyy106}, DOI={10.1093/jmammal/gyy106}, journal={Journal of Mammalogy}, publisher={Oxford University Press (OUP)}, author={Bobay, Louis-Marie}, year={2018}, month={Oct} }
 @article{raymann_bobay_moran_2017, title={Antibiotics reduce genetic diversity of core species in the honeybee gut microbiome}, volume={27}, ISSN={0962-1083 1365-294X}, url={http://dx.doi.org/10.1111/mec.14434}, DOI={10.1111/mec.14434}, abstractNote={AbstractThe gut microbiome plays a key role in animal health, and perturbing it can have detrimental effects. One major source of perturbation to microbiomes, in humans and human‐associated animals, is exposure to antibiotics. Most studies of how antibiotics affect the microbiome have used amplicon sequencing of highly conserved 16S rRNA sequences, as in a recent study showing that antibiotic treatment severely alters the species‐level composition of the honeybee gut microbiome. But because the standard 16S rRNA‐based methods cannot resolve closely related strains, strain‐level changes could not be evaluated. To address this gap, we used amplicon sequencing of protein‐coding genes to assess effects of antibiotics on fine‐scale genetic diversity of the honeybee gut microbiota. We followed the population dynamics of alleles within two dominant core species of the bee gut community, Gilliamella apicola and Snodgrassella alvi, following antibiotic perturbation. Whereas we observed a large reduction in genetic diversity in G. apicola, S. alvi diversity was mostly unaffected. The reduction in G. apicola diversity accompanied an increase in the frequency of several alleles, suggesting resistance to antibiotic treatment. We find that antibiotic perturbation can cause major shifts in diversity and that the extent of these shifts can vary substantially across species. Thus, antibiotics impact not only species composition, but also allelic diversity within species, potentially affecting hosts if variants with particular functions are reduced or eliminated. Overall, we show that amplicon sequencing of protein‐coding genes, without clustering into operational taxonomic units, provides an accurate picture of the fine‐scale dynamics of microbial communities over time.}, number={8}, journal={Molecular Ecology}, publisher={Wiley}, author={Raymann, Kasie and Bobay, Louis‐Marie and Moran, Nancy A.}, year={2017}, month={Dec}, pages={2057–2066} }
 @article{bobay_ochman_2017, title={Biological Species Are Universal across Life’s Domains}, volume={9}, ISSN={1759-6653}, url={http://dx.doi.org/10.1093/gbe/evx026}, DOI={10.1093/gbe/evx026}, abstractNote={Delineation of species is fundamental to organizing and understanding biological diversity. The most widely applied criterion for distinguishing species is the Biological Species Concept (BSC), which defines species as groups of interbreeding individuals that remain reproductively isolated from other such groups. The BSC has broad appeal; however, many organisms, most notably asexual lineages, cannot be classified according to the BSC. Despite their exclusively asexual mode of reproduction, Bacteria and Archaea can transfer and exchange genes though homologous recombination. Here we show that barriers to homologous gene exchange define biological species in prokaryotes with the same efficacy as in sexual eukaryotes. By analyzing the impact of recombination on the polymorphisms in thousands of genome sequences, we find that over half of named bacterial species undergo continuous recombination among sequenced constituents, indicative of true biological species. However, nearly a quarter of named bacterial species show sharp discontinuities and comprise multiple biological species. These interruptions of gene flow are not a simple function of genome identity, indicating that bacterial speciation does not uniformly proceed by the gradual divergence of genome sequences. The same genomic approach based on recombinant polymorphisms retrieves known species boundaries in sexually reproducing eukaryotes. Thus, a single biological species definition based on gene flow, once thought to be limited only to sexually reproducing organisms, is applicable to all cellular lifeforms.}, number={3}, journal={Genome Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Bobay, Louis-Marie and Ochman, Howard}, year={2017}, month={Mar}, pages={491–501} }
 @article{bobay_ochman_2017, title={Impact of Recombination on the Base Composition of Bacteria and Archaea}, volume={34}, ISSN={0737-4038 1537-1719}, url={http://dx.doi.org/10.1093/molbev/msx189}, DOI={10.1093/molbev/msx189}, abstractNote={The mutational process in bacteria is biased toward A and T, and most species are GC-rich relative to the mutational input to their genome. It has been proposed that the shift in base composition is an adaptive process-that natural selection operates to increase GC-contents-and there is experimental evidence that bacterial strains with GC-rich versions of genes have higher growth rates than those strains with AT-rich versions expressing identical proteins. Alternatively, a nonadaptive process, GC-biased gene conversion (gBGC), could also increase the GC-content of DNA due to the mechanistic bias of gene conversion events during recombination. To determine what role recombination plays in the base composition of bacterial genomes, we compared the spectrum of nucleotide polymorphisms introduced by recombination in all microbial species represented by large numbers of sequenced strains. We found that recombinant alleles are consistently biased toward A and T, and that the magnitude of AT-bias introduced by recombination is similar to that of mutations. These results indicate that recombination alone, without the intervention of selection, is unlikely to counteract the AT-enrichment of bacterial genomes.}, number={10}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Bobay, Louis-Marie and Ochman, Howard}, year={2017}, month={Jul}, pages={2627–2636} }
 @article{bobay_ochman_2017, title={The Evolution of Bacterial Genome Architecture}, volume={8}, ISSN={1664-8021}, url={http://dx.doi.org/10.3389/fgene.2017.00072}, DOI={10.3389/fgene.2017.00072}, abstractNote={The genome architecture of bacteria and eukaryotes evolves in opposite directions when subject to genetic drift, a difference that can be ascribed to the fact that bacteria exhibit a mutational bias that deletes superfluous sequences, whereas eukaryotes are biased toward large insertions. Expansion of eukaryotic genomes occurs through the addition of non-functional sequences, such as repetitive sequences and transposable elements, whereas variation in bacterial genome size is largely due to the acquisition and loss of functional accessory genes. These properties create the situation in which eukaryotes with very similar numbers of genes can have vastly different genome sizes, while in bacteria, gene number scales linearly with genome size. Some bacterial genomes, however, particularly those of species that undergo bottlenecks due to recent association with hosts, accumulate pseudogenes and mobile elements, conferring them a low gene content relative to their genome size. These non-functional sequences are gradually eroded and eliminated after long-term association with hosts, with the result that obligate symbionts have the smallest genomes of any cellular organism. The architecture of bacterial genomes is shaped by complex and diverse processes, but for most bacterial species, genome size is governed by a non-adaptive process, i.e., genetic drift coupled with a mutational bias towards deletions. Thus, bacteria with small effective population sizes typically have the smallest genomes. Some marine bacteria counter this near-universal trend: despite having immense population sizes, selection, not drift, acts to reduce genome size in response to metabolic constraints in their nutrient-limited environment.}, journal={Frontiers in Genetics}, publisher={Frontiers Media SA}, author={Bobay, Louis-Marie and Ochman, Howard}, year={2017}, month={May} }
 @article{wexler_bao_whitney_bobay_xavier_schofield_barry_russell_tran_goo_et al._2016, title={Human symbionts inject and neutralize antibacterial toxins to persist in the gut}, volume={113}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1525637113}, DOI={10.1073/pnas.1525637113}, abstractNote={Significance
          The microbial community in the human gut represents one of the densest known ecosystems. Community composition has broad impacts on health, and metabolic competition and host selection have both been implicated in shaping these communities. Here, we report that contact-dependent bacterial antagonism also determines the ability of human gut symbionts to persist in the microbiome. Simplified microbiomes, assembled in gnotobiotic mice, reveal effector transmission rates exceeding 1 billion events per minute per gram of colonic contents. Together, these results suggest that human gut symbionts define their closest competitors not only metabolically but also spatially. Moreover, strains within a single species can encode diverse effectors that may provide new avenues for shaping the microbiome to improve human health.}, number={13}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Wexler, Aaron G. and Bao, Yiqiao and Whitney, John C. and Bobay, Louis-Marie and Xavier, Joao B. and Schofield, Whitman B. and Barry, Natasha A. and Russell, Alistair B. and Tran, Bao Q. and Goo, Young Ah and et al.}, year={2016}, month={Mar}, pages={3639–3644} }
 @article{bobay_traverse_ochman_2015, title={Impermanence of bacterial clones}, volume={112}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1501724112}, DOI={10.1073/pnas.1501724112}, abstractNote={
            Bacteria reproduce asexually and pass on a single genome copied from the parent, a reproductive mode that assures the clonal descent of progeny; however, a truly clonal bacterial species is extremely rare. The signal of clonality can be interrupted by gene uptake and exchange, initiating homologous recombination that results in the unique sequence of one clone being incorporated into another. Because recombination occurs sporadically and on local scales, these events are often difficult to recognize, even when considering large samples of completely sequenced genomes. Moreover, several processes can produce the appearance of clonality in populations that undergo frequent recombination. The rates and consequences of recombination have been studied in
            Escherichia coli
            for over 40 y, and, during this time, there have been several shifting views of its clonal status, population structure, and rates of gene exchange. We reexamine the studies and retrace the evolution of the methods that have assessed the extent of DNA flux, largely focusing on its impact on the
            E. coli
            genome.
          }, number={29}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Bobay, Louis-Marie and Traverse, Charles C. and Ochman, Howard}, year={2015}, month={Jul}, pages={8893–8900} }
 @article{douam_bobay_maurin_fresquet_calland_maisse_durand_cosset_féray_lavillette_2016, title={Specialization of Hepatitis C Virus Envelope Glycoproteins for B Lymphocytes in Chronically Infected Patients}, volume={90}, ISSN={0022-538X 1098-5514}, url={http://dx.doi.org/10.1128/jvi.02516-15}, DOI={10.1128/jvi.02516-15}, abstractNote={ABSTRACT
          Hepatitis C virus (HCV) productively infects hepatocytes. Virion surface glycoproteins E1 and E2 play a major role in this restricted cell tropism by mediating virus entry into particular cell types. However, several pieces of evidence have suggested the ability of patient-derived HCV particles to infect peripheral blood mononuclear cells. The viral determinants and mechanisms mediating such events remain poorly understood. Here, we aimed at isolating viral determinants of HCV entry into B lymphocytes. For this purpose, we constructed a library of full E1E2 sequences isolated from serum and B lymphocytes of four chronically infected patients. We observed a strong phylogenetic compartmentalization of E1E2 sequences isolated from B lymphocytes in one patient, indicating that E1E2 glycoproteins can represent important mediators of the strong segregation of two specialized populations in some patients. Most of the E1E2 envelope glycoproteins were functional and allowed transduction of hepatocyte cell lines using HCV-derived pseudoparticles. Strikingly, introduction of envelope glycoproteins isolated from B lymphocytes into the HCV JFH-1 replicating virus switched the entry tropism of this nonlymphotropic virus from hepatotropism to lymphotropism. Significant detection of viral RNA and viral proteins within B cells was restricted to infections with JFH-1 harboring E1E2 from lymphocytes and depended on an endocytic, pH-dependent entry pathway. Here, we achieved for the first time the isolation of HCV viral proteins carrying entry-related lymphotropism determinants. The identification of genetic determinants within E1E2 represents a first step for a better understanding of the complex relationship between HCV infection, viral persistence, and extrahepatic disorders.
          
            IMPORTANCE
            Hepatitis C virus (HCV) mainly replicates within the liver. However, it has been shown that patient-derived HCV particles can slightly infect lymphocytes
            in vitro
            and
            in vivo
            , highlighting the existence of lymphotropism determinants within HCV viral proteins. We isolated HCV envelope glycoproteins from patient B lymphocytes that conferred to a nonlymphotropic HCV the ability to enter B cells, thus providing a platform for characterization of HCV entry into lymphocytes. This unusual tropism was accompanied by a loss of entry function into hepatocytes, suggesting that HCV lymphotropic variants likely constitute a distinct but parallel source for viral persistence and immune escape within chronically infected patients. Moreover, the level of genetic divergence of B-cell-derived envelopes correlated with their degree of lymphotropism, underlining a long-term specialization of some viral populations for B-lymphocytes. Consequently, the clearance of both hepatotropic and nonhepatotropic HCV populations may be important for effective treatment of chronically infected patients.
          }, number={2}, journal={Journal of Virology}, publisher={American Society for Microbiology}, author={Douam, Florian and Bobay, Louis-Marie and Maurin, Guillemette and Fresquet, Judith and Calland, Noémie and Maisse, Carine and Durand, Tony and Cosset, François-Loïc and Féray, Cyrille and Lavillette, Dimitri}, editor={Diamond, M. S.Editor}, year={2016}, month={Jan}, pages={992–1008} }
 @article{henry_bobay_chevallereau_saussereau_ceyssens_debarbieux_2015, title={The Search for Therapeutic Bacteriophages Uncovers One New Subfamily and Two New Genera of Pseudomonas-Infecting Myoviridae}, volume={10}, ISSN={1932-6203}, url={http://dx.doi.org/10.1371/journal.pone.0117163}, DOI={10.1371/journal.pone.0117163}, abstractNote={In a previous study, six virulent bacteriophages PAK_P1, PAK_P2, PAK_P3, PAK_P4, PAK_P5 and CHA_P1 were evaluated for their in vivo efficacy in treating Pseudomonas aeruginosa infections using a mouse model of lung infection. Here, we show that their genomes are closely related to five other Pseudomonas phages and allow a subdivision into two clades, PAK_P1-like and KPP10-like viruses, based on differences in genome size, %GC and genomic contents, as well as number of tRNAs. These two clades are well delineated, with a mean of 86% and 92% of proteins considered homologous within individual clades, and 25% proteins considered homologous between the two clades. By ESI-MS/MS analysis we determined that their virions are composed of at least 25 different proteins and electron microscopy revealed a morphology identical to the hallmark Salmonella phage Felix O1. A search for additional bacteriophage homologs, using profiles of protein families defined from the analysis of the 11 genomes, identified 10 additional candidates infecting hosts from different species. By carrying out a phylogenetic analysis using these 21 genomes we were able to define a new subfamily of viruses, the Felixounavirinae within the Myoviridae family. The new Felixounavirinae subfamily includes three genera: Felixounalikevirus, PAK_P1likevirus and KPP10likevirus. Sequencing genomes of bacteriophages with therapeutic potential increases the quantity of genomic data on closely related bacteriophages, leading to establishment of new taxonomic clades and the development of strategies for analyzing viral genomes as presented in this article.}, number={1}, journal={PLOS ONE}, publisher={Public Library of Science (PLoS)}, author={Henry, Marine and Bobay, Louis-Marie and Chevallereau, Anne and Saussereau, Emilie and Ceyssens, Pieter-Jan and Debarbieux, Laurent}, editor={Dąbrowska, KrystynaEditor}, year={2015}, month={Jan}, pages={e0117163} }
 @article{bobay_touchon_rocha_2014, title={Pervasive domestication of defective prophages by bacteria}, volume={111}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1405336111}, DOI={10.1073/pnas.1405336111}, abstractNote={Significance
          Several molecular systems with important adaptive roles have originated from the domestication of integrated phages (prophages). However, the evolutionary mechanisms and extent of prophage domestication remain poorly understood. In this work, we detected several hundred prophages originating from common integration events and described their dynamics of degradation within their hosts. Surprisingly, we observed strong conservation of the sequence of most vertically inherited prophages, including selection for genes encoding phage-specific functions. These results suggest pervasive domestication of parasites by the bacterial hosts. Because prophages account for a large fraction of bacterial genomes, phage domestication may drive bacterial adaptation.}, number={33}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Bobay, Louis-Marie and Touchon, Marie and Rocha, Eduardo P. C.}, year={2014}, month={Aug}, pages={12127–12132} }
 @article{touchon_bobay_rocha_2014, title={The chromosomal accommodation and domestication of mobile genetic elements}, volume={22}, ISSN={1369-5274}, url={http://dx.doi.org/10.1016/j.mib.2014.09.010}, DOI={10.1016/j.mib.2014.09.010}, abstractNote={Prokaryotes are constantly being infected by large mobile genetic elements (MGEs) such as conjugative elements and temperate phages. The fitness of these elements is tightly linked with the evolutionary success of the host. This leads to selection against disruptive effects their integration might have on the organization and structure of the chromosome. Seamless genetic accommodation of the mobile elements also involves silencing infectious mechanisms and expressing functions adaptive to the host. Ironically, these characteristics favor the host ability to domesticate the mobile element. Recent data suggest that the domestication of mobile elements might be frequent. Importantly, it might affect the evolution of chromosome organization and drive the diversification of social traits.}, journal={Current Opinion in Microbiology}, publisher={Elsevier BV}, author={Touchon, Marie and Bobay, Louis-Marie and Rocha, Eduardo PC}, year={2014}, month={Dec}, pages={22–29} }
 @article{raymann_bobay_doak_lynch_gribaldo_2013, title={A Genomic Survey of Reb Homologs Suggests Widespread Occurrence of R-Bodies in Proteobacteria}, volume={3}, ISSN={2160-1836}, url={http://dx.doi.org/10.1534/g3.112.005231}, DOI={10.1534/g3.112.005231}, abstractNote={Abstract
               Bacteria and eukaryotes are involved in many types of interaction in nature, with important ecological consequences. However, the diversity, occurrence, and mechanisms of these interactions often are not fully known. The obligate bacterial endosymbionts of Paramecium provide their hosts with the ability to kill sensitive Paramecium strains through the production of R-bodies, highly insoluble coiled protein ribbons. R-bodies have been observed in a number of free-living bacteria, where their function is unknown. We have performed an exhaustive survey of genes coding for homologs of Reb proteins (R-body components) in complete bacterial genomes. We found that reb genes are much more widespread than previously thought, being present in representatives of major Proteobacterial subdivisions, including many free-living taxa, as well as taxa known to be involved in various kinds of interactions with eukaryotes, from mutualistic associations to pathogenicity. Reb proteins display very good conservation at the sequence level, suggesting that they may produce functional R-bodies. Phylogenomic analysis indicates that reb genes underwent a complex evolutionary history and allowed the identification of candidates potentially involved in R-body assembly, functioning, regulation, or toxicity. Our results strongly suggest that the ability to produce R-bodies is likely widespread in Proteobacteria. The potential involvement of R-bodies in as yet unexplored interactions with eukaryotes and the consequent ecological implications are discussed.}, number={3}, journal={G3 Genes|Genomes|Genetics}, publisher={Oxford University Press (OUP)}, author={Raymann, Kasie and Bobay, Louis-Marie and Doak, Thomas G and Lynch, Michael and Gribaldo, Simonetta}, year={2013}, month={Mar}, pages={505–516} }
 @article{bobay_touchon_rocha_2013, title={Manipulating or Superseding Host Recombination Functions: A Dilemma That Shapes Phage Evolvability}, volume={9}, ISSN={1553-7404}, url={http://dx.doi.org/10.1371/journal.pgen.1003825}, DOI={10.1371/journal.pgen.1003825}, abstractNote={Phages, like many parasites, tend to have small genomes and may encode autonomous functions or manipulate those of their hosts'. Recombination functions are essential for phage replication and diversification. They are also nearly ubiquitous in bacteria. The E. coli genome encodes many copies of an octamer (Chi) motif that upon recognition by RecBCD favors repair of double strand breaks by homologous recombination. This might allow self from non-self discrimination because RecBCD degrades DNA lacking Chi. Bacteriophage Lambda, an E. coli parasite, lacks Chi motifs, but escapes degradation by inhibiting RecBCD and encoding its own autonomous recombination machinery. We found that only half of 275 lambdoid genomes encode recombinases, the remaining relying on the host's machinery. Unexpectedly, we found that some lambdoid phages contain extremely high numbers of Chi motifs concentrated between the phage origin of replication and the packaging site. This suggests a tight association between replication, packaging and RecBCD-mediated recombination in these phages. Indeed, phages lacking recombinases strongly over-represent Chi motifs. Conversely, phages encoding recombinases and inhibiting host recombination machinery select for the absence of Chi motifs. Host and phage recombinases use different mechanisms and the latter are more tolerant to sequence divergence. Accordingly, we show that phages encoding their own recombination machinery have more mosaic genomes resulting from recent recombination events and have more diverse gene repertoires, i.e. larger pan genomes. We discuss the costs and benefits of superseding or manipulating host recombination functions and how this decision shapes phage genome structure and evolvability.}, number={9}, journal={PLoS Genetics}, publisher={Public Library of Science (PLoS)}, author={Bobay, Louis-Marie and Touchon, Marie and Rocha, Eduardo P. C.}, editor={Casadesús, JosepEditor}, year={2013}, month={Sep}, pages={e1003825} }
 @article{deghorain_bobay_smeesters_bousbata_vermeersch_perez-morga_drèze_rocha_touchon_van melderen_2012, title={Characterization of Novel Phages Isolated in Coagulase-Negative Staphylococci Reveals Evolutionary Relationships with Staphylococcus aureus Phages}, volume={194}, ISSN={0021-9193 1098-5530}, url={http://dx.doi.org/10.1128/jb.01085-12}, DOI={10.1128/jb.01085-12}, abstractNote={ABSTRACT
          
            Despite increasing interest in coagulase-negative staphylococci (CoNS), little information is available about their bacteriophages. We isolated and sequenced three novel temperate
            Siphoviridae
            phages (StB12, StB27, and StB20) from the CoNS
            Staphylococcus hominis
            and
            S. capitis
            species. The genome sizes are around 40 kb, and open reading frames (ORFs) are arranged in functional modules encoding lysogeny, DNA metabolism, morphology, and cell lysis. Bioinformatics analysis allowed us to assign a potential function to half of the predicted proteins. Structural elements were further identified by proteomic analysis of phage particles, and DNA-packaging mechanisms were determined. Interestingly, the three phages show identical integration sites within their host genomes. In addition to this experimental characterization, we propose a novel classification based on the analysis of 85 phage and prophage genomes, including 15 originating from CoNS. Our analysis established 9 distinct clusters and revealed close relationships between
            S. aureus
            and CoNS phages. Genes involved in DNA metabolism and lysis and potentially in phage-host interaction appear to be widespread, while structural genes tend to be cluster specific. Our findings support the notion of a possible reciprocal exchange of genes between phages originating from
            S. aureus
            and CoNS, which may be of crucial importance for pathogenesis in staphylococci.
          }, number={21}, journal={Journal of Bacteriology}, publisher={American Society for Microbiology}, author={Deghorain, Marie and Bobay, Louis-Marie and Smeesters, Pierre R. and Bousbata, Sabrina and Vermeersch, Marjorie and Perez-Morga, David and Drèze, Pierre-Alexandre and Rocha, Eduardo P. C. and Touchon, Marie and Van Melderen, Laurence}, year={2012}, month={Nov}, pages={5829–5839} }
 @article{bobay_rocha_touchon_2012, title={The Adaptation of Temperate Bacteriophages to Their Host Genomes}, volume={30}, ISSN={1537-1719 0737-4038}, url={http://dx.doi.org/10.1093/molbev/mss279}, DOI={10.1093/molbev/mss279}, abstractNote={Rapid turnover of mobile elements drives the plasticity of bacterial genomes. Integrated bacteriophages (prophages) encode host-adaptive traits and represent a sizable fraction of bacterial chromosomes. We hypothesized that natural selection shapes prophage integration patterns relative to the host genome organization. We tested this idea by detecting and studying 500 prophages of 69 strains of Escherichia and Salmonella. Phage integrases often target not only conserved genes but also intergenic positions, suggesting purifying selection for integration sites. Furthermore, most integration hotspots are conserved between the two host genera. Integration sites seem also selected at the large chromosomal scale, as they are nonrandomly organized in terms of the origin–terminus axis and the macrodomain structure. The genes of lambdoid prophages are systematically co-oriented with the bacterial replication fork and display the host high frequency of polarized FtsK-orienting polar sequences motifs required for chromosome segregation. matS motifs are strongly avoided by prophages suggesting counter selection of motifs disrupting macrodomains. These results show how natural selection for seamless integration of prophages in the chromosome shapes the evolution of the bacterium and the phage. First, integration sites are highly conserved for many millions of years favoring lysogeny over the lytic cycle for temperate phages. Second, the global distribution of prophages is intimately associated with the chromosome structure and the patterns of gene expression. Third, the phage endures selection for DNA motifs that pertain exclusively to the biology of the prophage in the bacterial chromosome. Understanding prophage genetic adaptation sheds new lights on the coexistence of horizontal transfer and organized bacterial genomes.}, number={4}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Bobay, Louis-Marie and Rocha, Eduardo P.C. and Touchon, Marie}, year={2012}, month={Dec}, pages={737–751} }
 @article{lynch_bobay_catania_gout_rho_2011, title={The Repatterning of Eukaryotic Genomes by Random Genetic Drift}, volume={12}, ISSN={1527-8204 1545-293X}, url={http://dx.doi.org/10.1146/annurev-genom-082410-101412}, DOI={10.1146/annurev-genom-082410-101412}, abstractNote={ Recent observations on rates of mutation, recombination, and random genetic drift highlight the dramatic ways in which fundamental evolutionary processes vary across the divide between unicellular microbes and multicellular eukaryotes. Moreover, population-genetic theory suggests that the range of variation in these parameters is sufficient to explain the evolutionary diversification of many aspects of genome size and gene structure found among phylogenetic lineages. Most notably, large eukaryotic organisms that experience elevated magnitudes of random genetic drift are susceptible to the passive accumulation of mutationally hazardous DNA that would otherwise be eliminated by efficient selection. Substantial evidence also suggests that variation in the population-genetic environment influences patterns of protein evolution, with the emergence of certain kinds of amino-acid substitutions and protein-protein complexes only being possible in populations with relatively small effective sizes. These observations imply that the ultimate origins of many of the major genomic and proteomic disparities between prokaryotes and eukaryotes and among eukaryotic lineages have been molded as much by intrinsic variation in the genetic and cellular features of species as by external ecological forces. }, number={1}, journal={Annual Review of Genomics and Human Genetics}, publisher={Annual Reviews}, author={Lynch, Michael and Bobay, Louis-Marie and Catania, Francesco and Gout, Jean-François and Rho, Mina}, year={2011}, month={Sep}, pages={347–366} }
 @book{douam_bobay_martin_2010, place={Paris}, title={L'évolution c'est tout simple!}, ISBN={9782311002201}, publisher={Vuibert}, author={Douam, Florian and Bobay, Louis-Marie and Martin, Olivier}, year={2010} }