@article{cen_rasmussen_2024, title={Exploring the Accuracy and Limits of Algorithms for Localizing Recombination Breakpoints}, volume={41}, ISSN={["1537-1719"]}, DOI={10.1093/molbev/msae133}, abstractNote={Abstract Phylogenetic methods are widely used to reconstruct the evolutionary relationships among species and individuals. However, recombination can obscure ancestral relationships as individuals may inherit different regions of their genome from different ancestors. It is, therefore, often necessary to detect recombination events, locate recombination breakpoints, and select recombination-free alignments prior to reconstructing phylogenetic trees. While many earlier studies have examined the power of different methods to detect recombination, very few have examined the ability of these methods to accurately locate recombination breakpoints. In this study, we simulated genome sequences based on ancestral recombination graphs and explored the accuracy of three popular recombination detection methods: MaxChi, 3SEQ, and Genetic Algorithm Recombination Detection. The accuracy of inferred breakpoint locations was evaluated along with the key factors contributing to variation in accuracy across datasets. While many different genomic features contribute to the variation in performance across methods, the number of informative sites consistent with the pattern of inheritance between parent and recombinant child sequences always has the greatest contribution to accuracy. While partitioning sequence alignments based on identified recombination breakpoints can greatly decrease phylogenetic error, the quality of phylogenetic reconstructions depends very little on how breakpoints are chosen to partition the alignment. Our work sheds light on how different features of recombinant genomes affect the performance of recombination detection methods and suggests best practices for reconstructing phylogenies based on recombination-free alignments.}, number={7}, journal={MOLECULAR BIOLOGY AND EVOLUTION}, author={Cen, Shi and Rasmussen, David A.}, year={2024}, month={Jul} }
 @article{wang_muller_mcdowell_rasmussen_2024, title={Quantifying the strength of viral fitness trade-offs between hosts: a meta-analysis of pleiotropic fitness effects}, ISSN={["2056-3744"]}, DOI={10.1093/evlett/qrae038}, journal={EVOLUTION LETTERS}, author={Wang, Xuechun 'May' and Muller, Julia and McDowell, Mya and Rasmussen, David A.}, year={2024}, month={Jul} }
 @article{rivarez_faure_svanella-dumas_pecman_tusek-znidaric_schonegger_de jonghe_blouin_rasmussen_massart_et al._2023, title={Diversity and Pathobiology of an Ilarvirus Unexpectedly Detected in Diverse Plants and Global Sequencing Data}, ISSN={["1943-7684"]}, DOI={10.1094/PHYTO-12-22-0465-V}, abstractNote={ High-throughput sequencing (HTS) and sequence mining tools revolutionized virus detection and discovery in recent years, and implementing them with classical plant virology techniques results in a powerful approach to characterize viruses. An example of a virus discovered through HTS is Solanum nigrum ilarvirus 1 (SnIV1) ( Bromoviridae), which was recently reported in various solanaceous plants from France, Slovenia, Greece, and South Africa. It was likewise detected in grapevines ( Vitaceae) and several Fabaceae and Rosaceae plant species. Such a diverse set of source organisms is atypical for ilarviruses, thus warranting further investigation. In this study, modern and classical virological tools were combined to accelerate the characterization of SnIV1. Through HTS-based virome surveys, mining of sequence read archive datasets, and a literature search, SnIV1 was further identified from diverse plant and non-plant sources globally. SnIV1 isolates showed relatively low variability compared with other phylogenetically related ilarviruses. Phylogenetic analyses showed a distinct basal clade of isolates from Europe, whereas the rest formed clades of mixed geographic origin. Furthermore, systemic infection of SnIV1 in Solanum villosum and its mechanical and graft transmissibility to solanaceous species were demonstrated. Near-identical SnIV1 genomes from the inoculum ( S. villosum) and inoculated Nicotiana benthamiana were sequenced, thus partially fulfilling Koch's postulates. SnIV1 was shown to be seed-transmitted and potentially pollen-borne, has spherical virions, and possibly induces histopathological changes in infected N. benthamiana leaf tissues. Overall, this study provides information to better understand the diversity, global presence, and pathobiology of SnIV1; however, its possible emergence as a destructive pathogen remains uncertain.  [Formula: see text] Copyright © 2023 The Author(s). This is an open access article distributed under the CC BY 4.0 International license . }, journal={PHYTOPATHOLOGY}, author={Rivarez, Mark Paul Selda and Faure, Chantal and Svanella-Dumas, Laurence and Pecman, Anja and Tusek-Znidaric, Magda and Schonegger, Deborah and De Jonghe, Kris and Blouin, Arnaud and Rasmussen, David A. and Massart, Sebastien and et al.}, year={2023}, month={Jul} }
 @article{rasmussen_guo_2023, title={Espalier: Efficient Tree Reconciliation and Ancestral Recombination Graphs Reconstruction Using Maximum Agreement Forests}, volume={72}, ISSN={["1076-836X"]}, DOI={10.1093/sysbio/syad040}, abstractNote={Abstract
               In the presence of recombination individuals may inherit different regions of their genome from different ancestors, resulting in a mosaic of phylogenetic histories across their genome. Ancestral recombination graphs (ARGs) can capture how phylogenetic relationships vary across the genome due to recombination, but reconstructing ARGs from genomic sequence data is notoriously difficult. Here, we present a method for reconciling discordant phylogenetic trees and reconstructing ARGs using maximum agreement forests (MAFs). Given two discordant trees, a MAF identifies the smallest possible set of topologically concordant subtrees present in both trees. We show how discordant trees can be reconciled through their MAF in a way that retains discordances strongly supported by sequence data while eliminating conflicts likely attributable to phylogenetic noise. We further show how MAFs and our reconciliation approach can be combined to select a path of local trees across the genome that maximizes the likelihood of the genomic sequence data, minimizes discordance between neighboring local trees, and identifies the recombination events necessary to explain remaining discordances to obtain a fully connected ARG. While heuristic, our ARG reconstruction approach is often as accurate as more exact methods while being much more computationally efficient. Moreover, important demographic parameters such as recombination rates can be accurately estimated from reconstructed ARGs. Finally, we apply our approach to plant infecting RNA viruses in the genus Potyvirus to demonstrate how true recombination events can be disentangled from phylogenetic noise using our ARG reconstruction methods.}, number={5}, journal={SYSTEMATIC BIOLOGY}, author={Rasmussen, David A. and Guo, Fangfang}, year={2023}, month={Nov}, pages={1154–1170} }
 @article{hasegawa_techer_adjlane_al-hissnawi_antunez_beaurepaire_christmon_delatte_dukku_eliash_et al._2023, title={Evolutionarily diverse origins of deformed wing viruses in western honey bees}, volume={120}, ISSN={["1091-6490"]}, DOI={10.1073/pnas.2301258120}, abstractNote={Novel transmission routes can allow infectious diseases to spread, often with devastating consequences. Ectoparasitic varroa mites vector a diversity of RNA viruses, having switched hosts from the eastern to western honey bees (Apis ceranatoApis mellifera). They provide an opportunity to explore how novel transmission routes shape disease epidemiology. As the principal driver of the spread of deformed wing viruses (mainly DWV-A and DWV-B), varroa infestation has also driven global honey bee health declines. The more virulent DWV-B strain has been replacing the original DWV-A strain in many regions over the past two decades. Yet, how these viruses originated and spread remains poorly understood. Here, we use a phylogeographic analysis based on whole-genome data to reconstruct the origins and demography of DWV spread. We found that, rather than reemerging in western honey bees after varroa switched hosts, as suggested by previous work, DWV-A most likely originated in East Asia and spread in the mid-20th century. It also showed a massive population size expansion following the varroa host switch. By contrast, DWV-B was most likely acquired more recently from a source outside East Asia and appears absent from the original varroa host. These results highlight the dynamic nature of viral adaptation, whereby a vector’s host switch can give rise to competing and increasingly virulent disease pandemics. The evolutionary novelty and rapid global spread of these host–virus interactions, together with observed spillover into other species, illustrate how increasing globalization poses urgent threats to biodiversity and food security.}, number={26}, journal={PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA}, author={Hasegawa, Nonno and Techer, Maeva A. and Adjlane, Noureddine and al-Hissnawi, Muntasser Sabah and Antunez, Karina and Beaurepaire, Alexis and Christmon, Krisztina and Delatte, Helene and Dukku, Usman H. and Eliash, Nurit and et al.}, year={2023}, month={Jun} }
 @article{mahmud_wallace_reske_alvarado_muenks_rasmussen_burnham_lanzas_dubberke_dantas_2022, title={Epidemiology of Plasmid Lineages Mediating the Spread of Extended-Spectrum Beta-Lactamases among Clinical Escherichia coli}, volume={8}, ISSN={["2379-5077"]}, url={https://doi.org/10.1128/msystems.00519-22}, DOI={10.1128/msystems.00519-22}, abstractNote={
            The increasing incidence of nosocomial infections with extended-spectrum beta-lactamase (ESBL)-producing
            Escherichia coli
            represents a significant threat to public health, given the limited treatment options available for such infections. The rapid ESBL spread is suggested to be driven by localization of the resistance genes on conjugative plasmids.
          }, journal={MSYSTEMS}, author={Mahmud, Bejan and Wallace, Meghan A. and Reske, Kimberly A. and Alvarado, Kelly and Muenks, Carol E. and Rasmussen, David A. and Burnham, Carey-Ann D. and Lanzas, Cristina and Dubberke, Erik R. and Dantas, Gautam}, editor={Marshall, Christopher W.Editor}, year={2022}, month={Aug} }
 @article{lapp_obala_abel_rasmussen_sumner_freedman_taylor_prudhomme-o'meara_2022, title={Plasmodium falciparum Genetic Diversity in Coincident Human and Mosquito Hosts}, ISSN={["2150-7511"]}, DOI={10.1128/mbio.02277-22}, abstractNote={
            Plasmodium falciparum
            is the deadliest human malaria parasite, and infections consisting of concurrent, multiple strains are common in regions of high endemicity. During transitions within and between the parasite’s mosquito and human hosts, these strains are subject to population bottlenecks, and distinct parasite strains may have differential fitness in the various environments encountered.
          }, journal={MBIO}, author={Lapp, Zena and Obala, Andrew A. and Abel, Lucy and Rasmussen, David A. and Sumner, Kelsey M. and Freedman, Elizabeth and Taylor, Steve M. and Prudhomme-O'Meara, Wendy}, year={2022}, month={Sep} }
 @article{guo_carbone_rasmussen_2022, title={Recombination-aware phylogeographic inference using the structured coalescent with ancestral recombination}, volume={18}, ISSN={["1553-7358"]}, DOI={10.1371/journal.pcbi.1010422}, abstractNote={Movement of individuals between populations or demes is often restricted, especially between geographically isolated populations. The structured coalescent provides an elegant theoretical framework for describing how movement between populations shapes the genealogical history of sampled individuals and thereby structures genetic variation within and between populations. However, in the presence of recombination an individual may inherit different regions of their genome from different parents, resulting in a mosaic of genealogical histories across the genome, which can be represented by an Ancestral Recombination Graph (ARG). In this case, different genomic regions may have different ancestral histories and so different histories of movement between populations. Recombination therefore poses an additional challenge to phylogeographic methods that aim to reconstruct the movement of individuals from genealogies, although also a potential benefit in that different loci may contain additional information about movement. Here, we introduce the Structured Coalescent with Ancestral Recombination (SCAR) model, which builds on recent approximations to the structured coalescent by incorporating recombination into the ancestry of sampled individuals. The SCAR model allows us to infer how the migration history of sampled individuals varies across the genome from ARGs, and improves estimation of key population genetic parameters such as population sizes, recombination rates and migration rates. Using the SCAR model, we explore the potential and limitations of phylogeographic inference using full ARGs. We then apply the SCAR to lineages of the recombining fungusAspergillus flavussampled across the United States to explore patterns of recombination and migration across the genome.}, number={8}, journal={PLOS COMPUTATIONAL BIOLOGY}, author={Guo, Fangfang and Carbone, Ignazio and Rasmussen, David A.}, year={2022}, month={Aug} }
 @article{tegally_san_cotten_moir_tegomoh_mboowa_martin_baxter_lambisia_diallo_et al._2022, title={The evolving SARS-CoV-2 epidemic in Africa: Insights from rapidly expanding genomic surveillance}, volume={378}, ISSN={["1095-9203"]}, DOI={10.1126/science.abq5358}, abstractNote={Investment in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) sequencing in Africa over the past year has led to a major increase in the number of sequences that have been generated and used to track the pandemic on the continent, a number that now exceeds 100,000 genomes. Our results show an increase in the number of African countries that are able to sequence domestically and highlight that local sequencing enables faster turnaround times and more-regular routine surveillance. Despite limitations of low testing proportions, findings from this genomic surveillance study underscore the heterogeneous nature of the pandemic and illuminate the distinct dispersal dynamics of variants of concern—particularly Alpha, Beta, Delta, and Omicron—on the continent. Sustained investment for diagnostics and genomic surveillance in Africa is needed as the virus continues to evolve while the continent faces many emerging and reemerging infectious disease threats. These investments are crucial for pandemic preparedness and response and will serve the health of the continent well into the 21st century.}, number={6615}, journal={SCIENCE}, author={Tegally, Houriiyah and San, James E. and Cotten, Matthew and Moir, Monika and Tegomoh, Bryan and Mboowa, Gerald and Martin, Darren P. and Baxter, Cheryl and Lambisia, Arnold W. and Diallo, Amadou and et al.}, year={2022}, month={Oct}, pages={42-+} }
 @article{wilkinson_giovanetti_tegally_san_lessells_cuadros_martin_rasmussen_zekri_sangare_et al._2021, title={A year of genomic surveillance reveals how the SARS-CoV-2 pandemic unfolded in Africa}, volume={374}, ISSN={["1095-9203"]}, DOI={10.1126/science.abj4336}, abstractNote={SARS-CoV-2 across Africa
          
            The impact of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic has been hard to track in African countries, largely because of patchy data. Wilkinson
            et al
            . curated viral genomes collected in 2021 from several countries across the continent. Outbreaks during 2020 in each African country were initiated by imported cases, mostly from Europe. As the pandemic developed, case numbers in African countries were likely many times higher than reported, and subsequent waves of the pandemic appear to have been more severe. Consequently, high-transmission variants have emerged that have spread within the continent, and African countries must be included in global control efforts. —CA
          }, number={6566}, journal={SCIENCE}, author={Wilkinson, Eduan and Giovanetti, Marta and Tegally, Houriiyah and San, James E. and Lessells, Richard and Cuadros, Diego and Martin, Darren P. and Rasmussen, David A. and Zekri, Abdel-Rahman N. and Sangare, Abdoul K. and et al.}, year={2021}, month={Oct}, pages={423-+} }
 @article{kepler_hamins-puertolas_rasmussen_2021, title={Decomposing the sources of SARS-CoV-2 fitness variation in the United States}, volume={7}, ISSN={["2057-1577"]}, DOI={10.1093/ve/veab073}, abstractNote={Abstract
               The fitness of a pathogen is a composite phenotype determined by many different factors influencing growth rates both within and between hosts. Determining what factors shape fitness at the host population-level is especially challenging because both intrinsic factors like pathogen genetics and extrinsic factors such as host behavior influence between-host transmission potential. This challenge has been highlighted by controversy surrounding the population-level fitness effects of mutations in the SARS-CoV-2 genome and their relative importance when compared against non-genetic factors shaping transmission dynamics. Building upon phylodynamic birth–death models, we develop a new framework to learn how hundreds of genetic and non-genetic factors have shaped the fitness of SARS-CoV-2. We estimate the fitness effects of all amino acid variants and several structural variants that have circulated in the United States between February 2020 and March 2021 from viral phylogenies. We also estimate how much fitness variation among pathogen lineages is attributable to genetic versus non-genetic factors such as spatial heterogeneity in transmission rates. Before September 2020, most fitness variation between lineages can be explained by background spatial heterogeneity in transmission rates across geographic regions. Starting in late 2020, genetic variation in fitness increased dramatically with the emergence of several new lineages including B.1.1.7, B.1.427, B.1.429 and B.1.526. Our analysis also indicates that genetic variants in less well-explored genomic regions outside of Spike may be contributing significantly to overall fitness variation in the viral population.}, number={2}, journal={VIRUS EVOLUTION}, author={Kepler, Lenora and Hamins-Puertolas, Marco and Rasmussen, David A.}, year={2021}, month={Dec} }
 @article{graf_bello_andrade_arantes_pereira_silva_veiga_mariani_boullosa_arruda_et al._2021, title={HIV-1 molecular diversity in Brazil unveiled by 10 years of sampling by the national genotyping network}, volume={11}, ISSN={["2045-2322"]}, DOI={10.1038/s41598-021-94542-5}, abstractNote={AbstractHIV-1 has diversified into several subtypes and recombinant forms that are heterogeneously spread around the world. Understanding the distribution of viral variants and their temporal dynamics can help to design vaccines and monitor changes in viral transmission patterns. Brazil has one of the largest HIV-1 epidemics in the western-world and the molecular features of the virus circulating in the country are still not completely known. Over 50,000 partial HIV-1 genomes sampled between 2008 and 2017 by the Brazilian genotyping network (RENAGENO) were analyzed. Sequences were filtered by quality, duplicate sequences per patient were removed and subtyping was performed with online tools and molecular phylogeny. Association between patients’ demographic data and subtypes were performed by calculating the relative risk in a multinomial analysis and trends in subtype prevalence were tested by Pearson correlation. HIV-1B was found to be the most prevalent subtype throughout the country except in the south, where HIV-1C prevails. An increasing trend in the proportion of HIV-1C and F1 was observed in several regions of the country, while HIV-1B tended to decrease. Men and highly educated individuals were more frequently infected by HIV-1B and non-B variants were more prevalent among women with lower education. Our results suggest that socio-demographic factors partially segregate HIV-1 diversity in Brazil while shaping viral transmission networks. Historical events could explain a preferential circulation of HIV-1B among men who have sex with men (MSM) and non-B variants among heterosexual individuals. In view of an increasing male/female ratio of AIDS cases in Brazil in the last 10–15 years, the decrease of HIV-1B prevalence is surprising and suggests a greater penetrance of non-B subtypes in MSM transmission chains.}, number={1}, journal={SCIENTIFIC REPORTS}, author={Graf, Tiago and Bello, Gonzalo and Andrade, Paula and Arantes, Ighor and Pereira, Joao Marcos and Silva, Alexandre Bonfim and Veiga, Rafael V. and Mariani, Diana and Boullosa, Lidia Theodoro and Arruda, Monica B. and et al.}, year={2021}, month={Aug} }
 @article{dawson_rasmussen_peng_lanzas_2021, title={Inferring environmental transmission using phylodynamics: a case-study using simulated evolution of an enteric pathogen}, volume={18}, ISSN={["1742-5662"]}, url={https://doi.org/10.1098/rsif.2021.0041}, DOI={10.1098/rsif.2021.0041}, abstractNote={Indirect (environmental) and direct (host–host) transmission pathways cannot easily be distinguished when they co-occur in epidemics, particularly when they occur on similar time scales. Phylodynamic reconstruction is a potential approach to this problem that combines epidemiological information (temporal, spatial information) with pathogen whole-genome sequencing data to infer transmission trees of epidemics. However, factors such as differences in mutation and transmission rates between host and non-host environments may obscure phylogenetic inference from these methods. In this study, we used a network-based transmission model that explicitly models pathogen evolution to simulate epidemics with both direct and indirect transmission. Epidemics were simulated according to factorial combinations of direct/indirect transmission proportions, host mutation rates and conditions of environmental pathogen growth. Transmission trees were then reconstructed using the phylodynamic approach SCOTTI (structured coalescent transmission tree inference) and evaluated. We found that although insufficient diversity sets a lower bound on when accurate phylodynamic inferences can be made, transmission routes and assumed pathogen lifestyle affected pathogen population structure and subsequently influenced both reconstruction success and the likelihood of direct versus indirect pathways being reconstructed. We conclude that prior knowledge of the likely ecology and population structure of pathogens in host and non-host environments is critical to fully using phylodynamic techniques.}, number={179}, journal={JOURNAL OF THE ROYAL SOCIETY INTERFACE}, author={Dawson, Daniel and Rasmussen, David and Peng, Xinxia and Lanzas, Cristina}, year={2021}, month={Jun} }
 @article{rasmussen_grunwald_2021, title={Phylogeographic Approaches to Characterize the Emergence of Plant Pathogens}, volume={111}, ISSN={["1943-7684"]}, DOI={10.1094/PHYTO-07-20-0319-FI}, abstractNote={ Phylogeography combines geographic information with phylogenetic and population genomic approaches to infer the evolutionary history of a species or population in a geographic context. This approach has been instrumental in understanding the emergence, spread, and evolution of a range of plant pathogens. In particular, phylogeography can address questions about where a pathogen originated, whether it is native or introduced, and when and how often introductions occurred. We review the theory, methods, and approaches underpinning phylogeographic inference and highlight applications providing novel insights into the emergence and spread of select pathogens. We hope that this review will be useful in assessing the power, pitfalls, and opportunities presented by various phylogeographic approaches. }, number={1}, journal={PHYTOPATHOLOGY}, author={Rasmussen, David A. and Grunwald, Niklaus J.}, year={2021}, month={Jan}, pages={68–77} }
 @misc{gadhave_gautam_rasmussen_srinivasan_2020, title={Aphid Transmission ofPotyvirus: The Largest Plant-Infecting RNA Virus Genus}, volume={12}, ISSN={["1999-4915"]}, DOI={10.3390/v12070773}, abstractNote={Potyviruses are the largest group of plant infecting RNA viruses that cause significant losses in a wide range of crops across the globe. The majority of viruses in the genus Potyvirus are transmitted by aphids in a non-persistent, non-circulative manner and have been extensively studied vis-à-vis their structure, taxonomy, evolution, diagnosis, transmission, and molecular interactions with hosts. This comprehensive review exclusively discusses potyviruses and their transmission by aphid vectors, specifically in the light of several virus, aphid and plant factors, and how their interplay influences potyviral binding in aphids, aphid behavior and fitness, host plant biochemistry, virus epidemics, and transmission bottlenecks. We present the heatmap of the global distribution of potyvirus species, variation in the potyviral coat protein gene, and top aphid vectors of potyviruses. Lastly, we examine how the fundamental understanding of these multi-partite interactions through multi-omics approaches is already contributing to, and can have future implications for, devising effective and sustainable management strategies against aphid-transmitted potyviruses to global agriculture.}, number={7}, journal={VIRUSES-BASEL}, author={Gadhave, Kiran R. and Gautam, Saurabh and Rasmussen, David A. and Srinivasan, Rajagopalbabu}, year={2020}, month={Jul} }
 @article{ruark-seward_bonville_kennedy_rasmussen_2020, title={Evolutionary dynamics of Tomato spotted wilt virus within and between alternate plant hosts and thrips}, volume={10}, ISSN={2045-2322}, url={http://dx.doi.org/10.1038/s41598-020-72691-3}, DOI={10.1038/s41598-020-72691-3}, abstractNote={AbstractTomato spotted wilt virus (TSWV) is a generalist pathogen with one of the broadest known host ranges among RNA viruses. To understand how TSWV adapts to different hosts, we experimentally passaged viral populations between two alternate hosts, Emilia sochifolia and Datura stramonium, and an obligate vector in which it also replicates, western flower thrips (Frankliniella occidentalis). Deep sequencing viral populations at multiple time points allowed us to track the evolutionary dynamics of viral populations within and between hosts. High levels of viral genetic diversity were maintained in both plants and thrips between transmission events. Rapid fluctuations in the frequency of amino acid variants indicated strong host-specific selection pressures on proteins involved in viral movement (NSm) and replication (RdRp). While several genetic variants showed opposing fitness effects in different hosts, fitness effects were generally positively correlated between hosts indicating that positive rather than antagonistic pleiotropy is pervasive. These results suggest that high levels of genetic diversity together with the positive pleiotropic effects of mutations have allowed TSWV to rapidly adapt to new hosts and expand its host range.}, number={1}, journal={Scientific Reports}, publisher={Springer Science and Business Media LLC}, author={Ruark-Seward, Casey L. and Bonville, Brian and Kennedy, George and Rasmussen, David A.}, year={2020}, month={Sep} }
 @article{bouckaert_vaughan_barido-sottani_duchene_fourment_gavryushkina_heled_jones_kuehnert_de maio_et al._2019, title={BEAST 2.5: An advanced software platform for Bayesian evolutionary analysis}, volume={15}, ISSN={["1553-7358"]}, DOI={10.1371/journal.pcbi.1006650}, abstractNote={Elaboration of Bayesian phylogenetic inference methods has continued at pace in recent years with major new advances in nearly all aspects of the joint modelling of evolutionary data. It is increasingly appreciated that some evolutionary questions can only be adequately answered by combining evidence from multiple independent sources of data, including genome sequences, sampling dates, phenotypic data, radiocarbon dates, fossil occurrences, and biogeographic range information among others. Including all relevant data into a single joint model is very challenging both conceptually and computationally. Advanced computational software packages that allow robust development of compatible (sub-)models which can be composed into a full model hierarchy have played a key role in these developments. Developing such software frameworks is increasingly a major scientific activity in its own right, and comes with specific challenges, from practical software design, development and engineering challenges to statistical and conceptual modelling challenges. BEAST 2 is one such computational software platform, and was first announced over 4 years ago. Here we describe a series of major new developments in the BEAST 2 core platform and model hierarchy that have occurred since the first release of the software, culminating in the recent 2.5 release. Author summary Bayesian phylogenetic inference methods have undergone considerable development in recent years, and joint modelling of rich evolutionary data, including genomes, phenotypes and fossil occurrences is increasingly common. Advanced computational software packages that allow robust development of compatible (sub-)models which can be composed into a full model hierarchy have played a key role in these developments. Developing scientific software is increasingly crucial to advancement in many fields of biology. The challenges range from practical software development and engineering, distributed team coordination, conceptual development and statistical modelling, to validation and testing. BEAST 2 is one such computational software platform for phylogenetics, population genetics and phylodynamics, and was first announced over 4 years ago. Here we describe the full range of new tools and models available on the BEAST 2.5 platform, which expand joint evolutionary inference in many new directions, especially for joint inference over multiple data types, non-tree models and complex phylodynamics.}, number={4}, journal={PLOS COMPUTATIONAL BIOLOGY}, author={Bouckaert, Remco and Vaughan, Timothy G. and Barido-Sottani, Joelle and Duchene, Sebastian and Fourment, Mathieu and Gavryushkina, Alexandra and Heled, Joseph and Jones, Graham and Kuehnert, Denise and De Maio, Nicola and et al.}, year={2019}, month={Apr} }
 @article{rasmussen_stadler_2019, title={Coupling adaptive molecular evolution to phylodynamics using fittness-dependent birth-death models}, volume={8}, ISSN={["2050-084X"]}, DOI={10.7554/eLife.45562}, abstractNote={Beneficial and deleterious mutations cause the fitness of lineages to vary across a phylogeny and thereby shape its branching structure. While standard phylogenetic models do not allow mutations to feedback and shape trees, birth-death models can account for this feedback by letting the fitness of lineages depend on their type. To date, these multi-type birth-death models have only been applied to cases where a lineage’s fitness is determined by a single character state. We extend these models to track sequence evolution at multiple sites. This approach remains computationally tractable by tracking the genotype and fitness of lineages probabilistically in an approximate manner. Although approximate, we show that we can accurately estimate the fitness of lineages and site-specific mutational fitness effects from phylogenies. We apply this approach to estimate the population-level fitness effects of mutations in Ebola and influenza virus, and compare our estimates with in vitro fitness measurements for these mutations.}, journal={ELIFE}, author={Rasmussen, David A. and Stadler, Tanja}, year={2019}, month={Aug} }
 @article{chen_dessau_rotenberg_rasmussen_whitfield_2019, title={Entry of bunyaviruses into plants and vectors}, volume={104}, ISBN={["978-0-12-818394-6"]}, ISSN={["1557-8399"]}, DOI={10.1016/bs.aivir.2019.07.001}, abstractNote={The majority of plant-infecting viruses are transmitted by arthropod vectors that deliver them directly into a living plant cell. There are diverse mechanisms of transmission ranging from direct binding to the insect stylet (non-persistent transmission) to persistent-propagative transmission in which the virus replicates in the insect vector. Despite this diversity in interactions, most arthropods that serve as efficient vectors have feeding strategies that enable them to deliver the virus into the plant cell without extensive damage to the plant and thus effectively inoculate the plant. As such, the primary virus entry mechanism for plant viruses is mediated by the biological vector. Remarkably, viruses that are transmitted in a propagative manner (bunyaviruses, rhabdoviruses, and reoviruses) have developed an ability to replicate in hosts from two kingdoms. Viruses in the order Bunyavirales are of emerging importance and with the advent of new sequencing technologies, we are getting unprecedented glimpses into the diversity of these viruses. Plant-infecting bunyaviruses are transmitted in a persistent, propagative manner must enter two unique types of host cells, plant and insect. In the insect phase of the virus life cycle, the propagative viruses likely use typical cellular entry strategies to traverse cell membranes. In this review, we highlight the transmission and entry strategies of three genera of plant-infecting bunyaviruses: orthotospoviruses, tenuiviruses, and emaraviruses.}, journal={VIRUS ENTRY}, author={Chen, Yuting and Dessau, Moshe and Rotenberg, Dorith and Rasmussen, David A. and Whitfield, Anna E.}, year={2019}, pages={65–96} }
 @article{vaughan_leventhal_rasmussen_drummond_welch_stadler_2019, title={Estimating Epidemic Incidence and Prevalence from Genomic Data}, volume={36}, ISSN={["1537-1719"]}, DOI={10.1093/molbev/msz106}, abstractNote={AbstractModern phylodynamic methods interpret an inferred phylogenetic tree as a partial transmission chain providing information about the dynamic process of transmission and removal (where removal may be due to recovery, death, or behavior change). Birth–death and coalescent processes have been introduced to model the stochastic dynamics of epidemic spread under common epidemiological models such as the SIS and SIR models and are successfully used to infer phylogenetic trees together with transmission (birth) and removal (death) rates. These methods either integrate analytically over past incidence and prevalence to infer rate parameters, and thus cannot explicitly infer past incidence or prevalence, or allow such inference only in the coalescent limit of large population size. Here, we introduce a particle filtering framework to explicitly infer prevalence and incidence trajectories along with phylogenies and epidemiological model parameters from genomic sequences and case count data in a manner consistent with the underlying birth–death model. After demonstrating the accuracy of this method on simulated data, we use it to assess the prevalence through time of the early 2014 Ebola outbreak in Sierra Leone.}, number={8}, journal={MOLECULAR BIOLOGY AND EVOLUTION}, author={Vaughan, Timothy G. and Leventhal, Gabriel E. and Rasmussen, David A. and Drummond, Alexei J. and Welch, David and Stadler, Tanja}, year={2019}, month={Aug}, pages={1804–1816} }
 @article{mueller_rasmussen_stadler_2018, title={MASCOT: parameter and state inference under the marginal structured coalescent approximation}, volume={34}, ISSN={["1460-2059"]}, DOI={10.1093/bioinformatics/bty406}, abstractNote={Abstract
               
                  Motivation
                  The structured coalescent is widely applied to study demography within and migration between sub-populations from genetic sequence data. Current methods are either exact but too computationally inefficient to analyse large datasets with many sub-populations, or make strong approximations leading to severe biases in inference. We recently introduced an approximation based on weaker assumptions to the structured coalescent enabling the analysis of larger datasets with many different states. We showed that our approximation provides unbiased migration rate and population size estimates across a wide parameter range.
               
               
                  Results
                  We extend this approach by providing a new algorithm to calculate the probability of the state of internal nodes that includes the information from the full phylogenetic tree. We show that this algorithm is able to increase the probability attributed to the true sub-population of a node. Furthermore we use improved integration techniques, such that our method is now able to analyse larger datasets, including a H3N2 dataset with 433 sequences sampled from five different locations.
               
               
                  Availability and implementation
                  The presented methods are part of the BEAST2 package MASCOT, the Marginal Approximation of the Structured COalescenT. This package can be downloaded via the BEAUti package manager. The source code is available at https://github.com/nicfel/Mascot.git.
               
               
                  Supplementary information
                  Supplementary data are available at Bioinformatics online.
               }, number={22}, journal={BIOINFORMATICS}, author={Mueller, Nicola F. and Rasmussen, David and Stadler, Tanja}, year={2018}, month={Nov}, pages={3843–3848} }
 @article{rasmussen_wilkinson_vandormael_tanser_pillay_stadler_oliveira_2018, title={Tracking external introductions of HIV using phylodynamics reveals a major source of infections in rural KwaZulu-Natal, South Africa}, volume={4}, ISSN={["2057-1577"]}, DOI={10.1093/ve/vey037}, abstractNote={Abstract Despite increasing access to antiretrovirals, HIV incidence in rural KwaZulu-Natal remains among the highest ever reported in Africa. While many epidemiological factors have been invoked to explain such high incidence, widespread human mobility and viral movement suggest that transmission between communities may be a major source of new infections. High cross-community transmission rates call into question how effective increasing the coverage of antiretroviral therapy locally will be at preventing new infections, especially if many new cases arise from external introductions. To help address this question, we use a phylodynamic model to reconstruct epidemic dynamics and estimate the relative contribution of local transmission versus external introductions to overall incidence in KwaZulu-Natal from HIV-1 phylogenies. By comparing our results with population-based surveillance data, we show that we can reliably estimate incidence from viral phylogenies once viral movement in and out of the local population is accounted for. Our analysis reveals that early epidemic dynamics were largely driven by external introductions. More recently, we estimate that 35 per cent (95% confidence interval: 20–60%) of new infections arise from external introductions. These results highlight the growing need to consider larger-scale regional transmission dynamics when designing and testing prevention strategies.}, number={2}, journal={VIRUS EVOLUTION}, author={Rasmussen, David A. and Wilkinson, Eduan and Vandormael, Alain and Tanser, Frank and Pillay, Deenan and Stadler, Tanja and Oliveira, Tulio}, year={2018}, month={Jul} }