@article{shymanovich_saville_mohammad_wei_rasmussen_lahre_rotenberg_whitfield_ristaino_2024, title={Disease Progress and Detection of a California Resistance-Breaking Strain of Tomato Spotted Wilt Virus in Tomato with LAMP and CRISPR-Cas12a Assays}, volume={4}, ISSN={2690-5442}, url={http://dx.doi.org/10.1094/PHYTOFR-05-23-0058-FI}, DOI={10.1094/PHYTOFR-05-23-0058-FI}, abstractNote={Use of tomato cultivars with the Sw-5 resistance gene cluster has led to the occurrence of resistance-breaking (RB) tomato spotted wilt virus (TSWV) strains globally, including California and, recently, North Carolina and Texas. We documented disease on tomato infected with either an RB strain from California (CA-RB) or a wild type (CA-WT) strain of TSWV on tomato with (cultivar Mountain Merit) or without (cultivar Mountain Fresh Plus) the Sw-5b resistance gene and detected virus incidence over time using microneedle RNA extractions and LAMP. We developed a LAMP/Cas12a assay for detection of the CA-C118Y mutation in a CA-RB strain and tested the assay with field samples. Disease in the susceptible cultivar was less severe with CA-RB than with the CA-WT strain. In contrast, the resistant cultivar had little disease when inoculated with the CA-WT strain but exhibited stunting of greater than 50% when inoculated with the CA-RB strain. In the susceptible tomatoes, the detection rates over time by LAMP reaction were higher in CA-WT than in CA-RB-inoculated plants. In resistant tomato, CA-RB remained detectable by TSWV LAMP over 14 days, whereas the WT strain was undetectable. A two-step LAMP/Cas12a assay differentiated the two strains in 1 h. Our methods were validated with samples from TSWV-infected North Carolina fields. A phylogeny of NSm gene sequences that included North Carolina field samples revealed two independent origins of the North Carolina RB isolates. The LAMP/Cas12 assay showed excellent detection of the CA-C118Y mutation. The TSWV LAMP/Cas12a assay is adaptable for in-field applications on either a smart phone platform or heat block. [Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license .}, number={1}, journal={PhytoFrontiers™}, publisher={Scientific Societies}, author={Shymanovich, Tatsiana and Saville, Amanda C. and Mohammad, Noor and Wei, Qingshan and Rasmussen, David and Lahre, Kirsten A. and Rotenberg, Dorith and Whitfield, Anna E. and Ristaino, Jean Beagle}, year={2024}, month={Mar}, pages={50–60} } @article{cen_rasmussen_2024, title={Exploring the Accuracy and Limits of Algorithms for Localizing Recombination Breakpoints}, volume={41}, ISSN={0737-4038 1537-1719}, url={http://dx.doi.org/10.1093/molbev/msae133}, 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}, publisher={Oxford University Press (OUP)}, author={Cen, Shi and Rasmussen, David A}, editor={Ouangraoua, AidaEditor}, year={2024}, month={Jun} } @misc{koelle_rasmussen_2024, title={Phylodynamics beyond neutrality: The impact of incomplete purifying selection on viral phylogenies and inference}, url={http://dx.doi.org/10.1101/2024.08.28.610037}, DOI={10.1101/2024.08.28.610037}, abstractNote={Abstract Viral phylodynamics focuses on using sequence data to make inferences about the population dynamics of viral infectious diseases. These inferences commonly include estimation of the viral growth rate, the reproduction number, and the time of most recent common ancestor. With few exceptions, existing phylodynamic inference approaches assume that all observed and ancestral viral genetic variation is fitness-neutral. This assumption is violated more often than not, with a large body of analyses indicating that fitness varies substantially among genotypes circulating viral populations. Here, we focus specifically on fitness variation arising from deleterious mutations, asking whether incomplete purifying selection of deleterious mutations has the potential to bias phylodynamic inference. We use simulations of an exponentially growing population to explore how incomplete purifying selection distorts tree shape as well as how it shifts the distribution of non-neutral mutations over trees. Consistent with previous results, we find that incomplete purifying selection strongly shapes the distribution of mutations while only weakly impacting tree shape. Despite incomplete purifying selection shifting the distribution of mutations, we find little discernible bias in estimates of the viral growth rate and times of the most recent common ancestor. Our results reassuringly indicate that existing phylodynamic inference approaches may not yield biased epidemiological parameter estimates in the face of incomplete purifying selection, although more work is needed to assess the generalizability of these findings.}, publisher={Cold Spring Harbor Laboratory}, author={Koelle, Katia and Rasmussen, David A.}, year={2024}, month={Aug} } @misc{kepler_jara_mahmud_dantas_dubberke_lanzas_rasmussen_2024, title={Quantifying the genomic determinants of fitness inE. coliST131 using phylodynamics}, url={http://dx.doi.org/10.1101/2024.06.10.598183}, DOI={10.1101/2024.06.10.598183}, abstractNote={Abstract Antimicrobial resistant pathogens such as Escherichia coli sequence type 131 (ST131) pose a serious threat to public health globally. In the United States, ST131 acquired multiple antimicrobial resistance (AMR) genes and rapidly grew to its current high prevalence in healthcare settings. Notably, this coincided with the introduction and widespread use of antibiotics such as fluoroquinolones, suggesting AMR as the major driver of ST131’s expansion. Yet, within ST131, there remains considerable diversity between strains in resistance profiles and their repertoires of virulence factors, stress factors, plasmids, and other accessory elements. Understanding which genomic features contribute to ST131’s competitive advantage and their relative effects on population-level fitness therefore poses a considerable challenge. Here we use phylodynamic birth-death models to estimate the relative fitness of different ST131 lineages from bacterial phylogenies. By extending these phylodynamic methods to allow multiple genomic features to shape bacterial fitness, we further quantify the relative contribution of individual AMR genes to ST131’s fitness. Our analysis indicates that while many genomic elements, including various AMR genes, virulence factors, and plasmids, have all contributed substantially to ST131’s rapid growth, major increases in ST131’s fitness are largely attributable to mutations in gyrase A that confer resistance to fluoroquinolones. Author summary ST131 is a pandemic lineage of E. coli that has spread globally and is now responsible for a large percentage of blood and urinary tract infections that cannot be treated with many common antibiotics. While antibiotic resistance has undoubtedly given ST131 a competitive edge, the relative importance of resistance compared with other factors shaping a pathogen’s growth or transmission potential (i.e. fitness) is often difficult to measure in natural settings. Here, we present a method that allows us to look at the entire spectrum of factors determining a pathogen’s fitness and estimate the individual contribution of each component to pathogen’s overall fitness. Our results suggest that resistance to fluoroquinolones, a widely used class of antibiotics, provides ST131 with a disproportionately large fitness advantage relative to many other factors with more moderate fitness effects. Understanding what determines the fitness of ST131 therefore provides insights that can be used to curb the spread of resistance and monitor for emerging lineages with high pandemic potential due to shared fitness enhancing attributes.}, publisher={Cold Spring Harbor Laboratory}, author={Kepler, Lenora M. and Jara, Manuel and Mahmud, Bejan and Dantas, Gautam and Dubberke, Erik R. and Lanzas, Cristina and Rasmussen, David A.}, year={2024}, month={Jun} } @article{wang_muller_mcdowell_rasmussen_2024, title={Quantifying the strength of viral fitness trade-offs between hosts: a meta-analysis of pleiotropic fitness effects}, volume={8}, ISSN={2056-3744}, url={http://dx.doi.org/10.1093/evlett/qrae038}, DOI={10.1093/evlett/qrae038}, abstractNote={Abstract The range of hosts a given virus can infect is widely presumed to be limited by fitness trade-offs between alternative hosts. These fitness trade-offs may arise naturally due to antagonistic pleiotropy if mutations that increase fitness in one host tend to decrease fitness in alternate hosts. Yet there is also growing recognition that positive pleiotropy may be more common than previously appreciated. With positive pleiotropy, mutations have concordant fitness effects such that a beneficial mutation can simultaneously increase fitness in different hosts, providing a genetic mechanism by which selection can overcome fitness trade-offs. How readily evolution can overcome fitness trade-offs therefore depends on the overall distribution of mutational fitness effects between hosts, including the relative frequency of antagonistic versus positive pleiotropy. We therefore conducted a systematic meta-analysis of the pleiotropic fitness effects of viral mutations reported in different hosts. Our analysis indicates that while both antagonistic and positive pleiotropy are common, fitness effects are overall positively correlated between hosts and unconditionally beneficial mutations are not uncommon. Moreover, the relative frequency of antagonistic versus positive pleiotropy may simply reflect the underlying frequency of beneficial and deleterious mutations in individual hosts. Given a mutation is beneficial in one host, the probability that it is deleterious in another host is roughly equal to the probability that any mutation is deleterious, suggesting there is no natural tendency toward antagonistic pleiotropy. The widespread prevalence of positive pleiotropy suggests that many fitness trade-offs may be readily overcome by evolution given the right selection pressures.}, number={6}, journal={Evolution Letters}, publisher={Oxford University Press (OUP)}, author={Wang, Xuechun ‘May’ and Muller, Julia and McDowell, Mya and Rasmussen, David A}, year={2024}, month={Jul}, pages={851–865} } @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}, volume={7}, 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={1063-5157 1076-836X}, url={http://dx.doi.org/10.1093/sysbio/syad040}, 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}, publisher={Oxford University Press (OUP)}, author={Rasmussen, David A and Guo, Fangfang}, editor={Gascuel, OlivierEditor}, year={2023}, month={Jul}, pages={1154–1170} } @article{hasegawa_techer_adjlane_al-hissnawi_antúnez_beaurepaire_christmon_delatte_dukku_eliash_et al._2023, title={Evolutionarily diverse origins of deformed wing viruses in western honey bees}, volume={120}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.2301258120}, 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}, publisher={Proceedings of the National Academy of Sciences}, author={Hasegawa, Nonno and Techer, Maeva A. and Adjlane, Noureddine and al-Hissnawi, Muntasser Sabah and Antúnez, 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{cen_rasmussen_2023, title={Exploring the accuracy and limits of algorithms for localizing recombination breakpoints}, url={https://doi.org/10.1101/2023.12.08.570844}, DOI={10.1101/2023.12.08.570844}, 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 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 GARD. The accuracy of inferred breakpoint locations was evaluated along with the key factors contributing to variation in accuracy across data sets. 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.}, author={Cen, Shi and Rasmussen, David A.}, year={2023}, month={Dec} } @article{muller_mcdowell_rasmussen_2023, title={Quantifying the strength of viral fitness tradeoffs between hosts: A meta-analysis of pleiotropic fitness effects}, url={https://doi.org/10.1101/2023.12.16.571995}, DOI={10.1101/2023.12.16.571995}, abstractNote={Abstract The range of hosts a given virus can infect is widely presumed to be limited by fitness tradeoffs between alternative hosts. These fitness tradeoffs may arise naturally due to antagonistic pleiotropy if mutations that increase fitness in one host tend to decrease fitness in alternate hosts. Yet there is also growing recognition that positive pleiotropy may be more common than previously appreciated. With positive pleiotropy, mutations have concordant fitness effects such that a beneficial mutation can simultaneously increase fitness in different hosts, providing a genetic mechanism by which selection can overcome fitness tradeoffs. How readily evolution can overcome fitness tradeoffs therefore depends on the overall distribution of mutational fitness effects between hosts, including the relative frequency of antagonistic versus positive pleiotropy. We therefore conducted a systematic meta-analysis of the pleiotropic fitness effects of viral mutations reported in different hosts. Our analysis indicates that while both antagonistic and positive pleiotropy are common, fitness effects are overall positively correlated between hosts and unconditionally beneficial mutations are not uncommon. Moreover, the relative frequency of antagonistic versus positive pleiotropy may simply reflect the underlying frequency of beneficial and deleterious mutations in individual hosts. Given a mutation is beneficial in one host, the probability that it is deleterious in another host is roughly equal to the probability that any mutation is deleterious, suggesting there is no natural tendency towards antagonistic pleiotropy. The widespread prevalence of positive pleiotropy suggests that many fitness tradeoffs may be readily overcome by evolution given the right selection pressures. Lay summary Evolutionary theory suggests that fitness tradeoffs between alternative environments constrain the potential for organisms to simultaneously adapt to multiple environments. Likewise, fitness tradeoffs between alternative hosts are widely believed to limit the ability of viruses to adapt to multiple hosts and thereby expand their host range. How strongly viruses are constrained by such tradeoffs will largely depend on the fitness effects of new mutations. Fitness tradeoffs may inevitably constrain viral evolution if mutations that increase fitness in one host tend to decrease fitness in alternative hosts. However, mutations can sometimes increase fitness in multiple hosts, allowing viruses to adapt to new hosts without paying fitness costs. Geneticists refer to these two scenarios as antagonistic and positive pleiotropy depending on whether mutations have opposite or concordant fitness effects. Because the relative frequency of antagonistic versus positive pleiotropy is centrally important to viral evolution, we conducted a systematic meta-analysis of the fitness effects of mutations reported in different hosts. Our analysis reveals that cases of positive pleiotropy where mutations have beneficial effects in more than one host may be sufficiently common for evolution to resolve many apparent fitness tradeoffs between hosts.}, author={Muller, Julia and McDowell, Mya and Rasmussen, David A.}, year={2023}, month={Dec} } @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{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={7}, ISSN={2379-5077}, url={http://dx.doi.org/10.1128/msystems.00519-22}, DOI={https://doi.org/10.1128/msystems.00519-22}, abstractNote={The prevalence of extended-spectrum beta-lactamases (ESBLs) among clinical isolates of Escherichia coli has been increasing, with this spread driven by ESBL-encoding plasmids. However, the epidemiology of ESBL-disseminating plasmids remains understudied, obscuring the roles of individual plasmid lineages in ESBL spread. To address this, we performed an in-depth genomic investigation of 149 clinical ESBL-like E. coli isolates from a tertiary care hospital. We obtained high-quality assemblies for 446 plasmids, revealing an extensive map of plasmid sharing that crosses time, space, and bacterial sequence type boundaries. Through a sequence-based network, we identified specific plasmid lineages that are responsible for the dissemination of major ESBLs. Notably, we demonstrate that IncF plasmids separate into 2 distinct lineages that are enriched for different ESBLs and occupy distinct host ranges. Our work provides a detailed picture of plasmid-mediated spread of ESBLs, demonstrating the extensive sequence diversity within identified lineages, while highlighting the genetic elements that underlie the persistence of these plasmids within the clinical E. coli population. IMPORTANCE 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. Here, we identify the contributions of different plasmid lineages in the nosocomial spread of ESBLs. We provide further support for plasmid-mediated spread of ESBLs but demonstrate that some ESBL genes rely on dissemination through plasmids more than the others. We identify key plasmid lineages that are enriched in major ESBL genes and highlight the encoded genetic elements that facilitate the transmission and stable maintenance of these plasmid groups within the clinical E. coli population. Overall, our work provides valuable insight into the dissemination of ESBLs through plasmids, furthering our understating of factors underlying the increased prevalence of these genes in nosocomial settings.}, number={5}, journal={mSystems}, publisher={American Society for Microbiology}, 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={Oct} } @article{rasmussen_guo_2022, title={Espalier: Efficient tree reconciliation and ARG reconstruction using maximum agreement forests}, url={https://doi.org/10.1101/2022.01.17.476639}, DOI={10.1101/2022.01.17.476639}, 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 a 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.}, author={Rasmussen, David A. and Guo, Fangfang}, year={2022}, month={Jan} } @article{lapp_obala_abel_rasmussen_sumner_freedman_taylor_prudhomme-o'meara_2022, title={Plasmodium falciparum Genetic Diversity in Coincident Human and Mosquito Hosts}, volume={9}, 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{lapp_obala_abel_rasmussen_sumner_freedman_taylor_prudhomme-o’meara_2022, title={Plasmodium falciparum Genetic Diversity in Coincident Human and Mosquito Hosts}, volume={13}, ISSN={2150-7511}, url={http://dx.doi.org/10.1128/mbio.02277-22}, DOI={https://doi.org/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.}, number={5}, journal={mBio}, publisher={American Society for Microbiology}, 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}, editor={Miller, Louis H.Editor}, year={2022}, month={Oct} } @article{guo_carbone_rasmussen_2022, title={Recombination-aware Phylogeographic Inference Using the Structured Coalescent with Ancestral Recombination}, volume={2}, url={https://doi.org/10.1101/2022.02.08.479599}, DOI={10.1101/2022.02.08.479599}, abstractNote={Abstract 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 fungus Aspergillus flavus sampled across the United States to explore patterns of recombination and migration across the genome.}, publisher={Cold Spring Harbor Laboratory}, author={Guo, Fangfang and Carbone, Ignazio and Rasmussen, David A.}, year={2022}, month={Feb} } @article{guo_carbone_rasmussen_2022, title={Recombination-aware phylogeographic inference using the structured coalescent with ancestral recombination}, volume={18}, ISSN={1553-7358}, url={http://dx.doi.org/10.1371/journal.pcbi.1010422}, 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}, publisher={Public Library of Science (PLoS)}, author={Guo, Fangfang and Carbone, Ignazio and Rasmussen, David A.}, editor={Schiffels, StephanEditor}, year={2022}, month={Aug}, pages={e1010422} } @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={0036-8075 1095-9203}, url={http://dx.doi.org/10.1126/science.abq5358}, 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}, publisher={American Association for the Advancement of Science (AAAS)}, 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={0036-8075 1095-9203}, url={http://dx.doi.org/10.1126/science.abj4336}, 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}, publisher={American Association for the Advancement of Science (AAAS)}, 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={423–431} } @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}, url={http://dx.doi.org/10.1093/ve/veab073}, 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}, publisher={Oxford University Press (OUP)}, author={Kepler, Lenora and Hamins-Puertolas, Marco and Rasmussen, David A}, year={2021}, month={Sep} } @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={http://dx.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}, publisher={The Royal Society}, author={Dawson, Daniel and Rasmussen, David and Peng, Xinxia and Lanzas, Cristina}, year={2021}, month={Jun}, pages={20210041} } @article{gadhave_gautam_rasmussen_srinivasan_2020, title={Aphid Transmission of Potyvirus: The Largest Plant-Infecting RNA Virus Genus}, volume={12}, ISSN={1999-4915}, url={http://dx.doi.org/10.3390/v12070773}, 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}, publisher={MDPI AG}, author={Gadhave, Kiran R. and Gautam, Saurabh and Rasmussen, David A. and Srinivasan, Rajagopalbabu}, year={2020}, month={Jul}, pages={773} } @article{kepler_hamins-puertolas_rasmussen_2020, title={Decomposing the sources of SARS-CoV-2 fitness variation in the United States}, url={https://doi.org/10.1101/2020.12.14.422739}, DOI={10.1101/2020.12.14.422739}, 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 behaviour influence between-host transmission potential. These challenges have 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.}, author={Kepler, Lenora and Hamins-Puertolas, Marco and Rasmussen, David A.}, year={2020}, month={Dec} } @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{ruark-seward_bonville_kennedy_rasmussen_2020, title={Evolutionary dynamics ofTomato spotted wilt viruswithin and between alternate plant hosts and thrips}, url={https://doi.org/10.1101/2020.01.13.904250}, DOI={10.1101/2020.01.13.904250}, abstractNote={Abstract Tomato 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.}, author={Ruark-Seward, Casey L. and Bonville, Brian and Kennedy, George and Rasmussen, David A.}, year={2020}, month={Jan} } @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} } @article{jara_rasmussen_corzo_machado_2020, title={Porcine reproductive and respiratory syndrome virus dissemination across pig production systems in the United States}, volume={68}, ISSN={1865-1674 1865-1682}, url={http://dx.doi.org/10.1111/tbed.13728}, DOI={10.1111/tbed.13728}, abstractNote={Porcine reproductive and respiratory syndrome virus (PRRSV) remains widespread in the North American pig population. Despite improvements in virus characterization, it is unclear whether PRRSV infections are a product of viral circulation within a farm, within production systems (local) or across production systems (external). Here we examined the dissemination dynamics of PRRSV and the processes facilitating its spread within and among pig farms in three production systems. Overall, PRRSV genetic diversity declined since 2018, while phylodynamic results support frequent transmission across-production systems. We found that PRRSV dissemination occurred mostly through transmission between farms of different production companies, which were predominant for several months, especially from November until May when PRRSV tends to peak in the studied region. Within production systems, dissemination occurred mainly through regular pig flow (from sow to nursery and then to finisher farms); nevertheless, an important flux of PRRSV dissemination from finisher to sow and nursery farms highlighted the importance of downstream farms as sources of the virus. Farms at areas with pig density from500 to 1000 pig/km2 and farms located at a range within 0.5 km and 0.7 km from major roads were more likely to infect by PRRSV, whereas farms at elevation between41 and 61 meters and denser vegetation acted as dissemination barriers. Although remains a challenge, there is a need to disentangle the route of PRRSV transmission, results evidenced that dissemination among commercially unrelated pig production systems was intense, reinforcing the importance of farm proximity on PRRSV spread. Thus, consideration of farm location and their geographic characteristics may help to forecast dissemination. The understanding of PRRSV transmission routes has the potential to inform targeted strategies for its prevention and control. Further studies are needed to quantify the relative contribution of PRRSV transmission routes.}, number={2}, journal={Transboundary and Emerging Diseases}, publisher={Wiley}, author={Jara, Manuel and Rasmussen, David A. and Corzo, Cesar A. and Machado, Gustavo}, year={2020}, month={Aug}, pages={667–683} } @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 fitness-dependent birth-death models}, volume={1}, url={https://doi.org/10.1101/531525}, DOI={10.1101/531525}, abstractNote={Abstract Beneficial and deleterious mutations cause fitness to vary among individuals in a population, which natural selection can then act upon to drive adaptive evolution. Non-neutral mutations can likewise cause fitness to vary among lineages in a phylogeny and thereby shape its branching structure. While standard phylogenetic models do not allow mutations to feedback and shape tree topology, birth-death models can account for this feedback by letting the fitness of lineages vary depending on their type. To date though, these multi-type birth-death models have only been applied to cases where a lineage’s fitness is determined by a single evolving character state and have not been extended to model sequence evolution across multiple sites. We introduce an extension of the multi-type birth-death model, the marginal fitness birth-death model, that tracks sequence evolution at multiple sites and how the fitness of a lineage depends on its genotype across all sites. This approach remains computationally tractable even for many evolving sites because it tracks the genotype of a lineage probabilistically in an approximate manner, and then marginalizes over all possible genotypes to determine the expected fitness of a lineage. Although approximate, we show that we can accurately estimate the fitness of a lineage and even site-specific mutational fitness effects from the branching pattern of a phylogeny. To demonstrate the power of this approach, we apply it to estimate the host population level fitness effects of mutations previously identified to increase the infectivity of Ebola virus in human cell lines during the 2013-16 epidemic in West Africa.}, publisher={Cold Spring Harbor Laboratory}, author={Rasmussen, David A. and Stadler, Tanja}, year={2019}, month={Jan} } @article{rasmussen_stadler_2019, title={Coupling adaptive molecular evolution to phylodynamics using fittness-dependent birth-death models}, volume={8}, ISSN={["2050-084X"]}, url={https://doi.org/10.7554/eLife.45562}, 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}, publisher={eLife Sciences Publications, Ltd}, author={Rasmussen, David A. and Stadler, Tanja}, year={2019}, month={Aug} } @misc{chen_dessau_rotenberg_rasmussen_whitfield_2019, title={Entry of bunyaviruses into plants and vectors}, volume={104}, ISBN={["978-0-12-818394-6"]}, ISSN={0065-3527}, url={http://dx.doi.org/10.1016/bs.aivir.2019.07.001}, 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={Advances in Virus Research}, publisher={Elsevier}, 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"]}, url={https://doi.org/10.1093/ve/vey037}, 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}, publisher={Oxford University Press (OUP)}, 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} } @article{rasmussen_kouyos_günthard_stadler_2017, title={Phylodynamics on local sexual contact networks}, volume={13}, DOI={10.1371/journal.pcbi.1005448}, abstractNote={Phylodynamic models are widely used in infectious disease epidemiology to infer the dynamics and structure of pathogen populations. However, these models generally assume that individual hosts contact one another at random, ignoring the fact that many pathogens spread through highly structured contact networks. We present a new framework for phylodynamics on local contact networks based on pairwise epidemiological models that track the status of pairs of nodes in the network rather than just individuals. Shifting our focus from individuals to pairs leads naturally to coalescent models that describe how lineages move through networks and the rate at which lineages coalesce. These pairwise coalescent models not only consider how network structure directly shapes pathogen phylogenies, but also how the relationship between phylogenies and contact networks changes depending on epidemic dynamics and the fraction of infected hosts sampled. By considering pathogen phylogenies in a probabilistic framework, these coalescent models can also be used to estimate the statistical properties of contact networks directly from phylogenies using likelihood-based inference. We use this framework to explore how much information phylogenies retain about the underlying structure of contact networks and to infer the structure of a sexual contact network underlying a large HIV-1 sub-epidemic in Switzerland.}, number={3}, journal={PLOS Computational Biology}, publisher={Public Library of Science (PLoS)}, author={Rasmussen, David A. and Kouyos, Roger and Günthard, Huldrych F. and Stadler, Tanja}, editor={Alizon, SamuelEditor}, year={2017}, month={Mar}, pages={e1005448} } @article{barido-sottani_bošková_plessis_kühnert_magnus_mitov_müller_pečerska_rasmussen_zhang_et al._2017, title={Taming the BEAST—A Community Teaching Material Resource for BEAST 2}, volume={67}, ISSN={1063-5157 1076-836X}, url={http://dx.doi.org/10.1093/sysbio/syx060}, DOI={10.1093/sysbio/syx060}, abstractNote={Phylogenetics and phylodynamics are central topics in modern evolutionary biology. Phylogenetic methods reconstruct the evolutionary relationships among organisms, whereas phylodynamic approaches reveal the underlying diversification processes that lead to the observed relationships. These two fields have many practical applications in disciplines as diverse as epidemiology, developmental biology, palaeontology, ecology, and linguistics. The combination of increasingly large genetic data sets and increases in computing power is facilitating the development of more sophisticated phylogenetic and phylodynamic methods. Big data sets allow us to answer complex questions. However, since the required analyses are highly specific to the particular data set and question, a black-box method is not sufficient anymore. Instead, biologists are required to be actively involved with modeling decisions during data analysis. The modular design of the Bayesian phylogenetic software package BEAST 2 enables, and in fact enforces, this involvement. At the same time, the modular design enables computational biology groups to develop new methods at a rapid rate. A thorough understanding of the models and algorithms used by inference software is a critical prerequisite for successful hypothesis formulation and assessment. In particular, there is a need for more readily available resources aimed at helping interested scientists equip themselves with the skills to confidently use cutting-edge phylogenetic analysis software. These resources will also benefit researchers who do not have access to similar courses or training at their home institutions. Here, we introduce the "Taming the Beast" (https://taming-the-beast.github.io/) resource, which was developed as part of a workshop series bearing the same name, to facilitate the usage of the Bayesian phylogenetic software package BEAST 2.}, number={1}, journal={Systematic Biology}, publisher={Oxford University Press (OUP)}, author={Barido-Sottani, Joëlle and Bošková, Veronika and Plessis, Louis Du and Kühnert, Denise and Magnus, Carsten and Mitov, Venelin and Müller, Nicola F. and PečErska, Jūlija and Rasmussen, David A. and Zhang, Chi and et al.}, year={2017}, month={Jun}, pages={170–174} } @article{müller_rasmussen_stadler_2017, title={The Structured Coalescent and Its Approximations}, volume={34}, ISSN={0737-4038 1537-1719}, url={http://dx.doi.org/10.1093/molbev/msx186}, DOI={10.1093/molbev/msx186}, abstractNote={Phylogeographic methods can help reveal the movement of genes between populations of organisms. This has been widely done to quantify pathogen movement between different host populations, the migration history of humans, and the geographic spread of languages or gene flow between species using the location or state of samples alongside sequence data. Phylogenies therefore offer insights into migration processes not available from classic epidemiological or occurrence data alone. Phylogeographic methods have however several known shortcomings. In particular, one of the most widely used methods treats migration the same as mutation, and therefore does not incorporate information about population demography. This may lead to severe biases in estimated migration rates for data sets where sampling is biased across populations. The structured coalescent on the other hand allows us to coherently model the migration and coalescent process, but current implementations struggle with complex data sets due to the need to infer ancestral migration histories. Thus, approximations to the structured coalescent, which integrate over all ancestral migration histories, have been developed. However, the validity and robustness of these approximations remain unclear. We present an exact numerical solution to the structured coalescent that does not require the inference of migration histories. Although this solution is computationally unfeasible for large data sets, it clarifies the assumptions of previously developed approximate methods and allows us to provide an improved approximation to the structured coalescent. We have implemented these methods in BEAST2, and we show how these methods compare under different scenarios.}, number={11}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Müller, Nicola F. and Rasmussen, David A. and Stadler, Tanja}, year={2017}, month={Jun}, pages={2970–2981} } @article{wilkinson_rasmussen_ratmann_stadler_engelbrecht_de oliveira_2016, title={Origin, imports and exports of HIV-1 subtype C in South Africa: A historical perspective}, volume={46}, ISSN={1567-1348}, url={http://dx.doi.org/10.1016/j.meegid.2016.07.008}, DOI={10.1016/j.meegid.2016.07.008}, journal={Infection, Genetics and Evolution}, publisher={Elsevier BV}, author={Wilkinson, Eduan and Rasmussen, David and Ratmann, Oliver and Stadler, Tanja and Engelbrecht, Susan and de Oliveira, Tulio}, year={2016}, month={Dec}, pages={200–208} } @article{rasmussen_kouyos_günthard_stadler_2016, title={Phylodynamics on local sexual contact networks}, url={https://doi.org/10.1101/082966}, DOI={10.1101/082966}, abstractNote={Abstract Phylodynamic models are widely used in infectious disease epidemiology to infer the dynamics and structure of pathogen populations. However, these models generally assume that individual hosts contact one another at random, ignoring the fact that many pathogens spread through highly structured contact networks. We present a new framework for phylodynamics on local contact networks based on pairwise epidemiological models that track the status of pairs of nodes in the network rather than just individuals. Shifting our focus from individuals to pairs leads naturally to coalescent models that describe how lineages move through networks and the rate at which lineages coalesce. These pairwise coalescent models not only consider how network structure directly shapes pathogen phylogenies, but also how the relationship between phylogenies and contact networks changes depending on epidemic dynamics and the fraction of infected hosts sampled. By considering pathogen phylogenies in a probabilistic framework, these coalescent models can also be used to estimate the statistical properties of contact networks directly from phylogenies using likelihood-based inference. We use this framework to explore how much information phylogenies retain about the underlying structure of contact networks and to infer the structure of a sexual contact network underlying a large HIV-1 sub-epidemic in Switzerland.}, author={Rasmussen, David A. and Kouyos, Roger and Günthard, Huldrych F. and Stadler, Tanja}, year={2016}, month={Oct} } @article{ratmann_hodcroft_pickles_cori_hall_lycett_colijn_dearlove_didelot_frost_et al._2016, title={Phylogenetic Tools for Generalized HIV-1 Epidemics: Findings from the PANGEA-HIV Methods Comparison}, volume={34}, ISSN={0737-4038 1537-1719}, url={http://dx.doi.org/10.1093/molbev/msw217}, DOI={10.1093/molbev/msw217}, abstractNote={Viral phylogenetic methods contribute to understanding how HIV spreads in populations, and thereby help guide the design of prevention interventions. So far, most analyses have been applied to well-sampled concentrated HIV-1 epidemics in wealthy countries. To direct the use of phylogenetic tools to where the impact of HIV-1 is greatest, the Phylogenetics And Networks for Generalized HIV Epidemics in Africa (PANGEA-HIV) consortium generates full-genome viral sequences from across sub-Saharan Africa. Analyzing these data presents new challenges, since epidemics are principally driven by heterosexual transmission and a smaller fraction of cases is sampled. Here, we show that viral phylogenetic tools can be adapted and used to estimate epidemiological quantities of central importance to HIV-1 prevention in sub-Saharan Africa. We used a community-wide methods comparison exercise on simulated data, where participants were blinded to the true dynamics they were inferring. Two distinct simulations captured generalized HIV-1 epidemics, before and after a large community-level intervention that reduced infection levels. Five research groups participated. Structured coalescent modeling approaches were most successful: phylogenetic estimates of HIV-1 incidence, incidence reductions, and the proportion of transmissions from individuals in their first 3 months of infection correlated with the true values (Pearson correlation > 90%), with small bias. However, on some simulations, true values were markedly outside reported confidence or credibility intervals. The blinded comparison revealed current limits and strengths in using HIV phylogenetics in challenging settings, provided benchmarks for future methods' development, and supports using the latest generation of phylogenetic tools to advance HIV surveillance and prevention.}, number={1}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Ratmann, Oliver and Hodcroft, Emma B. and Pickles, Michael and Cori, Anne and Hall, Matthew and Lycett, Samantha and Colijn, Caroline and Dearlove, Bethany and Didelot, Xavier and Frost, Simon and et al.}, year={2016}, month={Oct}, pages={185–203} } @article{koelle_rasmussen_2015, title={The effects of a deleterious mutation load on patterns of influenza A/H3N2's antigenic evolution in humans}, volume={4}, ISSN={2050-084X}, url={http://dx.doi.org/10.7554/elife.07361}, DOI={10.7554/elife.07361}, abstractNote={Recent phylogenetic analyses indicate that RNA virus populations carry a significant deleterious mutation load. This mutation load has the potential to shape patterns of adaptive evolution via genetic linkage to beneficial mutations. Here, we examine the effect of deleterious mutations on patterns of influenza A subtype H3N2's antigenic evolution in humans. By first analyzing simple models of influenza that incorporate a mutation load, we show that deleterious mutations, as expected, act to slow the virus's rate of antigenic evolution, while making it more punctuated in nature. These models further predict three distinct molecular pathways by which antigenic cluster transitions occur, and we find phylogenetic patterns consistent with each of these pathways in influenza virus sequences. Simulations of a more complex phylodynamic model further indicate that antigenic mutations act in concert with deleterious mutations to reproduce influenza's spindly hemagglutinin phylogeny, co-circulation of antigenic variants, and high annual attack rates.}, journal={eLife}, publisher={eLife Sciences Publications, Ltd}, author={Koelle, Katia and Rasmussen, David A}, year={2015}, month={Sep} } @article{stadler_kühnert_rasmussen_du plessis_2014, title={Insights into the early epidemic spread of Ebola in Sierra Leone provided by viral sequence data}, volume={10}, DOI={10.1371/currents.outbreaks.02bc6d927ecee7bbd33532ec8ba6a25f}, abstractNote={The current Ebola virus epidemic in West Africa has been spreading at least since December 2013. The first confirmed case of Ebola virus in Sierra Leone was identified on May 25. Based on viral genetic sequencing data from 72 individuals in Sierra Leone collected between the end of May and mid June, we utilize a range of phylodynamic methods to estimate the basic reproductive number (R0). We additionally estimate the expected lengths of the incubation and infectious periods of the virus. Finally, we use phylogenetic trees to examine the role played by population structure in the epidemic.The median estimates of R0 based on sequencing data alone range between 1.65-2.18, with the most plausible model yielding a median R0 of 2.18 (95% HPD 1.24-3.55). Importantly, our results indicate that, at least until mid June, relief efforts in Sierra Leone were ineffective at lowering the effective reproductive number of the virus. We estimate the expected length of the infectious period to be 2.58 days (median; 95% HPD 1.24-6.98). The dataset appears to be too small in order to estimate the incubation period with high certainty (median expected incubation period 4.92 days; 95% HPD 2.11-23.20). While our estimates of the duration of infection tend to be smaller than previously reported, phylodynamic analyses support a previous estimate that 70% of cases were observed and included in the present dataset. The dataset is too small to show a particular population structure with high significance, however our preliminary analyses suggest that half the population is spreading the virus with an R0 well above 2, while the other half of the population is spreading with an R0 below 1.Overall we show that sequencing data can robustly infer key epidemiological parameters. Such estimates inform public health officials and help to coordinate effective public health efforts. Thus having more sequencing data available for the ongoing Ebola virus epidemic and at the start of new outbreaks will foster a quick understanding of the dynamics of the pathogen.}, journal={PLoS Currents}, author={Stadler, T. and Kühnert, D. and Rasmussen, D.A. and du Plessis, L.}, year={2014}, month={Oct} } @article{rasmussen_volz_koelle_2014, title={Phylodynamic Inference for Structured Epidemiological Models}, volume={10}, ISSN={1553-7358}, url={http://dx.doi.org/10.1371/journal.pcbi.1003570}, DOI={10.1371/journal.pcbi.1003570}, abstractNote={Coalescent theory is routinely used to estimate past population dynamics and demographic parameters from genealogies. While early work in coalescent theory only considered simple demographic models, advances in theory have allowed for increasingly complex demographic scenarios to be considered. The success of this approach has lead to coalescent-based inference methods being applied to populations with rapidly changing population dynamics, including pathogens like RNA viruses. However, fitting epidemiological models to genealogies via coalescent models remains a challenging task, because pathogen populations often exhibit complex, nonlinear dynamics and are structured by multiple factors. Moreover, it often becomes necessary to consider stochastic variation in population dynamics when fitting such complex models to real data. Using recently developed structured coalescent models that accommodate complex population dynamics and population structure, we develop a statistical framework for fitting stochastic epidemiological models to genealogies. By combining particle filtering methods with Bayesian Markov chain Monte Carlo methods, we are able to fit a wide class of stochastic, nonlinear epidemiological models with different forms of population structure to genealogies. We demonstrate our framework using two structured epidemiological models: a model with disease progression between multiple stages of infection and a two-population model reflecting spatial structure. We apply the multi-stage model to HIV genealogies and show that the proposed method can be used to estimate the stage-specific transmission rates and prevalence of HIV. Finally, using the two-population model we explore how much information about population structure is contained in genealogies and what sample sizes are necessary to reliably infer parameters like migration rates.}, number={4}, journal={PLoS Computational Biology}, publisher={Public Library of Science (PLoS)}, author={Rasmussen, David A. and Volz, Erik M. and Koelle, Katia}, editor={Kosakovsky Pond, Sergei L.Editor}, year={2014}, month={Apr}, pages={e1003570} } @article{koelle_rasmussen_2014, title={Prediction is worth a shot}, volume={507}, ISSN={0028-0836 1476-4687}, url={http://dx.doi.org/10.1038/nature13054}, DOI={10.1038/nature13054}, number={7490}, journal={Nature}, publisher={Springer Science and Business Media LLC}, author={Koelle, Katia and Rasmussen, David A.}, year={2014}, month={Feb}, pages={47–48} } @article{rasmussen_boni_koelle_2013, title={Reconciling Phylodynamics with Epidemiology: The Case of Dengue Virus in Southern Vietnam}, volume={31}, ISSN={1537-1719 0737-4038}, url={http://dx.doi.org/10.1093/molbev/mst203}, DOI={10.1093/molbev/mst203}, abstractNote={Coalescent methods are widely used to infer the demographic history of populations from gene genealogies. These approaches—often referred to as phylodynamic methods—have proven especially useful for reconstructing the dynamics of rapidly evolving viral pathogens. Yet, population dynamics inferred from viral genealogies often differ widely from those observed from other sources of epidemiological data, such as hospitalization records. We demonstrate how a modeling framework that allows for the direct fitting of mechanistic epidemiological models to genealogies can be used to test different hypotheses about what ecological factors cause phylodynamic inferences to differ from observed dynamics. We use this framework to test different hypotheses about why dengue serotype 1 (DENV-1) population dynamics in southern Vietnam inferred using existing phylodynamic methods differ from hospitalization data. Specifically, we consider how factors such as seasonality, vector dynamics, and spatial structure can affect inferences drawn from genealogies. The coalescent models we derive to take into account vector dynamics and spatial structure reveal that these ecological complexities can substantially affect coalescent rates among lineages. We show that incorporating these additional ecological complexities into coalescent models can also greatly improve estimates of historical population dynamics and lead to new insights into the factors shaping viral genealogies.}, number={2}, journal={Molecular Biology and Evolution}, publisher={Oxford University Press (OUP)}, author={Rasmussen, David A. and Boni, Maciej F. and Koelle, Katia}, year={2013}, month={Oct}, pages={258–271} } @article{koelle_ratmann_rasmussen_pasour_mattingly_2011, title={A dimensionless number for understanding the evolutionary dynamics of antigenically variable RNA viruses}, volume={278}, ISSN={0962-8452 1471-2954}, url={http://dx.doi.org/10.1098/rspb.2011.0435}, DOI={10.1098/rspb.2011.0435}, abstractNote={Antigenically variable RNA viruses are significant contributors to the burden of infectious disease worldwide. One reason for their ubiquity is their ability to escape herd immunity through rapid antigenic evolution and thereby to reinfect previously infected hosts. However, the ways in which these viruses evolve antigenically are highly diverse. Some have only limited diversity in the long-run, with every emergence of a new antigenic variant coupled with a replacement of the older variant. Other viruses rapidly accumulate antigenic diversity over time. Others still exhibit dynamics that can be considered evolutionary intermediates between these two extremes. Here, we present a theoretical framework that aims to understand these differences in evolutionary patterns by considering a virus's epidemiological dynamics in a given host population. Our framework, based on a dimensionless number, probabilistically anticipates patterns of viral antigenic diversification and thereby quantifies a virus's evolutionary potential. It is therefore similar in spirit to the basic reproduction number, the well-known dimensionless number which quantifies a pathogen's reproductive potential. We further outline how our theoretical framework can be applied to empirical viral systems, using influenza A/H3N2 as a case study. We end with predictions of our framework and work that remains to be done to further integrate viral evolutionary dynamics with disease ecology.}, number={1725}, journal={Proceedings of the Royal Society B: Biological Sciences}, publisher={The Royal Society}, author={Koelle, Katia and Ratmann, Oliver and Rasmussen, David A. and Pasour, Virginia and Mattingly, Jonathan}, year={2011}, month={May}, pages={3723–3730} } @article{rasmussen_ratmann_koelle_2011, title={Inference for Nonlinear Epidemiological Models Using Genealogies and Time Series}, volume={7}, ISSN={1553-7358}, url={http://dx.doi.org/10.1371/journal.pcbi.1002136}, DOI={10.1371/journal.pcbi.1002136}, abstractNote={Phylodynamics - the field aiming to quantitatively integrate the ecological and evolutionary dynamics of rapidly evolving populations like those of RNA viruses – increasingly relies upon coalescent approaches to infer past population dynamics from reconstructed genealogies. As sequence data have become more abundant, these approaches are beginning to be used on populations undergoing rapid and rather complex dynamics. In such cases, the simple demographic models that current phylodynamic methods employ can be limiting. First, these models are not ideal for yielding biological insight into the processes that drive the dynamics of the populations of interest. Second, these models differ in form from mechanistic and often stochastic population dynamic models that are currently widely used when fitting models to time series data. As such, their use does not allow for both genealogical data and time series data to be considered in tandem when conducting inference. Here, we present a flexible statistical framework for phylodynamic inference that goes beyond these current limitations. The framework we present employs a recently developed method known as particle MCMC to fit stochastic, nonlinear mechanistic models for complex population dynamics to gene genealogies and time series data in a Bayesian framework. We demonstrate our approach using a nonlinear Susceptible-Infected-Recovered (SIR) model for the transmission dynamics of an infectious disease and show through simulations that it provides accurate estimates of past disease dynamics and key epidemiological parameters from genealogies with or without accompanying time series data.}, number={8}, journal={PLoS Computational Biology}, publisher={Public Library of Science (PLoS)}, author={Rasmussen, David A. and Ratmann, Oliver and Koelle, Katia}, editor={Lemey, PhilippeEditor}, year={2011}, month={Aug}, pages={e1002136} } @article{koelle_rasmussen_2011, title={Rates of coalescence for common epidemiological models at equilibrium}, volume={9}, ISSN={1742-5689 1742-5662}, url={http://dx.doi.org/10.1098/rsif.2011.0495}, DOI={10.1098/rsif.2011.0495}, abstractNote={Coalescent theory provides a mathematical framework for quantitatively interpreting gene genealogies. With the increased availability of molecular sequence data, disease ecologists now regularly apply this body of theory to viral phylogenies, most commonly in attempts to reconstruct demographic histories of infected individuals and to estimate parameters such as the basic reproduction number. However, with few exceptions, the mathematical expressions at the core of coalescent theory have not been explicitly linked to the structure of epidemiological models, which are commonly used to mathematically describe the transmission dynamics of a pathogen. Here, we aim to make progress towards establishing this link by presenting a general approach for deriving a model's rate of coalescence under the assumption that the disease dynamics are at their endemic equilibrium. We apply this approach to four common families of epidemiological models: standard susceptible-infected-susceptible/susceptible-infected-recovered/susceptible-infected-recovered-susceptible models, models with individual heterogeneity in infectivity, models with an exposed but not yet infectious class and models with variable distributions of the infectious period. These results improve our understanding of how epidemiological processes shape viral genealogies, as well as how these processes affect levels of viral diversity and rates of genetic drift. Finally, we discuss how a subset of these coalescent rate expressions can be used for phylodynamic inference in non-equilibrium settings. For the ones that are limited to equilibrium conditions, we also discuss why this is the case. These results, therefore, point towards necessary future work while providing intuition on how epidemiological characteristics of the infection process impact gene genealogies.}, number={70}, journal={Journal of The Royal Society Interface}, publisher={The Royal Society}, author={Koelle, Katia and Rasmussen, David A.}, year={2011}, month={Sep}, pages={997–1007} } @article{blackman_scascitelli_kane_luton_rasmussen_bye_lentz_rieseberg_2011, title={Sunflower domestication alleles support single domestication center in eastern North America}, volume={108}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1104853108}, DOI={10.1073/pnas.1104853108}, abstractNote={Phylogenetic analyses of genes with demonstrated involvement in evolutionary transitions can be an important means of resolving conflicting hypotheses about evolutionary history or process. In sunflower, two genes have previously been shown to have experienced selective sweeps during its early domestication. In the present study, we identified a third candidate early domestication gene and conducted haplotype analyses of all three genes to address a recent, controversial hypothesis about the origin of cultivated sunflower. Although the scientific consensus had long been that sunflower was domesticated once in eastern North America, the discovery of pre-Columbian sunflower remains at archaeological sites in Mexico led to the proposal of a second domestication center in southern Mexico. Previous molecular studies with neutral markers were consistent with the former hypothesis. However, only two indigenous Mexican cultivars were included in these studies, and their provenance and genetic purity have been questioned. Therefore, we sequenced regions of the three candidate domestication genes containing SNPs diagnostic for domestication from large, newly collected samples of Mexican sunflower landraces and Mexican wild populations from a broad geographic range. The new germplasm also was genotyped for 12 microsatellite loci. Our evidence from multiple evolutionarily important loci and from neutral markers supports a single domestication event for extant cultivated sunflower in eastern North America.}, number={34}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Blackman, Benjamin K. and Scascitelli, Moira and Kane, Nolan C. and Luton, Harry H. and Rasmussen, David A. and Bye, Robert A. and Lentz, David L. and Rieseberg, Loren H.}, year={2011}, month={Aug}, pages={14360–14365} } @article{blackman_rasmussen_strasburg_raduski_burke_knapp_michaels_rieseberg_2011, title={Contributions of Flowering Time Genes to Sunflower Domestication and Improvement}, volume={187}, ISSN={1943-2631}, url={http://dx.doi.org/10.1534/genetics.110.121327}, DOI={10.1534/genetics.110.121327}, abstractNote={Determining the identity and distribution of molecular changes leading to the evolution of modern crop species provides major insights into the timing and nature of historical forces involved in rapid phenotypic evolution. In this study, we employed an integrated candidate gene strategy to identify loci involved in the evolution of flowering time during early domestication and modern improvement of the sunflower (Helianthus annuus). Sunflower homologs of many genes with known functions in flowering time were isolated and cataloged. Then, colocalization with previously mapped quantitative trait loci (QTLs), expression, or protein sequence differences between wild and domesticated sunflower, and molecular evolutionary signatures of selective sweeps were applied as step-wise criteria for narrowing down an original pool of 30 candidates. This process led to the discovery that five paralogs in the flowering locus T/terminal flower 1 gene family experienced selective sweeps during the evolution of cultivated sunflower and may be the causal loci underlying flowering time QTLs. Our findings suggest that gene duplication fosters evolutionary innovation and that natural variation in both coding and regulatory sequences of these paralogs responded to a complex history of artificial selection on flowering time during the evolution of cultivated sunflower.}, number={1}, journal={Genetics}, publisher={Oxford University Press (OUP)}, author={Blackman, Benjamin K and Rasmussen, David A and Strasburg, Jared L and Raduski, Andrew R and Burke, John M and Knapp, Steven J and Michaels, Scott D and Rieseberg, Loren H}, year={2011}, month={Jan}, pages={271–287} } @article{rasmussen_noor_2009, title={What can you do with 0.1× genome coverage? A case study based on a genome survey of the scuttle fly Megaselia scalaris (Phoridae)}, volume={10}, ISSN={1471-2164}, url={http://dx.doi.org/10.1186/1471-2164-10-382}, DOI={10.1186/1471-2164-10-382}, abstractNote={The declining cost of DNA sequencing is making genome sequencing a feasible option for more organisms, including many of interest to ecologists and evolutionary biologists. While obtaining high-depth, completely assembled genome sequences for most non-model organisms remains challenging, low-coverage genome survey sequences (GSS) can provide a wealth of biologically useful information at low cost. Here, using a random pyrosequencing approach, we sequence the genome of the scuttle fly Megaselia scalaris and evaluate the utility of our low-coverage GSS approach. Random pyrosequencing of the M. scalaris genome provided a depth of coverage (0.05x-0.1x) much lower than typical GSS studies. We demonstrate that, even with extremely low-coverage sequencing, bioinformatics approaches can yield extensive information about functional and repetitive elements. We also use our GSS data to develop genomic resources such as a nearly complete mitochondrial genome sequence and microsatellite markers for M. scalaris. We conclude that low-coverage genome surveys are effective at generating useful information about organisms currently lacking genomic sequence data.}, number={1}, journal={BMC Genomics}, publisher={Springer Science and Business Media LLC}, author={Rasmussen, David A and Noor, Mohamed AF}, year={2009}, pages={382} } @article{rasmussen_kramer_zimmer_2009, title={One size fits all? Molecular evidence for a commonly inherited petal identity program in Ranunculales}, volume={96}, ISSN={0002-9122 1537-2197}, url={http://dx.doi.org/10.3732/ajb.0800038}, DOI={10.3732/ajb.0800038}, abstractNote={Petaloid organs are a major component of the floral diversity observed across nearly all major clades of angiosperms. The variable morphology and development of these organs has led to the hypothesis that they are not homologous but, rather, have evolved multiple times. A particularly notable example of petal diversity, and potential homoplasy, is found within the order Ranunculales, exemplified by families such as Ranunculaceae, Berberidaceae, and Papaveraceae. To investigate the molecular basis of petal identity in Ranunculales, we used a combination of molecular phylogenetics and gene expression analysis to characterize APETALA3 (AP3) and PISTILLATA (PI) homologs from a total of 13 representative genera of the order. One of the most striking results of this study is that expression of orthologs of a single AP3 lineage is consistently petal-specific across both Ranunculaceae and Berberidaceae. We conclude from this finding that these supposedly homoplastic petals in fact share a developmental genetic program that appears to have been present in the common ancestor of the two families. We discuss the implications of this type of molecular data for long-held typological definitions of petals and, more broadly, the evolution of petaloid organs across the angiosperms.}, number={1}, journal={American Journal of Botany}, publisher={Wiley}, author={Rasmussen, David A. and Kramer, Elena M. and Zimmer, Elizabeth A.}, year={2009}, month={Jan}, pages={96–109} }