@article{HilgersHartmannPfaenderetal.2022,
  author    = {Hilgers, Leon and Hartmann, Stefanie and Pfaender, Jobst and Lentge-Maass, Nora and Marwoto, Ristiyanti M. and von Rintelen, Thomas and Hofreiter, Michael},
  title     = {Evolutionary divergence and radula diversification in two ecomorphs from an adaptive radiation of freshwater snails},
  series = {Genes},
  volume    = {13},
  journal   = {Genes},
  number    = {6},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {2073-4425},
  doi       = {10.3390/genes13061029},
  pages     = {16},
  year      = {2022},
  abstract  = {(1) Background: Adaptive diversification of complex traits plays a pivotal role in the evolution of organismal diversity. In the freshwater snail genus Tylomelania, adaptive radiations were likely promoted by trophic specialization via diversification of their key foraging organ, the radula. (2) Methods: To investigate the molecular basis of radula diversification and its contribution to lineage divergence, we used tissue-specific transcriptomes of two sympatric Tylomelania sarasinorum ecomorphs. (3) Results: We show that ecomorphs are genetically divergent lineages with habitat-correlated abundances. Sequence divergence and the proportion of highly differentially expressed genes are significantly higher between radula transcriptomes compared to the mantle and foot. However, the same is not true when all differentially expressed genes or only non-synonymous SNPs are considered. Finally, putative homologs of some candidate genes for radula diversification (hh, arx, gbb) were also found to contribute to trophic specialization in cichlids and Darwin's finches. (4) Conclusions: Our results are in line with diversifying selection on the radula driving Tylomelania ecomorph divergence and indicate that some molecular pathways may be especially prone to adaptive diversification, even across phylogenetically distant animal groups.},
  language  = {en}
}
@article{BarlowHartmannGonzalezetal.2020,
  author    = {Barlow, Axel and Hartmann, Stefanie and Gonzalez, Javier and Hofreiter, Michael and Paijmans, Johanna L. A.},
  title     = {Consensify},
  series = {Genes / Molecular Diversity Preservation International},
  volume    = {11},
  journal   = {Genes / Molecular Diversity Preservation International},
  number    = {1},
  publisher = {MDPI},
  address   = {Basel},
  issn      = {2073-4425},
  doi       = {10.3390/genes11010050},
  pages     = {22},
  year      = {2020},
  abstract  = {A standard practise in palaeogenome analysis is the conversion of mapped short read data into pseudohaploid sequences, frequently by selecting a single high-quality nucleotide at random from the stack of mapped reads. This controls for biases due to differential sequencing coverage, but it does not control for differential rates and types of sequencing error, which are frequently large and variable in datasets obtained from ancient samples. These errors have the potential to distort phylogenetic and population clustering analyses, and to mislead tests of admixture using D statistics. We introduce Consensify, a method for generating pseudohaploid sequences, which controls for biases resulting from differential sequencing coverage while greatly reducing error rates. The error correction is derived directly from the data itself, without the requirement for additional genomic resources or simplifying assumptions such as contemporaneous sampling. For phylogenetic and population clustering analysis, we find that Consensify is less affected by artefacts than methods based on single read sampling. For D statistics, Consensify is more resistant to false positives and appears to be less affected by biases resulting from different laboratory protocols than other frequently used methods. Although Consensify is developed with palaeogenomic data in mind, it is applicable for any low to medium coverage short read datasets. We predict that Consensify will be a useful tool for future studies of palaeogenomes.},
  language  = {en}
}
@misc{XenikoudakisAhmedHarrisetal.2020,
  author    = {Xenikoudakis, Georgios and Ahmed, Mayeesha and Harris, Jacob Colt and Wadleigh, Rachel and Paijmans, Johanna L. A. and Hartmann, Stefanie and Barlow, Axel and Lerner, Heather and Hofreiter, Michael},
  title     = {Ancient DNA reveals twenty million years of aquatic life in beavers},
  series = {Current biology : CB},
  volume    = {30},
  journal   = {Current biology : CB},
  number    = {3},
  publisher = {Current Biology Ltd.},
  address   = {London},
  issn      = {0960-9822},
  doi       = {10.1016/j.cub.2019.12.041},
  pages     = {R110 -- R111},
  year      = {2020},
  abstract  = {Xenikoudakis et al. report a partial mitochondrial genome of the extinct giant beaver Castoroides and estimate the origin of aquatic behavior in beavers to approximately 20 million years. This time estimate coincides with the extinction of terrestrial beavers and raises the question whether the two events had a common cause.},
  language  = {en}
}
@misc{HartmannHasenkampMayeretal.2015,
  author    = {Hartmann, Stefanie and Hasenkamp, Natascha and Mayer, Jens and Michaux, Johan and Morand, Serge and Mazzoni, Camila J. and Roca, Alfred L. and Greenwood, Alex D.},
  title     = {Endogenous murine leukemia retroviral variation across wild European and inbred strains of house mouse},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1329},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-43120},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-431200},
  pages     = {13},
  year      = {2015},
  abstract  = {Background: Endogenous murine leukemia retroviruses (MLVs) are high copy number proviral elements difficult to comprehensively characterize using standard low throughput sequencing approaches. However, high throughput approaches generate data that is challenging to process, interpret and present. Results: Next generation sequencing (NGS) data was generated for MLVs from two wild caught Mus musculus domesticus (from mainland France and Corsica) and for inbred laboratory mouse strains C3H, LP/J and SJL. Sequence reads were grouped using a novel sequence clustering approach as applied to retroviral sequences. A Markov cluster algorithm was employed, and the sequence reads were queried for matches to specific xenotropic (Xmv), polytropic (Pmv) and modified polytropic (Mpmv) viral reference sequences. Conclusions: Various MLV subtypes were more widespread than expected among the mice, which may be due to the higher coverage of NGS, or to the presence of similar sequence across many different proviral loci. The results did not correlate with variation in the major MLV receptor Xpr1, which can restrict exogenous MLVs, suggesting that endogenous MLV distribution may reflect gene flow more than past resistance to infection.},
  language  = {en}
}
@article{HofreiterHartmann2020,
  author    = {Hofreiter, Michael and Hartmann, Stefanie},
  title     = {Reconstructing protein-coding sequences from ancient DNA},
  series = {Odorant binding and chemosensory proteins},
  volume    = {642},
  journal   = {Odorant binding and chemosensory proteins},
  publisher = {Academic Press, an imprint of Elsevier},
  address   = {Cambridge, MA.},
  isbn      = {978-0-12-821157-1},
  issn      = {0076-6879},
  doi       = {10.1016/bs.mie.2020.05.008},
  pages     = {21 -- 33},
  year      = {2020},
  abstract  = {Obtaining information about functional details of proteins of extinct species is of critical importance for a better understanding of the real-life appearance, behavior and ecology of these lost entries in the book of life. In this chapter, we discuss the possibilities to retrieve the necessary DNA sequence information from paleogenomic data obtained from fossil specimens, which can then be used to express and subsequently analyze the protein of interest. We discuss the problems specific to ancient DNA, including mis-coding lesions, short read length and incomplete paleogenome assemblies. Finally, we discuss an alternative, but currently rarely used approach, direct PCR amplification, which is especially useful for comparatively short proteins.},
  language  = {en}
}
@article{LahLoeberHsiangetal.2017,
  author    = {Lah, Ljerka and L{\"o}ber, Ulrike and Hsiang, Tom and Hartmann, Stefanie},
  title     = {A genomic comparison of putative pathogenicity-related gene families in five members of the Ophiostomatales with different lifestyles},
  series = {Fungal biology},
  volume    = {121},
  journal   = {Fungal biology},
  publisher = {Elsevier},
  address   = {Oxford},
  issn      = {1878-6146},
  doi       = {10.1016/j.funbio.2016.12.002},
  pages     = {234 -- 252},
  year      = {2017},
  abstract  = {Ophiostomatoid fungi are vectored by their bark-beetle associates and colonize different host tree species. To survive and proliferate in the host, they have evolved mechanisms for detoxification and elimination of host defence compounds, efficient nutrient sequestration, and, in pathogenic species, virulence towards plants. Here, we assembled a draft genome of the spruce pathogen Ophiostoma bicolor. For our comparative and phylogenetic analyses, we mined the genomes of closely related species (Ophiostoma piceae, Ophiostoma ulmi, Ophiostoma novo-ulmi, and Grosmannia clavigera). Our aim was to acquire a genomic and evolutionary perspective of gene families important in host colonization. Genome comparisons showed that both the nuclear and mitochondrial genomes in our assembly were largely complete. Our O. bicolor 25.3 Mbp draft genome had 10 018 predicted genes, 6041 proteins with gene ontology (GO) annotation, 269 carbohydrate-active enzymes (CAZymes), 559 peptidases and inhibitors, and 1373 genes likely involved in pathogen-host interactions. Phylogenetic analyses of selected protein families revealed core sets of cytochrome P450 genes, ABC transporters and backbone genes involved in secondary metabolite (SM) biosynthesis (polyketide synthases (PKS) and non-ribosomal synthases), and species-specific gene losses and duplications. Phylogenetic analyses of protein families of interest provided insight into evolutionary adaptations to host biochemistry in ophiostomatoid fungi.},
  language  = {en}
}
@article{WestburyHartmannBarlowetal.2018,
  author    = {Westbury, Michael V. and Hartmann, Stefanie and Barlow, Axel and Wiesel, Ingrid and Leo, Viyanna and Welch, Rebecca and Parker, Daniel M. and Sicks, Florian and Ludwig, Arne and Dalen, Love and Hofreiter, Michael},
  title     = {Extended and continuous decline in effective population size results in low genomic diversity in the world's rarest hyena species, the brown hyena},
  series = {Molecular biology and evolution},
  volume    = {35},
  journal   = {Molecular biology and evolution},
  number    = {5},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {0737-4038},
  doi       = {10.1093/molbev/msy037},
  pages     = {1225 -- 1237},
  year      = {2018},
  abstract  = {Hyenas (family Hyaenidae), as the sister group to cats (family Felidae), represent a deeply diverging branch within the cat-like carnivores (Feliformia). With an estimated population size of <10,000 individuals worldwide, the brown hyena (Parahyaena brunnea) represents the rarest of the four extant hyena species and has been listed as Near Threatened by the IUCN. Here, we report a high-coverage genome from a captive bred brown hyena and both mitochondrial and low-coverage nuclear genomes of 14 wild-caught brown hyena individuals from across southern Africa. We find that brown hyena harbor extremely low genetic diversity on both the mitochondrial and nuclear level, most likely resulting from a continuous and ongoing decline in effective population size that started similar to 1 Ma and dramatically accelerated towards the end of the Pleistocene. Despite the strikingly low genetic diversity, we find no evidence of inbreeding within the captive bred individual and reveal phylogeographic structure, suggesting the existence of several potential subpopulations within the species.},
  language  = {en}
}
@article{HilgersHartmannHofreiteretal.2018,
  author    = {Hilgers, Leon and Hartmann, Stefanie and Hofreiter, Michael and von Rintelen, Thomas},
  title     = {Novel Genes, Ancient Genes, and Gene Co-Option Contributed o the Genetic Basis of the Radula, a Molluscan Innovation},
  series = {Molecular biology and evolution},
  volume    = {35},
  journal   = {Molecular biology and evolution},
  number    = {7},
  publisher = {Oxford Univ. Press},
  address   = {Oxford},
  issn      = {0737-4038},
  doi       = {10.1093/molbev/msy052},
  pages     = {1638 -- 1652},
  year      = {2018},
  abstract  = {The radula is the central foraging organ and apomorphy of the Mollusca. However, in contrast to other innovations, including the mollusk shell, genetic underpinnings of radula formation remain virtually unknown. Here, we present the first radula formative tissue transcriptome using the viviparous freshwater snail Tylomelania sarasinorum and compare it to foot tissue and the shell-building mantle of the same species. We combine differential expression, functional enrichment, and phylostratigraphic analyses to identify both specific and shared genetic underpinnings of the three tissues as well as their dominant functions and evolutionary origins. Gene expression of radula formative tissue is very distinct, but nevertheless more similar to mantle than to foot. Generally, the genetic bases of both radula and shell formation were shaped by novel orchestration of preexisting genes and continuous evolution of novel genes. A significantly increased proportion of radula-specific genes originated since the origin of stem-mollusks, indicating that novel genes were especially important for radula evolution. Genes with radula-specific expression in our study are frequently also expressed during the formation of other lophotrochozoan hard structures, like chaetae (hes1, arx), spicules (gbx), and shells of mollusks (gbx, heph) and brachiopods (heph), suggesting gene co-option for hard structure formation. Finally, a Lophotrochozoa-specific chitin synthase with a myosin motor domain (CS-MD), which is expressed during mollusk and brachiopod shell formation, had radula-specific expression in our study. CS-MD potentially facilitated the construction of complex chitinous structures and points at the potential of molecular novelties to promote the evolution of different morphological innovations.},
  language  = {en}
}
@misc{GurkeVidalGorosquietaPajimansetal.2021,
  author    = {Gurke, Marie and Vidal-Gorosquieta, Amalia and Pajimans, Johanna L. A. and Wȩcek, Karolina and Barlow, Axel and Gonz{\´a}lez-Fortes, Gloria M. and Hartmann, Stefanie and Grandal-d'Anglade, Aurora and Hofreiter, Michael},
  title     = {Insight into the introduction of domestic cattle and the process of Neolithization to the Spanish region Galicia by genetic evidence},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {4},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-52087},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-520875},
  pages     = {17},
  year      = {2021},
  abstract  = {Domestic cattle were brought to Spain by early settlers and agricultural societies. Due to missing Neolithic sites in the Spanish region of Galicia, very little is known about this process in this region. We sampled 18 cattle subfossils from different ages and different mountain caves in Galicia, of which 11 were subject to sequencing of the mitochondrial genome and phylogenetic analysis, to provide insight into the introduction of cattle to this region. We detected high similarity between samples from different time periods and were able to compare the time frame of the first domesticated cattle in Galicia to data from the connecting region of Cantabria to show a plausible connection between the Neolithization of these two regions. Our data shows a close relationship of the early domesticated cattle of Galicia and modern cow breeds and gives a general insight into cattle phylogeny. We conclude that settlers migrated to this region of Spain from Europe and introduced common European breeds to Galicia.},
  language  = {en}
}
@article{GurkeVidalGorosquietaPajimansetal.2021,
  author    = {Gurke, Marie and Vidal-Gorosquieta, Amalia and Pajimans, Johanna L. A. and Wȩcek, Karolina and Barlow, Axel and Gonz{\´a}lez-Fortes, Gloria M. and Hartmann, Stefanie and Grandal-d'Anglade, Aurora and Hofreiter, Michael},
  title     = {Insight into the introduction of domestic cattle and the process of Neolithization to the Spanish region Galicia by genetic evidence},
  series = {PLoS ONE},
  volume    = {16},
  journal   = {PLoS ONE},
  number    = {4},
  publisher = {Public Library of Science},
  address   = {San Francisco},
  issn      = {1932-6203},
  doi       = {10.1371/journal.pone.0249537},
  pages     = {15},
  year      = {2021},
  abstract  = {Domestic cattle were brought to Spain by early settlers and agricultural societies. Due to missing Neolithic sites in the Spanish region of Galicia, very little is known about this process in this region. We sampled 18 cattle subfossils from different ages and different mountain caves in Galicia, of which 11 were subject to sequencing of the mitochondrial genome and phylogenetic analysis, to provide insight into the introduction of cattle to this region. We detected high similarity between samples from different time periods and were able to compare the time frame of the first domesticated cattle in Galicia to data from the connecting region of Cantabria to show a plausible connection between the Neolithization of these two regions. Our data shows a close relationship of the early domesticated cattle of Galicia and modern cow breeds and gives a general insight into cattle phylogeny. We conclude that settlers migrated to this region of Spain from Europe and introduced common European breeds to Galicia.},
  language  = {en}
}
@article{BarlowCahillHartmannetal.2018,
  author    = {Barlow, Axel and Cahill, James A. and Hartmann, Stefanie and Theunert, Christoph and Xenikoudakis, Georgios and Gonzalez-Fortes, Gloria M. and Paijmans, Johanna L. A. and Rabeder, Gernot and Frischauf, Christine and Garcia-Vazquez, Ana and Murtskhvaladze, Marine and Saarma, Urmas and Anijalg, Peeter and Skrbinsek, Tomaz and Bertorelle, Giorgio and Gasparian, Boris and Bar-Oz, Guy and Pinhasi, Ron and Slatkin, Montgomery and Dalen, Love and Shapiro, Beth and Hofreiter, Michael},
  title     = {Partial genomic survival of cave bears in living brown bears},
  series = {Nature Ecology \& Evolution},
  volume    = {2},
  journal   = {Nature Ecology \& Evolution},
  number    = {10},
  publisher = {Nature Publ. Group},
  address   = {London},
  issn      = {2397-334X},
  doi       = {10.1038/s41559-018-0654-8},
  pages     = {1563 -- 1570},
  year      = {2018},
  abstract  = {Although many large mammal species went extinct at the end of the Pleistocene epoch, their DNA may persist due to past episodes of interspecies admixture. However, direct empirical evidence of the persistence of ancient alleles remains scarce. Here, we present multifold coverage genomic data from four Late Pleistocene cave bears (Ursus spelaeus complex) and show that cave bears hybridized with brown bears (Ursus arctos) during the Pleistocene. We develop an approach to assess both the directionality and relative timing of gene flow. We find that segments of cave bear DNA still persist in the genomes of living brown bears, with cave bears contributing 0.9 to 2.4\% of the genomes of all brown bears investigated. Our results show that even though extinction is typically considered as absolute, following admixture, fragments of the gene pool of extinct species can survive for tens of thousands of years in the genomes of extant recipient species.},
  language  = {en}
}
@article{AutenriethHartmannLahetal.2018,
  author    = {Autenrieth, Marijke and Hartmann, Stefanie and Lah, Ljerka and Roos, Anna and Dennis, Alice B. and Tiedemann, Ralph},
  title     = {High-quality whole-genome sequence of an abundant Holarctic odontocete, the harbour porpoise (Phocoena phocoena)},
  series = {Molecular ecology resources},
  volume    = {18},
  journal   = {Molecular ecology resources},
  number    = {6},
  publisher = {Wiley},
  address   = {Hoboken},
  issn      = {1755-098X},
  doi       = {10.1111/1755-0998.12932},
  pages     = {1469 -- 1481},
  year      = {2018},
  abstract  = {The harbour porpoise (Phocoena phocoena) is a highly mobile cetacean found across the Northern hemisphere. It occurs in coastal waters and inhabits basins that vary broadly in salinity, temperature and food availability. These diverse habitats could drive subtle differentiation among populations, but examination of this would be best conducted with a robust reference genome. Here, we report the first harbour porpoise genome, assembled de novo from an individual originating in the Kattegat Sea (Sweden). The genome is one of the most complete cetacean genomes currently available, with a total size of 2.39 Gb and 50\% of the total length found in just 34 scaffolds. Using 122 of the longest scaffolds, we were able to show high levels of synteny with the genome of the domestic cattle (Bos taurus). Our draft annotation comprises 22,154 predicted genes, which we further annotated through matches to the NCBI nucleotide database, GO categorization and motif prediction. Within the predicted genes, we have confirmed the presence of >20 genes or gene families that have been associated with adaptive evolution in other cetaceans. Overall, this genome assembly and draft annotation represent a crucial addition to the genomic resources currently available for the study of porpoises and Phocoenidae evolution, phylogeny and conservation.},
  language  = {en}
}
@article{HartmannPreickAbeltetal.2020,
  author    = {Hartmann, Stefanie and Preick, Michaela and Abelt, Silke and Scheffel, Andr{\´e} and Hofreiter, Michael},
  title     = {Annotated genome sequences of the carnivorous plant Roridula gorgonias and a non-carnivorous relative, Clethra arborea},
  series = {BMC Research Notes},
  volume    = {13},
  journal   = {BMC Research Notes},
  publisher = {Biomed Central},
  address   = {London},
  issn      = {1756-0500},
  doi       = {10.1186/s13104-020-05254-4},
  pages     = {6},
  year      = {2020},
  abstract  = {Objective Plant carnivory is distributed across the tree of life and has evolved at least six times independently, but sequenced and annotated nuclear genomes of carnivorous plants are currently lacking. We have sequenced and structurally annotated the nuclear genome of the carnivorous Roridula gorgonias and that of a non-carnivorous relative, Madeira's lily-of-the-valley-tree, Clethra arborea, both within the Ericales. This data adds an important resource to study the evolutionary genetics of plant carnivory across angiosperm lineages and also for functional and systematic aspects of plants within the Ericales. Results Our assemblies have total lengths of 284 Mbp (R. gorgonias) and 511 Mbp (C. arborea) and show high BUSCO scores of 84.2\% and 89.5\%, respectively. We used their predicted genes together with publicly available data from other Ericales' genomes and transcriptomes to assemble a phylogenomic data set for the inference of a species tree. However, groups of orthologs showed a marked absence of species represented by a transcriptome. We discuss possible reasons and caution against combining predicted genes from genome- and transriptome-based assemblies.},
  language  = {en}
}
@misc{HartmannPreickAbeltetal.2020,
  author    = {Hartmann, Stefanie and Preick, Michaela and Abelt, Silke and Scheffel, Andr{\´e} and Hofreiter, Michael},
  title     = {Annotated genome sequences of the carnivorous plant Roridula gorgonias and a non-carnivorous relative, Clethra arborea},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-50375},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-503752},
  pages     = {8},
  year      = {2020},
  abstract  = {Objective Plant carnivory is distributed across the tree of life and has evolved at least six times independently, but sequenced and annotated nuclear genomes of carnivorous plants are currently lacking. We have sequenced and structurally annotated the nuclear genome of the carnivorous Roridula gorgonias and that of a non-carnivorous relative, Madeira's lily-of-the-valley-tree, Clethra arborea, both within the Ericales. This data adds an important resource to study the evolutionary genetics of plant carnivory across angiosperm lineages and also for functional and systematic aspects of plants within the Ericales. Results Our assemblies have total lengths of 284 Mbp (R. gorgonias) and 511 Mbp (C. arborea) and show high BUSCO scores of 84.2\% and 89.5\%, respectively. We used their predicted genes together with publicly available data from other Ericales' genomes and transcriptomes to assemble a phylogenomic data set for the inference of a species tree. However, groups of orthologs showed a marked absence of species represented by a transcriptome. We discuss possible reasons and caution against combining predicted genes from genome- and transriptome-based assemblies.},
  language  = {en}
}
@article{ShengBaslerJietal.2019,
  author    = {Sheng, Gui-Lian and Basler, Nikolas and Ji, Xue-Ping and Paijmans, Johanna L. A. and Alberti, Federica and Preick, Michaela and Hartmann, Stefanie and Westbury, Michael V. and Yuan, Jun-Xia and Jablonski, Nina G. and Xenikoudakis, Georgios and Hou, Xin-Dong and Xiao, Bo and Liu, Jian-Hui and Hofreiter, Michael and Lai, Xu-Long and Barlow, Axel},
  title     = {Paleogenome reveals genetic contribution of extinct giant panda to extant populations},
  series = {Current biology},
  volume    = {29},
  journal   = {Current biology},
  number    = {10},
  publisher = {Cell Press},
  address   = {Cambridge},
  issn      = {0960-9822},
  doi       = {10.1016/j.cub.2019.04.021},
  pages     = {1695 -- 1700},
  year      = {2019},
  abstract  = {Historically, the giant panda was widely distributed from northern China to southwestern Asia [1]. As a result of range contraction and fragmentation, extant individuals are currently restricted to fragmented mountain ranges on the eastern margin of the Qinghai-Tibet plateau, where they are distributed among three major population clusters [2]. However, little is known about the genetic consequences of this dramatic range contraction. For example, were regions where giant pandas previously existed occupied by ancestors of present-day populations, or were these regions occupied by genetically distinct populations that are now extinct? If so, is there any contribution of these extinct populations to the genomes of giant pandas living today? To investigate these questions, we sequenced the nuclear genome of an similar to 5,000-year-old giant panda from Jiangdongshan, Teng-chong County in Yunnan Province, China. We find that this individual represents a genetically distinct population that diverged prior to the diversification of modern giant panda populations. We find evidence of differential admixture with this ancient population among modern individuals originating from different populations as well as within the same population. We also find evidence for directional gene flow, which transferred alleles from the ancient population into the modern giant panda lineages. A variable proportion of the genomes of extant individuals is therefore likely derived from the ancient population represented by our sequenced individual. Although extant giant panda populations retain reasonable genetic diversity, our results suggest that this represents only part of the genetic diversity this species harbored prior to its recent range contractions.},
  language  = {en}
}
@misc{BarlowHartmannGonzalezetal.2020,
  author    = {Barlow, Axel and Hartmann, Stefanie and Gonzalez, Javier and Hofreiter, Michael and Paijmans, Johanna L. A.},
  title     = {Consensify},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1033},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47252},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-472521},
  pages     = {24},
  year      = {2020},
  abstract  = {A standard practise in palaeogenome analysis is the conversion of mapped short read data into pseudohaploid sequences, frequently by selecting a single high-quality nucleotide at random from the stack of mapped reads. This controls for biases due to differential sequencing coverage, but it does not control for differential rates and types of sequencing error, which are frequently large and variable in datasets obtained from ancient samples. These errors have the potential to distort phylogenetic and population clustering analyses, and to mislead tests of admixture using D statistics. We introduce Consensify, a method for generating pseudohaploid sequences, which controls for biases resulting from differential sequencing coverage while greatly reducing error rates. The error correction is derived directly from the data itself, without the requirement for additional genomic resources or simplifying assumptions such as contemporaneous sampling. For phylogenetic and population clustering analysis, we find that Consensify is less affected by artefacts than methods based on single read sampling. For D statistics, Consensify is more resistant to false positives and appears to be less affected by biases resulting from different laboratory protocols than other frequently used methods. Although Consensify is developed with palaeogenomic data in mind, it is applicable for any low to medium coverage short read datasets. We predict that Consensify will be a useful tool for future studies of palaeogenomes.},
  language  = {en}
}
@misc{DennisBallesterosRobinetal.2020,
  author    = {Dennis, Alice B. and Ballesteros, Gabriel I. and Robin, St{\´e}phanie and Schrader, Lukas and Bast, Jens and Bergh{\"o}fer, Jan and Beukeboom, Leo W. and Belghazi, Maya and Bretaudeau, Anthony and Buellesbach, Jan and Cash, Elizabeth and Colinet, Dominique and Dumas, Zo{\´e} and Errbii, Mohammed and Falabella, Patrizia and Gatti, Jean-Luc and Geuverink, Elzemiek and Gibson, Joshua D. and Hertaeg, Corinne and Hartmann, Stefanie and Jacquin-Joly, Emmanuelle and Lammers, Mark and Lavandero, Blas I. and Lindenbaum, Ina and Massardier-Galata, Lauriane and Meslin, Camille and Montagn{\´e}, Nicolas and Pak, Nina and Poiri{\´e}, Maryl{\`e}ne and Salvia, Rosanna and Smith, Chris R. and Tagu, Denis and Tares, Sophie and Vogel, Heiko and Schwander, Tanja and Simon, Jean-Christophe and Figueroa, Christian C. and Vorburger, Christoph and Legeai, Fabrice and Gadau, J{\"u}rgen},
  title     = {Functional insights from the GC-poor genomes of two aphid parasitoids, Aphidius ervi and Lysiphlebus fabarum},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {989},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47612},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-476129},
  pages     = {29},
  year      = {2020},
  abstract  = {Background Parasitoid wasps have fascinating life cycles and play an important role in trophic networks, yet little is known about their genome content and function. Parasitoids that infect aphids are an important group with the potential for biological control. Their success depends on adapting to develop inside aphids and overcoming both host aphid defenses and their protective endosymbionts. Results We present the de novo genome assemblies, detailed annotation, and comparative analysis of two closely related parasitoid wasps that target pest aphids: Aphidius ervi and Lysiphlebus fabarum (Hymenoptera: Braconidae: Aphidiinae). The genomes are small (139 and 141 Mbp) and the most AT-rich reported thus far for any arthropod (GC content: 25.8 and 23.8\%). This nucleotide bias is accompanied by skewed codon usage and is stronger in genes with adult-biased expression. AT-richness may be the consequence of reduced genome size, a near absence of DNA methylation, and energy efficiency. We identify missing desaturase genes, whose absence may underlie mimicry in the cuticular hydrocarbon profile of L. fabarum. We highlight key gene groups including those underlying venom composition, chemosensory perception, and sex determination, as well as potential losses in immune pathway genes. Conclusions These findings are of fundamental interest for insect evolution and biological control applications. They provide a strong foundation for further functional studies into coevolution between parasitoids and their hosts. Both genomes are available at https://bipaa.genouest.org.},
  language  = {en}
}
@article{DennisBallesterosRobinetal.2020,
  author    = {Dennis, Alice B. and Ballesteros, Gabriel I. and Robin, St{\´e}phanie and Schrader, Lukas and Bast, Jens and Bergh{\"o}fer, Jan and Beukeboom, Leo W. and Belghazi, Maya and Bretaudeau, Anthony and Buellesbach, Jan and Cash, Elizabeth and Colinet, Dominique and Dumas, Zo{\´e} and Errbii, Mohammed and Falabella, Patrizia and Gatti, Jean-Luc and Geuverink, Elzemiek and Gibson, Joshua D. and Hertaeg, Corinne and Hartmann, Stefanie and Jacquin-Joly, Emmanuelle and Lammers, Mark and Lavandero, Blas I. and Lindenbaum, Ina and Massardier-Galata, Lauriane and Meslin, Camille and Montagn{\´e}, Nicolas and Pak, Nina and Poiri{\´e}, Maryl{\`e}ne and Salvia, Rosanna and Smith, Chris R. and Tagu, Denis and Tares, Sophie and Vogel, Heiko and Schwander, Tanja and Simon, Jean-Christophe and Figueroa, Christian C. and Vorburger, Christoph and Legeai, Fabrice and Gadau, J{\"u}rgen},
  title     = {Functional insights from the GC-poor genomes of two aphid parasitoids, Aphidius ervi and Lysiphlebus fabarum},
  series = {BMC Genomics},
  volume    = {21},
  journal   = {BMC Genomics},
  publisher = {BioMed Central},
  address   = {London},
  issn      = {1471-2164},
  doi       = {10.1186/s12864-020-6764-0},
  pages     = {27},
  year      = {2020},
  abstract  = {Background Parasitoid wasps have fascinating life cycles and play an important role in trophic networks, yet little is known about their genome content and function. Parasitoids that infect aphids are an important group with the potential for biological control. Their success depends on adapting to develop inside aphids and overcoming both host aphid defenses and their protective endosymbionts. Results We present the de novo genome assemblies, detailed annotation, and comparative analysis of two closely related parasitoid wasps that target pest aphids: Aphidius ervi and Lysiphlebus fabarum (Hymenoptera: Braconidae: Aphidiinae). The genomes are small (139 and 141 Mbp) and the most AT-rich reported thus far for any arthropod (GC content: 25.8 and 23.8\%). This nucleotide bias is accompanied by skewed codon usage and is stronger in genes with adult-biased expression. AT-richness may be the consequence of reduced genome size, a near absence of DNA methylation, and energy efficiency. We identify missing desaturase genes, whose absence may underlie mimicry in the cuticular hydrocarbon profile of L. fabarum. We highlight key gene groups including those underlying venom composition, chemosensory perception, and sex determination, as well as potential losses in immune pathway genes. Conclusions These findings are of fundamental interest for insect evolution and biological control applications. They provide a strong foundation for further functional studies into coevolution between parasitoids and their hosts. Both genomes are available at https://bipaa.genouest.org.},
  language  = {en}
}
@misc{HartmannVision2008,
  author    = {Hartmann, Stefanie and Vision, Todd J.},
  title     = {Using ESTs for phylogenomics},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch Naturwissenschaftliche Reihe},
  number    = {889},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-43667},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-436670},
  pages     = {15},
  year      = {2008},
  abstract  = {Background While full genome sequences are still only available for a handful of taxa, large collections of partial gene sequences are available for many more. The alignment of partial gene sequences results in a multiple sequence alignment containing large gaps that are arranged in a staggered pattern. The consequences of this pattern of missing data on the accuracy of phylogenetic analysis are not well understood. We conducted a simulation study to determine the accuracy of phylogenetic trees obtained from gappy alignments using three commonly used phylogenetic reconstruction methods (Neighbor Joining, Maximum Parsimony, and Maximum Likelihood) and studied ways to improve the accuracy of trees obtained from such datasets. Results We found that the pattern of gappiness in multiple sequence alignments derived from partial gene sequences substantially compromised phylogenetic accuracy even in the absence of alignment error. The decline in accuracy was beyond what would be expected based on the amount of missing data. The decline was particularly dramatic for Neighbor Joining and Maximum Parsimony, where the majority of gappy alignments contained 25\% to 40\% incorrect quartets. To improve the accuracy of the trees obtained from a gappy multiple sequence alignment, we examined two approaches. In the first approach, alignment masking, potentially problematic columns and input sequences are excluded from from the dataset. Even in the absence of alignment error, masking improved phylogenetic accuracy up to 100-fold. However, masking retained, on average, only 83\% of the input sequences. In the second approach, alignment subdivision, the missing data is statistically modelled in order to retain as many sequences as possible in the phylogenetic analysis. Subdivision resulted in more modest improvements to alignment accuracy, but succeeded in including almost all of the input sequences. Conclusion These results demonstrate that partial gene sequences and gappy multiple sequence alignments can pose a major problem for phylogenetic analysis. The concern will be greatest for high-throughput phylogenomic analyses, in which Neighbor Joining is often the preferred method due to its computational efficiency. Both approaches can be used to increase the accuracy of phylogenetic inference from a gappy alignment. The choice between the two approaches will depend upon how robust the application is to the loss of sequences from the input set, with alignment masking generally giving a much greater improvement in accuracy but at the cost of discarding a larger number of the input sequences.},
  language  = {en}
}
@article{WestburyBalekaBarlowetal.2017,
  author    = {Westbury, Michael V. and Baleka, Sina Isabelle and Barlow, Axel and Hartmann, Stefanie and Paijmans, Johanna L. A. and Kramarz, Alejandro and Forasiepi, Analia M. and Bond, Mariano and Gelfo, Javier N. and Reguero, Marcelo A. and Lopez-Mendoza, Patricio and Taglioretti, Matias and Scaglia, Fernando and Rinderknecht, Andres and Jones, Washington and Mena, Francisco and Billet, Guillaume and de Muizon, Christian and Luis Aguilar, Jose and MacPhee, Ross D. E. and Hofreiter, Michael},
  title     = {A mitogenomic timetree for Darwin's enigmatic South American mammal Macrauchenia patachonica},
  series = {Nature Communications},
  volume    = {8},
  journal   = {Nature Communications},
  publisher = {Nature Publ. Group},
  address   = {London},
  issn      = {2041-1723},
  doi       = {10.1038/ncomms15951},
  pages     = {8},
  year      = {2017},
  abstract  = {The unusual mix of morphological traits displayed by extinct South American native ungulates (SANUs) confounded both Charles Darwin, who first discovered them, and Richard Owen, who tried to resolve their relationships. Here we report an almost complete mitochondrial genome for the litoptern Macrauchenia. Our dated phylogenetic tree places Macrauchenia as sister to Perissodactyla, but close to the radiation of major lineages within Laurasiatheria. This position is consistent with a divergence estimate of B66Ma (95\% credibility interval, 56.64-77.83 Ma) obtained for the split between Macrauchenia and other Panperissodactyla. Combined with their morphological distinctiveness, this evidence supports the positioning of Litopterna (possibly in company with other SANU groups) as a separate order within Laurasiatheria. We also show that, when using strict criteria, extinct taxa marked by deep divergence times and a lack of close living relatives may still be amenable to palaeogenomic analysis through iterative mapping against more distant relatives.},
  language  = {en}
}