Publications

@article{nokey_97,

title = {VirJenDB: a FAIR (meta)data and bioinformatics platform for all viruses},

author = {Shahram Saghaei and Malte Siemers and Kilian L Ossetek and Stephan Richter and Robert A Edwards and Simon Roux and Andrzej Zielezinski and Bas E Dutilh and Manja Marz and Noriko A Cassman},

doi = {10.1093/nar/gkaf1224},

year  = {2025},

date = {2025-12-17},

journal = {Nucleic Acids Research},

abstract = {High-throughput sequencing has generated an unprecedented volume of data. However, researcher-submitted data in repositories requires extensive curation and quality control for reuse. These tasks are hindered by the multiplicity of repositories, the sheer volume of the data, and the complexity of virus (meta)data curation. To address these challenges, VirJenDB offers a user-friendly platform to facilitate versioned, community-driven curation, and ontology development. Virus sequences were ingested from 16 sources, including ~200 fields of metadata or standards, covering taxonomy, sample, and host information. Up to 85 metadata fields have undergone at least one round of curation, and are linked to 15.4 million virus sequences, with 88 % from those infecting eukaryotes and the remaining infecting prokaryotes. Subsets were created, including a novel collection of 0.91 million viral operational taxonomic unit (vOTU) sequences across all viruses, while keeping the original sequences from each vOTU to facilitate downstream analyses, e.g. sequence variation. The VirJenDB web portal (https://www.virjendb.org) provides HTTPS and Application Programming Interface (API) access to the sequence datasets and metadata, offering a search engine, filtering, download, visualizations, and documentation. VirJenDB aims to connect the phage and eukaryotic virus research communities by supporting webtool integration, meta-analyses, and metadata schema extensions.},

keywords = {database, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_67,

title = {AnchoRNA: Full virus genome alignments through conserved anchor regions},

author = {Tom Eulenfeld and Sandra Triebel and Manja Marz},

doi = {10.1101/2025.01.30.635689},

year  = {2025},

date = {2025-12-15},

urldate = {2025-02-01},

journal = {bioRxiv},

abstract = {Multiple sequence alignment of full viral genomes can be challenging due to factors such as long sequences, large insertions/deletions (spanning several 100 nucleotides), large number of sequences, sequence divergence, and high computational complexity in particular when computing alignments based on RNA secondary structures. Standard alignment methods often face these issues, in particular when processing highly variable sequences or when specific phylogenetic analysis is required on selected subsequences.

We present an algorithm to determine high quality anchors that define partitions of sequences and guide the alignment of viral genomes to respect well conserved, and therefore functionally significant, regions. This new approach is implemented in the Python-based command line tool AnchoRNA, which is designed to identify conserved regions, or anchors, within coding sequences. By default, anchors are searched in translated coding sequences accounting for high mutation rates in viral genomes. AnchoRNA enhances the accuracy and efficiency of full-genome alignment by focusing on these crucial conserved regions. AnchoRNA guided alignments are systematically compared to the results of 3 alignment programs. Utilizing a dataset of 55 representative Pestivirus genomes, AnchoRNA identified 55 anchors that are used for guiding the alignment process. The incorporation of these anchors led to improvements across tested alignment tools, highlighting the effectiveness of AnchoRNA in enhancing alignment quality, especially in viral genomes.},

keywords = {alignment, phylogenetics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_77,

title = {First full-genome alignment representative for the genus \textit{Pestivirus}},

author = {Sandra Triebel and Tom Eulenfeld and Nancy Ontiveros-Palacios and Blake Sweeney and Norbert Tautz and Manja Marz},

url = {https://doi.org/10.5281/zenodo.15490752},

doi = {10.1101/2025.05.22.655560},

year  = {2025},

date = {2025-05-27},

journal = {bioRxiv},

abstract = {The members of the genus Pestivirus in the family Flaviviridae comprise economically important pathogens of life stock like classical swine fever (CSFV) and bovine viral diarrhea virus (BVDV). Intense research over the last years revealed that at least 11 recognized and eight proposed pestivirus species exist. The single-stranded, positive-sense RNA genome encodes for one large polyprotein which is processed by viral and cell-derived proteases into 12 mature proteins. Besides its protein-coding function, the RNA genome also contains RNA secondary structures with critical importance for various stages of the viral life cycle. Some of those RNA secondary structures, like the internal ribosome entry site (IRES) and a 3’ stem-loop essential for genome replication, had already been studied for a few individual pestiviruses.

In this study, we provide the first genome-wide multiple sequence alignment (MSA) including all known pestivirus species (accepted and tentative). Moreover, we performed a comprehensive analysis of RNA secondary structures phylogenetically conserved across the complete genus. While showing well-described structures, like a 5’ stem-loop structure, the IRES element, and the 3’ stem loop SL I to be conserved between all pestiviruses, other RNA secondary structures in the 3’ untranslated region (UTR) were only conserved in subsets of the species. We identified 29 novel phylogenetically conserved RNA secondary structures in the protein-coding region, with so far unresolved functional importance. The microRNA binding site for miR-17 was previously known in species A, B, and C; in this study, we identified it in ten additional species, but not in species K, S, Q, and R. Another interesting finding is the identification of a putative long-distance RNA interaction between the IRES and the 3’ end of the genome. These results together with the now available comprehensive multiple sequence alignment including all 19 pestivirus species, represent a valuable resource for future research and diagnostic purposes.},

keywords = {alignment, evolution, phylogenetics, RNA structure, RNA-RNA interactions, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_66,

title = {Endogenous viral elements: insights into data availability and accessibility},

author = {Muriel Ritsch and Nadja Brait and Erin Harvey and Manja Marz and Sebastian Lequime},

doi = {10.1093/ve/veae099},

issn = {2057-1577},

year  = {2024},

date = {2024-11-23},

journal = {Virus Evolution},

volume = {10},

number = {1},

pages = {veae099},

abstract = {Endogenous viral elements (EVEs) are remnants of viral genetic material endogenized into the host genome. They have, in the last decades, attracted attention for their role as potential contributors to pathogenesis, drivers of selective advantage for the host, and genomic remnants of ancient viruses. EVEs have a nuanced and complex influence on both host health and evolution, and can offer insights on the deep evolutionary history of viruses. As an emerging field of research, several factors limit a comprehensive understanding of EVEs: they are currently underestimated and periodically overlooked in studies of the host genome, transcriptome, and virome. The absence of standardized guidelines for ensuring EVE-related data availability and accessibility following the FAIR (‘findable, accessible, interoperable, and reusable’) principles obstructs our ability to gather and connect information. Here, we discuss challenges to the availability and accessibility of EVE-related data and propose potential solutions. We identified the biological and research focus imbalance between different types of EVEs, and their overall biological complexity as genomic loci with viral ancestry, as potential challenges that can be addressed with the development of a user-oriented identification tool. In addition, reports of EVE identification are scattered between different subfields under different keywords, and EVE sequences and associated data are not properly gathered in databases. While developing an open and dedicated database might be ideal, targeted improvements of generalist databases might provide a pragmatic solution to EVE data and metadata accessibility. The implementation of these solutions, as well as the collective effort by the EVE scientific community in discussing and setting guidelines, is now drastically needed to lead the development of EVE research and offer insights into host–virus interactions and their evolutionary history.},

keywords = {evolution, phylogenetics, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_66,

title = {Endogenous Bornavirus-like Elements in Bats: Evolutionary Insights from the Conserved Riboviral L-Gene in Microbats and Its Antisense Transcription in \textit{Myotis daubentonii}},

author = {Muriel Ritsch and Tom Eulenfeld and Kevin Lamkiewicz and Andreas Schoen and Friedemann Weber and Martin Hölzer and Manja Marz},

doi = {10.3390/v16081210},

issn = {1999-4915},

year  = {2024},

date = {2024-07-27},

urldate = {2024-07-27},

journal = {Viruses},

volume = {16},

issue = {8},

abstract = {Bats are ecologically diverse vertebrates characterized by their ability to host a wide range of viruses without apparent illness and the presence of numerous endogenous viral elements (EVEs). EVEs are well preserved, expressed, and may affect host biology and immunity, but their role in bat immune system evolution remains unclear. Among EVEs, endogenous bornavirus-like elements (EBLs) are bornavirus sequences integrated into animal genomes. Here, we identified a novel EBL in the microbat \textit{Myotis daubentonii}, EBLL-Cultervirus.10-MyoDau (short name is CV.10-MyoDau) that shows protein-level conservation with the L-protein of a \textit{Cultervirus} (Wuhan sharpbelly bornavirus). Surprisingly, we discovered a transcript on the antisense strand comprising three exons, which we named AMCR-MyoDau. The active transcription in \textit{Myotis daubentonii} tissues of AMCR-MyoDau, confirmed by RNA-Seq analysis and RT-PCR, highlights its potential role during viral infections. Using comparative genomics comprising 63 bat genomes, we demonstrate nucleotide-level conservation of CV.10-MyoDau and AMCR-MyoDau across various bat species and its detection in 22 \textit{Yangochiropera<i/> and 12 \textit{Yinpterochiroptera} species. To the best of our knowledge, this marks the first occurrence of a conserved EVE shared among diverse bat species, which is accompanied by a conserved antisense transcript. This highlights the need for future research to explore the role of EVEs in shaping the evolution of bat immunity.},

keywords = {evolution, phylogenetics, RNA / transcriptomics, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_62,

title = {Comprehensive survey of conserved RNA secondary structures in full-genome alignment of Hepatitis C virus},

author = {Sandra Triebel and Kevin Lamkiewicz and Nancy Ontiveros and Blake Sweeney and Peter F. Stadler and Anton I. Petrov and Michael Niepmann and Manja Marz},

doi = {10.1038/s41598-024-62897-0},

year  = {2024},

date = {2024-07-02},

urldate = {2024-07-02},

journal = {Scientific Reports},

volume = {14},

issue = {1},

abstract = {Hepatitis C virus (HCV) is a plus-stranded RNA virus that often chronically infects liver hepatocytes and causes liver cirrhosis and cancer. These viruses replicate their genomes employing error-prone replicases. Thereby, they routinely generate a large ‘cloud’ of RNA genomes (quasispecies) which—by trial and error—comprehensively explore the sequence space available for functional RNA genomes that maintain the ability for efficient replication and immune escape. In this context, it is important to identify which RNA secondary structures in the sequence space of the HCV genome are conserved, likely due to functional requirements. Here, we provide the first genome-wide multiple sequence alignment (MSA) with the prediction of RNA secondary structures throughout all representative full-length HCV genomes. We selected 57 representative genomes by clustering all complete HCV genomes from the BV-BRC database based on k-mer distributions and dimension reduction and adding RefSeq sequences. We include annotations of previously recognized features for easy comparison to other studies. Our results indicate that mainly the core coding region, the C-terminal NS5A region, and the NS5B region contain secondary structure elements that are conserved beyond coding sequence requirements, indicating functionality on the RNA level. In contrast, the genome regions in between contain less highly conserved structures. The results provide a complete description of all conserved RNA secondary structures and make clear that functionally important RNA secondary structures are present in certain HCV genome regions but are largely absent from other regions. Full-genome alignments of all branches of Hepacivirus C are provided in the supplement.},

keywords = {evolution, ncRNAs, phylogenetics, RNA structure, RNA-RNA interactions, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_47,

title = {The International Virus Bioinformatics Meeting 2023},

author = {Franziska Hufsky and Ana B. Abecasis and Artem Babaian and Sebastian Beck and Liam Brierley and Simon Dellicour and Christian Eggeling and Santiago F. Elena and Udo Gieraths and Anh D. Ha and Will Harvey and Terry C. Jones and Kevin Lamkiewicz and Gabriel L. Lovate and Dominik Lücking and Martin Machyna and Luca Nishimura and Maximilian K. Nocke and Bernard Y. Renard and Shoichi Sakaguchi and Lygeri Sakellaridi and Jannes Spangenberg and Maria Tarradas-Alemany and Sandra Triebel and Yulia Vakulenko and Rajitha Yasas Wijesekara and Fernando González-Candelas and Sarah Krautwurst and Alba Pérez-Cataluña and Walter Randazzo and Gloria Sánchez and Manja Marz},

doi = {10.3390/v15102031},

issn = {1999-4915},

year  = {2023},

date = {2023-09-30},

urldate = {2023-09-30},

journal = {Viruses},

volume = {15},

issue = {10},

abstract = {The 2023 International Virus Bioinformatics Meeting was held in Valencia, Spain, from 24–26 May 2023, attracting approximately 180 participants worldwide. The primary objective of the conference was to establish a dynamic scientific environment conducive to discussion, collaboration, and the generation of novel research ideas. As the first in-person event following the SARS-CoV-2 pandemic, the meeting facilitated highly interactive exchanges among attendees. It served as a pivotal gathering for gaining insights into the current status of virus bioinformatics research and engaging with leading researchers and emerging scientists. The event comprised eight invited talks, 19 contributed talks, and 74 poster presentations across eleven sessions spanning three days. Topics covered included machine learning, bacteriophages, virus discovery, virus classification, virus visualization, viral infection, viromics, molecular epidemiology, phylodynamic analysis, RNA viruses, viral sequence analysis, viral surveillance, and metagenomics. This report provides rewritten abstracts of the presentations, a summary of the key research findings, and highlights shared during the meeting.},

keywords = {annotation, software, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_45,

title = {Functional comparisons of the virus sensor RIG-I from humans, the microbat \textit{Myotis daubentonii}, and the megabat \textit{Rousettus aegyptiacus}, and their response to SARS-CoV-2 infection},

author = {Andreas Schoen and Martin Hölzer and Marcel A. Müller and Kai B. Wallerang and Christian Drosten and Manja Marz and Benjamin Lamp and Friedemann Weber},

doi = {10.1128/jvi.00205-23},

year  = {2023},

date = {2023-09-20},

urldate = {2023-09-20},

journal = {Journal of Virology},

volume = {0},

issue = {0},

pages = {e00205-23},

abstract = {Bats (order Chiroptera) are a major reservoir for emerging and re-emerging zoonotic viruses. Their tolerance toward highly pathogenic human viruses led to the hypothesis that bats may possess an especially active antiviral interferon (IFN) system. Here, we cloned and functionally characterized the virus RNA sensor, retinoic acid-inducible gene-I (RIG-I), from the "microbat" Myotis daubentonii (suborder Yangochiroptera) and the "megabat" Rousettus aegyptiacus (suborder Yinpterochiroptera) and compared them to the human ortholog. Our data show that the overall sequence and domain organization are highly conserved and that all three RIG-I orthologs can mediate a similar IFN induction in response to viral RNA at 37° and 39°C but not at 30°C. Like human RIG-I, bat RIG-Is were optimally activated by double stranded RNA containing a 5'-triphosphate end and required mitochondrial antiviral-signaling protein (MAVS) for antiviral signaling. Moreover, the RIG-I orthologs of humans and of R. aegyptiacus, but not of M. daubentonii, enable innate immune sensing of SARS-CoV-2 infection. Our results thus show that microbats and megabats express a RIG-I that is not substantially different from the human counterpart with respect to function, temperature dependency, antiviral signaling, and RNA ligand properties, and that human and megabat RIG-I are able to sense SARS-CoV-2 infection. IMPORTANCE A common hypothesis holds that bats (order Chiroptera) are outstanding reservoirs for zoonotic viruses because of a special antiviral interferon (IFN) system. However, functional studies about key components of the bat IFN system are rare. RIG-I is a cellular sensor for viral RNA signatures that activates the antiviral signaling chain to induce IFN. We cloned and functionally characterized RIG-I genes from two species of the suborders Yangochiroptera and Yinpterochiroptera. The bat RIG-Is were conserved in their sequence and domain organization, and similar to human RIG-I in (i) mediating virus- and IFN-activated gene expression, (ii) antiviral signaling, (iii) temperature dependence, and (iv) recognition of RNA ligands. Moreover, RIG-I of Rousettus aegyptiacus (suborder Yinpterochiroptera) and of humans were found to recognize SARS-CoV-2 infection. Thus, members of both bat suborders encode RIG-Is that are comparable to their human counterpart. The ability of bats to harbor zoonotic viruses therefore seems due to other features.},

keywords = {DNA / genomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_43,

title = {Navigating the Landscape: A Comprehensive Review of Current Virus Databases},

author = {Muriel Ritsch and Noriko A. Cassman and Shahram Saghaei and Manja Marz},

doi = {10.3390/v15091834},

isbn = {1999-4915},

year  = {2023},

date = {2023-08-29},

journal = {Viruses},

volume = {15},

number = {1834},

issue = {9},

abstract = {Viruses are abundant and diverse entities that have important roles in public health, ecology, and agriculture. The identification and surveillance of viruses rely on an understanding of their genome organization, sequences, and replication strategy. Despite technological advancements in sequencing methods, our current understanding of virus diversity remains incomplete, highlighting the need to explore undiscovered viruses. Virus databases play a crucial role in providing access to sequences, annotations and other metadata, and analysis tools for studying viruses. However, there has not been a comprehensive review of virus databases in the last five years. This study aimed to fill this gap by identifying 24 active virus databases and included an extensive evaluation of their content, functionality and compliance with the FAIR principles. In this study, we thoroughly assessed the search capabilities of five database catalogs, which serve as comprehensive repositories housing a diverse array of databases and offering essential metadata. Moreover, we conducted a comprehensive review of different types of errors, encompassing taxonomy, names, missing information, sequences, sequence orientation, and chimeric sequences, with the intention of empowering users to effectively tackle these challenges. We expect this review to aid users in selecting suitable virus databases and other resources, and to help databases in error management and improve their adherence to the FAIR principles. The databases listed here represent the current knowledge of viruses and will help aid users find databases of interest based on content, functionality, and scope. The use of virus databases is integral to gaining new insights into the biology, evolution, and transmission of viruses, and developing new strategies to manage virus outbreaks and preserve global health.},

keywords = {database, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {VIRify: An integrated detection, annotation and taxonomic classification pipeline using virus-specific protein profile hidden Markov models},

author = {Guillermo Rangel-Pineros and Alexandre Almeida and Martin Beracochea and Ekaterina Sakharova and Manja Marz and Alejandro Reyes Muñoz and Martin Hölzer and Robert D. Finn },

doi = {10.1371/journal.pcbi.1011422},

year  = {2023},

date = {2023-08-28},

journal = {PLOS Comput Biol},

volume = {19},

issue = {8},

pages = {e1011422},

abstract = {The study of viral communities has revealed the enormous diversity and impact these biological entities have on various ecosystems. These observations have sparked widespread interest in developing computational strategies that support the comprehensive characterisation of viral communities based on sequencing data. Here we introduce VIRify, a new computational pipeline designed to provide a user-friendly and accurate functional and taxonomic characterisation of viral communities. VIRify identifies viral contigs and prophages from metagenomic assemblies and annotates them using a collection of viral profile hidden Markov models (HMMs). These include our manually-curated profile HMMs, which serve as specific taxonomic markers for a wide range of prokaryotic and eukaryotic viral taxa and are thus used to reliably classify viral contigs. We tested VIRify on assemblies from two microbial mock communities, a large metagenomics study, and a collection of publicly available viral genomic sequences from the human gut. The results showed that VIRify could identify sequences from both prokaryotic and eukaryotic viruses, and provided taxonomic classifications from the genus to the family rank with an average accuracy of 86.6%. In addition, VIRify allowed the detection and taxonomic classification of a range of prokaryotic and eukaryotic viruses present in 243 marine metagenomic assemblies. Finally, the use of VIRify led to a large expansion in the number of taxonomically classified human gut viral sequences and the improvement of outdated and shallow taxonomic classifications. Overall, we demonstrate that VIRify is a novel and powerful resource that offers an enhanced capability to detect a broad range of viral contigs and taxonomically classify them.},

keywords = {annotation, classification, metagenomics, phylogenetics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {NFDI4Microbiota – national research data infrastructure for microbiota research},

author = {Konrad U. Förstner and Anke Becker and Jochen Blom and Peer Bork and Thomas Clavel and Marius Dieckmann and Alexander Goesmann and Barbara Götz and Thomas Gübitz and Franziska Hufsky and Sebastian Jünemann and Marie-Louise Körner and Manja Marz and Ulisses Nunes Da Rocha and Jörg Overmann and Alfred Pühler and Dietrich Rebholz-Schuhmann and Alexander Sczyrba and Jens Stoye and Justine Vandendorpe and Thea Van Rossum and Alice McHardy},

doi = {10.3897/rio.9.e110501},

year  = {2023},

date = {2023-08-24},

journal = {Research Ideas and Outcomes},

volume = {9},

pages = {e110501},

abstract = {Microbes – bacteria, archaea, unicellular eukaryotes, and viruses – play an important role in human and environmental health. Growing awareness of this fact has led to a huge increase in microbiological research and applications in a variety of fields. Driven by technological advances that allow high-throughput molecular characterization of microbial species and communities, microbiological research now offers unparalleled opportunities to address current and emerging needs. As well as helping to address global health threats such as antimicrobial resistance and viral pandemics, it also has a key role to play in areas such as agriculture, waste management, water treatment, ecosystems remediation, and the diagnosis, treatment and prevention of various diseases. Reflecting this broad potential, billions of euros have been invested in microbiota research programs worldwide. Though run independently, many of these projects are closely related. However, Germany currently has no infrastructure to connect such projects or even compare their results. Thus, the potential synergy of data and expertise is being squandered. The goal of the NFDI4Microbiota consortium is to serve and connect this broad and heterogeneous research community by elevating the availability and quality of research results through dedicated training, and by facilitating the generation, management, interpretation, sharing, and reuse of microbial data. In doing so, we will also foster interdisciplinary interactions between researchers. NFDI4Microbiota will achieve this by creating a German microbial research network through training and community-building activities, and by creating a cloud-based system that will make the storage, integration and analysis of microbial data, especially omics data, consistent, reproducible, and accessible across all areas of life sciences. In addition to increasing the quality of microbial research in Germany, our training program will support widespread and proper usage of these services. Through this dual emphasis on education and services, NFDI4Microbiota will ensure that microbial research in Germany is synergistic and efficient, and thus excellent. By creating a central resource for German microbial research, NDFDI4Microbiota will establish a connecting hub for all NFDI consortia that work with microbiological data, including GHGA, NFDI4Biodiversity, NFDI4Agri and several others. NFDI4Microbiota will provide non-microbial specialists from these consortia with direct and easy access to the necessary expertise and infrastructure in microbial research in order to facilitate their daily work and enhance their research. The links forged through NFDI4Microbiota will not only increase the synergy between NFDI consortia, but also elevate the overall quality and relevance of microbial research in Germany.},

keywords = {bacteria, fungi, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_34,

title = {Sequential disruption of SPLASH-identified vRNA–vRNA interactions challenges their role in influenza A virus genome packaging},

author = {Celia Jakob and Gabriel L. Lovate and Daniel Desirò and Lara Gießler and Redmond Patrick Smyth and Roland Marquet and Kevin Lamkiewicz and Manja Marz and Martin Schwemmle and Hardin Bolte},

doi = {10.1093/nar/gkad442},

isbn = {0305-1048},

year  = {2023},

date = {2023-07-07},

urldate = {2023-07-07},

journal = {Nucleic Acids Research},

abstract = {A fundamental step in the influenza A virus (IAV) replication cycle is the coordinated packaging of eight distinct genomic RNA segments (i.e. vRNAs) into a viral particle. Although this process is thought to be controlled by specific vRNA–vRNA interactions between the genome segments, few functional interactions have been validated. Recently, a large number of potentially functional vRNA–vRNA interactions have been detected in purified virions using the RNA interactome capture method SPLASH. However, their functional significance in coordinated genome packaging remains largely unclear. Here, we show by systematic mutational analysis that mutant A/SC35M (H7N7) viruses lacking several prominent SPLASH-identified vRNA–vRNA interactions involving the HA segment package the eight genome segments as efficiently as the wild-type virus. We therefore propose that the vRNA–vRNA interactions identified by SPLASH in IAV particles are not necessarily critical for the genome packaging process, leaving the underlying molecular mechanism elusive.},

keywords = {RNA-RNA interactions, splash, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Magnipore: Prediction of differential single nucleotide changes in the Oxford Nanopore Technologies sequencing signal of SARS-CoV-2 samples},

author = {Jannes Spangenberg and Christian {Höner zu Siederdissen} and Milena Žarković and Sandra Triebel and Ruben Rose and Christina Martínez Christophersen and Lea Paltzow and Mohsen M. Hegab and Anna Wansorra and Akash Srivastava and Andi Krumbholz and Manja Marz},

doi = {10.1101/2023.03.17.533105},

year  = {2023},

date = {2023-03-17},

urldate = {2023-03-17},

journal = {bioRxiv},

abstract = {Oxford Nanopore Technologies (ONT) allows direct sequencing of ribonucleic acids (RNA) and, in addition, detection of possible RNA modifications due to deviations from the expected ONT signal. The software available so far for this purpose can only detect a small number of modifications. Alternatively, two samples can be compared for different RNA modifications. We present Magnipore, a novel tool to search for significant signal shifts between samples of Oxford Nanopore data from similar or related species. Magnipore classifies them into mutations and potential modifications. We use Magnipore to compare SARS-CoV-2 samples. Included were representatives of the early 2020s Pango lineages (n=6), samples from Pango lineages B.1.1.7 (n=2, Alpha), B.1.617.2 (n=1, Delta), and B.1.529 (n=7, Omicron). Magnipore utilizes position-wise Gaussian distribution models and a comprehensible significance threshold to find differential signals. In the case of Alpha and Delta, Magnipore identifies 55 detected mutations and 15 sites that hint at differential modifications. We predicted potential virus-variant and variant-group-specific differential modifications. Magnipore contributes to advancing RNA modification analysis in the context of viruses and virus variants.},

keywords = {coronavirus, nanopore, nucleic acid modifications, RNA / transcriptomics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Integrated genomic surveillance enables tracing of person-to-person SARS-CoV-2 transmission chains during community transmission and reveals extensive onward transmission of travel-imported infections, Germany, June to July 2021},

author = {Torsten Houwaart and Samir Belhaj and Emran Tawalbeh and Dirk Nagels and Yara Fröhlich and Patrick Finzer and Pilar Ciruela and Aurora Sabrià and Mercè Herrero and Cristina Andrés and Andrés Antón and Assia Benmoumene and Dounia Asskali and Hussein Haidar and Janina von Dahlen and Jessica Nicolai and Mygg Stiller and Jacqueline Blum and Christian Lange and Carla Adelmann and Britta Schroer and Ute Osmers and Christiane Grice and Phillipp P Kirfel and Hassan Jomaa and Daniel Strelow and Lisanna Hülse and Moritz Pigulla and Pascal Kreuzer and Alona Tyshaieva and Jonas Weber and Tobias Wienemann and Malte Kohns Vasconcelos and Katrin Hoffmann and Nadine Lübke and Sandra Hauka and Marcel Andree and Claus Jürgen Scholz and Nathalie Jazmati and Klaus Göbels and Rainer Zotz and Klaus Pfeffer and Jörg Timm and Lutz Ehlkes and Andreas Walker and Alexander T Dilthey and Deutsche COVID-19 OMICS Initiative (DeCOI)},

doi = {10.2807/1560-7917.ES.2022.27.43.2101089},

year  = {2022},

date = {2022-10-27},

urldate = {2022-10-27},

journal = {Euro Surveill},

volume = {27},

issue = {43},

pages = {2101089},

abstract = {BackgroundTracking person-to-person SARS-CoV-2 transmission in the population is important to understand the epidemiology of community transmission and may contribute to the containment of SARS-CoV-2. Neither contact tracing nor genomic surveillance alone, however, are typically sufficient to achieve this objective.AimWe demonstrate the successful application of the integrated genomic surveillance (IGS) system of the German city of Düsseldorf for tracing SARS-CoV-2 transmission chains in the population as well as detecting and investigating travel-associated SARS-CoV-2 infection clusters.MethodsGenomic surveillance, phylogenetic analysis, and structured case interviews were integrated to elucidate two genetically defined clusters of SARS-CoV-2 isolates detected by IGS in Düsseldorf in July 2021.ResultsCluster 1 (n = 67 Düsseldorf cases) and Cluster 2 (n = 36) were detected in a surveillance dataset of 518 high-quality SARS-CoV-2 genomes from Düsseldorf (53% of total cases, sampled mid-June to July 2021). Cluster 1 could be traced back to a complex pattern of transmission in nightlife venues following a putative importation by a SARS-CoV-2-infected return traveller (IP) in late June; 28 SARS-CoV-2 cases could be epidemiologically directly linked to IP. Supported by viral genome data from Spain, Cluster 2 was shown to represent multiple independent introduction events of a viral strain circulating in Catalonia and other European countries, followed by diffuse community transmission in Düsseldorf.ConclusionIGS enabled high-resolution tracing of SARS-CoV-2 transmission in an internationally connected city during community transmission and provided infection chain-level evidence of the downstream propagation of travel-imported SARS-CoV-2 cases.},

keywords = {coronavirus, nanopore, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Women in the European Virus Bioinformatics Center},

author = {Franziska Hufsky and Ana B. Abecasis and Patricia Agudelo-Romero and Magda Bletsa and Katherine Brown and Claudia Claus and Stefanie Deinhardt-Emmer and Li Deng and Caroline C. Friedel and María Inés Gismondi and Evangelia Georgia Kostaki and Denise Kühnert and Urmila Kulkarni-Kale and Karin J. Metzner and Irmtraud M. Meyer and Laura Miozzi and Luca Nishimura and Sofia Paraskevopoulou and Alba Pérez-Cataluña and Janina Rahlff and Emma Thomson and Charlotte Tumescheit and Lia van der Hoek and Lore Van Espen and Anne-Mieke Vandamme and Maryam Zaheri and Neta Zuckerman and Manja Marz},

doi = {10.3390/v14071522},

year  = {2022},

date = {2022-07-12},

urldate = {2022-07-12},

journal = {Viruses},

volume = {14},

issue = {7},

pages = {1522},

abstract = {Viruses are the cause of a considerable burden to human, animal and plant health, while on the other hand playing an important role in regulating entire ecosystems. The power of new sequencing technologies combined with new tools for processing “Big Data” offers unprecedented opportunities to answer fundamental questions in virology. Virologists have an urgent need for virus-specific bioinformatics tools. These developments have led to the formation of the European Virus Bioinformatics Center, a network of experts in virology and bioinformatics who are joining forces to enable extensive exchange and collaboration between these research areas. The EVBC strives to provide talented researchers with a supportive environment free of gender bias, but the gender gap in science, especially in math-intensive fields such as computer science, persists. To bring more talented women into research and keep them there, we need to highlight role models to spark their interest, and we need to ensure that female scientists are not kept at lower levels but are given the opportunity to lead the field. Here we showcase the work of the EVBC and highlight the achievements of some outstanding women experts in virology and viral bioinformatics.},

keywords = {viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hufsky2022,

title = {The International Virus Bioinformatics Meeting 2022},

author = {Franziska Hufsky and Denis Beslic and Dimitri Boeckaerts and Sebastian Duchene and Enrique González-Tortuero and Andreas J Gruber and Jiarong Guo and Daan Jansen and John Juma and Kunaphas Kongkitimanon and Antoni Luque and Muriel Ritsch and Gabriel L. Lovate and Luca Nishimura and Célia Pas and Esteban Domingo and Emma Hodcroft and Philippe Lemey and Matthew B Sullivan and Friedemann Weber and Fernando González-Candelas and Sarah Krautwurst and Alba Pérez-Cataluña and Walter Randazzo and Gloria Sánchez and Manja Marz },

doi = {10.3390/v14050973},

year  = {2022},

date = {2022-05-05},

urldate = {2022-05-05},

journal = {Viruses},

volume = {14},

issue = {5},

pages = {973},

abstract = {The International Virus Bioinformatics Meeting 2022 took place online, on 23-25 March 2022, and has attracted about 380 participants from all over the world. The goal of the meeting was to provide a meaningful and interactive scientific environment to promote discussion and collaboration and to inspire and suggest new research directions and questions. The participants created a highly interactive scientific environment even without physical face-to-face interactions. This meeting is a focal point to gain an insight into the state-of-the-art of the virus bioinformatics research landscape and to interact with researchers in the forefront as well as aspiring young scientists. The meeting featured eight invited and 18 contributed talks in eight sessions on three days, as well as 52 posters, which were presented during three virtual poster sessions. The main topics were: SARS-CoV-2, viral emergence and surveillance, virus-host interactions, viral sequence analysis, virus identification and annotation, phages, and viral diversity. This report summarizes the main research findings and highlights presented at the meeting.},

keywords = {annotation, software, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Gib mir den Virus und ich sag dir den Wirt},

author = {Franziska Hufsky and Manja Marz},

doi = {10.1007/s12268-022-1732-7},

year  = {2022},

date = {2022-03-28},

journal = {BIOSpektrum},

volume = {28},

pages = {225–226},

keywords = {software, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Comparative study of ten thogotovirus isolates and their distinct in vivo characteristics},

author = {Jonas Fuchs and Kevin Lamkiewicz and Larissa Kolesnikova and Martin Hölzer and Manja Marz and Georg Kochs},

doi = {10.1128/JVI.01556-21},

year  = {2022},

date = {2022-01-12},

journal = {J Virol},

abstract = {Thogotoviruses are tick-borne arboviruses that comprise a unique genus within the Orthomyxoviridae family. Infections with thogotoviruses primarily cause disease in livestock with occasional reports of human infections suggesting a zoonotic potential. In the past, multiple genetically distinct thogotoviruses were isolated mostly from collected ticks. However, many aspects regarding their phylogenetic relationships, morphological characteristics and virulence in mammals remain unclear. For the present comparative study, we used a collection of ten different thogotovirus isolates from different geographic areas. Next generation sequencing and subsequent phylogenetic analyses revealed a distinct separation of these viruses into two major clades - the Thogoto-like and Dhori-like viruses. Electron microscopy demonstrated a heterogeneous morphology with spherical and filamentous particles being present in virus preparations. To study their pathogenicity, we analyzed the viruses in a small animal model system. In intraperitoneally infected C57BL/6 mice, all isolates showed a tropism for liver, lung and spleen. Importantly, we did not observe horizontal transmission to uninfected, highly susceptible contact mice. The isolates enormously differed in their capacity to induce disease, ranging from subclinical to fatal outcomes. In vivo multi-step passaging experiments of two low-pathogenic isolates showed no increased virulence and sequence analyses of the passaged viruses indicated a high stability of the viral genomes after ten mouse passages. In summary, our analysis demonstrates the broad genetic and phenotypic variability within the thogotovirus genus. Moreover, thogotoviruses are well adapted to mammals but their horizontal transmission seems to depend on ticks as their vectors. Importance Since their discovery over sixty years ago, fifteen genetically distinct members of the thogotovirus genus have been isolated. These arboviruses belong to the Orthomyxovirus family and share many features with influenza viruses. However, numerous of these isolates have not been characterized in depth. In the present study, we comparatively analyzed a collection of ten different thogotovirus isolates to answer basic questions about their phylogenetic relationships, morphology and pathogenicity in mice. Our results highlight shared and unique characteristics of this diverse genus. Taken together, these observations provide a framework for the phylogenic classification and phenotypic characterization of newly identified thogotovirus isolates that could potentially cause severe human infections as exemplified by the recently reported, fatal Bourbon virus cases in the United States.},

keywords = {phylogenetics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {SARS-CoV-2 infection triggers profibrotic macrophage responses and lung fibrosis},

author = {Daniel Wendisch and Oliver Dietrich and Tommaso Mari and Saskia von Stillfried and Ignacio L. Ibarra and Mirja Mittermaier and Christin Mache and Robert Lorenz Chua and Rainer Knoll and Sara Timm and Sophia Brumhard and Tobias Krammer and Henrik Zauber and Anna Luisa Hiller and Anna Pascual-Reguant and Ronja Mothes and Roman David Bülow and Jessica Schulze and Alexander M. Leipold and Sonja Djudjaj and Florian Erhard and Robert Geffers and Fabian Pott and Julia Kazmierski and Josefine Radke and Panagiotis Pergantis and Kevin Baßler and Claudia Conrad and Anna C. Aschenbrenner and Birgit Sawitzki and Markus Landthaler and Emanuel Wyler and David Horst and Deutsche COVID-19 OMICS Initiative (DeCOI) and Stefan Hippenstiel and Andreas Hocke and Frank L. Heppner and Alexander Uhrig and Carmen Garcia and Felix Machleidt and Susanne Herold and Sefer Elezkurtaj and Charlotte Thibeault and Martin Witzenrath and Clément Cochain and Norbert Suttorp and Christian Drosten and Christine Goffinet and Florian Kurth and Joachim L. Schultze and Helena Radbruch and Matthias Ochs and Roland Eils and Holger Müller-Redetzky and Anja E. Hauser and Malte D. Luecken and Fabian J. Theis and Christian Conrad and Thorsten Wolff and Peter Boor and Matthias Selbach and Antoine-Emmanuel Saliba and Leif Erik Sander},

doi = {10.1016/j.cell.2021.11.033},

year  = {2021},

date = {2021-12-22},

journal = {Cell},

volume = {184},

number = {26},

pages = { 6243-6261},

abstract = {COVID-19-induced "acute respiratory distress syndrome" (ARDS) is associated with prolonged respiratory failure and high mortality, but the mechanistic basis of lung injury remains incompletely understood. Here, we analyze pulmonary immune responses and lung pathology in two cohorts of patients with COVID-19 ARDS using functional single-cell genomics, immunohistology, and electron microscopy. We describe an accumulation of CD163-expressing monocyte-derived macrophages that acquired a profibrotic transcriptional phenotype during COVID-19 ARDS. Gene set enrichment and computational data integration revealed a significant similarity between COVID-19-associated macrophages and profibrotic macrophage populations identified in idiopathic pulmonary fibrosis. COVID-19 ARDS was associated with clinical, radiographic, histopathological, and ultrastructural hallmarks of pulmonary fibrosis. Exposure of human monocytes to SARS-CoV-2, but not influenza A virus or viral RNA analogs, was sufficient to induce a similar profibrotic phenotype in vitro. In conclusion, we demonstrate that SARS-CoV-2 triggers profibrotic macrophage responses and pronounced fibroproliferative ARDS.},

keywords = {coronavirus, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Early IFN-α signatures and persistent dysfunction are distinguishing features of NK cells in severe COVID-19},

author = {Benjamin Krämer and Rainer Knoll and Lorenzo Bonaguro and Michael ToVinh and Jan Raabe and Rosario Astaburuaga-García and Jonas Schulte-Schrepping and Kim Melanie Kaiser and Gereon J. Rieke and Jenny Bischoff and Malte B. Monin and Christoph Hoffmeister and Stefan Schlabe and Elena De Domenico and Nico Reusch and Kristian Händler and Gary Reynolds and Nils Blüthgen and Gudrun Hack and Claudia Finnemann and Hans D. Nischalke and Christian P. Strassburg and Emily Stephenson and Yapeng Su and Louis Gardner and Dan Yuan and Daniel Chen and Jason Goldman and Philipp Rosenstiel and Susanne V. Schmidt and Eicke Latz and Kevin Hrusovsky and Andrew J. Ball and Joe M. Johnson and Paul-Albert Koenig and Florian I. Schmidt and Muzlifah Haniffa and James R. Heath and Beate M. Kümmerer and Verena Keitel and Björn Jensen and Paula Stubbemann and Florian Kurth and Leif E. Sander and Birgit Sawitzki and Deutsche COVID-19 OMICS Initiative (DeCOI) and Anna C. Aschenbrenner and Joachim L. Schultze and Jacob Nattermann },

doi = {10.1016/j.immuni.2021.09.002},

year  = {2021},

date = {2021-09-04},

urldate = {2021-09-04},

journal = {Immunity},

volume = {S1074-7613},

number = {21},

pages = {00365-4},

abstract = {Longitudinal analyses of the innate immune system, including the earliest time points, are essential to understand the immunopathogenesis and clinical course of coronavirus disease (COVID-19). Here, we performed a detailed characterization of natural killer (NK) cells in 205 patients (403 samples; days 2 to 41 after symptom onset) from four independent cohorts using single-cell transcriptomics and proteomics together with functional studies. We found elevated interferon (IFN)-α plasma levels in early severe COVD-19 alongside increased NK cell expression of IFN-stimulated genes (ISGs) and genes involved in IFN-α signaling, while upregulation of tumor necrosis factor (TNF)-induced genes was observed in moderate diseases. NK cells exert anti-SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) activity but are functionally impaired in severe COVID-19. Further, NK cell dysfunction may be relevant for the development of fibrotic lung disease in severe COVID-19, as NK cells exhibited impaired anti-fibrotic activity. Our study indicates preferential IFN-α and TNF responses in severe and moderate COVID-19, respectively, and associates a prolonged IFN-α-induced NK cell response with poorer disease outcome.},

keywords = {coronavirus, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Brandt2021,

title = {poreCov - An Easy to Use, Fast, and Robust Workflow for SARS-CoV-2 Genome Reconstruction via Nanopore Sequencing},

author = {Christian Brandt and Sebastian Krautwurst and Riccardo Spott and Mara Lohde and Mateusz Jundzill and Mike Marquet and Martin Hölzer},

url = {https://github.com/replikation/poreCov},

doi = {10.3389/fgene.2021.711437},

year  = {2021},

date = {2021-07-28},

urldate = {2021-07-28},

journal = {Front Genet},

volume = {12},

pages = {711437},

abstract = {In response to the SARS-CoV-2 pandemic, a highly increased sequencing effort has been established worldwide to track and trace ongoing viral evolution. Technologies, such as nanopore sequencing via the ARTIC protocol are used to reliably generate genomes from raw sequencing data as a crucial base for molecular surveillance. However, for many labs that perform SARS-CoV-2 sequencing, bioinformatics is still a major bottleneck, especially if hundreds of samples need to be processed in a recurring fashion. Pipelines developed for short-read data cannot be applied to nanopore data. Therefore, specific long-read tools and parameter settings need to be orchestrated to enable accurate genotyping and robust reference-based genome reconstruction of SARS-CoV-2 genomes from nanopore data. Here we present poreCov, a highly parallel workflow written in Nextflow, using containers to wrap all the tools necessary for a routine SARS-CoV-2 sequencing lab into one program. The ease of installation, combined with concise summary reports that clearly highlight all relevant information, enables rapid and reliable analysis of hundreds of SARS-CoV-2 raw sequence data sets or genomes. poreCov is freely available on GitHub under the GNUv3 license: github.com/replikation/poreCov.},

keywords = {coronavirus, nanopore, RNA / transcriptomics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Walker:21,

title = {Characterization of SARS-CoV-2 infection clusters based on integrated genomic surveillance, outbreak analysis and contact tracing in an urban setting},

author = {Andreas Walker and Torsten Houwaart and Patrick Finzer and Lutz Ehlkes and Alona Tyshaieva and Maximilian Damagnez and Daniel Strelow and Ashley Duplessis and Jessica Nicolai and Tobias Wienemann and Teresa Tamayo and Malte Kohns Vasconcelos and Lisanna Hülse and Katrin Hoffmann and Nadine Lübke and Sandra Hauka and Marcel Andree and Martin P Däumer and Alexander Thielen and Susanne Kolbe-Busch and Klaus Göbels and Rainer Zotz and Klaus Pfeffer and Jörg Timm and Alexander T Dilthey and Deutsche COVID-19 OMICS Initiative (DeCOI)},

doi = {10.1093/cid/ciab588},

year  = {2021},

date = {2021-06-28},

urldate = {2021-06-28},

journal = {Clin Infect Dis},

pages = {ciab588},

publisher = {Oxford University Press (OUP)},

abstract = {Background: Tracing of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) transmission chains is still a major challenge for public health authorities, when incidental contacts are not recalled or are not perceived as potential risk contacts. Viral sequencing can address key questions about SARS-CoV-2 evolution and may support reconstruction of viral transmission networks by integration of molecular epidemiology into classical contact tracing.



Methods: In collaboration with local public health authorities, we set up an integrated system of genomic surveillance in an urban setting, combining a) viral surveillance sequencing, b) genetically based identification of infection clusters in the population, c) integration of public health authority contact tracing data, and d) a user-friendly dashboard application as a central data analysis platform.



Results: Application of the integrated system from August to December 2020 enabled a characterization of viral population structure, analysis of 4 outbreaks at a maximum care hospital, and genetically based identification of 5 putative population infection clusters, all of which were confirmed by contact tracing. The system contributed to the development of improved hospital infection control and prevention measures and enabled the identification of previously unrecognized transmission chains, involving a martial arts gym and establishing a link between the hospital to the local population.



Conclusions: Integrated systems of genomic surveillance could contribute to the monitoring and, potentially, improved management of SARS-CoV-2 transmission in the population.},

keywords = {coronavirus, evolution, nanopore, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {SARS-CoV-2 infection paralyzes cytotoxic and metabolic functions of the immune cells},

author = {Yogesh Singh and Christoph Trautwein and Rolf Fendel and Naomi Krickeberg and Georgy Berezhnoy and Rosi Bissinger and Stephan Ossowski and Madhuri S Salker and Nicolas Casadei and Olaf Riess and Deutsche COVID-19 OMICS Initiative (DeCOI)},

doi = {10.1016/j.heliyon.2021.e07147},

year  = {2021},

date = {2021-05-28},

urldate = {2021-05-28},

journal = {Heliyon},

volume = {7},

number = {6},

pages = {e07147},

abstract = {The SARS-CoV-2 virus is the causative agent of the global COVID-19 infectious disease outbreak, which can lead to acute respiratory distress syndrome (ARDS). However, it is still unclear how the virus interferes with immune cell and metabolic functions in the human body. In this study, we investigated the immune response in acute or convalescent COVID-19 patients. We characterized the peripheral blood mononuclear cells (PBMCs) using flow cytometry and found that CD8+ T cells were significantly subsided in moderate COVID-19 and convalescent patients. Furthermore, characterization of CD8+ T cells suggested that convalescent patients have significantly diminished expression of both perforin and granzyme A. Using 1H-NMR spectroscopy, we characterized the metabolic status of their autologous PBMCs. We found that fructose, lactate and taurine levels were elevated in infected (mild and moderate) patients compared with control and convalescent patients. Glucose, glutamate, formate and acetate levels were attenuated in COVID-19 (mild and moderate) patients. In summary, our report suggests that SARS-CoV-2 infection leads to disrupted CD8+ T cytotoxic functions and changes the overall metabolic functions of immune cells.},

keywords = {coronavirus, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Swarm Learning for decentralized and confidential clinical machine learning},

author = {Stefanie Warnat-Herresthal and Hartmut Schultze and Krishnaprasad Lingadahalli Shastry and Sathyanarayanan Manamohan and Saikat Mukherjee and Vishesh Garg and Ravi Sarveswara and Kristian Händler and Peter Pickkers and N. Ahmad Aziz and Sofia Ktena and Florian Tran and Michael Bitzer and Stephan Ossowski and Nicolas Casadei and Christian Herr and Daniel Petersheim and Uta Behrends and Fabian Kern and Tobias Fehlmann and Philipp Schommers and Clara Lehmann and Max Augustin and Jan Rybniker and Janine Altmüller and Neha Mishra and Joana P. Bernardes and Benjamin Krämer and Lorenzo Bonaguro and Jonas Schulte-Schrepping and Elena De Domenico and Christian Siever and Michael Kraut and Milind Desai and Bruno Monnet and Maria Saridaki and Charles Martin Siegel and Anna Drews and Melanie Nuesch-Germano and Heidi Theis and Jan Heyckendorf and Stefan Schreiber and Sarah Kim-Hellmuth and COVID- Aachen Study (COVAS) and Jacob Nattermann and Dirk Skowasch and Ingo Kurth and Andreas Keller and Robert Bals and Peter Nürnberg and Olaf Rieß and Philip Rosenstiel and Mihai G. Netea and Fabian Theis and Sach Mukherjee and Michael Backes and Anna C. Aschenbrenner and Thomas Ulas and Deutsche COVID-19 Omics Initiative (DeCOI) and Monique M. B. Breteler and Evangelos J. Giamarellos-Bourboulis and Matthijs Kox and Matthias Becker and Sorin Cheran and Michael S. Woodacre and Eng Lim Goh and Joachim L. Schultze },

doi = {10.1038/s41586-021-03583-3},

year  = {2021},

date = {2021-05-26},

urldate = {2021-05-26},

journal = {Nature},

volume = {594},

number = {7862},

pages = {265-270},

abstract = {Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning-a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.



},

keywords = {coronavirus, machine learning, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Goettsch:21,

title = {ITN—VIROINF: Understanding (Harmful) Virus-Host Interactions by Linking Virology and Bioinformatics},

author = {Winfried Göttsch and Niko Beerenwinkel and Li Deng and Lars Dölken and Bas E. Dutilh and Florian Erhard and Lars Kaderali and Max Kleist and Roland Marquet and Jelle Matthijnssens and Shawna McCallin and Dino McMahon and Thomas Rattei and Ronald P. Van Rij and David L. Robertson and Martin Schwemmle and Noam Stern-Ginossar and Manja Marz},

doi = {10.3390/v13050766},

year  = {2021},

date = {2021-04-27},

urldate = {2021-04-27},

journal = {Viruses},

volume = {13},

number = {5},

pages = {766},

publisher = {MDPI AG},

abstract = {Many recent studies highlight the fundamental importance of viruses. Besides their important role as human and animal pathogens, their beneficial, commensal or harmful functions are poorly understood. By developing and applying tailored bioinformatical tools in important virological models, the Marie Skłodowska-Curie Initiative International Training Network VIROINF will provide a better understanding of viruses and the interaction with their hosts. This will open the door to validate methods of improving viral growth, morphogenesis and development, as well as to control strategies against unwanted microorganisms. The key feature of VIROINF is its interdisciplinary nature, which brings together virologists and bioinformaticians to achieve common goals. },

keywords = {review, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Disease severity-specific neutrophil signatures in blood transcriptomes stratify COVID-19 patients},

author = {Anna C. Aschenbrenner and Maria Mouktaroudi and Benjamin Krämer and Marie Oestreich and Nikolaos Antonakos and Melanie Nuesch-Germano and Konstantina Gkizeli and Lorenzo Bonaguro and Nico Reusch and Kevin Baßler and Maria Saridaki and Rainer Knoll and Tal Pecht and Theodore S. Kapellos and Sarandia Doulou and Charlotte Kröger and Miriam Herbert and Lisa Holsten and Arik Horne and Ioanna D. Gemünd and Nikoletta Rovina and Shobhit Agrawal and Kilian Dahm and Martina van Uelft and Anna Drews and Lena Lenkeit and Niklas Bruse and Jelle Gerretsen and Jannik Gierlich and Matthias Becker and Kristian Händler and Michael Kraut and Heidi Theis and Simachew Mengiste and Elena De Domenico and Jonas Schulte-Schrepping and Lea Seep and Jan Raabe and Christoph Hoffmeister and Michael ToVinh and Verena Keitel and Gereon Rieke and Valentina Talevi and Dirk Skowasch and N. Ahmad Aziz and Peter Pickkers and Frank L. van de Veerdonk and Mihai G. Netea and Joachim L. Schultze and Matthijs Kox and Monique M. B. Breteler and Jacob Nattermann and Antonia Koutsoukou and Evangelos J. Giamarellos-Bourboulis and Thomas Ulas and Deutsche COVID-19 OMICS Initiative (DeCOI)},

doi = {10.1186/s13073-020-00823-5},

year  = {2021},

date = {2021-01-13},

urldate = {2021-01-13},

journal = {Genome Med},

volume = {13},

number = {1},

pages = {7},

abstract = {Background: The SARS-CoV-2 pandemic is currently leading to increasing numbers of COVID-19 patients all over the world. Clinical presentations range from asymptomatic, mild respiratory tract infection, to severe cases with acute respiratory distress syndrome, respiratory failure, and death. Reports on a dysregulated immune system in the severe cases call for a better characterization and understanding of the changes in the immune system.



Methods: In order to dissect COVID-19-driven immune host responses, we performed RNA-seq of whole blood cell transcriptomes and granulocyte preparations from mild and severe COVID-19 patients and analyzed the data using a combination of conventional and data-driven co-expression analysis. Additionally, publicly available data was used to show the distinction from COVID-19 to other diseases. Reverse drug target prediction was used to identify known or novel drug candidates based on finding from data-driven findings.



Results: Here, we profiled whole blood transcriptomes of 39 COVID-19 patients and 10 control donors enabling a data-driven stratification based on molecular phenotype. Neutrophil activation-associated signatures were prominently enriched in severe patient groups, which was corroborated in whole blood transcriptomes from an independent second cohort of 30 as well as in granulocyte samples from a third cohort of 16 COVID-19 patients (44 samples). Comparison of COVID-19 blood transcriptomes with those of a collection of over 3100 samples derived from 12 different viral infections, inflammatory diseases, and independent control samples revealed highly specific transcriptome signatures for COVID-19. Further, stratified transcriptomes predicted patient subgroup-specific drug candidates targeting the dysregulated systemic immune response of the host.



Conclusions: Our study provides novel insights in the distinct molecular subgroups or phenotypes that are not simply explained by clinical parameters. We show that whole blood transcriptomes are extremely informative for COVID-19 since they capture granulocytes which are major drivers of disease severity.},

keywords = {coronavirus, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Longitudinal Multi-omics Analyses Identify Responses of Megakaryocytes, Erythroid Cells, and Plasmablasts as Hallmarks of Severe COVID-19},

author = {Joana P. Bernardes and Neha Mishra and Florian Tran and Thomas Bahmer and Lena Best and Johanna I. Blase and Dora Bordoni and Jeanette Franzenburg and Ulf Geisen and Jonathan Josephs-Spaulding and Philipp Köhler and Axel Künstner and Elisa Rosati and Anna C. Aschenbrenner and Petra Bacher and Nathan Baran and Teide Boysen and Burkhard Brandt and Niklas Bruse and Jonathan Dörr and Andreas Dräger and Gunnar Elke and David Ellinghaus and Julia Fischer and Michael Forster and Andre Franke and Sören Franzenburg and Norbert Frey and Anette Friedrichs and Janina Fuß and Andreas Glück and Jacob Hamm and Finn Hinrichsen and Marc P. Hoeppner and Simon Imm and Ralf Junker and Sina Kaiser and Ying H. Kan and Rainer Knoll and Christoph Lange and Georg Laue and Clemens Lier and Matthias Lindner and Georgios Marinos and Robert Markewitz and Jacob Nattermann and Rainer Noth and Peter Pickkers and Klaus F. Rabe and Alina Renz and Christoph Röcken and Jan Rupp and Annika Schaffarzyk and Alexander Scheffold and Jonas Schulte-Schrepping and Domagoj Schunk and Dirk Skowasch and Thomas Ulas and Klaus-Peter Wandinger and Michael Wittig and Johannes Zimmermann and Hauke Busch and Bimba F. Hoyer and Christoph Kaleta and Jan Heyckendorf and Matthijs Kox and Jan Rybniker and Stefan Schreiber and Joachim L. Schultze and Philip Rosenstiel and HCA Lung Biological Network and Deutsche COVID-19 Omics Initiative (DeCOI)

},

doi = {10.1016/j.immuni.2020.11.017},

year  = {2020},

date = {2020-12-15},

urldate = {2020-12-15},

journal = {Immunity},

volume = {53},

number = {6},

pages = {1296-1314.e9},

abstract = {Temporal resolution of cellular features associated with a severe COVID-19 disease trajectory is needed for understanding skewed immune responses and defining predictors of outcome. Here, we performed a longitudinal multi-omics study using a two-center cohort of 14 patients. We analyzed the bulk transcriptome, bulk DNA methylome, and single-cell transcriptome (>358,000 cells, including BCR profiles) of peripheral blood samples harvested from up to 5 time points. Validation was performed in two independent cohorts of COVID-19 patients. Severe COVID-19 was characterized by an increase of proliferating, metabolically hyperactive plasmablasts. Coinciding with critical illness, we also identified an expansion of interferon-activated circulating megakaryocytes and increased erythropoiesis with features of hypoxic signaling. Megakaryocyte- and erythroid-cell-derived co-expression modules were predictive of fatal disease outcome. The study demonstrates broad cellular effects of SARS-CoV-2 infection beyond adaptive immune cells and provides an entry point toward developing biomarkers and targeted treatments of patients with COVID-19.},

keywords = {coronavirus, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hufsky:20b,

title = {The International Virus Bioinformatics Meeting 2020},

author = {Franziska Hufsky and Niko Beerenwinkel and Irmtraud M. Meyer and Simon Roux and Georgia May Cook and Cormac M. Kinsella and Kevin Lamkiewicz and Mike Marquet and David F. Nieuwenhuijse and Ingrida Olendraite and Sofia Paraskevopoulou and Francesca Young and Ronald Dijkman and Bashar Ibrahim and Jenna Kelly and Philippe Le Mercier and Manja Marz and Alban Ramette and Volker Thiel},

doi = {10.3390/v12121398},

year  = {2020},

date = {2020-12-06},

urldate = {2020-01-01},

journal = {Viruses},

volume = {12},

number = {12},

pages = {1398},

publisher = {MDPI AG},

abstract = {The International Virus Bioinformatics Meeting 2020 was originally planned to take place in Bern, Switzerland, in March 2020. However, the COVID-19 pandemic put a spoke in the wheel of almost all conferences to be held in 2020. After moving the conference to 8–9 October 2020, we got hit by the second wave and finally decided at short notice to go fully online. On the other hand, the pandemic has made us even more aware of the importance of accelerating research in viral bioinformatics. Advances in bioinformatics have led to improved approaches to investigate viral infections and outbreaks. The International Virus Bioinformatics Meeting 2020 has attracted approximately 120 experts in virology and bioinformatics from all over the world to join the two-day virtual meeting. Despite concerns being raised that virtual meetings lack possibilities for face-to-face discussion, the participants from this small community created a highly interactive scientific environment, engaging in lively and inspiring discussions and suggesting new research directions and questions. The meeting featured five invited and twelve contributed talks, on the four main topics: (1) proteome and RNAome of RNA viruses, (2) viral metagenomics and ecology, (3) virus evolution and classification and (4) viral infections and immunology. Further, the meeting featured 20 oral poster presentations, all of which focused on specific areas of virus bioinformatics. This report summarizes the main research findings and highlights presented at the meeting.},

keywords = {classification, conference report, evolution, metagenomics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Kalvari:21,

title = {Rfam 14: expanded coverage of metagenomic, viral and microRNA families},

author = {Ioanna Kalvari and Eric P Nawrocki and Nancy Ontiveros-Palacios and Joanna Argasinska and Kevin Lamkiewicz and Manja Marz and Sam Griffiths-Jones and Claire Toffano-Nioche and Daniel Gautheret and Zasha Weinberg and Elena Rivas and Sean R Eddy and Robert D Finn and Alex Bateman and Anton I Petrov},

url = {https://rfam.org/},

doi = {10.1093/nar/gkaa1047},

year  = {2020},

date = {2020-11-19},

urldate = {2020-11-19},

journal = {Nucleic Acids Res},

volume = {49},

number = {D1},

pages = {D192--D200},

publisher = {Oxford University Press (OUP)},

abstract = {Rfam is a database of RNA families where each of the 3444 families is represented by a multiple sequence alignment of known RNA sequences and a covariance model that can be used to search for additional members of the family. Recent developments have involved expert collaborations to improve the quality and coverage of Rfam data, focusing on microRNAs, viral and bacterial RNAs. We have completed the first phase of synchronising microRNA families in Rfam and miRBase, creating 356 new Rfam families and updating 40. We established a procedure for comprehensive annotation of viral RNA families starting with Flavivirus and Coronaviridae RNAs. We have also increased the coverage of bacterial and metagenome-based RNA families from the ZWD database. These developments have enabled a significant growth of the database, with the addition of 759 new families in Rfam 14. To facilitate further community contribution to Rfam, expert users are now able to build and submit new families using the newly developed Rfam Cloud family curation system. New Rfam website features include a new sequence similarity search powered by RNAcentral, as well as search and visualisation of families with pseudoknots. Rfam is freely available at https://rfam.org.},

keywords = {alignment, annotation, bacteria, coronavirus, database, metagenomics, ncRNAs, RNA / transcriptomics, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hufsky:20a,

title = {Computational strategies to combat COVID-19: useful tools to accelerate SARS-CoV-2 and coronavirus research},

author = {Franziska Hufsky and Kevin Lamkiewicz and Alexandre Almeida and Abdel Aouacheria and Cecilia Arighi and Alex Bateman and Jan Baumbach and Niko Beerenwinkel and Christian Brandt and Marco Cacciabue and Sara Chuguransky and Oliver Drechsel and Robert D Finn and Adrian Fritz and Stephan Fuchs and Georges Hattab and Anne-Christin Hauschild and Dominik Heider and Marie Hoffmann and Martin Hölzer and Stefan Hoops and Lars Kaderali and Ioanna Kalvari and Max Kleist and Renó Kmiecinski and Denise Kühnert and Gorka Lasso and Pieter Libin and Markus List and Hannah F Löchel and Maria J Martin and Roman Martin and Julian Matschinske and Alice C McHardy and Pedro Mendes and Jaina Mistry and Vincent Navratil and Eric P Nawrocki and Áine Niamh O'Toole and Nancy Ontiveros-Palacios and Anton I Petrov and Guillermo Rangel-Pineros and Nicole Redaschi and Susanne Reimering and Knut Reinert and Alejandro Reyes and Lorna Richardson and David L Robertson and Sepideh Sadegh and Joshua B Singer and Kristof Theys and Chris Upton and Marius Welzel and Lowri Williams and Manja Marz},

url = {http://evbc.uni-jena.de/tools/coronavirus-tools/},

doi = {10.1093/bib/bbaa232},

year  = {2020},

date = {2020-11-04},

urldate = {2020-11-04},

journal = {Brief Bioinform},

volume = {22},

number = {2},

pages = {642--663},

publisher = {Oxford University Press (OUP)},

abstract = {SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) is a novel virus of the family Coronaviridae. The virus causes the infectious disease COVID-19. The biology of coronaviruses has been studied for many years. However, bioinformatics tools designed explicitly for SARS-CoV-2 have only recently been developed as a rapid reaction to the need for fast detection, understanding and treatment of COVID-19. To control the ongoing COVID-19 pandemic, it is of utmost importance to get insight into the evolution and pathogenesis of the virus. In this review, we cover bioinformatics workflows and tools for the routine detection of SARS-CoV-2 infection, the reliable analysis of sequencing data, the tracking of the COVID-19 pandemic and evaluation of containment measures, the study of coronavirus evolution, the discovery of potential drug targets and development of therapeutic strategies. For each tool, we briefly describe its use case and how it advances research specifically for SARS-CoV-2. All tools are free to use and available online, either through web applications or public code repositories.},

keywords = {coronavirus, evolution, review, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Jordan-Paiz:20,

title = {HIV-1 lethality and loss of Env protein expression induced by single synonymous substitutions in the virus genome intronic splicing silencer},

author = {Ana Jordan-Paiz and Maria Nevot and Kevin Lamkiewicz and Marie Lataretu and Sandra Franco and Manja Marz and Miguel Angel Martinez},

doi = {10.1128/jvi.01108-20},

year  = {2020},

date = {2020-10-14},

urldate = {2020-01-01},

journal = {J Virol},

volume = {94},

number = {21},

publisher = {American Society for Microbiology},

abstract = {Synonymous genome recoding has been widely used to study different aspects of virus biology. Codon usage affects the temporal regulation of viral gene expression. In this study, we performed synonymous codon mutagenesis to investigate whether codon usage affected HIV-1 Env protein expression and virus viability. We replaced the codons AGG, GAG, CCU, ACU, CUC, and GGG of the HIV-1 env gene with the synonymous codons CGU, GAA, CCG, ACG, UUA, and GGA, respectively. We found that recoding the Env protein gp120 coding region (excluding the Rev response element [RRE]) did not significantly affect virus replication capacity, even though we introduced 15 new CpG dinucleotides. In contrast, changing a single codon (AGG to CGU) located in the gp41 coding region (HXB2 env position 2125 to 2127), which was included in the intronic splicing silencer (ISS), completely abolished virus replication and Env expression. Computational analyses of this mutant revealed a severe disruption in the ISS RNA secondary structure. A variant that restored ISS secondary RNA structure also reestablished Env production and virus viability. Interestingly, this codon variant prevented both virus replication and Env translation in a eukaryotic expression system. These findings suggested that disrupting mRNA splicing was not the only means of inhibiting translation. Our findings indicated that synonymous gp120 recoding was not always deleterious to HIV-1 replication. Importantly¸ we found that disrupting an external ISS loop strongly affected HIV-1 replication and Env translation.

},

keywords = {proteins, RNA structure, splicing, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Gerresheim:20,

title = {Ribosome Pausing at Inefficient Codons at the End of the Replicase Coding Region Is Important for Hepatitis C Virus Genome Replication},

author = {Gesche K. Gerresheim and Carolin S. Hess and Lyudmila A. Shalamova and Markus Fricke and Manja Marz and Dmitri E. Andreev and Ivan N. Shatsky and Michael Niepmann},

doi = {10.3390/ijms21186955},

year  = {2020},

date = {2020-09-22},

urldate = {2020-09-22},

journal = {Int J Mol Sci},

volume = {21},

number = {18},

pages = {6955},

publisher = {MDPI AG},

abstract = {Hepatitis C virus (HCV) infects liver cells and often causes chronic infection, also leading to liver cirrhosis and cancer. In the cytoplasm, the viral structural and non-structural (NS) proteins are directly translated from the plus strand HCV RNA genome. The viral proteins NS3 to NS5B proteins constitute the replication complex that is required for RNA genome replication via a minus strand antigenome. The most C-terminal protein in the genome is the NS5B replicase, which needs to initiate antigenome RNA synthesis at the very 3′-end of the plus strand. Using ribosome profiling of cells replicating full-length infectious HCV genomes, we uncovered that ribosomes accumulate at the HCV stop codon and about 30 nucleotides upstream of it. This pausing is due to the presence of conserved rare, inefficient Wobble codons upstream of the termination site. Synonymous substitution of these inefficient codons to efficient codons has negative consequences for viral RNA replication but not for viral protein synthesis. This pausing may allow the enzymatically active replicase core to find its genuine RNA template in cis, while the protein is still held in place by being stuck with its C-terminus in the exit tunnel of the paused ribosome.

},

keywords = {cancer, liver, ncRNAs, RNA structure, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Collatz:20,

title = {EpiDope: A Deep Neural Network for linear B-cell epitope prediction},

author = {Maximilian Collatz and Florian Mock and Emanuel Barth and Martin Hölzer and Konrad Sachse and Manja Marz},

editor = {Lenore Cowen},

url = {https://github.com/rnajena/EpiDope},

doi = {10.1093/bioinformatics/btaa773},

year  = {2020},

date = {2020-09-11},

urldate = {2020-09-11},

journal = {Bioinformatics},

volume = {37},

number = {4},

pages = {448–455},

publisher = {Oxford University Press (OUP)},

abstract = {By binding to specific structures on antigenic proteins, the so-called epitopes, B-cell antibodies can neutralize pathogens. The identification of B-cell epitopes is of great value for the development of specific serodiagnostic assays and the optimization of medical therapy. However, identifying diagnostically or therapeutically relevant epitopes is a challenging task that usually involves extensive laboratory work. In this study, we show that the time, cost and labor-intensive process of epitope detection in the lab can be significantly reduced using in silico prediction.

Here, we present EpiDope, a python tool which uses a deep neural network to detect linear B-cell epitope regions on individual protein sequences. With an area under the curve between 0.67 ± 0.07 in the receiver operating characteristic curve, EpiDope exceeds all other currently used linear B-cell epitope prediction tools. Our software is shown to reliably predict linear B-cell epitopes of a given protein sequence, thus contributing to a significant reduction of laboratory experiments and costs required for the conventional approach.},

keywords = {machine learning, software, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Mock:20,

title = {VIDHOP, viral host prediction with Deep Learning},

author = {Florian Mock and Adrian Viehweger and Emanuel Barth and Manja Marz},

editor = {Jinbo Xu},

url = {https://github.com/rnajena/vidhop},

doi = {10.1093/bioinformatics/btaa705},

year  = {2020},

date = {2020-08-10},

urldate = {2020-08-10},

journal = {Bioinformatics},

volume = {37},

number = {3},

pages = {318–325},

publisher = {Oxford University Press (OUP)},

abstract = {Zoonosis, the natural transmission of infections from animals to humans, is a far-reaching global problem. The recent outbreaks of Zikavirus, Ebolavirus and Coronavirus are examples of viral zoonosis, which occur more frequently due to globalization. In case of a virus outbreak, it is helpful to know which host organism was the original carrier of the virus to prevent further spreading of viral infection. Recent approaches aim to predict a viral host based on the viral genome, often in combination with the potential host genome and arbitrarily selected features. These methods are limited in the number of different hosts they can predict or the accuracy of the prediction.

Here, we present a fast and accurate deep learning approach for viral host prediction, which is based on the viral genome sequence only. We tested our deep neural network (DNN) on three different virus species (influenza A virus, rabies lyssavirus and rotavirus A). We achieved for each virus species an AUC between 0.93 and 0.98, allowing highly accurate predictions while using only fractions (100–400 bp) of the viral genome sequences. We show that deep neural networks are suitable to predict the host of a virus, even with a limited amount of sequences and highly unbalanced available data. The trained DNNs are the core of our virus–host prediction tool VIrus Deep learning HOst Prediction (VIDHOP). VIDHOP also allows the user to train and use models for other viruses.},

keywords = {machine learning, software, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Schulte-Schrepping:20,

title = {Severe COVID-19 Is Marked by a Dysregulated Myeloid Cell Compartment},

author = {Jonas Schulte-Schrepping and Nico Reusch and Daniela Paclik and Kevin Baßler and Stephan Schlickeiser and Bowen Zhang and Benjamin Krämer and Tobias Krammer and Sophia Brumhard and Lorenzo Bonaguro and Elena De Domenico and Daniel Wendisch and Martin Grasshoff and Theodore S. Kapellos and Michael Beckstette and Tal Pecht and Adem Saglam and Oliver Dietrich and Henrik E. Mei and Axel R. Schulz and Claudia Conrad and Désirée Kunkel and Ehsan Vafadarnejad and Cheng-Jian Xu and Arik Horne and Miriam Herbert and Anna Drews and Charlotte Thibeault and Moritz Pfeiffer and Stefan Hippenstiel and Andreas Hocke and Holger Müller-Redetzky and Katrin-Moira Heim and Felix Machleidt and Alexander Uhrig and Laure Bosquillon Jarcy and Linda Jürgens and Miriam Stegemann and Christoph R. Glösenkamp and Hans-Dieter Volk and Christine Goffinet and Markus Landthaler and Emanuel Wyler and Philipp Georg and Maria Schneider and Chantip Dang-Heine and Nick Neuwinger and Kai Kappert and Rudolf Tauber and Victor Corman and Jan Raabe and Kim Melanie Kaiser and Michael To Vinh and Gereon Rieke and Christian Meisel and Thomas Ulas and Matthias Becker and Robert Geffers and Martin Witzenrath and Christian Drosten and Norbert Suttorp and Christof Kalle and Florian Kurth and Kristian Händler and Joachim L. Schultze and Anna C. Aschenbrenner and Yang Li and Jacob Nattermann and Birgit Sawitzki and Antoine-Emmanuel Saliba and Leif Erik Sander and Deutsche COVID-19 OMICS Initiative (DeCOI)

},

doi = {10.1016/j.cell.2020.08.001},

year  = {2020},

date = {2020-08-05},

urldate = {2020-01-01},

journal = {Cell},

volume = {182},

number = {6},

pages = {1419-1440.e23},

publisher = {Elsevier BV},

abstract = {Coronavirus disease 2019 (COVID-19) is a mild to moderate respiratory tract infection, however, a subset of patients progress to severe disease and respiratory failure. The mechanism of protective immunity in mild forms and the pathogenesis of severe COVID-19 associated with increased neutrophil counts and dysregulated immune responses remain unclear. In a dual-center, two-cohort study, we combined single-cell RNA-sequencing and single-cell proteomics of whole-blood and peripheral-blood mononuclear cells to determine changes in immune cell composition and activation in mild versus severe COVID-19 (242 samples from 109 individuals) over time. HLA-DRhiCD11chi inflammatory monocytes with an interferon-stimulated gene signature were elevated in mild COVID-19. Severe COVID-19 was marked by occurrence of neutrophil precursors, as evidence of emergency myelopoiesis, dysfunctional mature neutrophils, and HLA-DRlo monocytes. Our study provides detailed insights into the systemic immune response to SARS-CoV-2 infection and reveals profound alterations in the myeloid cell compartment associated with severe COVID-19.},

keywords = {coronavirus, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Overholt:20,

title = {Inclusion of Oxford Nanopore long reads improves all microbial and viral metagenome-assembled genomes from a complex aquifer system},

author = {Will A. Overholt and Martin Hölzer and Patricia Geesink and Celia Diezel and Manja Marz and Kirsten Küsel},

doi = {10.1111/1462-2920.15186},

year  = {2020},

date = {2020-08-05},

urldate = {2020-08-05},

journal = {Environ Microbiol},

volume = {22},

number = {9},

pages = {4000-4013},

publisher = {Wiley},

abstract = {Assembling microbial and viral genomes from metagenomes is a powerful and appealing method to understand structure–function relationships in complex environments. To compare the recovery of genomes from microorganisms and their viruses from groundwater, we generated shotgun metagenomes with Illumina sequencing accompanied by long reads derived from the Oxford Nanopore Technologies (ONT) sequencing platform. Assembly and metagenome-assembled genome (MAG) metrics for both microbes and viruses were determined from an Illumina-only assembly, ONT-only assembly, and a hybrid assembly approach. The hybrid approach recovered 2× more mid to high-quality MAGs compared to the Illumina-only approach and 4× more than the ONT-only approach. A similar number of viral genomes were reconstructed using the hybrid and ONT methods, and both recovered nearly fourfold more viral genomes than the Illumina-only approach. While yielding fewer MAGs, the ONT-only approach generated MAGs with a high probability of containing rRNA genes, 3× higher than either of the other methods. Of the shared MAGs recovered from each method, the ONT-only approach generated the longest and least fragmented MAGs, while the hybrid approach yielded the most complete. This work provides quantitative data to inform a cost–benefit analysis of the decision to supplement shotgun metagenomic projects with long reads towards the goal of recovering genomes from environmentally abundant groups.},

keywords = {assembly, DNA / genomics, groundwater, metagenomics, nanopore, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hufsky:20,

title = {Computational Strategies to Combat COVID-19: Useful Tools to Accelerate SARS-CoV-2 and Coronavirus Research},

author = {Franziska Hufsky and Kevin Lamkiewicz and Alexandre Almeida and Abdel Aouacheria and Cecilia Arighi and Alex Bateman and Jan Baumbach and Niko Beerenwinkel and Christian Brandt and Marco Cacciabue and Sara Chuguransky and Oliver Drechsel and Robert D. Finn and Adrian Fritz and Stephan Fuchs and Georges Hattab and Anne-Christin Hauschild and Dominik Heider and Marie Hoffmann and Martin Hölzer and Stefan Hoops and Lars Kaderali and Ioanna Kalvari and Max Kleist and Rene Kmiecinski and Denise Kühnert and Gorka Lasso and Pieter Libin and Markus List and Hannah F. Löchel and Maria J. Martin and Roman Martin and Julian Matschinske and Alice C. McHardy and Pedro Mendes and Jaina Mistry and Vincent Navratil and Eric Nawrocki and Áine Niamh O'Toole and Nancy Palacios-Ontiveros and Anton I. Petrov and Guillermo Rangel-Piñeros and Nicole Redaschi and Susanne Reimering and Knut Reinert and Alejandro Reyes and Lorna Richardson and David L. Robertson and Sepideh Sadegh and Joshua B. Singer and Kristof Theys and Chris Upton and Marius Welzel and Lowri Williams and Manja Marz},

doi = {10.20944/preprints202005.0376.v1},

year  = {2020},

date = {2020-05-23},

urldate = {2020-05-23},

journal = {Preprints},

publisher = {MDPI AG},

abstract = {SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) is a novel virus of the family Coronaviridae. The virus causes the infectious disease COVID-19. The biology of coronaviruses has been studied for many years. However, bioinformatics tools designed explicitly for SARS-CoV-2 have only recently been developed as a rapid reaction to the need for fast detection, understanding, and treatment of COVID-19. To control the ongoing COVID-19 pandemic, it is of utmost importance to get insight into the evolution and pathogenesis of the virus. In this review, we cover bioinformatics workflows and tools for the routine detection of SARS-CoV-2 infection, the reliable analysis of sequencing data, the tracking of the COVID-19 pandemic and evaluation of containment measures, the study of coronavirus evolution, the discovery of potential drug targets and development of therapeutic strategies. For each tool, we briefly describe its use case and how it advances research specifically for SARS-CoV-2. All tools are freely available online, either through web applications or public code repositories.

},

note = {Now published in Brief Bioinform: https://dx.doi.org/10.1093/bib/bbaa232},

keywords = {coronavirus, evolution, review, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Mostajo:20,

title = {A comprehensive annotation and differential expression analysis of short and long non-coding RNAs in 16 bat genomes},

author = {Nelly F. Mostajo and Marie Lataretu and Sebastian Krautwurst and Florian Mock and Daniel Desirò and Kevin Lamkiewicz and Maximilian Collatz and Andreas Schoen and Friedemann Weber and Manja Marz and Martin Hölzer},

url = {https://www.rna.uni-jena.de/supplements/bats/index.html},

doi = {10.1093/nargab/lqz006},

year  = {2019},

date = {2019-09-30},

urldate = {2019-09-30},

journal = {NAR Genomics Bioinf},

volume = {2},

number = {1},

pages = {lqz006},

abstract = {Although bats are increasingly becoming the focus of scientific studies due to their unique properties, these exceptional animals are still among the least studied mammals. Assembly quality and completeness of bat genomes vary a lot and especially non-coding RNA (ncRNA) annotations are incomplete or simply missing. Accordingly, standard bioinformatics pipelines for gene expression analysis often ignore ncRNAs such as microRNAs or long antisense RNAs. The main cause of this problem is the use of incomplete genome annotations. We present a complete screening for ncRNAs within 16 bat genomes. NcRNAs affect a remarkable variety of vital biological functions, including gene expression regulation, RNA processing, RNA interference and, as recently described, regulatory processes in viral infections. Within all investigated bat assemblies, we annotated 667 ncRNA families including 162 snoRNAs and 193 miRNAs as well as rRNAs, tRNAs, several snRNAs and lncRNAs, and other structural ncRNA elements. We validated our ncRNA candidates by six RNA-Seq data sets and show significant expression patterns that have never been described before in a bat species on such a large scale. Our annotations will be usable as a resource (rna.uni-jena.de/supplements/bats) for deeper studying of bat evolution, ncRNAs repertoire, gene expression and regulation, ecology and important host–virus interactions.},

keywords = {annotation, assembly, differential expression analysis, evolution, ncRNAs, RNA / transcriptomics, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hoelzer:19a,

title = {Virus- and interferon alpha-induced transcriptomes of cells from the microbat \textit{Myotis daubentonii}},

author = {Martin Hölzer and Andreas Schoen and Julia Wulle and Marcel A. Müller and Christian Drosten and Manja Marz and Friedemann Weber},

doi = {10.1016/j.isci.2019.08.016},

year  = {2019},

date = {2019-09-27},

urldate = {2019-01-01},

journal = {iScience},

volume = {19},

pages = {647-661},

publisher = {Elsevier BV},

abstract = {Antiviral interferons (IFN-alpha/beta) are possibly responsible for the high tolerance of bats to zoonotic viruses. Previous studies focused on the IFN system of megabats (suborder Yinpterochiroptera). We present statistically robust RNA sequencing (RNA-seq) data on transcriptomes of cells from the “microbat” Myotis daubentonii (suborder Yangochiroptera) responding at 6 and 24 h to either an IFN-inducing virus or treatment with IFN. Our data reveal genes triggered only by virus, either in both humans and Myotis (CCL4, IFNL3, CH25H), or exclusively in Myotis (STEAP4). Myotis cells also express a series of conserved IFN-stimulated genes (ISGs) and an unusually high paralog number of the antiviral ISG BST2 (tetherin) but lack several ISGs that were described for megabats (EMC2, FILIP1, IL17RC, OTOGL, SLC24A1). Also, in contrast to megabats, we detected neither different IFN-alpha subtypes nor an unusually high baseline expression of IFNs. Thus, Yangochiroptera microbats, represented by Myotis, may possess an IFN system with distinctive features.

},

keywords = {differential expression analysis, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Viehweger:19a,

title = {Direct RNA nanopore sequencing of full-length coronavirus genomes provides novel insights into structural variants and enables modification analysis.},

author = {Adrian Viehweger and Sebastian Krautwurst and Kevin Lamkiewicz and Ramakanth Madhugiri and John Ziebuhr and Martin Hölzer and Manja Marz},

doi = {10.1101/gr.247064.118},

year  = {2019},

date = {2019-08-22},

urldate = {2019-08-22},

journal = {Genome Res},

volume = {29},

pages = {1545-1554},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Sequence analyses of RNA virus genomes remain challenging owing to the exceptional genetic plasticity of these viruses. Because of high mutation and recombination rates, genome replication by viral RNA-dependent RNA polymerases leads to populations of closely related viruses, so-called “quasispecies.” Standard (short-read) sequencing technologies are ill-suited to reconstruct large numbers of full-length haplotypes of (1) RNA virus genomes and (2) subgenome-length (sg) RNAs composed of noncontiguous genome regions. Here, we used a full-length, direct RNA sequencing (DRS) approach based on nanopores to characterize viral RNAs produced in cells infected with a human coronavirus. By using DRS, we were able to map the longest (∼26-kb) contiguous read to the viral reference genome. By combining Illumina and Oxford Nanopore sequencing, we reconstructed a highly accurate consensus sequence of the human coronavirus (HCoV)-229E genome (27.3 kb). Furthermore, by using long reads that did not require an assembly step, we were able to identify, in infected cells, diverse and novel HCoV-229E sg RNAs that remain to be characterized. Also, the DRS approach, which circumvents reverse transcription and amplification of RNA, allowed us to detect methylation sites in viral RNAs. Our work paves the way for haplotype-based analyses of viral quasispecies by showing the feasibility of intra-sample haplotype separation. Even though several technical challenges remain to be addressed to exploit the potential of the nanopore technology fully, our work illustrates that DRS may significantly advance genomic studies of complex virus populations, including predictions on long-range interactions in individual full-length viral RNA haplotypes.},

keywords = {assembly, coronavirus, nanopore, nucleic acid modifications, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Dukhovny:19,

title = {A CRISPR activation screen identifies genes protecting from Zika virus infection},

author = {Anna Dukhovny and Kevin Lamkiewicz and Qian Chen and Markus Fricke and Nabila Jabrane-Ferrat and Manja Marz and Jae U. Jung and Ella H. Sklan},

doi = {10.1128/JVI.00211-19},

year  = {2019},

date = {2019-07-30},

urldate = {2019-07-30},

journal = {J Virol},

volume = {93},

number = {16},

publisher = {American Society for Microbiology Journals},

abstract = {Zika virus (ZIKV) is an arthropod borne emerging pathogen causing febrile illness. ZIKV is associated Guillain-Barré syndrome and other neurological complications. Infection during pregnancy is associated with pregnancy complications and developmental and neurological abnormalities collectively defined as congenital Zika syndrome. There is still no vaccine or specific treatment for ZIKV infection. To identify host factors that can rescue cells from ZIKV infection we used a genome scale CRISPR activation screen. Our highly ranking hits included a short list of interferon stimulated genes (ISGs) previously reported to have antiviral activity. Validation of the screen results highlighted IFNL2 and IFI6 as genes providing high levels of protection from ZIKV. Activation of these genes had an effect on an early stage in viral infection. In addition, infected cells expressing sgRNAs for both of these genes displayed lower levels of cell death compared to controls. Furthermore, the identified genes were significantly induced in ZIKV infected placenta explants. Thus, these results highlight a set of ISGs directly relevant for rescuing cells from ZIKV infection or its associated cell death and substantiates CRISPR activation screens as a tool to identify host factors impeding pathogen infection.IMPORTANCE Zika virus (ZIKV) is an emerging vector-borne pathogen causing a febrile disease. ZIKV infection might also trigger Guillain-Barré syndrome, neuropathy and myelitis. Vertical transmission of ZIKV can cause fetus demise, still birth or severe congenital abnormalities and neurological complications. There is no vaccine or specific antiviral treatment against ZIKV. We used a genome wide CRISPR activation screen, where genes are activated from their native promoters to identify host cell factors that protect cells from ZIKV infection or associated cell death. The results provide better understanding of key host factors that protect cells from ZIKV infection and might assist in identifying novel antiviral targets.},

keywords = {pregnancy, RNA / transcriptomics, virus host interaction, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Kallies:19,

title = {Evaluation of Sequencing Library Preparation Protocols for Viral Metagenomic Analysis from Pristine Aquifer Groundwaters.},

author = {René Kallies and Martin Hölzer and Rodolfo Brizola Toscan and Ulisses Nunes da Rocha and John Anders and Manja Marz and Antonis Chatzinotas},

doi = {10.3390/v11060484},

year  = {2019},

date = {2019-05-28},

urldate = {2019-01-01},

journal = {Viruses},

volume = {11},

number = {6},

pages = {484},

abstract = {Viral ecology of terrestrial habitats is yet-to be extensively explored, in particular the terrestrial subsurface. One problem in obtaining viral sequences from groundwater aquifer samples is the relatively low amount of virus particles. As a result, the amount of extracted DNA may not be sufficient for direct sequencing of such samples. Here we compared three DNA amplification methods to enrich viral DNA from three pristine limestone aquifer assemblages of the Hainich Critical Zone Exploratory to evaluate potential bias created by the different amplification methods as determined by viral metagenomics. Linker amplification shotgun libraries resulted in lowest redundancy among the sequencing reads and showed the highest diversity, while multiple displacement amplification produced the highest number of contigs with the longest average contig size, suggesting a combination of these two methods is suitable for the successful enrichment of viral DNA from pristine groundwater samples. In total, we identified 27,173, 5,886 and 32,613 viral contigs from the three samples from which 11.92 to 18.65% could be assigned to taxonomy using blast. Among these, members of the order were the most abundant group (52.20 to 69.12%) dominated by and . Those, and the high number of unknown viral sequences, substantially expand the known virosphere.},

keywords = {DNA / genomics, groundwater, metagenomics, viruses},

pubstate = {published},

tppubtype = {article}

}