Publications

@article{nokey,

title = {Screening great ape museum specimens for DNA viruses},

author = {Michelle Hämmerle and Meriam Guellil and Olivia Cheronet and Susanna Sawyer and Irune Ruiz-Gartzia and Esther Lizano and Aigerim Rymbekova and Pere Gelabert and Paolo Bernardi and Sojung Han and Lovro Trgovec-Greif and Thomas Rattei and Verena J. Schuenemann and Tomas Marques-Bonet and Katerina Guschanski and Sebastien Calvignac-Spencer and Ron Pinhasi and Martin Kuhlwilm},

doi = {10.1101/2024.04.25.591107v3},

year  = {2024},

date = {2024-11-01},

journal = {bioRxiv},

abstract = {Natural history museum collections harbour a record of wild species from the past centuries, providing a unique opportunity to study animals as well as their infectious agents. Thousands of great ape specimens are kept in these collections, and could become an important resource for studying the evolution of DNA viruses. Their genetic material is likely to be preserved in dry museum specimens, as reported previously for monkeypox virus genomes from historical orangutan specimens. Here, we screened 209 great ape museum specimens for 99 different DNA viruses, using hybridization capture coupled with short-read high-throughput sequencing. We determined the presence of multiple viruses within this dataset from historical specimens and obtained several near-complete viral genomes. In particular, we report high-coverage (>18-fold) hepatitis B virus genomes from one gorilla and two chimpanzee individuals, which are phylogenetically placed within clades infecting the respective host species.},

keywords = {Project 08},

pubstate = {published},

tppubtype = {article}

}

@article{Piedade2024,

title = {Seasonal dynamics and diversity of Antarctic marine viruses reveal a novel viral seascape},

author = {Gonçalo J. Piedade and Max E. Schön and Cédric Lood and Mikhail V. Fofanov and Ella M. Wesdorp and Tristan E. G. Biggs and Lingyi Wu and Henk Bolhuis and Matthias G. Fischer and Natalya Yutin and Bas E. Dutilh and Corina P. D. Brussaard},

doi = {10.1038/s41467-024-53317-y},

year  = {2024},

date = {2024-10-24},

urldate = {2024-10-24},

journal = {Nature Communications},

volume = {15},

pages = {9192},

abstract = {The Southern Ocean microbial ecosystem, with its pronounced seasonal shifts, is vulnerable to the impacts of climate change. Since viruses are key modulators of microbial abundance, diversity, and evolution, we need a better understanding of the effects of seasonality on the viruses in this region. Our comprehensive exploration of DNA viral diversity in the Southern Ocean reveals a unique and largely uncharted viral landscape, of which 75% was previously unidentified in other oceanic areas. We uncover novel viral taxa at high taxonomic ranks, expanding our understanding of crassphage, polinton-like virus, and virophage diversity. Nucleocytoviricota viruses represent an abundant and diverse group of Antarctic viruses, highlighting their potential as important regulators of phytoplankton population dynamics. Our temporal analysis reveals complex seasonal patterns in marine viral communities (bacteriophages, eukaryotic viruses) which underscores the apparent interactions with their microbial hosts, whilst deepening our understanding of their roles in the world’s most sensitive and rapidly changing ecosystem.},

keywords = {Project 13, WP 1.1 Virus identification, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{vanderToorn2024,

title = {Demultiplexing and barcode-specific adaptive sampling for nanopore direct RNA sequencing},

author = {Wiep van der Toorn and Patrick Bohn and Wang Liu-Wei and Marco Olguin-Nava and Redmond P Smyth and Max von Kleist},

doi = {10.1101/2024.07.22.604276v2},

year  = {2024},

date = {2024-10-23},

journal = {bioRxiv},

abstract = {Nanopore direct RNA sequencing (dRNA-seq) enables unique insights into (epi-)transcriptomics. However, applications are currently limited by the lack of accurate and cost-effective sample multiplexing. We introduce WarpDemuX, an ultra-fast and highly accurate adapter-barcoding and demultiplexing approach. WarpDemuX enhances speed and accuracy by fast processing of the raw nanopore signal, use of a light-weight machine-learning algorithm and design of optimized barcode sets. We demonstrate its utility by performing a rapid phenotypic profiling of different SARS-CoV-2 viruses, crucial for pandemic prevention and response, through multiplexed sequencing of longitudinal samples on a single flowcell. This identifies systematic differences in transcript abundance and poly(A) tail lengths during infection. Additionally, integrating WarpDemuX into sequencing control software enables real-time enrichment of target molecules through barcode-specific adaptive sampling, which we demonstrate by enriching low abundance viral RNA. In summary, WarpDemuX is a broadly applicable, high-performance, and economical multiplexing solution for nanopore dRNA-seq, facilitating advanced (epi-)transcriptomic research.},

keywords = {Project 08},

pubstate = {published},

tppubtype = {article}

}

@article{Fuhrmann2024b,

title = {V-pipe 3.0: a sustainable pipeline for within-sample viral genetic diversity estimation},

author = {Lara Fuhrmann and Kim Philipp Jablonski and Ivan Topolsky and Aashil A Batavia and Nico Borgsmüller and Pelin Icer Baykal and Matteo Carrara and Chaoran Chen and Arthur Dondi and Monica Dragan and David Dreifuss and Anika John and Benjamin Langer and Michal Okoniewski and Louis du Plessis and Uwe Schmitt and Franziska Singer and Tanja Stadler and Niko Beerenwinkel},

doi = {10.1093/gigascience/giae065},

year  = {2024},

date = {2024-09-30},

urldate = {2024-09-30},

journal = {GigaScience},

volume = {13},

pages = {giae065},

abstract = {The large amount and diversity of viral genomic datasets generated by next-generation sequencing technologies poses a set of challenges for computational data analysis workflows, including rigorous quality control, scaling to large sample sizes, and tailored steps for specific applications. Here, we present V-pipe 3.0, a computational pipeline designed for analyzing next-generation sequencing data of short viral genomes. It is developed to enable reproducible, scalable, adaptable, and transparent inference of genetic diversity of viral samples. By presenting 2 large-scale data analysis projects, we demonstrate the effectiveness of V-pipe 3.0 in supporting sustainable viral genomic data science.},

keywords = {Project 03, WP 1.3 Virus-host interactions, WP 2.1 Microevolution: Virus quasispecies},

pubstate = {published},

tppubtype = {article}

}

@article{Wijesekara2024,

title = {Jaeger: an accurate and fast deep-learning tool to detect bacteriophage sequences},

author = {Yasas Wijesekara and Ling-Yi Wu and Rick Beeloo and Piotr Rozwalak and Ernestina Hauptfeld and Swapnil P. Doijad and Bas E. Dutilh and Lars Kaderali},

year  = {2024},

date = {2024-09-24},

journal = {bioRxiv},

abstract = {Viruses are integral to every biome on Earth, yet we still need a more comprehensive picture of their identity and global distribution. Global metagenomics sequencing efforts revealed the genomic content of tens of thousands of environmental samples, however identifying the viral sequences in these datasets remains challenging due to their vast genomic diversity. Here, we address identifying bacteriophage sequences in unlabeled sequencing data. In a recent benchmarking paper, we observed that existing deep-learning tools show a high true positive rate, but may also produce many false positives when confronted with divergent sequences. To tackle this challenge, we introduce Jaeger, a novel deep-learning method designed specifically for identifying bacteriophage genome fragments. Extensive benchmarking on the IMG/VR database and real-world metagenomes reveals Jaeger’s consistent high sensitivity (0.87) and precision (0.92). Applying Jaeger to over 16,000 metagenomic assemblies from the MGnify database yielded over five million putative phage contigs. On average, Jaeger is around 20 times faster than the other state-of-the-art methods. Jaeger is available at https://github.com/MGXlab/Jaeger.},

keywords = {Project 14, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{Peng2024,

title = {Metagenomic analyses of single phages and phage cocktails show instances of contamination with temperate phages and bacterial DNA},

author = {Xue Peng and Sophie Elizabeth Smith and Wanqi Huang and Jinlong Ru and Mohammadali Khan Mirzaei and Li Deng},

doi = {10.1101/2024.09.12.612727},

year  = {2024},

date = {2024-09-12},

journal = {bioRxiv},

abstract = {Increasing antibiotic resistance has led to renewed attention being paid to bacteriophage therapy. Commercial phage cocktails are available but often their contents of the phages are not well defined. Some metagenomic studies have been done to retrospectively characterise these cocktails, but little is known about the replication cycle of the included phages, or about the possible bacterial DNA contamination. In this study, published metagenomic sequences were reanalysed using recent advances in viromics tools. Signs of temperate phage contigs were found in all cocktail metagenomes, as well as host DNA, which could poses a risk as it may lead to horizontal gene transfer of virulence factors to commensals and pathogens. This suggests the need to implement further quality measures before using phage cocktails therapeutically.},

keywords = {Project 05, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{deJonge2024,

title = {Phylogeny and disease associations of a widespread and ancient intestinal bacteriophage lineage},

author = {Patrick A. de Jonge and Bert-Jan H. van den Born and Aeilko H. Zwinderman and Max Nieuwdorp and Bas E. Dutilh and Hilde Herrema},

doi = {10.1038/s41467-024-50777-0},

year  = {2024},

date = {2024-07-27},

journal = {Nature Communications},

volume = {15},

issue = {1},

pages = {6346},

abstract = {Viruses are core components of the human microbiome, impacting health through interactions with gut bacteria and the immune system. Most human microbiome viruses are bacteriophages, which exclusively infect bacteria. Until recently, most gut virome studies focused on low taxonomic resolution (e.g., viral operational taxonomic units), hampering population-level analyses. We previously identified an expansive and widespread bacteriophage lineage in inhabitants of Amsterdam, the Netherlands. Here, we study their biodiversity and evolution in various human populations. Based on a phylogeny using sequences from six viral genome databases, we propose the Candidatus order Heliusvirales. We identify heliusviruses in 82% of 5441 individuals across 39 studies, and in nine metagenomes from humans that lived in Europe and North America between 1000 and 5000 years ago. We show that a large lineage started to diversify when Homo sapiens first appeared some 300,000 years ago. Ancient peoples and modern hunter-gatherers have distinct Ca. Heliusvirales populations with lower richness than modern urbanized people. Urbanized people suffering from type 1 and type 2 diabetes, as well as inflammatory bowel disease, have higher Ca. Heliusvirales richness than healthy controls. We thus conclude that these ancient core members of the human gut virome have thrived with increasingly westernized lifestyles.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Trgovec-Greif2024,

title = {VOGDB—Database of Virus Orthologous Groups},

author = {Lovro Trgovec-Greif and Hans-Jörg Hellinger and Jean Mainguy and Alexander Pfundner and Dmitrij Frishman and Michael Kiening and Nicole Suzanne Webster and Patrick William Laffy and Michael Feichtinger and Thomas Rattei},

doi = {10.3390/v16081191},

year  = {2024},

date = {2024-07-25},

urldate = {2024-07-25},

journal = {Viruses},

volume = {16},

issue = {8},

pages = {1191},

abstract = {Computational models of homologous protein groups are essential in sequence bioinformatics. Due to the diversity and rapid evolution of viruses, the grouping of protein sequences from virus genomes is particularly challenging. The low sequence similarities of homologous genes in viruses require specific approaches for sequence- and structure-based clustering. Furthermore, the annotation of virus genomes in public databases is not as consistent and up to date as for many cellular genomes. To tackle these problems, we have developed VOGDB, which is a database of virus orthologous groups. VOGDB is a multi-layer database that progressively groups viral genes into groups connected by increasingly remote similarity. The first layer is based on pair-wise sequence similarities, the second layer is based on the sequence profile alignments, and the third layer uses predicted protein structures to find the most remote similarity. VOGDB groups allow for more sensitive homology searches of novel genes and increase the chance of predicting annotations or inferring phylogeny. VOGD B uses all virus genomes from RefSeq and partially reannotates them. VOGDB is updated with every RefSeq release. The unique feature of VOGDB is the inclusion of both prokaryotic and eukaryotic viruses in the same clustering process, which makes it possible to explore old evolutionary relationships of the two groups. VOGDB is freely available at vogdb.org under the CC BY 4.0 license.},

keywords = {Project 14, WP 1.1 Virus identification},

pubstate = {published},

tppubtype = {article}

}

@article{Ritsch2024,

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

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

doi = {10.3390/v16081210},

year  = {2024},

date = {2024-07-24},

urldate = {2024-07-24},

journal = {Viruses},

volume = {16},

pages = {1210},

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 Myotis daubentonii, EBLL-Cultervirus.10-MyoDau (short name is CV.10-MyoDau) that shows protein-level conservation with the L-protein of a 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 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 Yangochiropera and 12 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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Triebel2024,

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 = {10.1101/2023.11.15.567179},

year  = {2024},

date = {2024-07-02},

journal = {Scientific Reports},

volume = {14},

pages = {15145},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Deboutte2024,

title = {Known and novel viruses in Belgian honey bees: yearly differences, spatial clustering, and associations with overwintering loss},

author = {Ward Deboutte and Lina De Smet and Marleen Brunain and Nikolas Basler and Riet De Rycke and Lena Smets and Dirk C. de Graaf and Jelle Matthijnssens},

doi = {10.1128/spectrum.03581-23},

year  = {2024},

date = {2024-07-02},

journal = {Microbiol Spectrum},

volume = {12},

issue = {7},

pages = {e0358123},

abstract = {In recent years, managed honey bee colonies have been suffering from an increasing number of biotic and abiotic stressors, resulting in numerous losses of colonies worldwide. A pan-European study, EPILOBEE, estimated the colony loss in Belgium to be 32.4% in 2012 and 14.8% in 2013. In the current study, absolute viral loads of four known honey bee viruses (DWV-A, DWV-B, AmFV, and BMLV) and three novel putative honey bee viruses (Apis orthomyxovirus 1, apthili virus, and apparli virus) were determined in 300 Flemish honey bee samples, and associations with winter survival were determined. This revealed that, in addition to the known influence of DWV-A and DWV-B on colony health, one of the newly described viruses (apthili virus) shows a strong yearly difference and is also associated with winter survival. Furthermore, all scrutinized viruses revealed significant spatial clustering patterns, implying that despite the limited surface area of Flanders, local virus transmission is paramount. The vast majority of samples were positive for at least one of the seven investigated viruses, and up to 20% of samples were positive for at least one of the three novel viruses. One of those three, Apis orthomyxovirus 1, was shown to be a genuine honey bee-infecting virus, able to infect all developmental stages of the honey bee, as well as the Varroa destructor mite. These results shed light on the most prevalent viruses in Belgium and their roles in the winter survival of honey bee colonies.



Importance: The western honey bee (Apis mellifera) is a highly effective pollinator of flowering plants, including many crops, which gives honey bees an outstanding importance both ecologically and economically. Alarmingly high annual loss rates of managed honey bee colonies are a growing concern for beekeepers and scientists and have prompted a significant research effort toward bee health. Several detrimental factors have been identified, such as varroa mite infestation and disease from various bacterial and viral agents, but annual differences are often not elucidated. In this study, we utilize the viral metagenomic survey of the EPILOBEE project, a European research program for bee health, to elaborate on the most abundant bee viruses of Flanders. We complement the existing metagenomic data with absolute viral loads and their spatial and temporal distributions. Furthermore, we identify Apis orthomyxovirus 1 as a potentially emerging pathogen, as we find evidence for its active replication honey bees.},

keywords = {Project 11, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{Fuhrmann2024,

title = {VILOCA: Sequencing quality-aware haplotype reconstruction and mutation calling for short- and long-read data},

author = {Lara Fuhrmann and Benjamin Langer and Ivan Topolsky and Niko Beerenwinkel},

doi = {10.1101/2024.06.06.597712},

year  = {2024},

date = {2024-06-09},

journal = {bioRxiv},

abstract = {RNA viruses exist in large heterogeneous populations within their host. The structure and diversity of virus populations affects disease progression and treatment outcomes. Next-generation sequencing allows detailed viral population analysis, but inferring diversity from error-prone reads is challenging. Here, we present VILOCA, a method for mutation calling and reconstruction of local haplotypes from short- and long-read viral sequencing data. Local haplotypes refer to genomic regions that have approximately the length of the input reads. VILOCA recovers local haplotypes by using a Dirichlet process mixture model to cluster reads around their unobserved haplotypes and leveraging quality scores of the sequencing reads. We assessed the performance of VILOCA in terms of mutation calling and haplotype reconstruction accuracy on simulated and experimental Illumina, PacBio, and Oxford Nanopore data. On simulated and experimental Illumina data, VILOCA performed better or similar to existing methods. On the simulated long-read data, VILOCA is able to recover on average 82% of the ground truth mutations with perfect precision compared to only 64% recall and 90% precision of the second-best method. In summary, VILOCA provides significantly improved accuracy in mutation and haplotype calling, especially for long-read sequencing data, and therefore facilitates the comprehensive characterization of heterogeneous within-host viral populations.},

keywords = {Project 03, WP 1.3 Virus-host interactions, WP 2.1 Microevolution: Virus quasispecies},

pubstate = {published},

tppubtype = {article}

}

@article{Liu-Wei2024,

title = {Sequencing accuracy and systematic errors of nanopore direct RNA sequencing},

author = {Wang Liu-Wei and Wiep van der Toorn and Patrick Bohn and Martin Hölzer and Redmond P. Smyth and Max von Kleist},

doi = {10.1186/s12864-024-10440-w},

year  = {2024},

date = {2024-05-28},

journal = {BMC Genomics},

volume = {25},

pages = {528},

abstract = {Background

Direct RNA sequencing (dRNA-seq) on the Oxford Nanopore Technologies (ONT) platforms can produce reads covering up to full-length gene transcripts, while containing decipherable information about RNA base modifications and poly-A tail lengths. Although many published studies have been expanding the potential of dRNA-seq, its sequencing accuracy and error patterns remain understudied.



Results

We present the first comprehensive evaluation of sequencing accuracy and characterisation of systematic errors in dRNA-seq data from diverse organisms and synthetic in vitro transcribed RNAs. We found that for sequencing kits SQK-RNA001 and SQK-RNA002, the median read accuracy ranged from 87% to 92% across species, and deletions significantly outnumbered mismatches and insertions. Due to their high abundance in the transcriptome, heteropolymers and short homopolymers were the major contributors to the overall sequencing errors. We also observed systematic biases across all species at the levels of single nucleotides and motifs. In general, cytosine/uracil-rich regions were more likely to be erroneous than guanines and adenines. By examining raw signal data, we identified the underlying signal-level features potentially associated with the error patterns and their dependency on sequence contexts. While read quality scores can be used to approximate error rates at base and read levels, failure to detect DNA adapters may be a source of errors and data loss. By comparing distinct basecallers, we reason that some sequencing errors are attributable to signal insufficiency rather than algorithmic (basecalling) artefacts. Lastly, we generated dRNA-seq data using the latest SQK-RNA004 sequencing kit released at the end of 2023 and found that although the overall read accuracy increased, the systematic errors remain largely identical compared to the previous kits.



Conclusions

As the first systematic investigation of dRNA-seq errors, this study offers a comprehensive overview of reproducible error patterns across diverse datasets, identifies potential signal-level insufficiency, and lays the foundation for error correction methods.},

keywords = {Project 08},

pubstate = {published},

tppubtype = {article}

}

@article{Costa2024,

title = {Human cytomegalovirus exploits STING signaling and counteracts IFN/ISG induction to facilitate infection of dendritic cells},

author = {Bibiana Costa and Jennifer Becker and Tobias Krammer and Felix Mulenge and Verónica Durán and Andreas Pavlou and Olivia Luise Gern and Xiaojing Chu and Yang Li and Luka Čičin-Šain and Britta Eiz-Vesper and Martin Messerle and Lars Dölken and Antoine-Emmanuel Saliba and Florian Erhard and Ulrich Kalinke},

doi = {10.1038/s41467-024-45614-3},

year  = {2024},

date = {2024-02-26},

urldate = {2024-02-26},

journal = {Nature Communications},

volume = {15},

pages = {1745},

abstract = {Human cytomegalovirus (HCMV) is a widespread pathogen that in immunocompromised hosts can cause life-threatening disease. Studying HCMV-exposed monocyte-derived dendritic cells by single-cell RNA sequencing, we observe that most cells are entered by the virus, whereas less than 30% of them initiate viral gene expression. Increased viral gene expression is associated with activation of the stimulator of interferon genes (STING) that usually induces anti-viral interferon responses, and with the induction of several pro- (RHOB, HSP1A1, DNAJB1) and anti-viral (RNF213, TNFSF10, IFI16) genes. Upon progression of infection, interferon-beta but not interferon-lambda transcription is inhibited. Similarly, interferon-stimulated gene expression is initially induced and then shut off, thus further promoting productive infection. Monocyte-derived dendritic cells are composed of 3 subsets, with one being especially susceptible to HCMV. In conclusion, HCMV permissiveness of monocyte-derived dendritic cells depends on complex interactions between virus sensing, regulation of the interferon response, and viral gene expression.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Ultraconserved bacteriophage genome sequence identified in 1300-year-old human palaeofaeces},

author = {Piotr Rozwalak and Jakub Barylski and Yasas Wijesekara and Bas E. Dutilh and Andrzej Zielezinski

},

doi = {10.1038/s41467-023-44370-0},

year  = {2024},

date = {2024-01-23},

urldate = {2024-01-23},

journal = {Nat Commun},

volume = {15},

issue = {1},

pages = {495},

abstract = {Bacteriophages are widely recognised as rapidly evolving biological entities. However, knowledge about ancient bacteriophages is limited. Here, we analyse DNA sequence datasets previously generated from ancient palaeofaeces and human gut-content samples, and identify an ancient phage genome nearly identical to present-day Mushuvirus mushu, a virus that infects gut commensal bacteria. The DNA damage patterns of the genome are consistent with its ancient origin and, despite 1300 years of evolution, the ancient Mushuvirus genome shares 97.7% nucleotide identity with its modern counterpart, indicating a long-term relationship between the prophage and its host. In addition, we reconstruct and authenticate 297 other phage genomes from the last 5300 years, including those belonging to unknown families. Our findings demonstrate the feasibility of reconstructing ancient phage genome sequences, thus expanding the known virosphere and offering insights into phage-bacteria interactions spanning several millennia.},

keywords = {Project 12, WP 1.1 Virus identification},

pubstate = {published},

tppubtype = {article}

}

@article{Lezcano2023,

title = {Parallel evolution and enhanced virulence upon in vivo passage of an RNA virus in \textit{Drosophila melanogaster}.},

author = {Oscar M. Lezcano and Lara Fuhrmann and Gayatri Ramakrishnan and Niko Beerenwinkel and Martijn A. Huynen and Ronald P. van Rij },

doi = {10.1093/ve/vead074},

year  = {2023},

date = {2023-12-15},

urldate = {2023-12-15},

journal = {Virus Evol},

volume = {9},

issue = {2},

pages = {vead074},

abstract = {Virus evolution is strongly affected by antagonistic co-evolution of virus and host. Host immunity positively selects for viruses that evade the immune response, which in turn may drive counter-adaptations in host immune genes. We investigated how host immune pressure shapes virus populations, using the fruit fly Drosophila melanogaster and its natural pathogen Drosophila C virus (DCV), as a model. We performed an experimental evolution study in which DCV was serially passaged for ten generations in three fly genotypes differing in their antiviral RNAi response: wild-type flies and flies in which the endonuclease gene Dicer-2 was either overexpressed or inactivated. All evolved virus populations replicated more efficiently in vivo and were more virulent than the parental stock. The number of polymorphisms increased in all three host genotypes with passage number, which was most pronounced in Dicer-2 knockout flies. Mutational analysis showed strong parallel evolution, as mutations accumulated in a specific region of the VP3 capsid protein in every lineage in a host genotype-independent manner. The parental tyrosine at position ninety-five of VP3 was substituted with either one of five different amino acids in fourteen out of fifteen lineages. However, no consistent amino acid changes were observed in the viral RNAi suppressor gene 1A, nor elsewhere in the genome in any of the host backgrounds. Our study indicates that the RNAi response restricts the sequence space that can be explored by viral populations. Moreover, our study illustrates how evolution towards higher virulence can be a highly reproducible, yet unpredictable process.},

keywords = {Project 03, Project 09, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Helicobacter pylori infection alters gut virome by expanding temperate phages linked to increased risk of colorectal cancer},

author = {Shiqi Luo and Jinlong Ru and Mohammadali Khan Mirzaei and Jinling Xue and Xue Peng and Anna Ralser and Joshua Lemuel Hadi and Raquel Mejías-Luque and Markus Gerhard and Li Deng},

doi = {10.1136/gutjnl-2023-330362},

year  = {2023},

date = {2023-11-02},

journal = {Gut},

pages = {gutjnl-2023-330362},

abstract = {No abstract available.},

keywords = {Project 05, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

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 Lencioni 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 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},

year  = {2023},

date = {2023-09-30},

urldate = {2023-09-30},

journal = {Viruses},

volume = {15},

issue = {10},

pages = {2031},

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 = {Project 01, Project 06, WP 1.3 Virus-host interactions, WP 1.4 Virus regulation},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Gut virome profiling identifies an association between temperate phages and colorectal cancer promoted by Helicobacter pylori infection},

author = {Shiqi Luo and Jinlong Ru and Mohammadali Khan Mirzaei and Jinling Xue and Xue Peng and Anna Ralser and Raquel Mejías Luque and Markus Gerhard and Li Deng},

doi = {10.1080/19490976.2023.2257291},

year  = {2023},

date = {2023-09-25},

journal = {Gut Microbes},

volume = {15},

issue = {2},

pages = {2257291},

abstract = {Colorectal cancer (CRC) is one of the most commonly diagnosed cancers worldwide. While a close correlation between chronic Helicobacter pylori infection and CRC has been reported, the role of the virome has been overlooked. Here, we infected Apc-mutant mouse models and C57BL/6 mice with H. pylori and conducted a comprehensive metagenomics analysis of H. pylori-induced changes in lower gastrointestinal tract bacterial and viral communities. We observed an expansion of temperate phages in H. pylori infected Apc+/1638N mice at the early stage of carcinogenesis. Some of the temperate phages were predicted to infect bacteria associated with CRC, including Enterococcus faecalis. We also observed a high prevalence of virulent genes, such as flgJ, cwlJ, and sleB, encoded by temperate phages. In addition, we identified phages associated with pre-onset and onset of H. pylori-promoted carcinogenesis. Through co-occurrence network analysis, we found strong associations between the viral and bacterial communities in infected mice before the onset of carcinogenesis. These findings suggest that the expansion of temperate phages, possibly caused by prophage induction triggered by H. pylori infection, may have contributed to the development of CRC in mice by interacting with the bacterial community.},

keywords = {Project 05, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{Ritsch2023,

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},

year  = {2023},

date = {2023-08-29},

journal = {Viruses},

volume = {15},

issue = {9},

pages = {1834},

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 = {WP 1.1 Virus identification},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Guidelines for public database submission of uncultivated virus genome sequences for taxonomic classification},

author = {Evelien M. Adriaenssens and Simon Roux and J. Rodney Brister and Ilene Karsch-Mizrachi and Jens H. Kuhn and Arvind Varsani and Tong Yigang and Alejandro Reyes and Cédric Lood and Elliot J. Lefkowitz and Matthew B. Sullivan and Robert A. Edwards and Peter Simmonds and Luisa Rubino and Sead Sabanadzovic and Mart Krupovic and Bas E. Dutilh },

doi = {10.1038/s41587-023-01844-2},

year  = {2023},

date = {2023-07-10},

urldate = {2023-07-10},

journal = {Nature Biotechnology},

volume = {41},

pages = {898–902},

abstract = {Mining data derived from high-throughput DNA or RNA sequencing approaches, including metagenomics, has led to the discovery of a multitude of uncultivated virus genome sequences1,2,3,4,5,6,7,8,9,10,11,12. These sequences improve our knowledge about the representation of the global virosphere and fuel the expansion and refinement of virus taxonomy. Incorporation of these newly discovered viral sequences into high-quality reference databases adds a bottleneck to virology. For formal taxonomic classification, International Committee on Taxonomy of Viruses (ICTV) guidelines stipulate that genome sequences must be available from a public database. However, the correct use of nomenclature and the inclusion of standardized metadata fields are just as important as the availability of sequence data to enable the use and reuse of the data by the global research community. Here, we present standards and recommendations for the submission of virus genome sequence data to public databases for the purpose of taxonomic classification. These represent a conceptual and practical extension to the Minimum Information about an Uncultivated Virus Genome (MIUViG) standards that include guidelines for reporting the virus origin, genome quality, genome annotation, taxonomic classification, biogeographic distribution and host prediction13. Aspects of these standards have been reiterated in a recently published consensus viewpoint statement indicating that viruses inferred from metagenomic sequences require strict quality control before they can be used for taxonomic assignments14. The guidelines presented here focus on the MIUViG standards on genome quality and expand on the naming of sequences and their submission to public databases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {grandR: a comprehensive package for nucleotide conversion RNA-seq data analysis},

author = {Teresa Rummel and Lygeri Sakellaridi and Florian Erhard

},

doi = {10.1038/s41467-023-39163-4},

year  = {2023},

date = {2023-06-15},

journal = {Nat Commun},

volume = {14},

issue = {1},

pages = {3559},

abstract = {Metabolic labeling of RNA is a powerful technique for studying the temporal dynamics of gene expression. Nucleotide conversion approaches greatly facilitate the generation of data but introduce challenges for their analysis. Here we present grandR, a comprehensive package for quality control, differential gene expression analysis, kinetic modeling, and visualization of such data. We compare several existing methods for inference of RNA synthesis rates and half-lives using progressive labeling time courses. We demonstrate the need for recalibration of effective labeling times and introduce a Bayesian approach to study the temporal dynamics of RNA using snapshot experiments.},

keywords = {Project 06, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{,

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

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

doi = {doi:10.1093/nar/gkad442},

year  = {2023},

date = {2023-05-24},

urldate = {2023-05-24},

journal = {Nucleic Acids Research},

volume = {51},

issue = {12},

pages = {6479-6494},

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 = {Project 01, WP 1.4 Virus regulation},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Virus taxonomy and the role of the International Committee on Taxonomy of Viruses (ICTV)},

author = {Stuart G. Siddell and Donald B. Smith and Evelien Adriaenssens and Poliane Alfenas-Zerbini and Bas E. Dutilh and Maria Laura Garcia and Sandra Junglen and Mart Krupovic and Jens H. Kuhn and Amy J. Lambert and Elliot J. Lefkowitz and Małgorzata Łobocka and Arcady R. Mushegian and Hanna M. Oksanen and David L. Robertson and Luisa Rubino and Sead Sabanadzovic and Peter Simmonds and Nobuhiro Suzuki and Koenraad Van Doorslaer and Anne-Mieke Vandamme and Arvind Varsani and F. Murilo Zerbini},

doi = {https://doi.org/10.1099/jgv.0.001840},

year  = {2023},

date = {2023-05-04},

journal = {Journal of General Virology},

volume = {104},

issue = {5},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Benchmarking Bioinformatic Virus Identification Tools Using Real-World Metagenomic Data across Biomes},

author = {Ling-Yi Wu and Nikolaos Pappas and Yasas Wijesekara and Gonçalo J. Piedade and Corina P.D. Brussaard and Bas E. Dutilh},

doi = {10.1101/2023.04.26.538077},

year  = {2023},

date = {2023-04-28},

journal = {bioRxiv},

abstract = {As most viruses remain uncultivated, metagenomics is currently the main method for virus discovery. Detecting viruses in metagenomic data is not trivial. In the past few years, many bioinformatic virus identification tools have been developed for this task, making it challenging to choose the right tools, parameters, and cutoffs. As all these tools measure different biological signals, and use different algorithms and training/reference databases, it is imperative to conduct an independent benchmarking to give users objective guidance. We compared the performance of ten state-of-the-art virus identification tools in thirteen modes on eight paired viral and microbial datasets from three distinct biomes, including a new complex dataset from Antarctic coastal waters. The tools had highly variable true positive rates (0 – 68%) and false positive rates (0 – 15%). PPR-Meta best distinguished viral from microbial contigs, followed by DeepVirFinder, VirSorter2, and VIBRANT. Different tools identified different subsets of the benchmarking data and all tools, except for Sourmash, found unique viral contigs. Tools performance could be improved with adjusted parameter cutoffs, indicating that adjustment of parameter cutoffs before usage should be considered. Together, our independent benchmarking provides guidance on choices of bioinformatic virus identification tools and gives suggestions for parameter adjustments for viromics researchers.},

keywords = {Project 12, Project 13, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {iPHoP: An integrated machine learning framework to maximize host prediction for metagenome-derived viruses of archaea and bacteria},

author = {Simon Roux and Antonio Pedro Camargo and Felipe H. Coutinho and Shareef M. Dabdoub and Bas E. Dutilh and Stephen Nayfach and Andrew Tritt},

doi = {10.1371/journal.pbio.3002083},

year  = {2023},

date = {2023-04-21},

urldate = {2023-04-21},

journal = {PLOS Biology},

abstract = {The extraordinary diversity of viruses infecting bacteria and archaea is now primarily studied through metagenomics. While metagenomes enable high-throughput exploration of the viral sequence space, metagenome-derived sequences lack key information compared to isolated viruses, in particular host association. Different computational approaches are available to predict the host(s) of uncultivated viruses based on their genome sequences, but thus far individual approaches are limited either in precision or in recall, i.e., for a number of viruses they yield erroneous predictions or no prediction at all. Here, we describe iPHoP, a two-step framework that integrates multiple methods to reliably predict host taxonomy at the genus rank for a broad range of viruses infecting bacteria and archaea, while retaining a low false discovery rate. Based on a large dataset of metagenome-derived virus genomes from the IMG/VR database, we illustrate how iPHoP can provide extensive host prediction and guide further characterization of uncultivated viruses.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Prediction of virus-host association using protein language models and multiple instance learning},

author = {Dan Liu and Francesca Young and David L. Robertson and Ke Yuan},

doi = {10.1101/2023.04.07.536023},

year  = {2023},

date = {2023-04-08},

urldate = {2023-04-08},

journal = {bioRxiv},

abstract = {Predicting virus-host association is essential to understand how viruses interact with host species, and discovering new therapeutics for viral diseases across humans and animals. Currently, the host of the majority of viruses is unknown. Here, we introduce EvoMIL, a deep learning method that predicts virus-host association at the species level from viral sequence only. The method combines a pre-trained large protein language model and attention-based multiple instance learning to allow protein-orientated predictions. Our results show that protein embeddings capture stronger predictive signals than traditional handcrafted features, including amino acids and DNA k-mers, and physio-chemical properties. EvoMIL binary classifiers achieve AUC values of over 0.95 for all prokaryotic and nearly 0.8 for almost all eukaryotic hosts. In multi-host prediction tasks, EvoMIL achieved median performance improvements of 8.6% in prokaryotic hosts and 1.8% in eukaryotic hosts. Furthermore, EvoMIL estimates the importance of single proteins in the prediction and maps them to an embedding landscape of all viral proteins, where proteins with similar functions are distinctly clustered together.},

keywords = {Project 10, WP 1.2 Host prediction, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {ViroProfiler: a containerized bioinformatics pipeline for viral metagenomic data analysis},

author = {Jinlong Ru and Mohammadali Khan Mirzaei and Jinling Xue and Xue Peng and Li Deng

},

doi = {10.1080/19490976.2023.2192522},

year  = {2023},

date = {2023-03-30},

journal = {Gut Microbes},

volume = {15},

issue = {1},

pages = {2192522},

abstract = {Bacteriophages play central roles in the maintenance and function of most ecosystems by regulating bacterial communities. Yet, our understanding of their diversity remains limited due to the lack of robust bioinformatics standards. Here we present ViroProfiler, an in-silico workflow for analyzing shotgun viral metagenomic data. ViroProfiler can be executed on a local Linux computer or cloud computing environments. It uses the containerization technique to ensure computational reproducibility and facilitate collaborative research. ViroProfiler is freely available at https://github.com/deng-lab/viroprofiler.



},

keywords = {Project 05, WP 1.1 Virus identification, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Expanding epidemic of recently acquired HCV in HIV-coinfected patients over a period of 10 years},

author = {Christiana Graf and Lara Fuhrmann and Thomas Lutz and Christoph Stephan and Gaby Knecht and Peter Gute and Markus Bickel and Kai-Henrik Peiffer and Fabian Finkelmeier and Georg Dultz and Antonia Mondorf and Nils Wetzstein and Natalie Filmann and Eva Herrmann and Stefan Zeuzem and Niko Beerenwinkel and Julia Dietz and Christoph Sarrazin},

doi = {10.1016/j.jhepr.2023.100701},

year  = {2023},

date = {2023-02-19},

journal = {JHEP Rep},

volume = {5},

issue = {7},

pages = {100701},

abstract = {Background & aims: Ongoing transmission of HCV infections is associated with risk factors such as drug injection, needlestick injuries, and men who have sex with men (MSM). Ways of transmission, the course of acute infection, changes of virologic features, and incidence over time are not well known.



Methods: Over a period of 10 years, n = 161 patients with recently acquired HCV infection (RAHC) (median follow-up 6.8 years) were prospectively enrolled. NS5B sequencing was performed to re-evaluate the HCV genotype (GT) and for phylogenetic analyses.



Results: Patients with RAHC were mainly male (92.5%), MSM (90.1%), and HIV-coinfected (86.3%). Transmission risk factors for MSM and non-MSM were sexual risk behaviour (100 and 6.3%, respectively), injection drug use (9.7 and 37.5%, respectively), and nasal drug use (15.2 and 0%, respectively). Spontaneous and interferon- or direct-acting antiviral-based clearance rates were 13.6, 84.3 and 93.4%, respectively. Mean RAHC declined from 19.8 in the first to 13.2 in the past five study years. Although the majority of infections was caused by HCV GT1a, the frequency of HCV GT4d and slightly HCV GT3a increased over time. No relevant clustering of HCV isolates was observed in non-MSM. However, 45% of HCV GT1a and 100% of HCV GT4d MSM cases clustered with MSM isolates from other countries. Travel-associated infections were supported by personal data in an MSM subgroup. No international clustering was detected in MSM with HCV GT1b or HCV GT3a.



Conclusions: RAHCs were mainly diagnosed in HIV-coinfected MSM patients and were associated with sexual risk behaviour. Spontaneous clearance rates were low, and phylogenetic clusters were observed in the majority of patients.



Impact and implications: We evaluated the occurrence and transmission of recently acquired HCV infections (RAHCs) over a period of 10 years. Our data demonstrate that the presence of RAHC was mainly found in HIV-coinfected MSM, with internationally connected transmission networks being observed in the majority of patients. Spontaneous clearance rates were low, and reinfection rates increased mainly driven by a small subset of MSM patients with high-risk behaviour.},

keywords = {Project 03, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Rational Design of Profile HMMs for Sensitive and Specific Sequence Detection with Case Studies Applied to Viruses, Bacteriophages, and Casposons},

author = {Liliane S. Oliveira and Alejandro Reyes and Bas E. Dutilh and Arthur Gruber },

doi = {10.3390/v15020519},

year  = {2023},

date = {2023-02-13},

urldate = {2023-02-13},

journal = {Viruses},

volume = {15},

issue = {2},

pages = {519},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Abolishment of morphology-based taxa and change to binomial species names: 2022 taxonomy update of the ICTV bacterial viruses subcommittee},

author = {Dann Turner and Andrey N. Shkoporov and Cédric Lood and Andrew D. Millard and Bas E. Dutilh and Poliane Alfenas-Zerbini and Leonardo J. van Zyl and Ramy K. Aziz and Hanna M. Oksanen and Minna M. Poranen and Andrew M. Kropinski and Jakub Barylski and J Rodney Brister and Nina Chanisvili and Rob A. Edwards and François Enault and Annika Gillis and Petar Knezevic and Mart Krupovic and Ipek Kurtböke and Alla Kushkina and Rob Lavigne and Susan Lehman and Malgorzata Lobocka and Cristina Moraru and Andrea Moreno Switt and Vera Morozova and Jesca Nakavuma and Alejandro Reyes Muñoz and Jānis Rūmnieks and BL Sarkar and Matthew B. Sullivan and Jumpei Uchiyama and Johannes Wittmann and Tong Yigang and Evelien M. Adriaenssens},

doi = {10.1007/s00705-022-05694-2},

year  = {2023},

date = {2023-01-23},

urldate = {2023-01-23},

journal = {Virology Division News},

volume = {168},

pages = {74},

abstract = {This article summarises the activities of the Bacterial Viruses Subcommittee of the International Committee on Taxonomy of Viruses for the period of March 2021−March 2022. We provide an overview of the new taxa proposed in 2021, approved by the Executive Committee, and ratified by vote in 2022. Significant changes to the taxonomy of bacterial viruses were introduced: the paraphyletic morphological families Podoviridae, Siphoviridae, and Myoviridae as well as the order Caudovirales were abolished, and a binomial system of nomenclature for species was established. In addition, one order, 22 families, 30 subfamilies, 321 genera, and 862 species were newly created, promoted, or moved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Liu-Wei2022c,

title = {FrameRate: learning the coding potential of unassembled metagenomic reads},

author = {Wang Liu-Wei and Wayne Aubrey and Amanda Clare and Robert Hoehndorf and Christopher J. Creevey and Nicholas J. Dimonaco},

doi = {10.1101/2022.09.16.508314},

year  = {2022},

date = {2022-09-19},

journal = {bioRxiv},

abstract = {Motivation Metagenomic assembly is a slow and computationally intensive process and despite needing iterative rounds for improvement and completeness the resulting assembly often fails to incorporate many of the input sequencing reads. This is further complicated when there is reduced read-depth and/or artefacts which result in chimeric assemblies both of which are especially prominent in the assembly of metagenomic datasets. Many of these limitations could potentially be overcome by exploiting the information content stored in the reads directly and thus eliminating the need for assembly in a number of situations.



Results We explored the prediction of coding potential of DNA reads by training a machine learning model on existing protein sequences. Named ‘FrameRate’, this model can predict the coding frame(s) from unassembled DNA sequencing reads directly, thus greatly reducing the computational resources required for genome assembly and similarity-based inference to pre-computed databases. Using the eggNOG-mapper function annotation tool, the predicted coding frames from FrameRate were functionally verified by comparing to the results from full-length protein sequences reconstructed with an established metagenome assembly and gene prediction pipeline from the same metagenomic sample. FrameRate captured equivalent functional profiles from the coding frames while reducing the required storage and time resources significantly. FrameRate was also able to annotate reads that were not represented in the assembly, capturing this ‘missing’ information. As an ultra-fast read-level assembly-free coding profiler, FrameRate enables rapid characterisation of almost every sequencing read directly, whether it can be assembled or not, and thus circumvent many of the problems caused by contemporary assembly workflows.},

keywords = {Project 08, WP 2.1 Microevolution: Virus quasispecies},

pubstate = {published},

tppubtype = {article}

}

@article{Rummel2022,

title = {grandR: a comprehensive package for nucleotide conversion sequencing data analysis},

author = {Teresa Rummel and Lygeri Sakellaridi and Florian Erhard },

doi = {10.1101/2022.09.12.507665},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

journal = {bioRxiv},

abstract = {Metabolic labeling of RNA is a powerful technique for studying the temporal dynamics of gene expression. Nucleotide conversion approaches greatly facilitate the generation of data but introduce challenges for their analysis. We here present grandR, a comprehensive package for quality control, differential gene expression analysis, kinetic modeling, and visualization of such data. We compare several existing methods for inference of RNA synthesis rates and half-lives using progressive labeling time courses. We demonstrate the need for recalibration of effective labeling times and introduce a Bayesian approach to study the temporal dynamics of RNA using snapshot experiments.},

keywords = {Project 06, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Arbovirus-vector protein interactomics identifies Loquacious as a co-factor for dengue virus replication in Aedes mosquitoes},

author = {Benoit Besson and Oscar M. Lezcano and Gijs J Overheul and Kirsten Janssen and Cornelia G. Spruijt and Michiel Vermeulen and Jieqiong Qu and Ronald P. van Rij},

doi = {10.1371/journal.ppat.1010329},

year  = {2022},

date = {2022-09-08},

urldate = {2022-09-08},

journal = {PLoS Pathogens},

volume = {18},

issue = {9},

pages = {e1010329},

abstract = {Efficient virus replication in Aedes vector mosquitoes is essential for the transmission of arboviral diseases such as dengue virus (DENV) in human populations. Like in vertebrates, virus-host protein-protein interactions are essential for viral replication and immune evasion in the mosquito vector. Here, 79 mosquito host proteins interacting with DENV non-structural proteins NS1 and NS5 were identified by label-free mass spectrometry, followed by a functional screening. We confirmed interactions with host factors previously observed in mammals, such as the oligosaccharyltransferase complex, and we identified protein-protein interactions that seem to be specific for mosquitoes. Among the interactors, the double-stranded RNA (dsRNA) binding protein Loquacious (Loqs), an RNA interference (RNAi) cofactor, was found to be essential for efficient replication of DENV and Zika virus (ZIKV) in mosquito cells. Loqs did not affect viral RNA stability or translation of a DENV replicon and its proviral activity was independent of its RNAi regulatory activity. Interestingly, Loqs colocalized with DENV dsRNA replication intermediates in infected cells and directly interacted with high affinity with DENV RNA in the 3' untranslated region in vitro (KD = 48-62 nM). Our study provides an interactome for DENV NS1 and NS5 and identifies Loqs as a key proviral host factor in mosquitoes. We propose that DENV hijacks a factor of the RNAi mechanism for replication of its own RNA.},

keywords = {Project 09, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {The influenza A virus genome packaging network - complex, flexible and yet unsolved},

author = {Celia Jakob and Rithu Paul-Stansilaus and Martin Schwemmle and Roland Marquet and Hardin Bolte},

doi = {10.1093/nar/gkac688},

year  = {2022},

date = {2022-08-22},

journal = {Nucleic Acids Res.},

abstract = {The genome of influenza A virus (IAV) consists of eight unique viral RNA segments. This genome organization allows genetic reassortment between co-infecting IAV strains, whereby new IAVs with altered genome segment compositions emerge. While it is known that reassortment events can create pandemic IAVs, it remains impossible to anticipate reassortment outcomes with pandemic prospects. Recent research indicates that reassortment is promoted by a viral genome packaging mechanism that delivers the eight genome segments as a supramolecular complex into the virus particle. This finding holds promise of predicting pandemic IAVs by understanding the intermolecular interactions governing this genome packaging mechanism. Here, we critically review the prevailing mechanistic model postulating that IAV genome packaging is orchestrated by a network of intersegmental RNA-RNA interactions. Although we find supporting evidence, including segment-specific packaging signals and experimentally proposed RNA-RNA interaction networks, this mechanistic model remains debatable due to a current shortage of functionally validated intersegmental RNA-RNA interactions. We speculate that identifying such functional intersegmental RNA-RNA contacts might be hampered by limitations of the utilized probing techniques and the inherent complexity of the genome packaging mechanism. Nevertheless, we anticipate that improved probing strategies combined with a mutagenesis-based validation could facilitate their discovery.},

keywords = {Project 02, WP 1.4 Virus regulation},

pubstate = {published},

tppubtype = {article}

}

@article{Burkart2022,

title = {High Resolution Kinetic Characterization and Dynamic Mathematical Modeling of the RIG-I Signaling Pathway and the Antiviral Responses},

author = {Sandy S. Burkart and Darius Schweinoch and Jamie Frankish and Carola Sparn and Sandra Wüst and Christian Urban and Antonio Piras and Andreas Pichlmair and Joschka Willemsen and Lars Kaderali and Marco Binder},

doi = {10.1101/2022.08.05.502818},

year  = {2022},

date = {2022-08-05},

journal = {bioRxiv},

abstract = {The pattern recognition receptor RIG-I is essential for the recognition of viral dsRNA and the activation of a cell-autonomous antiviral response. Upon stimulation, RIG-I triggers a signaling cascade leading to the expression of cytokines, most prominently type I and III interferons (IFNs). IFNs are secreted and signal in an auto- and paracrine manner to trigger the expression of a large variety of IFN-stimulated genes, which in concert establish an antiviral state of the cell. While the topology of this pathway has been studied quite intensively, the dynamics, particularly of the RIG-I-mediated IFN induction, is much less understood. Here, we employed electroporation-based transfection to synchronously activate the RIG-I signaling pathway, enabling us to characterize the kinetics and dynamics of cell-intrinsic innate immune signaling to virus infections. By employing an A549 IFNAR1/IFNLR deficient cell line, we could analyze the difference between the primary RIG-I signaling phase and the secondary signaling phase downstream of the IFN receptors. We further used our quantitative data to set up and calibrate a comprehensive dynamic mathematical model of the RIG-I and IFN signaling pathways. This model accurately predicts the kinetics of signaling events downstream of dsRNA recognition by RIG-I as well as the feedback and signal amplification by secreted IFN and JAK/STAT signaling. We have furthermore investigated the impact of various viral immune antagonists on the signaling dynamics experimentally, and we utilized the here described modelling approach to simulate and in silico study these critical virus-host interactions. Our work provides a comprehensive insight into the signaling events occurring early upon virus infection and opens up new avenues to study and disentangle the complexity of the host-virus interface.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Replidec - Use naive Bayes classifier to identify virus lifecycle from metagenomics data},

author = {Xue Peng and Jinlong Ru and Mohammadali Khan Mirzaei and Li Deng

},

doi = {10.1101/2022.07.18.500415},

year  = {2022},

date = {2022-07-19},

journal = {bioRxiv},

abstract = {Motivation: Viruses are the most abundant biological entities on earth. The majority of these entities are bacterial viruses or phages which specifically infect bacteria. Phages can use different replication strategies to invade their hosts including lytic, lysogenic, chronic cycle and pseudolysogeny. While the determination of the replication strategy used by phages is important to explore the phage-bacteria relationships in different ecosystems there are not many tools that can predict this in metagenomic data. In addition, most of the tools available can only predict lytic and lysogenic cycles. To address this issue, we have developed a new software called Replidec to identify three most common phage replication cycles (virulent, temperate, chronic) in viral sequences.



Results: Replidec uses Naive Bayes classifier combined with alignment-based methods to improve the prediction accuracy in metagenomic data. We test Replidec on viral genomes with known replication cycle and simulated metagenomic sequences. Replidec perform relatively good both in isolated genomes (F1 score: 92.29% ± 0.81; mcc: 89.14% ± 1.22) and simulated metagenomic sequences(F1 score: 87.55% ± 2.12; mcc: 88.23% ± 2.55). Moreover, Replidec can also accurately predict the replication cycle in small viral fragments(∼3000bp). In conclusion, Replidec can achieve the best performance in simulated metagenomic data compared to most prediction softwares including BACPHLIP.},

keywords = {Project 05, WP 1.2 Host prediction},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Early detection and surveillance of SARS-CoV-2 genomic variants in wastewater using COJAC},

author = {Katharina Jahn and David Dreifuss and Ivan Topolsky and Anina Kull and Pravin Ganesanandamoorthy and Xavier Fernandez-Cassi and Carola Bänziger and Alexander J. Devaux and Elyse Stachler and Lea Caduff and Federica Cariti and Alex Tuñas Corzón and Lara Fuhrmann and Chaoran Chen and Kim Philipp Jablonski and Sarah Nadeau and Mirjam Feldkamp and Christian Beisel and Catharine Aquino and Tanja Stadler and Christoph Ort and Tamar Kohn and Timothy R. Julian and Niko Beerenwinkel},

doi = {10.1038/s41564-022-01185-x},

year  = {2022},

date = {2022-07-18},

urldate = {2022-07-18},

journal = {Nat Microbiol},

abstract = {The continuing emergence of SARS-CoV-2 variants of concern and variants of interest emphasizes the need for early detection and epidemiological surveillance of novel variants. We used genomic sequencing of 122 wastewater samples from three locations in Switzerland to monitor the local spread of B.1.1.7 (Alpha), B.1.351 (Beta) and P.1 (Gamma) variants of SARS-CoV-2 at a population level. We devised a bioinformatics method named COJAC (Co-Occurrence adJusted Analysis and Calling) that uses read pairs carrying multiple variant-specific signature mutations as a robust indicator of low-frequency variants. Application of COJAC revealed that a local outbreak of the Alpha variant in two Swiss cities was observable in wastewater up to 13 d before being first reported in clinical samples. We further confirmed the ability of COJAC to detect emerging variants early for the Delta variant by analysing an additional 1,339 wastewater samples. While sequencing data of single wastewater samples provide limited precision for the quantification of relative prevalence of a variant, we show that replicate and close-meshed longitudinal sequencing allow for robust estimation not only of the local prevalence but also of the transmission fitness advantage of any variant. We conclude that genomic sequencing and our computational analysis can provide population-level estimates of prevalence and fitness of emerging variants from wastewater samples earlier and on the basis of substantially fewer samples than from clinical samples. Our framework is being routinely used in large national projects in Switzerland and the UK.},

keywords = {Project 03, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{McCallin2022,

title = {Antibiotic Exposure Leads to Reduced Phage Susceptibility in Vancomycin Intermediate Staphylococcus aureus (VISA)},

author = {Shawna McCallin and Carmen Menzi and Swenja Lassen and Jean Daraspe and Frank Oechslin and Philippe Moreillon

},

doi = {10.1128/aac.02247-21},

year  = {2022},

date = {2022-06-16},

urldate = {2022-06-16},

journal = {Antimicrob Agents Chemother},

abstract = {In the time of antimicrobial resistance, phage therapy is frequently suggested as a possible solution for such difficult-to-treat infections. Vancomycin-intermediate Staphylococcus aureus (VISA) remains a relatively rare yet increasing occurrence in the clinic for which phage therapy may be an option. However, the data presented herein suggest a potential cross-resistance mechanism to phage following vancomycin exposure in VISA strains. When comparing genetically similar strains differing in their susceptibility to vancomycin, those with intermediate levels of vancomycin resistance displayed decreased sensitivity to phage in solid and liquid assays. Serial passaging with vancomycin induced both reduced vancomycin susceptibility and phage sensitivity. As a consequence, the process of phage infection was shown to be interrupted after DNA ejection from adsorbed phage but prior to phage DNA replication, as demonstrated through adsorption assays, lysostaphin sensitivity assays, electron microscopy, and quantitative PCR (qPCR). At a time when phage products are being used for experimental treatments and tested in clinical trials, it is important to understand possible interference between mechanisms underlying antibiotic and phage resistance in order to design effective therapeutic regimens.},

keywords = {Project 07, WP 1.5 Virus products},

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 Lencioni 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 = {Project 01, WP 1.4 Virus regulation},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Quantification of the spread of SARS-CoV-2 variant B.1.1.7 in Switzerland},

author = {Chaoran Chen and Sarah Ann Nadeau and Ivan Topolsky and Marc Manceau and Jana S. Huisman and Kim Philipp Jablonski and Lara Fuhrmann and David Dreifuss and Katharina Jahn and Christiane Beckmann and Maurice Redondo and Christoph Noppen and Lorenz Risch and Martin Risch and Nadia Wohlwend and Sinem Kas and Thomas Bodmer and Tim Roloff and Madlen Stange and Adrian Egli and Isabella Eckerle and Laurent Kaiser and Rebecca Denes and Mirjam Feldkamp and Ina Nissen and Natascha Santacroce and Elodie Burcklen and Catharine Aquino and Andreia Cabral de Gouvea and Maria Domenica Moccia and Simon Grüter and Timothy Sykes and Lennart Opitz and Griffin White and Laura Neff and Doris Popovic and Andrea Patrignani and Jay Tracy and Ralph Schlapbach and Emmanouil T Dermitzakis and Keith Harshman and Ioannis Xenarios and Henri Pegeot and Lorenzo Cerutti and Deborah Penet and Anthony Blin and Melyssa Elies and Christian L. Althaus and Christian Beisel and Niko Beerenwinkel and Martin Ackermann and Tanja Stadler},

doi = {10.1016/j.epidem.2021.100480},

year  = {2021},

date = {2021-08-09},

urldate = {2021-08-09},

journal = {Epidemics},

volume = {37},

pages = {100480},

abstract = {Background: In December 2020, the United Kingdom (UK) reported a SARS-CoV-2 Variant of Concern (VoC) which is now named B.1.1.7. Based on initial data from the UK and later data from other countries, this variant was estimated to have a transmission fitness advantage of around 40-80 % (Volz et al., 2021; Leung et al., 2021; Davies et al., 2021).



Aim: This study aims to estimate the transmission fitness advantage and the effective reproductive number of B.1.1.7 through time based on data from Switzerland.



Methods: We generated whole genome sequences from 11.8 % of all confirmed SARS-CoV-2 cases in Switzerland between 14 December 2020 and 11 March 2021. Based on these data, we determine the daily frequency of the B.1.1.7 variant and quantify the variant's transmission fitness advantage on a national and a regional scale.



Results: We estimate B.1.1.7 had a transmission fitness advantage of 43-52 % compared to the other variants circulating in Switzerland during the study period. Further, we estimate B.1.1.7 had a reproductive number above 1 from 01 January 2021 until the end of the study period, compared to below 1 for the other variants. Specifically, we estimate the reproductive number for B.1.1.7 was 1.24 [1.07-1.41] from 01 January until 17 January 2021 and 1.18 [1.06-1.30] from 18 January until 01 March 2021 based on the whole genome sequencing data. From 10 March to 16 March 2021, once B.1.1.7 was dominant, we estimate the reproductive number was 1.14 [1.00-1.26] based on all confirmed cases. For reference, Switzerland applied more non-pharmaceutical interventions to combat SARS-CoV-2 on 18 January 2021 and lifted some measures again on 01 March 2021.



Conclusion: The observed increase in B.1.1.7 frequency in Switzerland during the study period is as expected based on observations in the UK. In absolute numbers, B.1.1.7 increased exponentially with an estimated doubling time of around 2-3.5 weeks. To monitor the ongoing spread of B.1.1.7, our plots are available online.},

keywords = {Project 03, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Quantitative measures of within-host viral genetic diversity},

author = {Lara Fuhrmann and Kim Philipp Jablonski and Niko Beerenwinkel

},

doi = {10.1016/j.coviro.2021.06.002},

year  = {2021},

date = {2021-06-18},

urldate = {2021-06-18},

journal = {Curr Opin Virol},

volume = {49},

pages = {157-163},

abstract = {The genetic diversity of virus populations within their hosts is known to influence disease progression, treatment outcome, drug resistance, cell tropism, and transmission risk, and the study of dynamic changes of genetic heterogeneity can provide insights into the evolution of viruses. Several measures to quantify within-host genetic diversity capturing different aspects of diversity patterns in a sample or population are used, based on incidence, relative frequencies, pairwise distances, or phylogenetic trees. Here, we review and compare several of these measures.},

keywords = {Project 03, WP 1.3 Virus-host interactions},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

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

author = {Winfried Goettsch and Niko Beerenwinkel and Li Deng and Lars Dölken and Bas E. Dutilh and Florian Erhard and Lars Kaderali and Max von 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},

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 = {Project 01, Project 02, Project 03, Project 04, Project 05, Project 06, Project 07, Project 08, Project 09, Project 10, Project 11, Project 12, Project 13, Project 14, Project 15, WP 1.1 Virus identification, WP 1.2 Host prediction, WP 1.3 Virus-host interactions, WP 1.4 Virus regulation, WP 1.5 Virus products, WP 2.1 Microevolution: Virus quasispecies, WP 2.2 Macroevolution: Natural selection of viruses},

pubstate = {published},

tppubtype = {article}

}