Publications

@article{nokey_81,

title = {Targeted decontamination of sequencing data with CLEAN},

author = {Marie Lataretu and Sebastian Krautwurst and Matthew R Huska and Mike Marquet and Adrian Viehweger and Sascha D Braun and Christian Brandt and Martin Hölzer},

doi = {10.1093/nargab/lqaf105},

year  = {2025},

date = {2025-07-04},

urldate = {2025-07-04},

journal = {NAR Genomics and Bioinformatics},

volume = {7},

abstract = {Many biological and medical questions are answered based on the analysis of sequence data. However, we can find contamination, artificial spike-ins, and overrepresented rRNA (ribosomal RNA) sequences in various read collections and assemblies. In particular, spike-ins used as controls, as those known from Illumina or Nanopore data, are often not considered as contaminants and also not appropriately removed during analyses. Additionally, removing human host DNA may be necessary for data protection and ethical considerations to ensure that individuals cannot be identified. We developed CLEAN, a pipeline to remove unwanted sequences from both long- and short-read sequencing techniques. While focusing on Illumina and Nanopore data with their technology-specific control sequences, the pipeline can also be used for host decontamination of metagenomic reads and assemblies, or the removal of rRNA from RNA-Seq data. The results are the purified sequences and sequences identified as contaminated with statistics summarized in a report. The output can be used directly in subsequent analyses, resulting in faster computations and improved results. Although decontamination seems mundane, many contaminants are routinely overlooked, cleaned by steps that are not fully reproducible or difficult to trace. CLEAN facilitates reproducible, platform-independent data analysis in genomics and transcriptomics and is freely available at https://github.com/rki-mf1/clean under a BSD3 license.},

keywords = {assembly, metagenomics, nanopore, RNA / transcriptomics, software},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {\textit{Arabidopsis thaliana} accumulates dehydroepiandrosterone after infection with phytopathogenic fungi – effects on plants and fungi},

author = {Ceren Oktay and Glendis Shiko and Maximilian Liebl and Felix Feistel and Sarah Mußbach and Karl Ludwig Körber and Emanuel Barth and Ludwig Huber and Anna Antony and Ralf Oelmüller and Michael Reichelt and Kilian Ossetek and Christoph Müller and Alexandra C.U. Furch and Jan Klein},

doi = {10.1016/j.plaphy.2025.109570},

year  = {2025},

date = {2025-01-28},

urldate = {2025-01-28},

journal = {Plant Physiology and Biochemistry},

abstract = {Progestogens and androgens have been found in many plants, but little is known about their physiological function. We used a previously established UPLC-ESI-MS/MS method to analyze progestogen and androgen profiles in fungal infections. Here we show that dehydroepiandrosterone (DHEA), a C19 steroid, specifically accumulates in shoots of Arabidopsis thaliana (L.) HEYNH. infected with Alternaria brassicicola (SCHWEIN). Elevated DHEA levels in plants seem not to be product of fungal sterol/steroid precursor activity, but an intrinsic plant response to the infection. DHEA was applied exogenously to analyze the effects of the androgen on development and gene expression in A. thaliana. Our findings reveal that DHEA treatment downregulates membrane-associated, salicylic acid and abscisic acid-regulated, as well as stress-responsive genes. Notably, DHEA does not inhibit the isoprenoid or post-lanosterol pathway of the ergosterol biosynthesis. Moreover, A. brassicicola was also treated with DHEA to analyze the growth, sterol pattern and membrane-integrity. Our data suggest that DHEA enhances the permeability of plant and fungal biomembranes. We propose that DHEA accumulation is a plant defense response which reduces fungal growth in plant tissues.},

keywords = {fungi, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_79,

title = {The RMaP challenge of predicting RNA modifications by nanopore sequencing},

author = {Jannes Spangenberg and Stefan Mündnich and Anne Busch and Stefan Pastore and Anna Wierczeiko and Winfried Goettsch and Vincent Dietrich and Leszek P. Pryszcz and Sonia Cruciani and Eva Maria Novoa and Kandarp Joshi and Ranjan Perera and Salvatore Di Giorgio and Paola Arrubarrena and Irem Tellioglu and Chi-Lam Poon and Yuk Kei Wan and Jonathan Göke and Andreas Hildebrandt and Christoph Dieterich and Mark Helm and Manja Marz and Susanne Gerber and Nicolo Alagna},

doi = {10.1038/s42004-025-01507-0},

year  = {2024},

date = {2024-12-04},

urldate = {2024-12-04},

journal = {Communications Chemistry},

volume = {8},

issue = {1},

abstract = {The field of epitranscriptomics is undergoing a technology-driven revolution. During past decades, RNA modifications like N6-methyladenosine (m6A), pseudouridine (ψ), and 5-methylcytosine (m5C) became acknowledged for playing critical roles in cellular processes. Direct RNA sequencing by Oxford Nanopore Technologies (ONT) enabled the detection of modifications in native RNA, by detecting noncanonical RNA nucleosides properties in raw data. Consequently, the field’s cutting edge has a heavy component in computer science, opening new avenues of cooperation across the community, as exchanging data is as impactful as exchanging samples. Therefore, we seize the occasion to bring scientists together within the RNA Modification and Processing (RMaP) challenge to advance solutions for RNA modification detection and discuss ideas, problems and approaches. We show several computational methods to detect the most researched mRNA modifications (m6A, ψ, and m5C). Results demonstrate that a low prediction error and a high prediction accuracy can be achieved on these modifications across different approaches and algorithms. The RMaP challenge marks a substantial step towards improving algorithms’ comparability, reliability, and consistency in RNA modification prediction. It points out the deficits in this young field that need to be addressed in further challenges.},

keywords = {machine learning, nanopore, nucleic acid modifications, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_66,

title = {RNA-protein interaction prediction without high-throughput data: An overview and benchmark of \textit{in silico} tools},

author = {Sarah Krautwurst and Kevin Lamkiewicz},

doi = {10.1016/j.csbj.2024.11.015},

issn = {2001-0370},

year  = {2024},

date = {2024-11-08},

journal = {Computational and Structural Biotechnology Journal},

volume = {23},

pages = {4036-4046},

abstract = {RNA-protein interactions (RPIs) are crucial for accurately operating various processes in and between organisms across kingdoms of life. Mutual detection of RPI partner molecules depends on distinct sequential, structural, or thermodynamic features, which can be determined via experimental and bioinformatic methods. Still, the underlying molecular mechanisms of many RPIs are poorly understood. It is further hypothesized that many RPIs are not even described yet. Computational RPI prediction is continuously challenged by the lack of data and detailed research of very specific examples. With the discovery of novel RPI complexes in all kingdoms of life, adaptations of existing RPI prediction methods are necessary. Continuously improving computational RPI prediction is key in advancing the understanding of RPIs in detail and supplementing experimental RPI determination. The growing amount of data covering more species and detailed mechanisms support the accuracy of prediction tools, which in turn support specific experimental research on RPIs. Here, we give an overview of RPI prediction tools that do not use high-throughput data as the user's input. We review the tools according to their input, usability, and output. We then apply the tools to known RPI examples across different kingdoms of life. Our comparison shows that the investigated prediction tools do not favor a certain species and equip the user with results varying in degree of information, from an overall RPI score to detailed interacting residues. Furthermore, we provide a guide tree to assist users which RPI prediction tool is appropriate for their available input data and desired output.},

keywords = {ncRNAs, proteins, RNA / transcriptomics, RNA structure},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Data report on gene expression after hepatic portal vein ligation (PVL) in rats},

author = {Daria Meyer and Joanna Kosacka and Martin von Bergen and Bruno Christ and Manja Marz},

doi = {10.3389/fgene.2024.1421955},

year  = {2024},

date = {2024-08-21},

journal = {Front Genet},

volume = {15},

pages = {1421955},

keywords = {liver, RNA / transcriptomics},

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_64,

title = {Exploring the impact of primer length on efficient gene detection via high-throughput sequencing},

author = {Julia Micheel and Aram Safrastyan and Franziska Aron and Damian Wollny},

doi = {10.1038/s41467-024-49685-0},

year  = {2024},

date = {2024-07-12},

journal = {Nature Communications},

volume = {15},

issue = {1},

abstract = {Reverse transcription (RT) is a crucial step in most RNA analysis methods. Optimizing protocols for this initial stage is critical for effective target detection, particularly when working with limited input RNA. Several factors, such as the input material quality and reaction conditions, influence RT efficiency. However, the effect of RT primer length on gene detection efficiency remains largely unknown. Thus, we investigate its impact by generating RNA-seq libraries with random RT primers of 6, 12, 18, or 24 nucleotides. To our surprise, the 18mer primer shows superior efficiency in overall transcript detection compared to the commonly used 6mer primer, especially in detecting longer RNA transcripts in complex human tissue samples. This study highlights the critical role of primer length in RT efficiency, which has significant potential to benefit various transcriptomic assays, from basic research to clinical diagnostics, given the central role of RT in RNA-related analyses.},

keywords = {RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Immunity and bacterial recruitment in plant leaves are parallel processes whose link shapes sensitivity to temperature stress},

author = {Jisna Jose and Erik Teutloff and Simrat Naseem and Emanuel Barth and Rayko Halitschke and Manja Marz and Matthew T. Agler},

doi = {10.1101/2024.06.10.598336},

year  = {2024},

date = {2024-06-10},

journal = {bioRxiv},

abstract = {Rising global temperatures necessitate developing climate-resilient crops with better adaptability to changing climates. Under elevated temperatures, plant immunity is downregulated, putting them at risk of foliar pathogen attack. Manipulating plant defense hormones is one way to mitigate this detrimental effect. However, it is unclear how plant immunity interacts with plant microbiome assembly and how temperature will thus affect overall plant health and stability. We used chemical mutagenesis to identify a phenotypically healthy genotype of A. thaliana, “CLLF”, that compared to the wild type naturally recruits an altered leaf bacteriome, including unusually high bacteria loads. Simultaneously, CLLF hyperaccumulates salicylic acid (SA) and jasmonates, has constitutively upregulated systemic and innate defenses, and has increased resistance to necrotrophic fungal and hemi-biotrophic bacterial pathogens, indicating that pathogen immunity and non-pathogen recruitment function in parallel. Growth of specific non-pathogenic leaf bacteria on SA as a carbon source suggests the same hormones may even link the two processes. CLLF also showed high tolerance to heat stress in comparison to the wild type, but SA-associated defense processes are not downregulated under heat. Synthetic community (SynCom) experiments showed that when the taxonomic diversity of bacteria available to CLLF is artificially reduced, resilience to heat stress is compromised, leading to dysbiosis, but this does not occur with the full SynCom or in the wild type with any SynCom. Thus, the downregulation of defenses in response to heat may contribute to avoidance of dysbiosis caused by some leaf bacteria, but full bacteriome taxonomic diversity can restore balance.



Significance Statement Plants are living ecosystems colonized by diverse microorganisms who strongly shape host health. Understanding how balance arises in host-associated microbiomes is a key step to understanding how to preserve, manage and possibly optimize these complex ecosystems, especially in a changing climate. Using a random mutagenesis approach in a natural A. thaliana ecotype, we find that constitutively upregulated defenses are associated with both tolerance to (a)biotic threats and healthy recruitment of leaf bacteria, very likely in a direct manner. Thus, immunity and bacterial recruitment in leaves operate in parallel. Synthetic community experiments show further that this link plays important roles in shaping plant resilience to heat stress, an important consideration in developing plants more stable to climate change.},

keywords = {bacteria, evolution, fungi, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Comprehensive transcriptome analysis reveals altered mRNA splicing and post-transcriptional changes in the aged mouse brain},

author = {Nisha Hemandhar Kumar and Verena Kluever and Emanuel Barth and Sebastian Krautwurst and Mattia Furlan and Mattia Pelizzola and Manja Marz and Eugenio F Fornasiero},

doi = {10.1093/nar/gkae172},

year  = {2024},

date = {2024-04-12},

urldate = {2024-04-12},

journal = {Nucleic Acids Research},

volume = {52},

abstract = {A comprehensive understanding of molecular changes during brain aging is essential to mitigate cognitive decline and delay neurodegenerative diseases. The interpretation of mRNA alterations during brain aging is influenced by the health and age of the animal cohorts studied. Here, we carefully consider these factors and provide an in-depth investigation of mRNA splicing and dynamics in the aging mouse brain, combining short- and long-read sequencing technologies with extensive bioinformatic analyses. Our findings encompass a spectrum of age-related changes, including differences in isoform usage, decreased mRNA dynamics and a module showing increased expression of neuronal genes. Notably, our results indicate a reduced abundance of mRNA isoforms leading to nonsense-mediated RNA decay and suggest a regulatory role for RNA-binding proteins, indicating that their regulation may be altered leading to the reshaping of the aged brain transcriptome. Collectively, our study highlights the importance of studying mRNA splicing events during brain aging.},

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Differential Transcriptional Responses of Human Granulocytes to Fungal Infection with \textit{Candida albicans} and \textit{Aspergillus fumigatus}},

author = {Tilman E. Klassert and Martin Hölzer and Cristina Zubiria-Barrera and Julia Bethge and Esther Klaile and Mario M. Müller and Manja Marz and Hortense Slevogt},

doi = {doi.org/10.3390/jof9101014},

year  = {2023},

date = {2023-10-14},

journal = {J Fungi},

volume = {9},

issue = {10},

pages = {1014},

abstract = {Neutrophils are critical phagocytic cells in innate immunity, playing a significant role in defending against invasive fungal pathogens. This study aimed to explore the transcriptional activation of human neutrophils in response to different fungal pathogens, including Candida albicans and Aspergillus fumigatus, compared to the bacterial pathogen Escherichia coli. We identified distinct transcriptional profiles and stress-related pathways in neutrophils during fungal infections, highlighting their functional diversity and adaptability. The transcriptional response was largely redundant across all pathogens in immune-relevant categories and cytokine pathway activation. However, differences in the magnitude of differentially expressed genes (DEGs) were observed, with A. fumigatus inducing a lower transcriptional effect compared to C. albicans and E. coli. Notably, specific gene signatures associated with cell death were differentially regulated by fungal pathogens, potentially increasing neutrophil susceptibility to autophagy, pyroptosis, and neutrophil extracellular trap (NET) formation. These findings provide valuable insights into the complex immunological responses of neutrophils during fungal infections, offering new avenues for diagnostic and therapeutic strategies, particularly in the management of invasive fungal diseases.},

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_46,

title = {RNA-based sensitive fungal pathogen detection},

author = {Julia Micheel and Franziska Aron and Abdulrahman A. Kelani and Christian Girbardt and Matthew G. Blango and Grit Walther and Damian Wollny},

doi = {10.1101/2023.09.26.559494},

year  = {2023},

date = {2023-09-26},

urldate = {2023-09-26},

journal = {bioRxiv},

abstract = {Detecting fungal pathogens, a major cause of severe systemic infections, remains challenging due to the difficulty and time-consuming nature of diagnostic methods. This delay in identification hinders targeted treatment decisions and may lead to unnecessary use of broad-spectrum antibiotics. To expedite treatment initiation, one promising approach is to directly detect pathogen nucleic acids such as DNA, which is often preferred to RNA because of its inherent stability. However, a higher number of RNA molecules per cell makes RNA a more promising diagnostic target which is particularly prominent for highly expressed genes such as rRNA. Here, we investigated the utility of a minimal input-specialized reverse transcription protocol to increase diagnostic sensitivity. This proof-of-concept study demonstrates that fungal rRNA detection by the minimal input protocol is drastically more sensitive compared to detection of genomic DNA even with high levels of human RNA background. This approach can detect several of the most relevant human pathogenic fungal genera, such as Aspergillus, Candida, and Fusarium and thus represents a powerful, cheap, and easily adaptable addition to currently available diagnostic assays.},

keywords = {fungi, ncRNAs, RNA / transcriptomics},

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 = {Identification of altered miRNAs and their targets in placenta accreta},

author = {José M Murrieta-Coxca and Emanuel Barth and Paulina Fuentes-Zacarias and Ruby N Gutiérrez-Samudio and Tanja Groten and Alexandra Gellhaus and Angela Köninger and Manja Marz and Udo R Markert and Diana M Morales-Prieto

},

doi = {10.3389/fendo.2023.1021640},

year  = {2023},

date = {2023-03-03},

journal = {Front Endocrinol},

volume = {14},

pages = {1021640},

abstract = {Placenta accreta spectrum (PAS) is one of the major causes of maternal morbidity and mortality worldwide with increasing incidence. PAS refers to a group of pathological conditions ranging from the abnormal attachment of the placenta to the uterus wall to its perforation and, in extreme cases, invasion into surrounding organs. Among them, placenta accreta is characterized by a direct adhesion of the villi to the myometrium without invasion and remains the most common diagnosis of PAS. Here, we identify the potential regulatory miRNA and target networks contributing to placenta accreta development. Using small RNA-Seq followed by RT-PCR confirmation, altered miRNA expression, including that of members of placenta-specific miRNA clusters (e.g., C19MC and C14MC), was identified in placenta accreta samples compared to normal placental tissues. In situ hybridization (ISH) revealed expression of altered miRNAs mostly in trophoblast but also in endothelial cells and this profile was similar among all evaluated degrees of PAS. Kyoto encyclopedia of genes and genomes (KEGG) analyses showed enriched pathways dysregulated in PAS associated with cell cycle regulation, inflammation, and invasion. mRNAs of genes associated with cell cycle and inflammation were downregulated in PAS. At the protein level, NF-κB was upregulated while PTEN was downregulated in placenta accreta tissue. The identified miRNAs and their targets are associated with signaling pathways relevant to controlling trophoblast function. Therefore, this study provides miRNA:mRNA associations that could be useful for understanding PAS onset and progression.},

keywords = {ncRNAs, pregnancy, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Genome Structure, Life Cycle, and Taxonomy of Coronaviruses and the Evolution of SARS-CoV-2},

author = {Kevin Lamkiewicz and Luis Roger Esquivel Gomez and Denise Kühnert and Manja Marz

},

doi = {10.1007/978-3-031-15640-3_9},

year  = {2023},

date = {2023-01-03},

journal = {Curr Top Microbiol Immunol},

volume = {439},

pages = {305-339},

abstract = {Coronaviruses have a broad host range and exhibit high zoonotic potential. In this chapter, we describe their genomic organization in terms of encoded proteins and provide an introduction to the peculiar discontinuous transcription mechanism. Further, we present evolutionary conserved genomic RNA secondary structure features, which are involved in the complex replication mechanism. With a focus on computational methods, we review the emergence of SARS-CoV-2 starting with the 2019 strains. In that context, we also discuss the debated hypothesis of whether SARS-CoV-2 was created in a laboratory. We focus on the molecular evolution and the epidemiological dynamics of this recently emerged pathogen and we explain how variants of concern are detected and characterised. COVID-19, the disease caused by SARS-CoV-2, can spread through different transmission routes and also depends on a number of risk factors. We describe how current computational models of viral epidemiology, or more specifically, phylodynamics, have facilitated and will continue to enable a better understanding of the epidemic dynamics of SARS-CoV-2.},

keywords = {coronavirus, DNA / genomics, evolution, phylogenetics, RNA / transcriptomics},

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 = {Comparative transcriptomics identifies candidate genes involved in the evolutionary transition from dehiscent to indehiscent fruits in Lepidium (Brassicaceae)},

author = {Lydia Gramzow and Katharina Klupsch and Noé Fernández-Pozo and Martin Hölzer and Manja Marz and Stefan A Rensing and Günter Theißen},

doi = {10.1186/s12870-022-03631-8},

year  = {2022},

date = {2022-07-14},

journal = {BMC Plant Biol},

volume = {22},

issue = {1},

pages = {340},

abstract = {Background: Fruits are the seed-bearing structures of flowering plants and are highly diverse in terms of morphology, texture and maturation. Dehiscent fruits split open upon maturation to discharge their seeds while indehiscent fruits are dispersed as a whole. Indehiscent fruits evolved from dehiscent fruits several times independently in the crucifer family (Brassicaceae). The fruits of Lepidium appelianum, for example, are indehiscent while the fruits of the closely related L. campestre are dehiscent. Here, we investigate the molecular and genetic mechanisms underlying the evolutionary transition from dehiscent to indehiscent fruits using these two Lepidium species as model system.



Results: We have sequenced the transcriptomes and small RNAs of floral buds, flowers and fruits of L. appelianum and L. campestre and analyzed differentially expressed genes (DEGs) and differently differentially expressed genes (DDEGs). DEGs are genes that show significantly different transcript levels in the same structures (buds, flowers and fruits) in different species, or in different structures in the same species. DDEGs are genes for which the change in expression level between two structures is significantly different in one species than in the other. Comparing the two species, the highest number of DEGs was found in flowers, followed by fruits and floral buds while the highest number of DDEGs was found in fruits versus flowers followed by flowers versus floral buds. Several gene ontology terms related to cell wall synthesis and degradation were overrepresented in different sets of DEGs highlighting the importance of these processes for fruit opening. Furthermore, the fruit valve identity genes FRUITFULL and YABBY3 were among the DEGs identified. Finally, the microRNA miR166 as well as the TCP transcription factors BRANCHED1 (BRC1) and TCP FAMILY TRANSCRIPTION FACTOR 4 (TCP4) were found to be DDEGs.



Conclusions: Our study reveals differences in gene expression between dehiscent and indehiscent fruits and uncovers miR166, BRC1 and TCP4 as candidate genes for the evolutionary transition from dehiscent to indehiscent fruits in Lepidium.},

keywords = {RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Characterization of RNA content in individual phase-separated coacervate microdroplets},

author = {Damian Wollny and Benjamin Vernot and Jie Wang and Maria Hondele and Aram Safrastyan and Franziska Aron and Julia Micheel and Zhisong He and Anthony Hyman and Karsten Weis and J. Gray Camp and T-Y Dora Tang and Barbara Treutlein},

url = {10.1038/s41467-022-30158-1},

year  = {2022},

date = {2022-05-12},

urldate = {2022-05-12},

journal = {Nat Commun},

volume = {13},

issue = {1},

pages = {2626},

abstract = {Condensates formed by complex coacervation are hypothesized to have played a crucial part during the origin-of-life. In living cells, condensation organizes biomolecules into a wide range of membraneless compartments. Although RNA is a key component of biological condensates and the central component of the RNA world hypothesis, little is known about what determines RNA accumulation in condensates and to which extend single condensates differ in their RNA composition. To address this, we developed an approach to read the RNA content from single synthetic and protein-based condensates using high-throughput sequencing. We find that certain RNAs efficiently accumulate in condensates. These RNAs are strongly enriched in sequence motifs which show high sequence similarity to short interspersed elements (SINEs). We observe similar results for protein-derived condensates, demonstrating applicability across different in vitro reconstituted membraneless organelles. Thus, our results provide a new inroad to explore the RNA content of phase-separated droplets at single condensate resolution.},

keywords = {RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {The Role of Non-Coding RNAs in the Human Placenta},

author = {Milena Žarković and Franziska Hufsky and Udo R Markert and Manja Marz},

doi = {10.3390/cells11091588},

year  = {2022},

date = {2022-05-09},

journal = {Cells},

volume = {11},

issue = {9},

pages = {1588},

abstract = {Non-coding RNAs (ncRNAs) play a central and regulatory role in almost all cells, organs, and species, which has been broadly recognized since the human ENCODE project and several other genome projects. Nevertheless, a small fraction of ncRNAs have been identified, and in the placenta they have been investigated very marginally. To date, most examples of ncRNAs which have been identified to be specific for fetal tissues, including placenta, are members of the group of microRNAs (miRNAs). Due to their quantity, it can be expected that the fairly larger group of other ncRNAs exerts far stronger effects than miRNAs. The syncytiotrophoblast of fetal origin forms the interface between fetus and mother, and releases permanently extracellular vesicles (EVs) into the maternal circulation which contain fetal proteins and RNA, including ncRNA, for communication with neighboring and distant maternal cells. Disorders of ncRNA in placental tissue, especially in trophoblast cells, and in EVs seem to be involved in pregnancy disorders, potentially as a cause or consequence. This review summarizes the current knowledge on placental ncRNA, their transport in EVs, and their involvement and pregnancy pathologies, as well as their potential for novel diagnostic tools.},

keywords = {extracellular vesicles, ncRNAs, pregnancy, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Age-dependent expression changes of circadian system-related genes reveal a potentially conserved link to aging},

author = {Emanuel Barth and Akash Srivastava and Diane Wengerodt and Milan Stojiljkovic and Hubertus Axer and Otto W Witte and Alexandra Kretz and Manja Marz

},

doi = {10.18632/aging.203788},

year  = {2021},

date = {2021-12-19},

journal = {Aging},

volume = {13},

number = {24},

pages = {25694-25716},

abstract = {The circadian clock system influences the biology of life by establishing circadian rhythms in organisms, tissues, and cells, thus regulating essential biological processes based on the day/night cycle. Circadian rhythms change over a lifetime due to maturation and aging, and disturbances in the control of the circadian system are associated with several age-related pathologies. However, the impact of chronobiology and the circadian system on healthy organ and tissue aging remains largely unknown. Whether aging-related changes of the circadian system's regulation follow a conserved pattern across different species and tissues, hence representing a common driving force of aging, is unclear. Based on a cross-sectional transcriptome analysis covering 329 RNA-Seq libraries, we provide indications that the circadian system is subjected to aging-related gene alterations shared between evolutionarily distinct species, such as Homo sapiens, Mus musculus, Danio rerio, and Nothobranchius furzeri. We discovered differentially expressed genes by comparing tissue-specific transcriptional profiles of mature, aged, and old-age individuals and report on six genes (per2, dec2, cirp, klf10, nfil3, and dbp) of the circadian system, which show conserved aging-related expression patterns in four organs of the species examined. Our results illustrate how the circadian system and aging might influence each other in various tissues over a long lifespan and conceptually complement previous studies tracking short-term diurnal and nocturnal gene expression oscillations.},

keywords = {aging, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{Christ2021,

title = {Hepatectomy-Induced Alterations in Hepatic Perfusion and Function - Toward Multi-Scale Computational Modeling for a Better Prediction of Post-hepatectomy Liver Function},

author = {Bruno Christ and Maximilian Collatz and Uta Dahmen and Karl-Heinz Herrmann and Sebastian Höpfl and Matthias König and Lena Lambers and Manja Marz and Daria Meyer and Nicole Radde and Jürgen R. Reichenbach and Tim Ricken and Hans-Michael Tautenhahn},

doi = {10.3389/fphys.2021.733868},

year  = {2021},

date = {2021-11-18},

urldate = {2021-11-18},

journal = {Front Physiol},

volume = {12},

pages = {733868},

abstract = {Liver resection causes marked perfusion alterations in the liver remnant both on the organ scale (vascular anatomy) and on the microscale (sinusoidal blood flow on tissue level). These changes in perfusion affect hepatic functions via direct alterations in blood supply and drainage, followed by indirect changes of biomechanical tissue properties and cellular function. Changes in blood flow impose compression, tension and shear forces on the liver tissue. These forces are perceived by mechanosensors on parenchymal and non-parenchymal cells of the liver and regulate cell-cell and cell-matrix interactions as well as cellular signaling and metabolism. These interactions are key players in tissue growth and remodeling, a prerequisite to restore tissue function after PHx. Their dysregulation is associated with metabolic impairment of the liver eventually leading to liver failure, a serious post-hepatectomy complication with high morbidity and mortality. Though certain links are known, the overall functional change after liver surgery is not understood due to complex feedback loops, non-linearities, spatial heterogeneities and different time-scales of events. Computational modeling is a unique approach to gain a better understanding of complex biomedical systems. This approach allows (i) integration of heterogeneous data and knowledge on multiple scales into a consistent view of how perfusion is related to hepatic function; (ii) testing and generating hypotheses based on predictive models, which must be validated experimentally and clinically. In the long term, computational modeling will (iii) support surgical planning by predicting surgery-induced perfusion perturbations and their functional (metabolic) consequences; and thereby (iv) allow minimizing surgical risks for the individual patient. Here, we review the alterations of hepatic perfusion, biomechanical properties and function associated with hepatectomy. Specifically, we provide an overview over the clinical problem, preoperative diagnostics, functional imaging approaches, experimental approaches in animal models, mechanoperception in the liver and impact on cellular metabolism, omics approaches with a focus on transcriptomics, data integration and uncertainty analysis, and computational modeling on multiple scales. Finally, we provide a perspective on how multi-scale computational models, which couple perfusion changes to hepatic function, could become part of clinical workflows to predict and optimize patient outcome after complex liver surgery.},

keywords = {liver, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Advances in Non-Coding RNA Sequencing},

author = {Julia Micheel and Aram Safrastyan and Damian Wollny

},

doi = {10.3390/ncrna7040070},

year  = {2021},

date = {2021-10-30},

journal = {Noncoding RNA},

volume = {7},

number = {4},

pages = {70},

abstract = {Non-coding RNAs (ncRNAs) comprise a set of abundant and functionally diverse RNA molecules. Since the discovery of the first ncRNA in the 1960s, ncRNAs have been shown to be involved in nearly all steps of the central dogma of molecular biology. In recent years, the pace of discovery of novel ncRNAs and their cellular roles has been greatly accelerated by high-throughput sequencing. Advances in sequencing technology, library preparation protocols as well as computational biology helped to greatly expand our knowledge of which ncRNAs exist throughout the kingdoms of life. Moreover, RNA sequencing revealed crucial roles of many ncRNAs in human health and disease. In this review, we discuss the most recent methodological advancements in the rapidly evolving field of high-throughput sequencing and how it has greatly expanded our understanding of ncRNA biology across a large number of different organisms.},

keywords = {ncRNAs, RNA / transcriptomics},

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{nokey,

title = {Analysis of microRNA expression reveals convergent evolution of the molecular control of diapause in annual fish},

author = {Emanuel Barth and Mario Baumgart and Luca Dolfi and Rongfeng Cui and Marco Groth and Roberto Ripa and Aurora Savino and Dario R. Valenzano and Manja Marz and Alessandro Cellerino},

doi = {10.21203/rs.3.rs-744922/v1},

year  = {2021},

date = {2021-07-01},

urldate = {2021-07-01},

journal = {Research Square},

abstract = {Background. Diapause is a key adaptation that enabled the colonization of ephemeral habitats subject to the alternation of dry and wet seasons by annual killifishes. Upon desiccation of the ponds, killifish embryos remain vital but quiescent in the clay, where they can survive months or even years. Diapause can occur at three different developmental stages, but Diapause II (DII), which occurs at mid-somitogenesis, is the primary point of developmental arrest. However, diapause is not obligatory, and some embryos can proceed to direct development, skipping one or more diapauses. The precise molecular mechanisms that regulate entry and exit from diapause are beginning to be investigated, but this knowledge is yet fragmentary.

Diapause has evolved independently several times in killifish clades from Africa and South America, enabling the identification of possible molecular determinants of diapause by comparative expression analysis. MicroRNAs are small RNAs that represent central nodes in the control of gene expression at the post-transcriptional level and are involved in many developmental processes. Here, we compare microRNA expression profiles of annual killifishes during DII with non-annual killifish in a comparable stage of morphological development.



Results. We used smallRNA-Seq to quantify microRNA expression from four annual- and four non-annual killifish species from three independent clades and from direct-developing embryos of the annual fish Nothobranchius furzeri. We analyzed the expression of broadly conserved microRNAs and microRNAs that appear to have evolved in the killifish lineage.

We found several microRNAs that showed convergent regulation in the three different clades, and for some microRNAs also a phenomenon of switch in the prevalent form between 3p and 5p or vice versa was noted. In addition, we detected a significant overlap between the microRNA regulation during diapause and aging.

Particularly interesting is the regulation of the miR-430 family. These microRNAs represent the second most expressed microRNA family in the killifish embryos, and diapause is associated with dramatic down-regulation of the prevalent -3p form and up-regulation of the -5p form. Members of the miR-430 family are contained in a large repetitive cluster whose organization is variable among teleost. Analysis of recently sequenced 45 low-coverage killifish genomes revealed that the miR-430 locus contains a lower number of copies in annual- as opposed to non-annual killifish.



Conclusions. The Evolution of diapause is reflected in the convergent evolution of microRNA regulation in killifishes. A prominent feature is a dramatic down-regulation of miR-430 expression that could be partially explained with a reduction of its copy numbers in the genome.},

keywords = {RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{VanDamme:21,

title = {Metagenomics workflow for hybrid assembly, differential coverage binning, metatranscriptomics and pathway analysis (MUFFIN)},

author = {Renaud Van Damme and Martin Hölzer and Adrian Viehweger and Bettina Müller and Erik Bongcam-Rudloff and Christian Brandt},

editor = {Mihaela Pertea},

url = {https://github.com/RVanDamme/MUFFIN},

doi = {10.1371/journal.pcbi.1008716},

year  = {2021},

date = {2021-02-09},

urldate = {2021-02-09},

journal = {PLOS Comput Biol},

volume = {17},

number = {2},

pages = {e1008716},

publisher = {Public Library of Science (PLoS)},

abstract = {Metagenomics has redefined many areas of microbiology. However, metagenome-assembled genomes (MAGs) are often fragmented, primarily when sequencing was performed with short reads. Recent long-read sequencing technologies promise to improve genome reconstruction. However, the integration of two different sequencing modalities makes downstream analyses complex. We, therefore, developed MUFFIN, a complete metagenomic workflow that uses short and long reads to produce high-quality bins and their annotations. The workflow is written by using Nextflow, a workflow orchestration software, to achieve high reproducibility and fast and straightforward use. This workflow also produces the taxonomic classification and KEGG pathways of the bins and can be further used for quantification and annotation by providing RNA-Seq data (optionally). We tested the workflow using twenty biogas reactor samples and assessed the capacity of MUFFIN to process and output relevant files needed to analyze the microbial community and their function. MUFFIN produces functional pathway predictions and, if provided de novo metatranscript annotations across the metagenomic sample and for each bin. MUFFIN is available on github under GNUv3 licence: https://github.com/RVanDamme/MUFFIN.},

keywords = {annotation, assembly, classification, DNA / genomics, metagenomics, RNA / transcriptomics, software},

pubstate = {published},

tppubtype = {article}

}

@article{Heinze:21,

title = {RUNX3 Transcript Variants Have Distinct Roles in Ovarian Carcinoma and Differently Influence Platinum Sensitivity and Angiogenesis},

author = {Karolin Heinze and Martin Hölzer and Martin Ungelenk and Melanie Gerth and Jürgen Thomale and Regine Heller and Claire R. Morden and Kirk J. McManus and Alexander S. Mosig and Matthias Dürst and Ingo B. Runnebaum and Norman Häfner},

doi = {10.3390/cancers13030476},

year  = {2021},

date = {2021-01-26},

urldate = {2021-01-26},

journal = {Cancers},

volume = {13},

number = {3},

pages = {476},

publisher = {MDPI AG},

abstract = {The prognosis of late-stage epithelial ovarian cancer (EOC) patients is affected by chemotherapy response and the malignant potential of the tumor cells. In earlier work, we identified hypermethylation of the runt-related transcription factor 3 gene (RUNX3) as a prognostic biomarker and contrary functions of transcript variants (TV1 and TV2) in A2780 and SKOV3 cells. The aim of the study was to further validate these results and to increase the knowledge about RUNX3 function in EOC. New RUNX3 overexpression models of high-grade serous ovarian cancer (HGSOC) were established and analyzed for phenotypic (IC50 determination, migration, proliferation and angiogenesis assay, DNA damage analysis) and transcriptomic consequences (NGS) of RUNX3 TV1 and TV2 overexpression. Platinum sensitivity was affected by a specific transcript variant depending on BRCA background. RUNX3 TV2 induced an increased sensitivity in BRCA1wt cells (OVCAR3), whereas TV1 increased the sensitivity and induced a G2/M arrest under treatment in BRCA1mut cells (A13-2-12). These different phenotypes relate to differences in DNA repair: homologous recombination deficient A13-2-12 cells show less γH2AX foci despite higher levels of Pt-DNA adducts. RNA-Seq analyses prove transcript variant and cell-line-specific RUNX3 effects. Pathway analyses revealed another clinically important function of RUNX3—regulation of angiogenesis. This was confirmed by thrombospondin1 analyses, HUVEC spheroid sprouting assays and proteomic profiling. Importantly, conditioned media (CM) from RUNX3 TV1 overexpressing A13-2-12 cells induced an increased HUVEC sprouting. Altogether, the presented data support the hypothesis of different functions of RUNX3 transcript variants related to the clinically relevant processes—platinum resistance and angiogenesis. },

keywords = {cancer, differential expression analysis, proteins, RNA / transcriptomics},

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{Lataretu:20,

title = {RNAflow: An Effective and Simple RNA-Seq Differential Gene Expression Pipeline Using Nextflow},

author = {Marie Lataretu and Martin Hölzer},

url = {https://github.com/hoelzer-lab/rnaflow},

doi = {10.3390/genes11121487},

year  = {2020},

date = {2020-12-10},

urldate = {2020-01-01},

journal = {Genes},

volume = {11},

number = {12},

pages = {1487},

publisher = {MDPI AG},

abstract = {RNA-Seq enables the identification and quantification of RNA molecules, often with the aim of detecting differentially expressed genes (DEGs). Although RNA-Seq evolved into a standard technique, there is no universal gold standard for these data’s computational analysis. On top of that, previous studies proved the irreproducibility of RNA-Seq studies. Here, we present a portable, scalable, and parallelizable Nextflow RNA-Seq pipeline to detect DEGs, which assures a high level of reproducibility. The pipeline automatically takes care of common pitfalls, such as ribosomal RNA removal and low abundance gene filtering. Apart from various visualizations for the DEG results, we incorporated downstream pathway analysis for common species as Homo sapiens and Mus musculus. We evaluated the DEG detection functionality while using qRT-PCR data serving as a reference and observed a very high correlation of the logarithmized gene expression fold changes.},

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

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{Hoelzer:20,

title = {A decade of de novo transcriptome assembly: Are we there yet?},

author = {Martin Hölzer},

doi = {10.1111/1755-0998.13268},

year  = {2020},

date = {2020-10-08},

urldate = {2020-01-01},

journal = {Mol Ecol Resour},

volume = {21},

number = {1},

pages = {11-13},

publisher = {Wiley},

abstract = {A decade ago, de novo transcriptome assembly evolved as a versatile and powerful approach to make evolutionary assumptions, analyse gene expression, and annotate novel transcripts, in particular, for non-model organisms lacking an appropriate reference genome. Various tools have been developed to generate a transcriptome assembly, and even more computational methods depend on the results of these tools for further downstream analyses. In this issue of Molecular Ecology Resources, Freedman et al. (Mol Ecol Resourc 2020) present a comprehensive analysis of errors in de novo transcriptome assemblies across public data sets and different assembly methods. They focus on two implicit assumptions that are often violated: First, the assembly presents an unbiased view of the transcriptome. Second, the expression estimates derived from the assembly are reasonable, albeit noisy, approximations of the relative frequency of expressed transcripts. They show that appropriate filtering can reduce this bias but can also lead to the loss of a reasonable number of highly expressed transcripts. Thus, to partly alleviate the noise in expression estimates, they propose a new normalization method called length-rescaled CPM. Remarkably, the authors found considerable distortions at the nucleotide level, which leads to an underestimation of diversity in transcriptome assemblies. The study by Freedman et al. (Mol Ecol Resourc 2020) clearly shows that we have not yet reached “high-quality” in the field of transcriptome assembly. Above all, it helps researchers be aware of these problems and filter and interpret their transcriptome assembly data appropriately and with caution.},

keywords = {assembly, review, RNA / transcriptomics},

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{Srivastava:20,

title = {Tissue-specific Gene Expression Changes Are Associated with Aging in Mice},

author = {Akash Srivastava and Emanuel Barth and Maria A. Ermolaeva and Madlen Guenther and Christiane Frahm and Manja Marz and Otto W. Witte},

doi = {10.1016/j.gpb.2020.12.001},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Genomics Proteomics Bioinformatics},

volume = {18},

number = {4},

pages = {430--442},

publisher = {Elsevier BV},

abstract = {Aging is a complex process that can be characterized by functional and cognitive decline in an individual. Aging can be assessed based on the functional capacity of vital organs and their intricate interactions with one another. Thus, the nature of aging can be described by focusing on a specific organ and an individual itself. However, to fully understand the complexity of aging, one must investigate not only a single tissue or biological process but also its complex interplay and interdependencies with other biological processes. Here, using RNA-seq, we monitored changes in the transcriptome during aging in four tissues (including brain, blood, skin and liver) in mice at 9 months, 15 months, and 24 months, with a final evaluation at the very old age of 30 months. We identified several genes and processes that were differentially regulated during aging in both tissue-dependent and tissue-independent manners. Most importantly, we found that the electron transport chain (ETC) of mitochondria was similarly affected at the transcriptome level in the four tissues during the aging process. We also identified the liver as the tissue showing the largest variety of differentially expressed genes (DEGs) over time. Lcn2 (Lipocalin-2) was found to be similarly regulated among all tissues, and its effect on longevity and survival was validated using its orthologue in Caenorhabditis elegans. Our study demonstrated that the molecular processes of aging are relatively subtle in their progress, and the aging process of every tissue depends on the tissue’s specialized function and environment. Hence, individual gene or process alone cannot be described as the key of aging in the whole organism.},

keywords = {aging, differential expression analysis, liver, RNA / transcriptomics},

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{Hoelzer:19,

title = {\textit{De novo} transcriptome assembly: A comprehensive cross-species comparison of short-read RNA-Seq assemblers},

author = {Martin Hölzer and Manja Marz},

doi = {10.1093/gigascience/giz039},

year  = {2019},

date = {2019-05-11},

urldate = {2019-01-01},

journal = {GigaScience},

volume = {8},

number = {5},

pages = {giz039},

publisher = {Oxford University Press (OUP)},

abstract = {Background: In recent years, massively parallel complementary DNA sequencing (RNA sequencing [RNA-Seq]) has emerged as a fast, cost-effective, and robust technology to study entire transcriptomes in various manners. In particular, for non-model organisms and in the absence of an appropriate reference genome, RNA-Seq is used to reconstruct the transcriptome de novo. Although the de novo transcriptome assembly of non-model organisms has been on the rise recently and new tools are frequently developing, there is still a knowledge gap about which assembly software should be used to build a comprehensive de novo assembly.



Results: Here, we present a large-scale comparative study in which 10 de novo assembly tools are applied to 9 RNA-Seq data sets spanning different kingdoms of life. Overall, we built >200 single assemblies and evaluated their performance on a combination of 20 biological-based and reference-free metrics. Our study is accompanied by a comprehensive and extensible Electronic Supplement that summarizes all data sets, assembly execution instructions, and evaluation results. Trinity, SPAdes, and Trans-ABySS, followed by Bridger and SOAPdenovo-Trans, generally outperformed the other tools compared. Moreover, we observed species-specific differences in the performance of each assembler. No tool delivered the best results for all data sets.



Conclusions: We recommend a careful choice and normalization of evaluation metrics to select the best assembling results as a critical step in the reconstruction of a comprehensive de novo transcriptome assembly.},

keywords = {assembly, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{Barth:19,

title = {Conserved aging-related signatures of senescence and inflammation in different tissues and species.},

author = {Emanuel Barth and Akash Srivastava and Milan Stojiljkovic and Christiane Frahm and Hubertus Axer and Otto W Witte and Manja Marz},

doi = {10.18632/aging.102345},

year  = {2019},

date = {2019-02-26},

urldate = {2019-02-26},

journal = {Aging},

volume = {11},

number = {19},

pages = {8556—8572},

abstract = {Increasing evidence indicates that chronic inflammation and senescence are the cause of many severe age-related diseases, with both biological processes highly upregulated during aging. However, until now, it has remained unknown whether specific inflammation- or senescence-related genes exist that are common between different species or tissues. These potential markers of aging could help to identify possible targets for therapeutic interventions of aging-associated afflictions and might also deepen our understanding of the principal mechanisms of aging. With the objective of identifying such signatures of aging and tissue-specific aging markers, we analyzed a multitude of cross-sectional RNA-Seq data from four evolutionarily distinct species (human, mouse and two fish) and four different tissues (blood, brain, liver and skin). In at least three different species and three different tissues, we identified several genes that displayed similar expression patterns that might serve as potential aging markers. Additionally, we show that genes involved in aging-related processes tend to be tighter controlled in long-lived than in average-lived individuals. These observations hint at a general genetic level that affect an individual's life span. Altogether, this descriptive study contributes to a better understanding of common aging signatures as well as tissue-specific aging patterns and supplies the basis for further investigative age-related studies.},

keywords = {aging, liver, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{Sieber:19,

title = {The landscape of the alternatively spliced transcriptome remains stable during aging across different species and tissues},

author = {Patricia Sieber and Emanuel Barth and Manja Marz},

doi = {10.1101/541417},

year  = {2019},

date = {2019-02-05},

urldate = {2019-02-05},

journal = {bioRxiv},

pages = {541417},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Aging is characterized by a decline of cellular homeostasis over time, leading to various severe disorders and death. Alternative splicing is an important regulatory level of gene expression and thus takes on a key role in the maintenance of accurate cell and tissue function. Missplicing of certain genes has already been linked to several age-associated diseases, such as progeria, Alzheimer’s disease, Parkinson’s disease and cancer. Nevertheless, many studies focus only on transcriptional variations of single genes or the expression changes of spliceosomal genes, coding for the proteins that aggregate to the spliceosomal machinery. Little is known on the general change of present and switching isoforms in different tissues over time. In this descriptive RNA-Seq study, we report differences and commonalities of isoform usage during aging among different tissues within one species and compare changes of alternative splicing among different, evolutionarily distinct species. Although we identified a multitude of differntially spliced genes among different time points, we observed little to no general changes in the transcriptomic landscape of the investigated samples. Although there is undoubtedly considerable influence of specifically spliced genes on certain age-associated processes, this work shows that alternative splicing remains stable for the majority of genes with aging.},

keywords = {aging, RNA / transcriptomics, splicing},

pubstate = {published},

tppubtype = {article}

}

@article{Lamkiewicz:18,

title = {Identification of potential microRNAs associated with Herpesvirus family based on bioinformatic analysis},

author = {Kevin Lamkiewicz and Emanuel Barth and Manja Marz and Bashar Ibrahim},

doi = {10.1101/417782},

year  = {2018},

date = {2018-11-09},

urldate = {2018-11-09},

journal = {bioRxiv},

pages = {417782},

publisher = {Cold Spring Harbor Laboratory},

abstract = {MicroRNAs (miRNAs) are known key regulators of gene expression on posttranscriptional level in many organisms encoded in mammals, plants and also several viral families. To date, no homologous gene of a virus-originated miRNA is known in other organisms. To date, only a few homologous miRNA between two different viruses are known, however, no gene of a virus-originated miRNA is known in any organism of other kingdoms. This can be attributed to the fact that classical miRNA detection approaches such as homology-based predictions fail at viruses due to their highly diverse genomes and their high mutation rate.



Here, we applied the virus-derived precursor miRNA (pre-miRNA) prediction pipeline ViMiFi, which combines information about sequence conservation and machine learning-based approaches, on Human Herpesvirus 7 (HHV7) and Epstein-Barr virus (EBV). ViMiFi was able to predict 61 candidates in EBV, which has 25 known pre-miRNAs. From these 25, ViMiFi identified 20. It was further able to predict 18 candidates in the HHV7 genome, in which no miRNA had been described yet. We also studied the undescribed candidates of both viruses for potential functions and found similarities with human snRNAs and miRNAs from mammals and plants.},

keywords = {machine learning, ncRNAs, RNA / transcriptomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Gerst:18,

title = {PCAGO: An interactive web service to analyze RNA-Seq data with principal component analysis},

author = {Ruman Gerst and Martin Hölzer},

url = {https://github.com/rnajena/pcago-unified},

doi = {10.1101/433078},

year  = {2018},

date = {2018-10-03},

urldate = {2018-10-03},

journal = {bioRxiv},

pages = {433078},

publisher = {Cold Spring Harbor Laboratory},

abstract = {The initial characterization and clustering of biological samples is a critical step in the analysis of any transcriptomics study. In many studies, principal component analysis (PCA) is the clustering algorithm of choice to predict the relationship of samples or cells based solely on differential gene expression. In addition to the pure quality evaluation of the data, a PCA can also provide initial insights into the biological background of an experiment and help researchers to interpret the data and design the subsequent computational steps accordingly. However, to avoid misleading clusterings and interpretations, an appropriate selection of the underlying gene sets to build the PCA and the choice of the most fitting principal components for the visualization are crucial parts. Here, we present PCAGO, an easy-to-use and interactive tool to analyze gene quantification data derived from RNA sequencing experiments with PCA. The tool includes features such as read-count normalization, filtering of read counts by gene annotation, and various visualization options. In addition, PCAGO helps to select appropriate parameters such as the number of genes and principal components to create meaningful visualizations.},

keywords = {annotation, differential expression analysis, RNA / transcriptomics, software},

pubstate = {published},

tppubtype = {article}

}

@article{Fricke:18,

title = {Global importance of RNA secondary structures in protein coding sequences},

author = {Markus Fricke and Ruman Gerst and Bashar Ibrahim and Michael Niepmann and Manja Marz},

doi = {10.1093/bioinformatics/bty678},

year  = {2018},

date = {2018-08-07},

urldate = {2018-08-07},

journal = {Bioinformatics},

volume = {35},

number = {4},

pages = {579–583},

abstract = {The protein-coding sequences of messenger RNAs are the linear template for translation of the gene sequence into protein. Nevertheless, the RNA can also form secondary structures by intramolecular base-pairing. We show that the nucleotide distribution within codons is biased in all taxa of life on a global scale. Thereby, RNA secondary structures that require base-pairing between the position 1 of a codon with the position 1 of an opposing codon (here named RNA secondary structure class c1) are under-represented. We conclude that this bias may result from the co-evolution of codon sequence and mRNA secondary structure, suggesting that RNA secondary structures are generally important in protein coding regions of mRNAs. The above result also implies that codon position 2 has a smaller influence on the amino acid choice than codon position 1.},

keywords = {evolution, RNA / transcriptomics, RNA structure, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Hillmann:18,

title = {Multiple Roots of Fruiting Body Formation in Amoebozoa},

author = {Falk Hillmann and Gillian Forbes and Silvia Novohradská and Iuliia Ferling and Konstantin Riege and Marco Groth and Martin Westermann and Manja Marz and Thomas Spaller and Thomas Winckler and Pauline Schaap and Gernot Glöckner},

doi = {10.1093/gbe/evy011},

year  = {2018},

date = {2018-01-25},

urldate = {2018-01-25},

journal = {Genome Biol Evol},

volume = {10},

pages = {591--606},

abstract = {Establishment of multicellularity represents a major transition in eukaryote evolution. A subgroup of Amoebozoa, the dictyosteliids, has evolved a relatively simple aggregative multicellular stage resulting in a fruiting body supported by a stalk. Protosteloid amoeba, which are scattered throughout the amoebozoan tree, differ by producing only one or few single stalked spores. Thus, one obvious difference in the developmental cycle of protosteliids and dictyosteliids seems to be the establishment of multicellularity. To separate spore development from multicellular interactions, we compared the genome and transcriptome of a Protostelium species (Protostelium aurantium var. fungivorum) with those of social and solitary members of the Amoebozoa. During fruiting body formation nearly 4,000 genes, corresponding to specific pathways required for differentiation processes, are upregulated. A comparison with genes involved in the development of dictyosteliids revealed conservation of >500 genes, but most of them are also present in Acanthamoeba castellanii for which fruiting bodies have not been documented. Moreover, expression regulation of those genes differs between P. aurantium and Dictyostelium discoideum. Within Amoebozoa differentiation to fruiting bodies is common, but our current genome analysis suggests that protosteliids and dictyosteliids used different routes to achieve this. Most remarkable is both the large repertoire and diversity between species in genes that mediate environmental sensing and signal processing. This likely reflects an immense adaptability of the single cell stage to varying environmental conditions. We surmise that this signaling repertoire provided sufficient building blocks to accommodate the relatively simple demands for cell-cell communication in the early multicellular forms.},

keywords = {evolution, RNA / transcriptomics},

pubstate = {published},

tppubtype = {article}

}

@article{Madhugiri:18,

title = {Structural and functional conservation of cis-acting RNA elements in coronavirus 5'-terminal genome regions},

author = {Ramakanth Madhugiri and Nadja Karl and Daniel Petersen and Kevin Lamkiewicz and Markus Fricke and Ulrike Wend and Robina Scheuer and Manja Marz and John Ziebuhr},

doi = {10.1016/j.virol.2017.11.025},

year  = {2017},

date = {2017-12-06},

urldate = {2017-12-06},

journal = {Virology},

volume = {517},

pages = {44--55},

abstract = {Structure predictions suggest a partial conservation of RNA structure elements in coronavirus terminal genome regions. Here, we determined the structures of stem-loops (SL) 1 and 2 of two alphacoronaviruses, human coronavirus (HCoV) 229E and NL63, by RNA structure probing and studied the functional relevance of these putative cis-acting elements. HCoV-229E SL1 and SL2 mutants generated by reverse genetics were used to study the effects on viral replication of single-nucleotide substitutions predicted to destabilize the SL1 and SL2 structures. The data provide conclusive evidence for the critical role of SL1 and SL2 in HCoV-229E replication and, in some cases, revealed parallels with previously characterized betacoronavirus SL1 and SL2 elements. Also, we were able to rescue viable HCoV-229E mutants carrying replacements of SL2 with equivalent betacoronavirus structural elements. The data obtained in this study reveal a remarkable degree of structural and functional conservation of 5'-terminal RNA structural elements across coronavirus genus boundaries.},

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

pubstate = {published},

tppubtype = {article}

}