Publications

@article{nokey_97,

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

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

doi = {10.1093/nar/gkaf1224},

year  = {2025},

date = {2025-12-17},

journal = {Nucleic Acids Research},

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

keywords = {database, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_67,

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

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

doi = {10.1101/2025.01.30.635689},

year  = {2025},

date = {2025-12-15},

urldate = {2025-02-01},

journal = {bioRxiv},

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

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_88,

title = {Nanopore sequencing-derived methylation biomarker prediction for methylation-specific PCR in patients with head and neck squamous cell carcinoma},

author = {Daria Meyer and Anne Hennig and Anna-Bawany Hums and Orlando Guntinas-Lichius and Martina Schmitz and Manja Marz },

doi = {10.1186/s13148-025-01960-7},

year  = {2025},

date = {2025-09-13},

journal = {Clinical Epigenetics},

volume = {17},

abstract = {DNA methylation of CpG islands is altered in cancer cells. Hypermethylation of single CpG islands in the promoter regions of tumor-suppressor genes occurs already in the early stages of cancer. These methylation changes are cancer-type specific and therefore can serve as early cancer biomarker. Identifying good and reliable biomarkers is crucial for the development of diagnostic tests and their application in clinical practice and remains the most significant challenge to date.},

keywords = {cancer, nanopore, nucleic acid modifications},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_82,

title = {Accurately assembling nanopore sequencing data of highly pathogenic bacteria},

author = {Christine Thomas and Hanka Brangsch and Valentina Galeone and Martin Hölzer and Manja Marz and Jörg Linde},

doi = {10.1186/s12864-025-11793-6},

year  = {2025},

date = {2025-08-28},

journal = {BMC Genomics},

volume = {26},

abstract = {Background: Bacterial genome exploration and outbreak analysis rely heavily on robust whole-genome sequencing and bioinformatics analysis. Widely-used genomic methods, such as genotyping and detection of genetic markers demand high sequencing accuracy and precise genome assembly for reliable results.

Methods: To assess the utility of nanopore sequencing for genotyping highly pathogenic bacteria with low mutation rates, we sequenced six reference strains using Oxford Nanopore Technologies (ONT) R10.4.1 chemistry and Illumina and evaluated different assembly strategies. The publicly available RefSeq assemblies were chosen as the ground truth. Publicly available sequencing data from key foodborne and public-health-related bacterial pathogens were examined to provide a broader context for the analysis.

Results: While for Bacillus (Ba.) anthracis an almost perfect assembly was achieved, results varied for other species. For Brucella (Br.) spp., the final assemblies comprised five to 46 different nucleotides in comparison to Sanger-sequenced references. For some key foodborne and public-health-related bacterial pathogens (Klebsiella (K.) variicola, Listeria spp., Mycobacterium (M.) tuberculosis, Staphylococcus (Sta.) aureus, and Streptococcus (Str.) pyogenes) perfect genomes were obtained. Enhanced basecalling models have generally improved assembly accuracy, however, for certain species such as Br. abortus, older models have produced higher accuracy. While long-read polishing mainly improves assembly quality with only one round needed, our results indicate that this process may also degrade assembly quality. Overall, 81% of the observed errors in ONT assemblies were located within coding sequences (CDS). Furthermore, we found that methylation caused 6.5% of the errors, and the bacterial methylation-aware medaka polishing model reduced the number of errors linked to methylation. Core-genome Multilocus Sequence Typing (cgMLST) analysis revealed allele differences in Ba. anthracis, Br. abortus, and Francisella (F.) tularensis for some assemblers, although with fewer than five allele differences. In the case of Br. melitensis, some assemblies included five allele differences, whereas for Br. suis the correct cgMLST alleles were observed.

Conclusions: Assembling nanopore data from pathogenic bacteria vary in quality across different species and methods. However, errors persist in the final assemblies, including within cgMLST loci, influencing the reliability of outbreak predictions. Nevertheless, specific combinations of existing tools can generate perfect genome assemblies from bacterial ONT sequencing data for outbreak analysis without short-read polishing.},

keywords = {assembly, bacteria, DNA / genomics, nanopore},

pubstate = {published},

tppubtype = {article}

}

@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_78,

title = {Identification and functional genomic analyses of Bartonella isolates from honey bees, and reassessment of the taxonomy of the genus Bartonella},

author = {Juliana Botero and Nikolas Basler and Margo Cnockaert and Charlotte Peeters and Maria Schreiber and Manja Marz and Dirk C. {de Graaf} and Jelle Matthijnssens and Peter Vandamme},

doi = {10.1016/j.syapm.2025.126625},

isbn = {0723-2020},

year  = {2025},

date = {2025-06-06},

journal = {Systematic and Applied Microbiology},

volume = {48},

abstract = {We used matrix-assisted laser desorption/ionization time-of-flight mass spectrometry and whole-genome sequence analyses to identify 90 Bartonella isolates from honey bee gut samples in Belgium. While the identification of 62 isolates as Bartonella apihabitans and three as Bartonella choladocola was straightforward, the identification of 25 Bartonella apis-like isolates was challenging. A taxonomic and functional analysis of four B. apis-like genomes and of publicly available B. apis genomes demonstrated that neither OrthoANIu and digital DNA-DNA hybridization analyses, nor functional annotation supported a clear separation of B. apis and B. apis-like genomes. Different phylogenomic analyses showed that B. apis and B. apis-like strains formed a monophyletic clade with an inconsistent internal structure. We therefore considered the remaining 25 isolates identified as B. apis. We subsequently re-addressed an earlier phylogenetic and functional divergence between three major clades of Bartonella species which differed not only in phylogenomic position and ecology, but also in genome size and genomic percentage G + C content, and in many metabolic capabilities. We propose to reclassify the single species of the Bartonella tamiae clade into the novel genus Attibartonella gen. nov., with Attibartonella tamiae comb. nov. as the type species. Similarly, we propose to reclassify species of the honey bee-associated Bartonella clade into the novel genus Ditibartonella gen. nov., with Ditibartonella apis comb. nov. as the type species. The phylogenomic analyses of publicly available genome and metagenome sequences revealed additional Ditibartonella species in honey bee samples, highlighted an evolutionary adaptation of Ditibartonella bacteria to bee hosts and suggested shared transmission routes.},

keywords = {bacteria, classification, DNA / genomics, phylogenetics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_77,

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

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

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

doi = {10.1101/2025.05.22.655560},

year  = {2025},

date = {2025-05-27},

journal = {bioRxiv},

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

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_76,

title = {Immunity and bacterial recruitment in plant leaves are parallel processes that together shape sensitivity to temperature stress},

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

doi = {10.1101/2024.06.10.598336},

year  = {2025},

date = {2025-04-25},

journal = {bioRxiv},

abstract = {Rising global temperatures necessitate developing resilient crops with better adaptability to changing climates. Under elevated temperatures, plant immunity is downregulated, increasing 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. In this study, we compared two Arabidopsis thaliana genotypes that feature divergent strategies for recruitment of commensal bacteria from natural soil. NG2, an A. thaliana ecotype we collected from Jena, Germany, was grown in its native soil and compared to CLLF, a genotype that recruits higher bacterial loads and higher bacterial diversity but without any dysbiotic phenotype. CLLF hyperaccumulates salicylic acid (SA) and jasmonates, has constitutively upregulated innate defenses, and shows increased resistance to necrotrophic fungal and hemi-biotrophic bacterial pathogens, indicating that pathogen immunity and non-pathogen recruitment function in parallel. Some of its leaf bacteria can utlize SA as a carbon source, suggesting that immunity and recruitment may even be linked by chemical hormones. CLLF exhibits high tolerance to heat stress in comparison to the NG2, with SA-associated defense processes remaining active under heat. Synthetic community (SynCom) experiments revealed that when the taxonomic diversity of bacteria available to CLLF is artificially reduced, resilience to heat stress is compromised, leading to dysbiosis. However, this dysbiosis does not occur in CLLF with a full SynCom or in the NG2 with any SynCom. These findings suggest that the downregulation of defenses in response to heat may contribute to the avoidance of dysbiosis caused by certain leaf bacteria, while full bacteriome taxonomic diversity can help maintain balance.Competing Interest StatementThe authors have declared no competing interest.},

keywords = {bacteria, evolution, fungi, metagenomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_89,

title = {AssayBLAST: A Bioinformatic Tool for In Silico Analysis of Molecular Multiparameter Assays},

author = {Maximilian Collatz and Sascha D. Braun and Martin Reinicke and Elke Müller and Stefan Monecke and Ralf Ehricht},

doi = {10.3390/applbiosci4020018},

year  = {2025},

date = {2025-04-01},

journal = {Applied Biosciences},

volume = {4},

abstract = {Accurate primer and probe design is essential for molecular applications, including PCR, qPCR, and molecular multiparameter assays like microarrays. The novel software tool AssayBLAST addresses this need by simulating interactions between oligonucleotides and target sequences. AssayBLAST handles large sets of primer and probe sequences simultaneously and supports comprehensive assay designs by allowing users to identify off-target binding, calculate melting temperatures, and ensure strand specificity, a critical but often overlooked aspect. AssayBLAST performs two optimized BLAST-based searches for each primer or probe sequence, checking the forward and reverse strands for off-target interactions and strand-specific binding accuracy. The results are compiled into a mapping table containing binding sites, mismatches, and strand orientation, allowing users to validate large sets of oligonucleotides across predefined custom databases for a complete and optimal theoretical assay design. AssayBLAST was evaluated against experimental Staphylococcus aureus microarray data, achieving 97.5% accuracy in predicting probe–target hybridization outcomes. This high accuracy demonstrates the method’s effectiveness in reliably using BLAST hits and mismatch counts to predict microarray results. AssayBLAST provides a reliable, scalable solution for in silico primer and probe validation, effectively supporting large-scale assay designs and optimizations. Its accurate prediction of hybridization outcomes demonstrates its utility in enhancing the efficiency and reliability of molecular assays.},

keywords = {alignment, DNA / genomics, software},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_95,

title = {Multiplex Real-Time Polymerase Chain Reaction and Recombinase Polymerase Amplification: Methods for Quick and Cost-Effective Detection of Vancomycin-Resistant Enterococci (VRE)},

author = {Ibukun Elizabeth Osadare and Abdinasir Abdilahi and Martin Reinicke and Celia Diezel and Maximilian Collatz and Annett Reissig and Stefan Monecke and Ralf Ehricht},

doi = {10.3390/antibiotics14030295},

year  = {2025},

date = {2025-03-12},

journal = {Antibiotics},

volume = {14},

abstract = {Background/Objectives: Vancomycin-resistant enterococci (VRE) are one of the leading causes of antibiotic-resistant infections in the hospital setting worldwide, and this has become a major issue, because most patients infected with this strain are difficult to treat. Multiplex real-time polymerase chain reaction (RT PCR) is an advantageous technique that can amplify multiple targets in a single reaction, and can be used to quickly detect specific targets in VRE within two hours, starting from suspected colonies of bacterial cultures, without sample preparation. Methods: In this study, we selected the glycopeptide/vancomycin resistance genes that are most common in clinical settings, vanA and vanB, in combination with the species markers ddl_faecium and ddl_faecalis for the most common VRE species—Enterococcus faecium and Enterococcus faecalis. Results: DNA from forty clinical VRE strains was prepared using a fast and economic heat lysis method, and a multiplex real-time PCR assay was optimized and carried out subsequently. The results were in concordance with the results from recombinase polymerase amplification (RPA) of the same VRE samples. Conclusions: Multiplex RT PCR and RPA for VRE detection proffers a second method for the confirmation of vancomycin resistance, and it can be developed as a fast screening assay for patients before admission into high-risk settings.},

keywords = {bacteria, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_73,

title = {diffONT: predicting methylation-specific PCR biomarkers based on nanopore sequencing data for clinical application},

author = {Daria Meyer and Emanuel Barth and Laura Wiehle and Manja Marz},

doi = {10.1101/2025.02.17.638597},

year  = {2025},

date = {2025-02-20},

urldate = {2025-02-20},

journal = {bioRxiv},

abstract = {DNA methylation is known to act as biomarker applicable for clinical diagnostics, especially in cancer detection. Methylation-specific PCR (MSP) is a widely used approach to screen patient samples fast and efficiently for differential methylation. During MSP, methylated regions are selectively amplified with specific primers. With nanopore sequencing, knowledge about DNA methylation is generated during direct DNA sequencing, without any need for pretreatment of the DNA. Multiple methods, mainly developed for whole-genome bisulfite sequencing (WGBS) data, exist to predict differentially methylated regions (DMRs) in the genome. However, the predicted DMRs are often very large, and not sufficiently discriminating to generate meaningful results in MSP creating a gap between theoretical cancer marker research and practical application, as no tool currently provides methylation difference predictions tailored for PCR-based diagnostics. Here we present diffONT, which predicts differentially methylated primer regions, directly suitable for MSP primer design and thus allowing a direct translation into practical approaches. diffONT takes into account (i) the specific length of primer and amplicon regions, (ii) the fact that one condition should be unmethylated, and (iii) a minimal required amount of differentially methylated cytosines within the primer regions. Based on two nanopore sequencing data sets we compared the results of diffONT to metilene, DSS and pycoMeth. We show that the regions predicted by diffONT are more specific towards hypermethylated regions and more usable for MSP. diffONT accelerates the design of methylation-specific diagnostic assays, bridging the gap between theoretical research and clinical application.Competing Interest Statement. The authors have declared no competing interest.},

keywords = {cancer, DNA / genomics, nanopore, nucleic acid modifications, software},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_80,

title = {Exploring the genomic landscape of Chlamydiifrater species: novel features include multiple truncated major outer membrane proteins, unique genes and chlamydial plasticity zone orthologs},

author = {Martin Hölzer and Charlotte Reuschel and Fabien Vorimore and Karine Laroucau and Konrad Sachse},

doi = {10.1099/acmi.0.000936.v3},

year  = {2025},

date = {2025-02-03},

urldate = {2025-02-03},

journal = {Access Microbiology},

volume = {7},

abstract = {Recently discovered obligate intracellular bacteria belonging to the genus Chlamydiifrater with the species of Chlamydiifrater phoenicopteri and Chlamydiifrater volucris were studied to explore the composition of their genomes and their relatedness to Chlamydia, the other genus of the family Chlamydiaceae. We investigated 4 isolates of Cf. volucris, 2 of them newly sequenced, and one of Cf. phoenicopteri alongside 12 representatives of the Chlamydia species. Our study uncovers previously unrecognized genomic structures within Chlamydiifrater using a hybrid sequencing approach and advanced annotation pipelines, providing insights into species-specific adaptations and evolutionary dynamics. The integration of long-read sequencing data, comprehensive re-annotation strategies and pan-genomics enabled the localization of the unique plasticity zone and the identification of novel gene clusters in Chlamydiifrater strains, which improves our understanding of chlamydial genome architecture and plasticity in the family Chlamydiaceae. Our analysis revealed that 761 CDS (~80%) are shared among members of both genera. We further identified 158 unique genes of Chlamydiifrater species, but their annotation remains challenging because of the absence of functionally annotated orthologs in public databases. A full-length ompA gene encoding the major outer membrane porin was seen in all Chlamydiifrater strains. We also describe the localization and structure of multiple truncated CDS of ompA family members, representing one of this study’s most interesting findings. While genome analysis of Chlamydiifrater spp. confirmed numerous common features shared with representatives of the genus Chlamydia, many unique genomic elements were identified that underpin the distinct phenotype and separate genetic position of these new microorganisms.},

keywords = {annotation, bacteria, DNA / genomics, evolution, pregnancy},

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,

title = {Unlocking the Full Potential of Nanopore Sequencing: Tips, Tricks, and Advanced Data Analysis Techniques},

author = {Daria Meyer and Winfried Göttsch and Jannes Spangenberg and Bettina Stieber and Sebastian Krautwurst and Martin Hoelzer and Christian Brandt and Joerg Linde and Christian {Höner zu Siederdissen} and Akash Srivastava and Milena Zarkovic and Damian Wollny and Manja Marz},

doi = {10.1101/2023.12.06.570356},

year  = {2025},

date = {2025-01-27},

urldate = {2025-01-27},

journal = {bioRxiv},

abstract = {Nucleic acid sequencing is the process of identifying the sequence of DNA or RNA, with DNA used for genomes and RNA for transcriptomes. Deciphering this information has the potential to greatly advance our understanding of genomic features and cellular functions. In comparison to other available sequencing methods, nanopore sequencing stands out due to its unique advantages of processing long nucleic acid strands in real time, within a small portable device, enabling the rapid analysis of samples in diverse settings. Evolving over the past decade, nanopore sequencing remains in a state of ongoing development and refinement, resulting in persistent challenges in protocols and technology. This article employs an interdisciplinary approach, evaluating experimental and computational methods to address critical gaps in our understanding in order to maximize the information gain from this advancing technology. Here we present both overview and analysis of all aspects of nanopore sequencing by providing statistically supported insights. Thus, we aim to provide fresh perspectives on nanopore sequencing and give comprehensive guidelines for the diverse challenges that frequently impede optimal experimental outcomes.},

keywords = {differential expression analysis, DNA / genomics, nanopore, nucleic acid modifications},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_75,

title = {\textit{Trichosporon asahii}: A Potential Growth Promoter for \textit{C. gallinacea}? Implications for Chlamydial Infections and Cell Culture},

author = {Erika Ornelas-Eusebio and Fabien Vorimore and Rachid Aaziz and Maria-Lucia Mandola and Francesca Rizzo and Monica Marchino and Chiara Nogarol and Veronica Risco-Castillo and Gina Zanella and Christiane Schnee and Konrad Sachse and Karine Laroucau},

doi = {10.3390/microorganisms13020288},

year  = {2025},

date = {2025-01-27},

urldate = {2025-01-27},

journal = {Microorganisms},

volume = {13},

number = {2},

abstract = {The cultivation of Chlamydia gallinacea, a recently identified species, is challenging due to the lack of an optimized protocol. In this study, several infection protocols were tested, including different cell lines, incubation temperatures, centrifugation methods and culture media. However, none were successful in field samples. The only exception was a chance co-culture with Trichosporon asahii, a microorganism commonly found in the chicken gut. This suggests that current in vitro methods may not be optimized for this species and that host-associated microorganisms may influence the in vivo growth of C. gallinacea, which is typically found in the chicken gut. These findings raise new questions and highlight the need for further investigation of microbial interactions within the host, particularly to understand their role in the proliferation of chlamydial species.},

keywords = {bacteria, fungi, metagenomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_67,

title = {Rfam 15: RNA families database in 2025},

author = {Nancy Ontiveros-Palacios and Emma Cooke and Eric P. Nawrocki and Sandra Triebel and Manja Marz and Elena Rivas and Sam Griffiths-Jones and Anton I. Petrov and Alex Bateman and Blake Sweeney},

doi = {10.1093/nar/gkae1023},

year  = {2025},

date = {2025-01-06},

urldate = {2024-11-11},

journal = {Nucleic Acids Research},

abstract = {The Rfam database, a widely used repository of non-coding RNA families, has undergone significant updates in release 15.0. This paper introduces major improvements, including the expansion of Rfamseq to 26 106 genomes, a 76% increase, incorporating the latest UniProt reference proteomes and additional viral genomes. Sixty-five RNA families were enhanced using experimentally determined 3D structures, improving the accuracy of consensus secondary structures and annotations. R-scape covariation analysis was used to refine structural predictions in 26 families. Gene Ontology (GO) and Sequence Ontology annotations were comprehensively updated, increasing GO term coverage to 75% of families. The release adds 14 new Hepatitis C Virus RNA families and completes microRNA family synchronization with miRBase, resulting in 1603 microRNA families. New data types, including FULL alignments, have been implemented. Integration with APICURON for improved curator attribution and multiple website enhancements further improve user experience. These updates significantly expand Rfam’s coverage and improve annotation quality, reinforcing its critical role in RNA research, genome annotation and the development of machine learning models. Rfam is freely available at https://rfam.org.},

keywords = {database, ncRNAs, RNA structure, RNA-RNA interactions},

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,

title = {Engineering extracellular vesicles to transiently permeabilize the blood–brain barrier},

author = {Francesca Tomatis and Susana Rosa and Susana Simões and Marta Barão and Carlos Jesus and João Novo and Emanuel Barth and Manja Marz and Lino Ferreira},

doi = {10.1186/s12951-024-03019-w},

year  = {2024},

date = {2024-12-02},

journal = {Journal of Nanobiotechnology},

volume = {22},

abstract = {Background

Drug delivery to the brain is challenging due to the restrict permeability of the blood brain barrier (BBB). Recent studies indicate that BBB permeability increases over time during physiological aging likely due to factors (including extracellular vesicles (EVs)) that exist in the bloodstream. Therefore, inspiration can be taken from aging to develop new strategies for the transient opening of the BBB for drug delivery to the brain.

Results

Here, we evaluated the impact of small EVs (sEVs) enriched with microRNAs (miRNAs) overexpressed during aging, with the capacity to interfere transiently with the BBB. Initially, we investigated whether the miRNAs were overexpressed in sEVs collected from plasma of aged individuals. Next, we evaluated the opening properties of the miRNA-enriched sEVs in a static or dynamic (under flow) human in vitro BBB model. Our results showed that miR-383-3p-enriched sEVs significantly increased BBB permeability in a reversible manner by decreasing the expression of claudin 5, an important tight junction protein of brain endothelial cells (BECs) of the BBB, mediated in part by the knockdown of activating transcription factor 4 (ATF4).

Conclusions

Our findings suggest that engineered sEVs have potential as a strategy for the temporary BBB opening, making it easier for drugs to reach the brain when injected into the bloodstream.},

keywords = {aging, extracellular vesicles, ncRNAs},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_66,

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

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

doi = {10.1093/ve/veae099},

issn = {2057-1577},

year  = {2024},

date = {2024-11-23},

journal = {Virus Evolution},

volume = {10},

number = {1},

pages = {veae099},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_66,

title = {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 = {Algal Growth and Morphogenesis-Promoting Factors Released by Cold-Adapted Bacteria Contribute to the Resilience and Morphogenesis of the Seaweed Ulva (Chlorophyta) in Antarctica (Potter Cove)},

author = {Fatemeh Ghaderiardakani and Johann F. Ulrich and Emanuel Barth and Maria Liliana Quartino and Thomas Wichard},

doi = {10.1007/s00344-024-11507-4},

year  = {2024},

date = {2024-10-14},

journal = {Journal of Plant Growth Regulation},

abstract = {Macroalgae are found in a variety of marine vegetation ecosystems around the world, contributing significantly to global net primary production. In particular, the sea lettuce species, i.e., members of the genus Ulva (Chlorophyta), are located in many ecological niches and are characterized by excellent adaptability to environmental changes but depend on essential associated bacteria, which release algal growth and morphogenesis-promoting-factors (AGMPFs). Our work investigated the hypothesis that bacteria need to be stress-adapted to provide sufficient amounts of AGMPFs for the growth and morphogenesis of Ulva throughout its life cycle, even under severe environmental conditions. Our study thus aimed to understand which bacteria contribute to overcoming a variety of stressors in polar regions. Green macroalgae were collected from Potter Cove, King George Island (Isla 25 de Mayo), Antarctica, to study the associated microbiome and, subsequently, to identify AGMPFs releasing bacteria. Therefore, microbiome analysis was combined with morphogenetic bioassays and chemical analysis, identifying bacteria essential for algal growth under Antarctic conditions. Hereby, axenic cultures of Ulva compressa (cultivar Ulva mutabilis, Ria Formosa, Portugal), previously developed as a model system for bacteria-induced algal growth and morphogenesis, were inoculated with freshly isolated and cultivable Antarctic bacteria to determine their morphogenetic activity. The exploratory microbiome investigation identified numerous cold-adapted AGMPF-producing bacteria. Unlike the temperate-adapted bacterial strains originally isolated from the U. mutabilis holobiont, the cold-adapted isolates Maribacter sp. BPC-D8 and Sulfitobacter sp. BPC-C4 released sufficient amounts of AGMPFs, such as thallusin and still unknown compounds, necessary for the morphogenesis of the Antarctic Ulva even at 2 °C. Our results illustrate the role of chemical mediators provided by bacteria in cross-kingdom interactions under cold conditions within aquatic systems. The newly isolated bacteria will enable further functional studies to understand the resilience of the holobiont Ulva and might be applied in algal aquaculture even under adverse conditions. The study highlights the importance of eco-physiological assays in microbiome analysis.},

keywords = {algae, bacteria},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_94,

title = {Fast and Economic Microarray-Based Detection of Species-, Resistance-, and Virulence-Associated Genes in Clinical Strains of Vancomycin-Resistant Enterococci (VRE)},

author = {Ibukun Elizabeth Osadare and Stefan Monecke and Abdinasir Abdilahi and Elke Müller and Maximilian Collatz and Sascha Braun and Annett Reissig and Wulf Schneider-Brachert and Bärbel Kieninger and Anja Eichner and Anca Rath and Jürgen Fritsch and Dominik Gary and Katrin Frankenfeld and Thomas Wellhöfer and Ralf Ehricht},

doi = {10.3390/s24196476},

year  = {2024},

date = {2024-10-08},

journal = {Sensors},

volume = {24},

abstract = {Today, there is a continuous worldwide battle against antimicrobial resistance (AMR) and that includes vancomycin-resistant enterococci (VRE). Methods that can adequately and quickly detect transmission chains in outbreaks are needed to trace and manage this problem fast and cost-effectively. In this study, DNA-microarray-based technology was developed for this purpose. It commenced with the bioinformatic design of specific oligonucleotide sequences to obtain amplification primers and hybridization probes. Microarrays were manufactured using these synthesized oligonucleotides. A highly parallel and stringent labeling and hybridization protocol was developed and employed using isolated genomic DNA from previously sequenced (referenced) clinical VRE strains for optimal sensitivity and specificity. Microarray results showed the detection of virulence, resistance, and species-specific genes in the VRE strains. Theoretical predictions of the microarray results were also derived from the sequences of the same VRE strain and were compared to array results while optimizing protocols until the microarray result and theoretical predictions were a match. The study concludes that DNA microarray technology can be used to quickly, accurately, and economically detect specifically and massively parallel target genes in enterococci.},

keywords = {bacteria, classification, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_74,

title = {Nanopore sequencing enables novel detection of deuterium incorporation in DNA},

author = {Christian {Höner zu Siederdissen} and Jannes Spangenberg and Kevin Bisdorf and Sebastian Krautwurst and Akash Srivastava and Manja Marz and Martin Taubert},

doi = {10.1016/j.csbj.2024.09.027},

year  = {2024},

date = {2024-10-03},

urldate = {2024-10-03},

journal = {Computational and Structural Biotechnology Journal},

volume = {23},

abstract = {Identifying active microbes is crucial to understand their role in ecosystem functions. Metabolic labeling with heavy, non-radioactive isotopes, i.e., stable isotope probing (SIP), can track active microbes by detecting heavy isotope incorporation in biomolecules such as DNA. However, the detection of heavy isotope-labeled nucleotides directly during sequencing has, to date, not been achieved. In this study, Oxford nanopore sequencing was utilized to detect heavy isotopes incorporation in DNA molecules. Two isotopes widely used in SIP experiments were employed to label a bacterial isolate: deuterium (D, as D2O) and carbon-13 (13C, as glucose). We hypothesize that labeled DNA is distinguishable from unlabeled DNA by changes in the nanopore signal. To verify this distinction, we employed a Bayesian classifier trained on signal distributions of short oligonucleotides (k-mers) from labeled and unlabeled sequencing reads. Our results show a clear distinction between D-labeled and unlabeled reads, based on changes in median and median absolute deviation (MAD) of the nanopore signals for different k-mers. In contrast, 13C-labeled DNA cannot be distinguished from unlabeled DNA. For D, the model employed correctly predicted more than 85% of the reads. Even when metabolic labeling was conducted with only 30% D2O, 80% of the obtained reads were correctly classified with a 5% false discovery rate. Our work demonstrates the feasibility of direct detection of deuterium incorporation in DNA molecules during Oxford nanopore sequencing. This finding represents a first step in establishing the combined use of nanopore sequencing and SIP for tracking active organisms in microbial ecology.},

keywords = {bacteria, DNA / genomics, machine learning, metagenomics, nanopore, nucleic acid modifications},

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_62,

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

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

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

year  = {2024},

date = {2024-07-02},

urldate = {2024-07-02},

journal = {Scientific Reports},

volume = {14},

issue = {1},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_63,

title = {RIBAP: a comprehensive bacterial core genome annotation pipeline for pangenome calculation beyond the species level},

author = {Kevin Lamkiewicz and Lisa-Marie Barf and Konrad Sachse and Martin Hölzer},

doi = {10.1186/s13059-024-03312-9},

year  = {2024},

date = {2024-07-01},

journal = {Genome Biology},

volume = {25},

issue = {1},

abstract = {Microbial pangenome analysis identifies present or absent genes in prokaryotic genomes. However, current tools are limited when analyzing species with higher sequence diversity or higher taxonomic orders such as genera or families. The Roary ILP Bacterial core Annotation Pipeline (RIBAP) uses an integer linear programming approach to refine gene clusters predicted by Roary for identifying core genes. RIBAP successfully handles the complexity and diversity of Chlamydia, Klebsiella, Brucella, and Enterococcus genomes, outperforming other established and recent pangenome tools for identifying all-encompassing core genes at the genus level. RIBAP is a freely available Nextflow pipeline at github.com/hoelzer-lab/ribap and zenodo.org/doi/10.5281/zenodo.10890871.},

keywords = {annotation, bacteria, DNA / genomics, evolution, software},

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_93,

title = {ConsensusPrime—A Bioinformatic Pipeline for Efficient Consensus Primer Design—Detection of Various Resistance and Virulence Factors in MRSA—A Case Study},

author = {Maximilian Collatz and Martin Reinicke and Celia Diezel and Sascha D. Braun and Stefan Monecke and Annett Reissig and Ralf Ehricht},

doi = {10.3390/biomedinformatics4020068},

year  = {2024},

date = {2024-05-10},

urldate = {2024-05-10},

journal = {BioMedInformatics},

volume = {4},

abstract = {Background: The effectiveness and reliability of diagnostic tests that detect DNA sequences largely hinge on the quality of the used primers and probes. This importance is especially evident when considering the specific sample being analyzed, as it affects the molecular background and potential for cross-reactivity, ultimately determining the test’s performance.

Methods: Predicting primers based on the consensus sequence of the target has multiple advantages, including high specificity, diagnostic reliability, broad applicability, and long-term validity. Automated curation of the input sequences ensures high-quality primers and probes.

Results: Here, we present a use case for developing a set of consensus primers and probes to identify antibiotic resistance and virulence genes in Staphylococcus (S.) aureus using the ConsensusPrime pipeline. Extensive qPCR experiments with several S. aureus strains confirm the exceptional quality of the primers designed using the pipeline.

Conclusions: By improving the quality of the input sequences and using the consensus sequence as a basis, the ConsensusPrime pipeline pipeline ensures high-quality primers and probes, which should be the basis of molecular assays.},

keywords = {bacteria, DNA / genomics, software},

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_60,

title = {Detection of a novel genotype of \textit{Chlamydia buteonis} in falcons from the Emirates},

author = {F. Vorimore and R. Aaziz and L. {Al Qaysi} and U. Wernery and N. Borel and Konrad Sachse and K. Laroucau},

doi = {10.1016/j.vetmic.2024.110027},

year  = {2024},

date = {2024-02-16},

journal = {Veterinary Microbiology},

volume = {291},

pages = {110027},

abstract = {Chlamydiaceae are a family of obligate intracellular bacterial pathogens that affect both humans and animals. Recently, a new species named Chlamydia (C.) buteonis was isolated from hawks. In this study, we aimed to investigate the prevalence of Chlamydiaceae in 60 falcons that underwent a routine health check at a specialized clinic in Dubai, United Arab Emirates. Using real-time PCR, we analyzed cloacal and tracheal swabs from these birds and found that 39 of them tested positive for Chlamydiaceae. Subsequent real-time PCR assays specific for C. psittaci, C. abortus, C. avium, and C. gallinacea yielded negative results, while testing positive for C. buteonis. Analysis of ompA and MLST sequences indicated a highly conserved group of strains within this set of samples, but with sequences distinct from the C. buteonis RSHA reference strains and other C. buteonis strains isolated from hawks in the United States. Two strains were further isolated by cell culture and sequenced using whole-genome sequencing, confirming the clustering of these falcon strains within the C. buteonis species, but in a separate clade from the previously identified hawk strains. We also developed a SNP-based PCR-HRM assay to distinguish between these different genotypes. Overall, our findings suggest a high prevalence of C. buteonis in falcons in Dubai and highlight the importance of monitoring this pathogen in birds of prey.},

keywords = {bacteria, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_42,

title = {PAPAS Suppresses Breast Carcinogenesis by Promoting Differentiation of Mammary Epithelial Cells},

author = {Sijia Ren and Feng Bai and Clara Stanko and Muriel Ritsch and Tino Schenk and Emanuel Barth and Xin-Hai Pei and Holger Bierhoff

},

doi = {10.2139/ssrn.4436847},

year  = {2024},

date = {2024-01-23},

urldate = {2023-05-23},

journal = {Cell Reports},

abstract = {Extensive remodeling of the female mammary epithelium during development and pregnancy has been linked to cancer susceptibility. The faithful response of mammary epithelial cells (MECs) to hormone signaling is key to avoid breast cancer development. Here we show that lactogenic differentiation of murine MECs requires epigenetic silencing of genes encoding ribosomal RNA (rRNA) by the antisense transcript PAPAS. Accordingly, knockdown of PAPAS derepresses rRNA genes, attenuates the response to lactogenic hormones, and induces malignant transformation. Restoring PAPAS levels in breast cancer cells reduces tumorigenicity and, as revealed by transcriptomics, immune evasion potential. Mechanistically, we show that PAPAS transcription depends on R-loop formation at the 3’ end of rRNA genes, which is repressed by RNase H1 and replication protein A (RPA) overexpression in breast cancer cells. Depletion of PAPAS, and upregulation of RNase H1 and RPA in human breast cancer underpin the clinical relevance of our findings.},

keywords = {cancer, ncRNAs, RNA structure},

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_49,

title = {Decoding cell-type contributions to the cfRNA transcriptomic landscape of liver cancer},

author = {Aram Safrastyan and Christian {Höner Zu Siederdissen} and Damian Wollny},

doi = {10.1186/s40246-023-00537-w},

year  = {2023},

date = {2023-10-05},

journal = {Hum Genomics},

volume = {17},

issue = {1},

pages = {90},

abstract = {Background

Liquid biopsy, particularly cell-free RNA (cfRNA), has emerged as a promising non-invasive diagnostic tool for various diseases, including cancer, due to its accessibility and the wealth of information it provides. A key area of interest is the composition and cellular origin of cfRNA in the blood and the alterations in the cfRNA transcriptomic landscape during carcinogenesis. Investigating these changes can offer insights into the manifestations of tissue alterations in the blood, potentially leading to more effective diagnostic strategies. However, the consistency of these findings across different studies and their clinical utility remains to be fully elucidated, highlighting the need for further research in this area.



Results

In this study, we analyzed over 350 blood samples from four distinct studies, investigating the cell type contributions to the cfRNA transcriptomic landscape in liver cancer. We found that an increase in hepatocyte proportions in the blood is a consistent feature across most studies and can be effectively utilized for classifying cancer and healthy samples. Moreover, our analysis revealed that in addition to hepatocytes, liver endothelial cell signatures are also prominent in the observed changes. By comparing the classification performance of cellular proportions to established markers, we demonstrated that cellular proportions could distinguish cancer from healthy samples as effectively as existing markers and can even enhance classification when used in combination with these markers.



Conclusions

Our comprehensive analysis of liver cell-type composition changes in blood revealed robust effects that help classify cancer from healthy samples. This is especially noteworthy, considering the heterogeneous nature of datasets and the etiological distinctions of samples. Furthermore, the observed differences in results across studies underscore the importance of integrative and comparative approaches in the future research to determine the consistency and robustness of findings. This study contributes to the understanding of cfRNA composition in liver cancer and highlights the potential of cellular deconvolution in liquid biopsy.},

keywords = {cancer, ncRNAs},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_47,

title = {The International Virus Bioinformatics Meeting 2023},

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

doi = {10.3390/v15102031},

issn = {1999-4915},

year  = {2023},

date = {2023-09-30},

urldate = {2023-09-30},

journal = {Viruses},

volume = {15},

issue = {10},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_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_48,

title = {Detection of reproducible liver cancer specific ligand-receptor signaling in blood},

author = {Aram Safrastyan and Damian Wollny},

doi = {10.1101/2023.09.25.559274},

year  = {2023},

date = {2023-09-25},

urldate = {2023-09-25},

journal = {bioRxiv},

abstract = {Cell-cell communication mediated by ligand-receptor interactions (LRI) is critical to coordinating diverse biological processes in homeostasis and disease. Lately, our understanding of these processes has greatly expanded through the inference of cellular communication, utilizing RNA extracted from bulk tissue or individual cells. Considering the challenge of obtaining tissue biopsies for these approaches, we considered the potential of studying cell-free RNA obtained from blood. To test the feasibility of this approach, we used the BulkSignalR algorithm across 295 cell-free RNA samples and compared the LRI profiles across multiple cancer types and healthy donors. Interestingly, we detected specific and reproducible LRIs particularly in the blood of liver cancer patients compared to healthy donors. We found an increase in the magnitude of hepatocyte interactions, notably hepatocyte autocrine interactions in liver cancer patients. Additionally, a robust panel of 30 liver cancer-specific LRIs presents a bridge linking liver cancer pathogenesis to discernible blood markers. In summary, our approach shows the plausibility of detecting liver LRIs in blood and builds upon the biological understanding of cell-free transcriptomes.},

keywords = {cancer, ncRNAs},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_45,

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

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

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

year  = {2023},

date = {2023-09-20},

urldate = {2023-09-20},

journal = {Journal of Virology},

volume = {0},

issue = {0},

pages = {e00205-23},

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

keywords = {DNA / genomics, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_44,

title = {\textit{De novo} genome assembly resolving repetitive structures enables genomic analysis of 35 European \textit{Mycoplasmopsis bovis} strains},

author = {Sandra Triebel and Konrad Sachse and Michael Weber and Martin Heller and Celia Diezel and Martin Hölzer and Christiane Schnee and Manja Marz },

doi = {10.1186/s12864-023-09618-5},

isbn = {1471-2164},

year  = {2023},

date = {2023-09-16},

urldate = {2023-09-16},

journal = {BMC Genomics},

volume = {24},

number = {548},

issue = {1},

abstract = {Mycoplasmopsis (M.) bovis, the agent of mastitis, pneumonia, and arthritis in cattle, harbors a small genome of approximately 1 Mbp. Combining data from Illumina and Nanopore technologies, we sequenced and assembled the genomes of 35 European strains and isolate DL422_88 from Cuba. While the high proportion of repetitive structures in M. bovis genomes represent a particular challenge, implementation of our own pipeline Mycovista (available on GitHub www.github.com/sandraTriebel/mycovista ) in a hybrid approach enabled contiguous assembly of the genomes and, consequently, improved annotation rates considerably. To put our European strain panel in a global context, we analyzed the new genome sequences together with 175 genome assemblies from public databases. Construction of a phylogenetic tree based on core genes of these 219 strains revealed a clustering pattern according to geographical origin, with European isolates positioned on clades 4 and 5. Genomic data allowing assignment of strains to tissue specificity or certain disease manifestations could not be identified. Seven strains isolated from cattle with systemic circular condition (SCC), still a largely unknown manifestation of M. bovis disease, were located on both clades 4 and 5. Pairwise association analysis revealed 108 genomic elements associated with a particular clade of the phylogenetic tree. Further analyzing these hits, 25 genes are functionally annotated and could be linked to a M. bovis protein, e.g. various proteases and nucleases, as well as ten variable surface lipoproteins (Vsps) and other surface proteins. These clade-specific genes could serve as useful markers in epidemiological and clinical surveys.},

keywords = {assembly, bacteria, DNA / genomics, nanopore, phylogenetics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_43,

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

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

doi = {10.3390/v15091834},

isbn = {1999-4915},

year  = {2023},

date = {2023-08-29},

journal = {Viruses},

volume = {15},

number = {1834},

issue = {9},

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

keywords = {database, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

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

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

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

year  = {2023},

date = {2023-08-28},

journal = {PLOS Comput Biol},

volume = {19},

issue = {8},

pages = {e1011422},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

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

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

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

year  = {2023},

date = {2023-08-24},

journal = {Research Ideas and Outcomes},

volume = {9},

pages = {e110501},

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

keywords = {bacteria, fungi, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_41,

title = {\textit{Streptomyces marispadix} sp. nov., isolated from marine beach sediment},

author = {José Diogo Neves Dos Santos and Inês Rosado Vitorino and Nicolai Kallscheuer and Akash Srivastava and Sebastian Krautwurst and Manja Marz and Christian Jogler and Alexandre Lobo-da-Cunha and José Catita and Hugo Gonçalves and Ignacio González and Fernando Reyes and Olga Maria Lage},

doi = {10.1099/ijsem.0.005956},

isbn = {1466-5034},

year  = {2023},

date = {2023-07-25},

urldate = {2023-07-25},

journal = {International Journal of Systematic and Evolutionary Microbiology},

volume = {73},

number = {7},

abstract = {A novel actinomycetal strain, designated M600PL45_2T, was isolated from marine sediments obtained from Ingleses beach, Porto, on the Northern Coast of Portugal and was subjected to a polyphasic taxonomic characterisation study. The here described Gram-reaction-positive strain is characterised by the production of a brown pigment in both solid and liquid medium and forms typical helical hyphae that differentiate into smooth spores. The results of a phylogenetic analysis based on the 16S rRNA gene sequence indicated that M600PL45_2T has a high similarity to two members of the genus Streptomyces , Streptomyces bathyalis ASO4wetT (98.51 %) and Streptomyces daqingensis NEAU ZJC8T (98.44 %). The genome of M600PL45_2T has a size of 6 695 159 bp, a DNA G+C content of 70.71 mol% and 5538 coding sequences. M600PL45_2T grows at 15–37 °C and with a maximal growth rate between 25 °C and 30 °C. Growth at pH 6.0 to 9.0 with the optimal range between 6.0 and 7.5 was observed. M600PL45_2T showed a high salinity tolerance, growing with 0–10 % (w/v) NaCl, with best growth with 1–3% (w/v) NaCl. Major cellular fatty acids are iso-C15:0 (25.03 %), anteiso-C15:0 (17.70) and iso-C16:0 (26.90 %). The novel isolate was able to grow in media containing a variety of nitrogen and carbon sources. An antimicrobial activity screening indicated that an extract of M600PL45_2T has inhibitory activity against Staphylococcus aureus . On the basis of the polyphasic data, M600PL45_2T (= CECT 30365T = DSM 114036T) is introduced as the type strain of a novel species, that we named Streptomyces marispadix sp. nov.},

keywords = {bacteria, phylogenetics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_34,

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

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

doi = {10.1093/nar/gkad442},

isbn = {0305-1048},

year  = {2023},

date = {2023-07-07},

urldate = {2023-07-07},

journal = {Nucleic Acids Research},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_40,

title = {Oxford nanopore technologies-a valuable tool to generate whole-genome sequencing data for \textit{in silico} serotyping and the detection of genetic markers in \textit{Salmonella}},

author = {Christine Thomas and Ulrich Methner and Manja Marz and Jörg Linde},

doi = {10.3389/fvets.2023.1178922},

isbn = {2297-1769},

year  = {2023},

date = {2023-06-01},

urldate = {2023-06-01},

journal = {Frontiers in Veterinary Science},

volume = {10},

abstract = {Bacteria of the genus Salmonella pose a major risk to livestock, the food economy, and public health. Salmonella infections are one of the leading causes of food poisoning. The identification of serovars of Salmonella achieved by their diverse surface antigens is essential to gain information on their epidemiological context. Traditionally, slide agglutination has been used for serotyping. In recent years, whole-genome sequencing (WGS) followed by in silico serotyping has been established as an alternative method for serotyping and the detection of genetic markers for Salmonella. Until now, WGS data generated with Illumina sequencing are used to validate in silico serotyping methods. Oxford Nanopore Technologies (ONT) opens the possibility to sequence ultra-long reads and has frequently been used for bacterial sequencing. In this study, ONT sequencing data of 28 Salmonella strains of different serovars with epidemiological relevance in humans, food, and animals were taken to investigate the performance of the in silico serotyping tools SISTR and SeqSero2 compared to traditional slide agglutination tests. Moreover, the detection of genetic markers for resistance against antimicrobial agents, virulence, and plasmids was studied by comparing WGS data based on ONT with WGS data based on Illumina. Based on the ONT data from flow cell version R9.4.1, in silico serotyping achieved an accuracy of 96.4 and 92% for the tools SISTR and SeqSero2, respectively. Highly similar sets of genetic markers comparing both sequencing technologies were identified. Taking the ongoing improvement of basecalling and flow cells into account, ONT data can be used for Salmonella in silico serotyping and genetic marker detection.},

keywords = {bacteria, nanopore},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_35,

title = {Genomic analysis of 61 \textit{Chlamydia psittaci} strains reveals extensive divergence associated with host preference},

author = {Konrad Sachse and Martin Hölzer and Fabien Vorimore and Lisa-Marie Barf and Carsten Sachse and Karine Laroucau and Manja Marz and Kevin Lamkiewicz },

doi = {10.1186/s12864-023-09370-w},

isbn = {1471-2164},

year  = {2023},

date = {2023-05-29},

urldate = {2023-05-29},

journal = {BMC Genomics},

volume = {24},

issue = {1},

pages = {288},

abstract = {Background

Chlamydia (C.) psittaci, the causative agent of avian chlamydiosis and human psittacosis, is a genetically heterogeneous species. Its broad host range includes parrots and many other birds, but occasionally also humans (via zoonotic transmission), ruminants, horses, swine and rodents. To assess whether there are genetic markers associated with host tropism we comparatively analyzed whole-genome sequences of 61 C. psittaci strains, 47 of which carrying a 7.6-kbp plasmid.



Results

Following clean-up, reassembly and polishing of poorly assembled genomes from public databases, phylogenetic analyses using C. psittaci whole-genome sequence alignment revealed four major clades within this species. Clade 1 represents the most recent lineage comprising 40/61 strains and contains 9/10 of the psittacine strains, including type strain 6BC, and 10/13 of human isolates. Strains from different non-psittacine hosts clustered in Clades 2– 4. We found that clade membership correlates with typing schemes based on SNP types, ompA genotypes, multilocus sequence types as well as plasticity zone (PZ) structure and host preference. Genome analysis also revealed that i) sequence variation in the major outer membrane porin MOMP can result in 3D structural changes of immunogenic domains, ii) past host change of Clade 3 and 4 strains could be associated with loss of MAC/perforin in the PZ, rather than the large cytotoxin, iii) the distinct phylogeny of atypical strains (Clades 3 and 4) is also reflected in their repertoire of inclusion proteins (Inc family) and polymorphic membrane proteins (Pmps).



Conclusions

Our study identified a number of genomic features that can be correlated with the phylogeny and host preference of C. psittaci strains. Our data show that intra-species genomic divergence is associated with past host change and includes deletions in the plasticity zone, structural variations in immunogenic domains and distinct repertoires of virulence factors.},

keywords = {alignment, assembly, bacteria, DNA / genomics, phylogenetics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Assembling highly repetitive Xanthomonas TALomes using Oxford Nanopore sequencing},

author = {Annett Erkes and René P Grove and Milena Žarković and Sebastian Krautwurst and Ralf Koebnik and Richard D Morgan and Geoffrey G Wilson and Martin Hölzer and Manja Marz and Jens Boch and Jan Grau

},

doi = {10.1186/s12864-023-09228-1},

year  = {2023},

date = {2023-03-27},

journal = {BMC Genomics},

volume = {24},

issue = {1},

pages = {151},

abstract = {Background: Most plant-pathogenic Xanthomonas bacteria harbor transcription activator-like effector (TALE) genes, which function as transcriptional activators of host plant genes and support infection. The entire repertoire of up to 29 TALE genes of a Xanthomonas strain is also referred to as TALome. The DNA-binding domain of TALEs is comprised of highly conserved repeats and TALE genes often occur in gene clusters, which precludes the assembly of TALE-carrying Xanthomonas genomes based on standard sequencing approaches.



Results: Here, we report the successful assembly of the 5 Mbp genomes of five Xanthomonas strains from Oxford Nanopore Technologies (ONT) sequencing data. For one of these strains, Xanthomonas oryzae pv. oryzae (Xoo) PXO35, we illustrate why Illumina short reads and longer PacBio reads are insufficient to fully resolve the genome. While ONT reads are perfectly suited to yield highly contiguous genomes, they suffer from a specific error profile within homopolymers. To still yield complete and correct TALomes from ONT assemblies, we present a computational correction pipeline specifically tailored to TALE genes, which yields at least comparable accuracy as Illumina-based polishing. We further systematically assess the ONT-based pipeline for its multiplexing capacity and find that, combined with computational correction, the complete TALome of Xoo PXO35 could have been reconstructed from less than 20,000 ONT reads.



Conclusions: Our results indicate that multiplexed ONT sequencing combined with a computational correction of TALE genes constitutes a highly capable tool for characterizing the TALomes of huge collections of Xanthomonas strains in the future.},

keywords = {assembly, DNA / genomics, nanopore},

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}

}