Publications

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

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

},

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

year  = {2023},

date = {2023-01-03},

journal = {Curr Top Microbiol Immunol},

volume = {439},

pages = {305-339},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey_91,

title = {ConsensusPrime—A Bioinformatic Pipeline for Ideal Consensus Primer Design},

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

doi = {10.3390/biomedinformatics2040041},

year  = {2022},

date = {2022-11-24},

urldate = {2022-11-24},

journal = {BioMedInformatics},

volume = {2},

abstract = {Background: High-quality oligonucleotides for molecular amplification and detection procedures of diverse target sequences depend on sequence homology. Processing input sequences and identifying homogeneous regions in alignments can be carried out by hand only if they are small and contain sequences of high similarity. Finding the best regions for large and inhomogeneous alignments needs to be automated.

Results: The ConsensusPrime pipeline was developed to sort out redundant and technical interfering data in multiple sequence alignments and detect the most homologous regions from multiple sequences. It automates the prediction of optimal consensus primers for molecular analytical and sequence-based procedures/assays.

Conclusion: ConsensusPrime is a fast and easy-to-use pipeline for predicting optimal consensus primers that is executable on local systems without depending on external resources and web services. An implementation in a Docker image ensures platform-independent executability and installability despite the combination of multiple programs. The source code and installation instructions are publicly available on GitHub.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Mock2022,

title = {Taxonomic classification of DNA sequences beyond sequence similarity using deep neural networks},

author = {Florian Mock and Fleming Kretschmer and Anton Kriese and Sebastian Böcker and Manja Marz

},

doi = {10.1073/pnas.2122636119},

year  = {2022},

date = {2022-08-30},

journal = {Proc Natl Acad Sci},

volume = {119},

issue = {35},

pages = {e2122636119},

abstract = {Taxonomic classification, that is, the assignment to biological clades with shared ancestry, is a common task in genetics, mainly based on a genome similarity search of large genome databases. The classification quality depends heavily on the database, since representative relatives must be present. Many genomic sequences cannot be classified at all or only with a high misclassification rate. Here we present BERTax, a deep neural network program based on natural language processing to precisely classify the superkingdom and phylum of DNA sequences taxonomically without the need for a known representative relative from a database. We show BERTax to be at least on par with the state-of-the-art approaches when taxonomically similar species are part of the training data. For novel organisms, however, BERTax clearly outperforms any existing approach. Finally, we show that BERTax can also be combined with database approaches to further increase the prediction quality in almost all cases. Since BERTax is not based on similar entries in databases, it allows precise taxonomic classification of a broader range of genomic sequences, thus increasing the overall information gain.},

keywords = {classification, DNA / genomics, machine learning},

pubstate = {published},

tppubtype = {article}

}

@article{Fuesslin2022,

title = {Prediction of Antibiotic Susceptibility Profiles of \textit{Vibrio cholerae} Isolates From Whole Genome Illumina and Nanopore Sequencing Data: CholerAegon},

author = {Valeria Fuesslin and Sebastian Krautwurst and Akash Srivastava and Doris Winter and Britta Liedigk and Thorsten Thye and Silvia Herrera-León and Shirlee Wohl and Jürgen May and Julius N. Fobil and Daniel Eibach and Manja Marz and Kathrin Schuldt},

url = {https://github.com/RaverJay/CholerAegon },

doi = {10.3389/fmicb.2022.909692},

year  = {2022},

date = {2022-06-22},

journal = {Front Microbiol},

volume = {13},

pages = {909692},

abstract = {During the last decades, antimicrobial resistance (AMR) has become a global public health concern. Nowadays multi-drug resistance is commonly observed in strains of Vibrio cholerae, the etiological agent of cholera. In order to limit the spread of pathogenic drug-resistant bacteria and to maintain treatment options the analysis of clinical samples and their AMR profiles are essential. Particularly, in low-resource settings a timely analysis of AMR profiles is often impaired due to lengthy culturing procedures for antibiotic susceptibility testing or lack of laboratory capacity. In this study, we explore the applicability of whole genome sequencing for the prediction of AMR profiles of V. cholerae. We developed the pipeline CholerAegon for the in silico prediction of AMR profiles of 82 V. cholerae genomes assembled from long and short sequencing reads. By correlating the predicted profiles with results from phenotypic antibiotic susceptibility testing we show that the prediction can replace in vitro susceptibility testing for five of seven antibiotics. Because of the relatively low costs, possibility for real-time data analyses, and portability, the Oxford Nanopore Technologies MinION sequencing platform—especially in light of an upcoming less error-prone technology for the platform—appears to be well suited for pathogen genomic analyses such as the one described here. Together with CholerAegon, it can leverage pathogen genomics to improve disease surveillance and to control further spread of antimicrobial resistance.},

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

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Nanopore sequencing for mapping of retrotransposon integration sites in the \textit{Dictyostelium discoideum} genome},

author = {Emanuel Barth and Johannes Burggraaff and Akash Srivastava and Thomas Winckler

},

doi = {10.17912/micropub.biology.000543},

year  = {2022},

date = {2022-03-18},

journal = {MicroPubl Biol},

abstract = {The unicellular eukaryote \textit{Dictyostelium discoideum} has a gene-dense haploid genome. This configuration presents mobile elements with the particular challenge of replicating without causing excessive damage to the host through insertional mutagenesis or recombination between repetitive sequences. \textit{D. discoideum} harbors an active population of the retrotransposon TRE5-A that integrates in a narrow window of ~50 bp upstream of tRNA genes. We assume that this integration preference was developed to avoid the disruption of protein-coding genes. Therefore, we recently mapped new integrations of a genetically tagged TRE5-A element at tRNA genes using PCR-based enrichment of integration junctions. However, the PCR-based enrichment produced several artificial DNA fusions that prevented the mapping of integration sites in unknown places of the genome. Here, we reanalyzed the previous experiment using nanopore sequencing. We summarize the advantages and limitations of direct genome resequencing for the mapping of mobile element integrations.},

keywords = {DNA / genomics, nanopore},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Draft genome assembly and sequencing dataset of the marine diatom Skeletonema cf. costatum RCC75},

author = {Maria Sorokina and Emanuel Barth and Mahnoor Zulfiqar and Michiel Kwantes and Georg Pohnert and Christoph Steinbeck

},

doi = {10.1016/j.dib.2022.107931},

year  = {2022},

date = {2022-02-19},

urldate = {2022-02-05},

journal = {Data Brief},

volume = {41},

pages = {107931},

abstract = {Diatoms (Bacillariophyceae) are a major constituent of the phytoplankton and have a universally recognized ecological importance. Between 1,000 and 1,300 diatom genera have been described in the literature, but only 10 nuclear genomes have been published and made available to the public up to date. Skeletonema costatum is a cosmopolitan marine diatom, principally occurring in coastal regions, and is one of the most abundant members of the Skeletonema genus. Here we present a draft assembly of the Skeletonema cf. costatum RCC75 genome, obtained from PacBio and Illumina NovaSeq data. This dataset will expand the knowledge of the Bacillariophyceae genetics and contribute to the global understanding of phytoplankton's physiological, ecological, and environmental functioning.},

keywords = {DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{Sofer2022,

title = {A genome-wide CRISPR activation screen reveals Hexokinase 1 as a critical factor in promoting resistance to multi-kinase inhibitors in hepatocellular carcinoma cells},

author = {Summer Sofer and Kevin Lamkiewicz and Shir Armoza Eilat and Shirly Partouche and Manja Marz and Neta Moskovits and Salomon M Stemmer and Amir Shlomai and Ella H Sklan},

doi = {10.1096/fj.202101507RR},

year  = {2022},

date = {2022-02-11},

urldate = {2022-02-11},

journal = {FASEB J },

volume = {36},

issue = {3},

pages = {e22191},

abstract = {Hepatocellular carcinoma (HCC) is often diagnosed at an advanced stage and is, therefore, treated with systemic drugs, such as tyrosine-kinase inhibitors (TKIs). These drugs, however, offer only modest survival benefits due to the rapid development of drug resistance. To identify genes implicated in TKI resistance, a cluster of regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated protein 9 activation screen was performed in hepatoma cells treated with regorafenib, a TKI used as second-line therapy for advanced HCC. The screen results show that Hexokinase 1 (HK1), catalyzing the first step in glucose metabolism, is a top candidate for conferring TKI resistance. Compatible with this, HK1 was upregulated in regorafenib-resistant cells. Using several experimental approaches, both in vitro and in vivo, we show that TKI resistance correlates with HK1 expression. Furthermore, an HK inhibitor resensitized resistant cells to TKI treatment. Together, our data indicate that HK1 may function as a critical factor modulating TKI resistance in hepatoma cells and, therefore, may serve as a biomarker for treatment success.},

keywords = {cancer, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_96,

title = {Characterisation and Molecular Analysis of an Unusual Chimeric Methicillin Resistant Staphylococcus Aureus Strain and its Bacteriophages},

author = {Sindy Burgold-Voigt and Stefan Monecke and Alexandra Simbeck and Thomas Holzmann and Bärbel Kieninger and Elisabeth M. Liebler-Tenorio and Sascha D. Braun and Maximilian Collatz and Celia Diezel and Elke Müller and Wulf Schneider-Brachert and Ralf Ehricht},

doi = {10.3389/fgene.2021.723958},

year  = {2021},

date = {2021-11-18},

journal = {Frontiers in Genetics},

volume = {12},

abstract = {In the context of microarray-based epidemiological typing of the clonal organism Staphylococcus aureus/MRSA, a strain was identified that did not belong to known clonal complexes. The molecular analysis by microarray-based typing yielded signals suggesting that it was a mosaic or hybrid strain of two lineages. To verify this result, the isolate was sequenced with both, short-read Illumina and long-read Nanopore technologies and analysed in detail. This supported the hypothesis that the genome of this strain, ST6610-MRSA-IVg comprised of segments originating from two different clonal complexes (CC).

While the backbone of the strain´s genome, i.e., roughly 2 megabases, belongs to CC8, a continuous insert of 894 kb (approx. 30% of the genome) originated from CC140. Beside core genomic markers in the normal succession and orientation, this insert also included the mecA gene, coding for PbP2a and causing methicillin resistance , localised on an SCCmec IVg element. This particular SCCmec type was also previously observed in CC140 MRSA from African countries. A second conspicuous observation was the presence of the trimethoprim resistance gene dfrG within on a prophage that occupied an attachment site normally used by Panton-Valentine Leucocidin (PVL) phages. 

This observation could indicate a role of large-scale chromosomal recombination in the evolution of S. aureus as well as a role of phages in the dissemination of antibiotic resistance genes.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Martín-Hernández2021,

title = {Chromosome-level genome assembly and transcriptome-based annotation of the oleaginous yeast Rhodotorula toruloides CBS 14},

author = {Giselle C Martín-Hernández and Bettina Müller and Mikołaj Chmielarz and Christian Brandt and Martin Hölzer and Adrian Viehweger and Volkmar Passoth

},

doi = {10.1016/j.ygeno.2021.10.006},

year  = {2021},

date = {2021-10-11},

urldate = {2021-10-11},

journal = {Genomics},

volume = {113},

number = {6},

pages = {4022-4027},

abstract = {Rhodotorula toruloides is an oleaginous yeast with high biotechnological potential. In order to understand the molecular physiology of lipid synthesis in R. toruloides and to advance metabolic engineering, a high-resolution genome is required. We constructed a genome draft of R. toruloides CBS 14, using a hybrid assembly approach, consisting of short and long reads generated by Illumina and Nanopore sequencing, respectively. The genome draft consists of 23 contigs and 3 scaffolds, with a N50 length of 1,529,952 bp, thus largely representing chromosomal organization. The total size of the genome is 20,534,857 bp and the overall GC content is 61.83%. Transcriptomic data from different growth conditions was used to aid species-specific gene annotation. We annotated 9464 genes and identified 11,691 transcripts. Furthermore, we demonstrated the presence of a potential plasmid, an extrachromosomal circular structure of about 11 kb with a copy number about three times as high as the other chromosomes.},

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

pubstate = {published},

tppubtype = {article}

}

@article{VanDamme:21,

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

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

editor = {Mihaela Pertea},

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

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

year  = {2021},

date = {2021-02-09},

urldate = {2021-02-09},

journal = {PLOS Comput Biol},

volume = {17},

number = {2},

pages = {e1008716},

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

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

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

pubstate = {published},

tppubtype = {article}

}

@article{Kotolloshi:21,

title = {SLC35F2, a Transporter Sporadically Mutated in the Untranslated Region, Promotes Growth, Migration, and Invasion of Bladder Cancer Cells},

author = {Roland Kotolloshi and Martin Hölzer and Mieczyslaw Gajda and Marc-Oliver Grimm and Daniel Steinbach},

doi = {10.3390/cells10010080},

year  = {2021},

date = {2021-01-06},

urldate = {2021-01-01},

journal = {Cells},

volume = {10},

number = {1},

pages = {80},

publisher = {MDPI AG},

abstract = {Bladder cancer is a very heterogeneous disease and the molecular mechanisms of carcinogenesis and progression are insufficiently investigated. From the DNA sequencing analysis of matched non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC) samples from eight patients, we identified the tumour-associated gene SLC35F2 to be mutated in the 5′ and 3′ untranslated region (UTR). One mutation in 3′UTR increased the luciferase activity reporter, suggesting its influence on the protein expression of SLC35F2. The mRNA level of SLC35F2 was increased in MIBC compared with NMIBC. Furthermore, in immunohistochemical staining, we observed a strong intensity of SLC35F2 in single tumour cells and in the border cells of solid tumour areas with an atypical accumulation around the nucleus, especially in the MIBC. This suggests that SLC35F2 might be highly expressed in aggressive and invasive tumour cells. Moreover, knockdown of SLC35F2 repressed the growth of bladder cancer cells in the monolayer and spheroid model and suppressed migration and invasion of bladder cancer cells. In conclusion, we suggest that SLC35F2 is involved in bladder cancer progression and might provide a new therapeutic approach, for example, by the anti-cancer drug YM155, a cargo of the SLC35F2 transporter.},

keywords = {cancer, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{Flores:20,

title = {A marine Chlamydomonas sp. emerging as an algal model},

author = {David Carrasco Flores and Markus Fricke and Valentin Wesp and Daniel Desirò and Anja Kniewasser and Martin Hölzer and Manja Marz and Maria Mittag},

doi = {10.1111/jpy.13083},

year  = {2020},

date = {2020-10-11},

urldate = {2020-10-11},

journal = {J Phycol},

volume = {57},

number = {1},

pages = {54--69},

publisher = {Wiley},

abstract = {The freshwater microalga Chlamydomonas reinhardtii, which lives in wet soil, has served for decades as a model for numerous biological processes, and many tools have been introduced for this organism. Here, we have established a stable nuclear transformation for its marine counterpart, Chlamydomonas sp. SAG25.89, by fusing specific cis-acting elements from its Actin gene with the gene providing hygromycin resistance and using an elaborated electroporation protocol. Like C. reinhardtii, Chlamydomonas sp. has a high GC content, allowing reporter genes and selection markers to be applicable in both organisms. Chlamydomonas sp. grows purely photoautotrophically and requires ammonia as a nitrogen source because its nuclear genome lacks some of the genes required for nitrogen metabolism. Interestingly, it can grow well under both low and very high salinities (up to 50 g · L-1) rendering it as a model for osmotolerance. We further show that Chlamydomonas sp. grows well from 15 to 28°C, but halts its growth at 32°C. The genome of Chlamydomonas sp. contains some gene homologs the expression of which is regulated according to the ambient temperatures and/or confer thermal acclimation in C. reinhardtii. Thus, knowledge of temperature acclimation can now be compared to the marine species. Furthermore, Chlamydomonas sp. can serve as a model for studying marine microbial interactions and for comparing mechanisms in freshwater and marine environments. Chlamydomonas sp. was previously shown to be immobilized rapidly by a cyclic lipopeptide secreted from the antagonistic bacterium Pseudomonas protegens PF-5, which deflagellates C. reinhardtii.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Overholt:20,

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

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

doi = {10.1111/1462-2920.15186},

year  = {2020},

date = {2020-08-05},

urldate = {2020-08-05},

journal = {Environ Microbiol},

volume = {22},

number = {9},

pages = {4000-4013},

publisher = {Wiley},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{Hölzer:20,

title = {Comparative Genome Analysis of 33 \textit{Chlamydia} Strains Reveals Characteristic Features of \textit{Chlamydia Psittaci} and Closely Related Species},

author = {Martin Hölzer and Lisa-Marie Barf and Kevin Lamkiewicz and Fabien Vorimore and Marie Lataretu and Alison Favaroni and Christiane Schnee and Karine Laroucau and Manja Marz and Konrad Sachse},

url = {github.com/hoelzer-lab/ribap},

doi = {10.3390/pathogens9110899},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Pathogens},

volume = {9},

number = {11},

pages = {899},

publisher = {MDPI AG},

abstract = {To identify genome-based features characteristic of the avian and human pathogen Chlamydia (C.) psittaci and related chlamydiae, we analyzed whole-genome sequences of 33 strains belonging to 12 species. Using a novel genome analysis tool termed Roary ILP Bacterial Annotation Pipeline (RIBAP), this panel of strains was shown to share a large core genome comprising 784 genes and representing approximately 80% of individual genomes. Analyzing the most variable genomic sites, we identified a set of features of C. psittaci that in its entirety is characteristic of this species: (i) a relatively short plasticity zone of less than 30,000 nt without a tryptophan operon (also in C. abortus, C. avium, C. gallinacea, C. pneumoniae), (ii) a characteristic set of of Inc proteins comprising IncA, B, C, V, X, Y (with homologs in C. abortus, C. caviae and C. felis as closest relatives), (iii) a 502-aa SinC protein, the largest among Chlamydia spp., and (iv) an elevated number of Pmp proteins of subtype G (14 in C. psittaci, 14 in Cand. C. ibidis). In combination with future functional studies, the common and distinctive criteria revealed in this study provide important clues for understanding the complexity of host-specific behavior of individual Chlamydia spp.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Kallies:19,

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

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

doi = {10.3390/v11060484},

year  = {2019},

date = {2019-05-28},

urldate = {2019-01-01},

journal = {Viruses},

volume = {11},

number = {6},

pages = {484},

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

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

pubstate = {published},

tppubtype = {article}

}

@article{Chen:18,

title = {Cohesin-mediated NF-κB signaling limits hematopoietic stem cell self-renewal in aging and inflammation},

author = {Zhiyang Chen and Elias Moris Amro and Friedrich Becker and Martin Hölzer and Seyed Mohammad Mahdi Rasa and Sospeter Ngoci Njeru and Bing Han and Simone Di Sanzo and Yulin Chen and Duozhuang Tang and Si Tao and Ronny Haenold and Marco Groth and Vasily S. Romanov and Joanna M. Kirkpatrick and Johann M. Kraus and Hans A. Kestler and Manja Marz and Alessandro Ori and Francesco Neri and Yohei Morita and K. Lenhard Rudolph},

doi = {10.1084/jem.20181505},

year  = {2018},

date = {2018-12-07},

urldate = {2018-01-01},

journal = {J Exp Med},

volume = {216},

number = {1},

pages = {152--175},

publisher = {Rockefeller University Press},

abstract = {Organism aging is characterized by increased inflammation and decreased stem cell function, yet the relationship between these factors remains incompletely understood. This study shows that aged hematopoietic stem and progenitor cells (HSPCs) exhibit increased ground-stage NF-κB activity, which enhances their responsiveness to undergo differentiation and loss of self-renewal in response to inflammation. The study identifies Rad21/cohesin as a critical mediator of NF-κB signaling, which increases chromatin accessibility in the vicinity of NF-κB target genes in response to inflammation. Rad21 is required for normal differentiation, but limits self-renewal of hematopoietic stem cells (HSCs) during aging and inflammation in an NF-κB–dependent manner. HSCs from aged mice fail to down-regulate Rad21/cohesin and inflammation/differentiation signals in the resolution phase of inflammation. Inhibition of cohesin/NF-κB reverts hypersensitivity of aged HSPCs to inflammation-induced differentiation and myeloid-biased HSCs with disrupted/reduced expression of Rad21/cohesin are increasingly selected during aging. Together, Rad21/cohesin-mediated NF-κB signaling limits HSPC function during aging and selects for cohesin-deficient HSCs with myeloid-skewed differentiation.},

keywords = {aging, differential expression analysis, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{Hoelzer:17,

title = {Software Dedicated to Virus Sequence Analysis },

author = {Martin Hölzer and Manja Marz},

doi = {10.1016/bs.aivir.2017.08.004},

year  = {2017},

date = {2017-09-28},

urldate = {2017-09-28},

journal = {Adv Virus Res},

volume = {99},

pages = {233--257},

abstract = {Computer-assisted technologies of the genomic structure, biological function, and evolution of viruses remain a largely neglected area of research. The attention of bioinformaticians to this challenging field is currently unsatisfying in respect to its medical and biological importance. The power of new genome sequencing technologies, associated with new tools to handle "big data", provides unprecedented opportunities to address fundamental questions in virology. Here, we present an overview of the current technologies, challenges, and advantages of Next-Generation Sequencing (NGS) in relation to the field of virology. We present how viral sequences can be detected de novo out of current short-read NGS data. Furthermore, we discuss the challenges and applications of viral quasispecies and how secondary structures, commonly shaped by RNA viruses, can be computationally predicted. The phylogenetic analysis of viruses, as another ubiquitous field in virology, forms an essential element of describing viral epidemics and challenges current algorithms. Recently, the first specialized virus-bioinformatic organizations have been established. We need to bring together virologists and bioinformaticians and provide a platform for the implementation of interdisciplinary collaborative projects at local and international scales. Above all, there is an urgent need for dedicated software tools to tackle various challenges in virology.},

keywords = {DNA / genomics, evolution, phylogenetics, review, RNA / transcriptomics, RNA structure, software, viruses},

pubstate = {published},

tppubtype = {article}

}

@article{Moebius:17,

title = {Complete Genome Sequence of JII-1961, a Bovine \textit{Mycobacterium avium} subsp. \textit{paratuberculosis} Field Isolate from Germany},

author = {Petra Möbius and Gabriele Nordsiek and Martin Hölzer and Michael Jarek and Manja Marz and Heike Köhler},

doi = {10.1128/genomeA.00870-17},

year  = {2017},

date = {2017-08-24},

urldate = {2017-01-01},

journal = {Genome Announc},

volume = {5},

number = {34},

abstract = {Mycobacterium avium subsp. paratuberculosis causes Johne’s disease in ruminants and was also detected in nonruminant species, including human beings, and in milk products. We announce here the 4.829-Mb complete genome sequence of the cattle-type strain JII-1961 from Germany, which is very similar to cattle-type strains recovered from different continents.

},

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

pubstate = {published},

tppubtype = {article}

}

@article{Consortium:18,

title = {Computational pan-genomics: status, promises and challenges},

author = {Tobias Marschall and Manja Marz and Thomas Abeel and Louis Dijkstra and Bas E. Dutilh and Ali Ghaffaari and Paul Kersey and Wigard P. Kloosterman and Veli Mäkinen and Adam M. Novak and Benedict Paten and David Porubsky and Eric Rivals and Can Alkan and Jasmijn A. Baaijens and Paul I. W. De Bakker and Valentina Boeva and Raoul J. P. Bonnal and Francesca Chiaromonte and Rayan Chikhi and Francesca D. Ciccarelli and Robin Cijvat and Erwin Datema and Cornelia M. Van Duijn and Evan E. Eichler and Corinna Ernst and Eleazar Eskin and Erik Garrison and Mohammed El-Kebir and Gunnar W. Klau and Jan O. Korbel and Eric-Wubbo Lameijer and Benjamin Langmead and Marcel Martin and Paul Medvedev and John C. Mu and Pieter Neerincx and Klaasjan Ouwens and Pierre Peterlongo and Nadia Pisanti and Sven Rahmann and Ben Raphael and Knut Reinert and Dick Ridder and Jeroen Ridder and Matthias Schlesner and Ole Schulz-Trieglaff and Ashley D. Sanders and Siavash Sheikhizadeh and Carl Shneider and Sandra Smit and Daniel Valenzuela and Jiayin Wang and Lodewyk Wessels and Ying Zhang and Victor Guryev and Fabio Vandin and Kai Ye and Alexander Schönhuth},

doi = {10.1093/bib/bbw089},

year  = {2016},

date = {2016-10-21},

urldate = {2016-10-21},

journal = {Briefings Bioinf},

volume = {19},

pages = {118--135},

abstract = {Many disciplines, from human genetics and oncology to plant breeding, microbiology and virology, commonly face the challenge of analyzing rapidly increasing numbers of genomes. In case of Homo sapiens, the number of sequenced genomes will approach hundreds of thousands in the next few years. Simply scaling up established bioinformatics pipelines will not be sufficient for leveraging the full potential of such rich genomic data sets. Instead, novel, qualitatively different computational methods and paradigms are needed. We will witness the rapid extension of computational pan-genomics, a new sub-area of research in computational biology. In this article, we generalize existing definitions and understand a pan-genome as any collection of genomic sequences to be analyzed jointly or to be used as a reference. We examine already available approaches to construct and use pan-genomes, discuss the potential benefits of future technologies and methodologies and review open challenges from the vantage point of the above-mentioned biological disciplines. As a prominent example for a computational paradigm shift, we particularly highlight the transition from the representation of reference genomes as strings to representations as graphs. We outline how this and other challenges from different application domains translate into common computational problems, point out relevant bioinformatics techniques and identify open problems in computer science. With this review, we aim to increase awareness that a joint approach to computational pan-genomics can help address many of the problems currently faced in various domains.},

keywords = {annotation, DNA / genomics},

pubstate = {published},

tppubtype = {article}

}

@article{Winter:16,

title = {Finding approximate gene clusters with Gecko 3},

author = {Sascha Winter and Katharina Jahn and Stefanie Wehner and Leon Kuchenbecker and Manja Marz and Jens Stoye and Sebastian Böcker},

url = {http://bio.informatik.uni-jena.de/software/gecko3/},

doi = {10.1093/nar/gkw843},

year  = {2016},

date = {2016-09-26},

urldate = {2016-09-26},

journal = {Nucleic Acids Res},

volume = {44},

pages = {9600--9610},

abstract = {Gene-order-based comparison of multiple genomes provides signals for functional analysis of genes and the evolutionary process of genome organization. Gene clusters are regions of co-localized genes on genomes of different species. The rapid increase in sequenced genomes necessitates bioinformatics tools for finding gene clusters in hundreds of genomes. Existing tools are often restricted to few (in many cases, only two) genomes, and often make restrictive assumptions such as short perfect conservation, conserved gene order or monophyletic gene clusters. We present Gecko 3, an open-source software for finding gene clusters in hundreds of bacterial genomes, that comes with an easy-to-use graphical user interface. The underlying gene cluster model is intuitive, can cope with low degrees of conservation as well as misannotations and is complemented by a sound statistical evaluation. To evaluate the biological benefit of Gecko 3 and to exemplify our method, we search for gene clusters in a dataset of 678 bacterial genomes using Synechocystis sp. PCC 6803 as a reference. We confirm detected gene clusters reviewing the literature and comparing them to a database of operons; we detect two novel clusters, which were confirmed by publicly available experimental RNA-Seq data. The computational analysis is carried out on a laptop computer in <40 min.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Hoelzer:16a,

title = {Whole-Genome Sequence of \textit{Chlamydia gallinacea} Type Strain 08-1274/3},

author = {Martin Hölzer and Karine Laroucau and Heather Huot Creasy and Sandra Ott and Fabien Vorimore and Patrik M. Bavoil and Manja Marz and Konrad Sachse},

doi = {10.1128/genomeA.00708-16},

year  = {2016},

date = {2016-07-21},

urldate = {2016-07-21},

journal = {Genome Announc},

volume = {4},

number = {4},

abstract = {The recently introduced bacterial species Chlamydia gallinacea is known to occur in domestic poultry and other birds. Its potential as an avian pathogen and zoonotic agent is under investigation. The whole-genome sequence of its type strain, 08-1274/3, consists of a 1,059,583-bp chromosome with 914 protein-coding sequences (CDSs) and a plasmid (p1274) comprising 7,619 bp with 9 CDSs.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Moebius:15,

title = {Comprehensive insights in the \textit{Mycobacterium avium} subsp. \textit{paratuberculosis} genome using new WGS data of sheep strain JIII-386 from Germany},

author = {Petra Möbius and Martin Hölzer and Marius Felder and Gabriele Nordsiek and Marco Groth and Heike Köhler and Kathrin Reichwald and Matthias Platzer and Manja Marz},

doi = {10.1093/gbe/evv154},

year  = {2015},

date = {2015-09-17},

urldate = {2015-09-17},

journal = {Genome Biol Evol},

volume = {7},

number = {9},

pages = {2585--2601},

abstract = {Mycobacterium avium (M. a.) subsp. paratuberculosis (MAP) - the etiologic agent of Johne's disease - affects cattle, sheep and other ruminants worldwide. To decipher phenotypic differences among sheep and cattle strains (belonging to MAP-S [Type-I/III] respectively MAP-C [Type-II]) comparative genome analysis needs data from diverse isolates originating from different geographic regions of the world. The current study presents the so far best assembled genome of a MAP-S-strain: sheep isolate JIII-386 from Germany. One newly sequenced cattle isolate (JII-1961, Germany), four published MAP strains of MAP-C and MAP-S from U.S. and Australia and M. a. subsp. hominissuis (MAH) strain 104 were used for assembly improvement and comparisons. All genomes were annotated by BacProt and results compared with NCBI annotation. Corresponding protein-coding sequences (CDSs) were detected, but also CDSs that were exclusively determined either by NCBI or BacProt. A new Shine-Dalgarno sequence motif (5'AGCTGG3') was extracted. Novel CDSs including PE-PGRS family protein genes and about 80 non-coding RNAs exhibiting high sequence conservation are presented. Previously found genetic differences between MAP-types are partially revised. Four out of ten assumed MAP-S-specific large sequence polymorphism regions (LSP s) are still present in MAP-C strains; new LSP s were identified. Independently of the regional origin of the strains, the number of individual CDSs and single nucleotide variants confirm the strong similarity of MAP-C strains and show higher diversity among MAP-S strains. This study gives ambiguous results regarding the hypothesis that MAP-S is the evolutionary intermediate between MAH and MAP-C, but it clearly shows a higher similarity of MAP to MAH than to M. intracellulare.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Vierna:13,

title = {Systematic analysis and evolution of 5S ribosomal DNA in metazoans},

author = {Joaquin Vierna and Stefanie Wehner and Christian {Höner zu Siederdissen} and Andrés Martínez-Lage and Manja Marz},

doi = {10.1038/hdy.2013.63},

year  = {2013},

date = {2013-07-10},

urldate = {2013-07-10},

journal = {Heredity},

volume = {111},

pages = {410--421},

abstract = {Several studies on 5S ribosomal DNA (5S rDNA) have been focused on a subset of the following features in mostly one organism: number of copies, pseudogenes, secondary structure, promoter and terminator characteristics, genomic arrangements, types of non-transcribed spacers and evolution. In this work, we systematically analyzed 5S rDNA sequence diversity in available metazoan genomes, and showed organism-specific and evolutionary-conserved features. Putatively functional sequences (12,766) from 97 organisms allowed us to identify general features of this multigene family in animals. Interestingly, we show that each mammal species has a highly conserved (housekeeping) 5S rRNA type and many variable ones. The genomic organization of 5S rDNA is still under debate. Here, we report the occurrence of several paralog 5S rRNA sequences in 58 of the examined species, and a flexible genome organization of 5S rDNA in animals. We found heterogeneous 5S rDNA clusters in several species, supporting the hypothesis of an exchange of 5S rDNA from one locus to another. A rather high degree of variation of upstream, internal and downstream putative regulatory regions appears to characterize metazoan 5S rDNA. We systematically studied the internal promoters and described three different types of termination signals, as well as variable distances between the coding region and the typical termination signal. Finally, we present a statistical method for detection of linkage among noncoding RNA (ncRNA) gene families. This method showed no evolutionary-conserved linkage among 5S rDNAs and any other ncRNA genes within Metazoa, even though we found 5S rDNA to be linked to various ncRNAs in several clades.},

keywords = {DNA / genomics, evolution, ncRNAs, RNA structure},

pubstate = {published},

tppubtype = {article}

}

@article{Huang:13,

title = {The duck genome and transcriptome provide insight into an avian influenza virus reservoir species},

author = {Yinhua Huang and Yingrui Li and David W. Burt and Hualan Chen and Yong Zhang and Wubin Qian and Heebal Kim and Shangquan Gan and Yiqiang Zhao and Jianwen Li and Kang Yi and Huapeng Feng and Pengyang Zhu and Bo Li and Qiuyue Liu and Suan Fairley and Katharine E. Magor and Zhenlin Du and Xiaoxiang Hu and Laurie Goodman and Hakim Tafer and Alain Vignal and Taeheon Lee and Kyu-Won Kim and Zheya Sheng and Yang An and Steve Searle and Javier Herrero and Martien A. M. Groenen and Richard P. M. A. Crooijmans and Thomas Faraut and Qingle Cai and Robert G. Webster and Jerry R. Aldridge and Wesley C. Warren and Sebastian Bartschat and Stephanie Kehr and Manja Marz and Peter F. Stadler and Jacqueline Smith and Robert H. S. Kraus and Yaofeng Zhao and Liming Ren and Jing Fei and Mireille Morisson and Pete Kaiser and Darren K. Griffin and Man Rao and Frederique Pitel and Jun Wang and Ning Li},

doi = {10.1038/ng.2657},

year  = {2013},

date = {2013-06-09},

urldate = {2013-06-09},

journal = {Nat Genet},

volume = {45},

pages = {776--783},

abstract = {The duck (Anas platyrhynchos) is one of the principal natural hosts of influenza A viruses. We present the duck genome sequence and perform deep transcriptome analyses to investigate immune-related genes. Our data indicate that the duck possesses a contractive immune gene repertoire, as in chicken and zebra finch, and this repertoire has been shaped through lineage-specific duplications. We identify genes that are responsive to influenza A viruses using the lung transcriptomes of control ducks and ones that were infected with either a highly pathogenic (A/duck/Hubei/49/05) or a weakly pathogenic (A/goose/Hubei/65/05) H5N1 virus. Further, we show how the duck's defense mechanisms against influenza infection have been optimized through the diversification of its β-defensin and butyrophilin-like repertoires. These analyses, in combination with the genomic and transcriptomic data, provide a resource for characterizing the interaction between host and influenza viruses.},

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

pubstate = {published},

tppubtype = {article}

}

@article{Lechner:13,

title = {The correlation of genome size and DNA methylation rate in metazoans},

author = {Marcus Lechner and Manja Marz and Christian Ihling and Andrea Sinz and Peter F Stadler and Veiko Krauss},

doi = {10.1007/s12064-012-0167-y},

year  = {2012},

date = {2012-11-07},

urldate = {2012-11-07},

journal = {Theory Biosci},

volume = {132},

pages = {47--60},

abstract = {Total DNA methylation rates are well known to vary widely between different metazoans. The phylogenetic distribution of this variation, however, has not been investigated systematically. We combine here publicly available data on methylcytosine content with the analysis of nucleotide compositions of genomes and transcriptomes of 78 metazoan species to trace the evolution of abundance and distribution of DNA methylation. The depletion of CpG and the associated enrichment of TpG and CpA dinucleotides are used to infer the intensity and localization of germline CpG methylation and to estimate its evolutionary dynamics. We observe a positive correlation of the relative methylation of CpG motifs with genome size. We tested this trend successfully by measuring total DNA methylation with LC/MS in orthopteran insects with very different genome sizes: house crickets, migratory locusts and meadow grasshoppers. We hypothesize that the observed correlation between methylation rate and genome size is due to a dependence of both variables from long-term effective population size and is driven by the accumulation of repetitive sequences that are typically methylated during periods of small population sizes. This process may result in generally methylated, large genomes such as those of jawed vertebrates. In this case, the emergence of a novel demethylation pathway and of novel reader proteins for methylcytosine may have enabled the usage of cytosine methylation for promoter-based gene regulation. On the other hand, persistently large populations may lead to a compression of the genome and to the loss of the DNA methylation machinery, as observed, e.g., in nematodes.},

keywords = {DNA / genomics, evolution, insects, nucleic acid modifications, phylogenetics},

pubstate = {published},

tppubtype = {article}

}

@article{Dalloul:10,

title = {Multi-platform next-generation sequencing of the domestic turkey (\textit{Meleagris gallopavo}): genome assembly and analysis},

author = {Rami A. Dalloul and Julie A. Long and Aleksey V. Zimin and Luqman Aslam and Kathryn Beal and Le Ann Blomberg and Pascal Bouffard and David W. Burt and Oswald Crasta and Richard P. M. A. Crooijmans and Kristal Cooper and Roger A. Coulombe and Supriyo De and Mary E. Delany and Jerry B. Dodgson and Jennifer J. Dong and Clive Evans and Karin M. Frederickson and Paul Flicek and Liliana Florea and Otto Folkerts and Martien A. M. Groenen and Tim T. Harkins and Javier Herrero and Steve Hoffmann and Hendrik-Jan Megens and Andrew Jiang and Pieter Jong and Pete Kaiser and Heebal Kim and Kyu-Won Kim and Sungwon Kim and David Langenberger and Mi-Kyung Lee and Taeheon Lee and Shrinivasrao Mane and Guillaume Marcais and Manja Marz and Audrey P. McElroy and Thero Modise and Mikhail Nefedov and Cédric Notredame and Ian R. Paton and William S. Payne and Geo Pertea and Dennis Prickett and Daniela Puiu and Dan Qioa and Emanuele Raineri and Magali Ruffier and Steven L. Salzberg and Michael C. Schatz and Chantel Scheuring and Carl J. Schmidt and Steven Schroeder and Stephen M. J. Searle and Edward J. Smith and Jacqueline Smith and Tad S. Sonstegard and Peter F. Stadler and Hakim Tafer and Zhijian Jake Tu and Curtis P. Van Tassell and Albert J. Vilella and Kelly P. Williams and James A. Yorke and Liqing Zhang and Hong-Bin Zhang and Xiaojun Zhang and Yang Zhang and Kent M. Reed},

doi = {10.1371/journal.pbio.1000475},

year  = {2010},

date = {2010-09-07},

urldate = {2010-09-07},

journal = {PLoS Biol},

volume = {8},

abstract = {A synergistic combination of two next-generation sequencing platforms with a detailed comparative BAC physical contig map provided a cost-effective assembly of the genome sequence of the domestic turkey (Meleagris gallopavo). Heterozygosity of the sequenced source genome allowed discovery of more than 600,000 high quality single nucleotide variants. Despite this heterozygosity, the current genome assembly (∼1.1 Gb) includes 917 Mb of sequence assigned to specific turkey chromosomes. Annotation identified nearly 16,000 genes, with 15,093 recognized as protein coding and 611 as non-coding RNA genes. Comparative analysis of the turkey, chicken, and zebra finch genomes, and comparing avian to mammalian species, supports the characteristic stability of avian genomes and identifies genes unique to the avian lineage. Clear differences are seen in number and variety of genes of the avian immune system where expansions and novel genes are less frequent than examples of gene loss. The turkey genome sequence provides resources to further understand the evolution of vertebrate genomes and genetic variation underlying economically important quantitative traits in poultry. This integrated approach may be a model for providing both gene and chromosome level assemblies of other species with agricultural, ecological, and evolutionary interest.},

keywords = {alignment, annotation, assembly, DNA / genomics, ncRNAs},

pubstate = {published},

tppubtype = {article}

}

@article{nokey_92,

title = {Molecular Characterization of Chimeric Staphylococcus aureus Strains from Waterfowl},

author = { Stefan Monecke and Sascha D. Braun and Maximillian Collatz and Celia Diezel and Elke Müller and Martin Reinicke and Adriana Cabal Rosel and Andrea T. Feßler and Dennis Hanke and Igor Loncaric and Stefan Schwarz and Sonia Cortez de Jäckel and Werner Ruppitsch and Dolores Gavier Widen and Helmut Hotzel and Ralf Ehricht},

doi = {10.3390/microorganisms12010096},

journal = {Microorganisms},

volume = {12},

abstract = {Staphylococcus aureus is a versatile pathogen that does not only occur in humans but also in various wild and domestic animals, including several avian species. When characterizing S. aureus isolates from waterfowl, isolates were identified as atypical CC133 by DNA microarray analysis. They differed from previously sequenced CC133 strains in the presence of the collagen adhesin gene cna; some also showed a different capsule type and a deviant spa type. Thus, they were subjected to whole-genome sequencing. This revealed multiple insertions of large regions of DNA from other S. aureus lineages into a CC133-derived backbone genome. Three distinct strains were identified based on the size and extent of these inserts. One strain comprised two small inserts of foreign DNA up- and downstream of oriC; one of about 7000 nt or 0.25% originated from CC692 and the other, at ca. 38,000 nt or 1.3% slightly larger one was of CC522 provenance. The second strain carried a larger CC692 insert (nearly 257,000 nt or 10% of the strain’s genome), and its CC522-derived insert was also larger, at about 53,500 nt or 2% of the genome). The third strain carried an identical CC692-derived region (in which the same mutations were observed as in the second strain), but it had a considerably larger CC522-like insertion of about 167,000 nt or 5.9% of the genome. Both isolates of the first, and two out of four isolates of the second strain also harbored a hemolysin-beta-integrating prophage carrying “bird-specific” virulence factors, ornithine cyclodeaminase D0K6J8 and a putative protease D0K6J9. Furthermore, isolates had two different variants of SCC elements that lacked mecA/mecC genes. These findings highlight the role of horizontal gene transfer in the evolution of S. aureus facilitated by SCC elements, by phages, and by a yet undescribed mechanism for large-scale exchange of core genomic DNA.},

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

pubstate = {published},

tppubtype = {article}

}