Research » Projects

@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 = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christ2021,

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

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

doi = {10.3389/fphys.2021.733868},

year  = {2021},

date = {2021-11-18},

urldate = {2021-11-18},

journal = {Front Physiol},

volume = {12},

pages = {733868},

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

keywords = {},

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 = {},

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 = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {Carbon fixation rates in groundwater similar to those in oligotrophic marine systems},

author = {Will A. Overholt and Susan Trumbore and Xiaomei Xu and Till L. V. Bornemann and Alexander J. Probst and Markus Krüger and Martina Herrmann and Bo Thamdrup and Laura A. Bristow and Martin Taubert and Valérie F. Schwab and Martin Hölzer and Manja Marz and Kirsten Küsel},

doi = {10.1038/s41561-022-00968-5},

year  = {2022},

date = {2022-06-30},

journal = {Nat Geosci},

volume = {15},

pages = {561–567},

abstract = {The terrestrial subsurface contains nearly all of Earth’s freshwater reserves and harbours the majority of our planet’s total prokaryotic biomass. Although genetic surveys suggest these organisms rely on in situ carbon fixation, rather than the photosynthetically derived organic carbon transported from surface environments, direct measurements of carbon fixation in the subsurface are absent. Using an ultra-low level 14C-labelling technique, we estimate in situ carbon fixation rates in a carbonate aquifer. We find these rates are similar to those measured in oligotrophic marine surface waters and up to six-fold greater than those observed in the lower euphotic zone. Our empirical carbon fixation rates agree with nitrification rate data. Metagenomic analyses reveal abundant putative chemolithoautotrophic members of an uncharacterized order of Nitrospiria that may be behind the carbon fixation. On the basis of our determined carbon fixation rates, we conservatively extrapolate global primary production in carbonate groundwaters (10% of global reserves) to be 0.11 Pg carbon per year. These rates fall within the range found for oligotrophic marine surface waters, indicating a substantial contribution of in situ primary production to subsurface ecosystem processes. We further suggest that, just as phototrophs are for marine biogeochemical cycling, such subsurface carbon fixation is potentially foundational to subsurface trophic webs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

title = {The economical lifestyle of CPR bacteria in groundwater allows little preference for environmental drivers},

author = {Narendrakumar M. Chaudhari and Will A. Overholt and Perla Abigail Figueroa-Gonzalez and Martin Taubert and Till L. V. Bornemann and Alexander J. Probst and Martin Hölzer and Manja Marz and Kirsten Küsel},

doi = {10.1186/s40793-021-00395-w},

year  = {2021},

date = {2021-12-14},

urldate = {2021-12-14},

journal = {Environ Microbiome},

volume = {16},

number = {1},

pages = {24},

abstract = {Background: The highly diverse Cand. Patescibacteria are predicted to have minimal biosynthetic and metabolic pathways, which hinders understanding of how their populations differentiate in response to environmental drivers or host organisms. Their mechanisms employed to cope with oxidative stress are largely unknown. Here, we utilized genome-resolved metagenomics to investigate the adaptive genome repertoire of Patescibacteria in oxic and anoxic groundwaters, and to infer putative host ranges.



Results: Within six groundwater wells, Cand. Patescibacteria was the most dominant (up to 79%) super-phylum across 32 metagenomes sequenced from DNA retained on 0.2 and 0.1 µm filters after sequential filtration. Of the reconstructed 1275 metagenome-assembled genomes (MAGs), 291 high-quality MAGs were classified as Cand. Patescibacteria. Cand. Paceibacteria and Cand. Microgenomates were enriched exclusively in the 0.1 µm fractions, whereas candidate division ABY1 and Cand. Gracilibacteria were enriched in the 0.2 µm fractions. On average, Patescibacteria enriched in the smaller 0.1 µm filter fractions had 22% smaller genomes, 13.4% lower replication measures, higher proportion of rod-shape determining proteins, and of genomic features suggesting type IV pili mediated cell-cell attachments. Near-surface wells harbored Patescibacteria with higher replication rates than anoxic downstream wells characterized by longer water residence time. Except prevalence of superoxide dismutase genes in Patescibacteria MAGs enriched in oxic groundwaters (83%), no major metabolic or phylogenetic differences were observed. The most abundant Patescibacteria MAG in oxic groundwater encoded a nitrate transporter, nitrite reductase, and F-type ATPase, suggesting an alternative energy conservation mechanism. Patescibacteria consistently co-occurred with one another or with members of phyla Nanoarchaeota, Bacteroidota, Nitrospirota, and Omnitrophota. Among the MAGs enriched in 0.2 µm fractions,, only 8% Patescibacteria showed highly significant one-to-one correlation, mostly with Omnitrophota. Motility and transport related genes in certain Patescibacteria were highly similar to genes from other phyla (Omnitrophota, Proteobacteria and Nanoarchaeota).



Conclusion: Other than genes to cope with oxidative stress, we found little genomic evidence for niche adaptation of Patescibacteria to oxic or anoxic groundwaters. Given that we could detect specific host preference only for a few MAGs, we speculate that the majority of Patescibacteria is able to attach multiple hosts just long enough to loot or exchange supplies.},

keywords = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Wegner:19,

title = {Biogeochemical regimes in shallow aquifers reflect the metabolic coupling of elements of nitrogen, sulfur and carbon.},

author = {Carl-Eric Wegner and Michael Gaspar and Patricia Geesink and Martina Herrmann and Manja Marz and Kirsten Küsel},

doi = {10.1128/AEM.02346-18},

year  = {2019},

date = {2019-02-20},

urldate = {2019-01-01},

journal = {Appl Environ Microbiol},

volume = {85},

number = {5},

pages = {e02346-18},

abstract = {Near-surface groundwaters are prone to receive (in)organic matter input from their recharge areas and are known to harbour autotrophic microbial communities linked to nitrogen and sulfur metabolism. Here, we use multi-"omic" profiling to gain holistic insights into the turnover of inorganic nitrogen compounds, carbon fixation processes and organic matter processing in groundwater. We sampled microbial biomass from two superimposed aquifers via monitoring wells that follow groundwater flow from its recharge area through differences in hydrogeochemical settings and land use. Functional profiling revealed that groundwater microbiomes are mainly driven by nitrogen (nitrification, denitrification, anammox) and to a lesser extent sulfur cycling (sulfur oxidation and sulfate reduction), dependent on local hydrochemical differences. Surprisingly, the differentiation potential of the groundwater microbiome surpasses that of hydrochemistry for individual monitoring wells. Dominated by few phyla (Bacteroidetes, Proteobacteria, Planctomycetes, Thaumarchaeota), the taxonomic profiling of groundwater metagenomes and metatranscriptomes revealed pronounced differences between merely present microbiome members and those actively participating in community gene expression and biogeochemical cycling. Unexpectedly, we observed a constitutive expression of carbohydrate-active enzymes, encoded by different microbiome members, along with the groundwater flow path. The turnover of organic carbon apparently complements for lithoautotrophic carbon assimilation pathways mainly used by the groundwater microbiome dependent on the availability of oxygen and inorganic electron donors like ammonium. Groundwater is a key resource for drinking water production and irrigation. The interplay between geological setting, hydrochemistry, carbon storage and groundwater microbiome ecosystem functioning is crucial for our understanding of these important ecosystem services. We targeted the encoded and expressed metabolic potential of groundwater microbiomes along an aquifer transect that diversifies in terms of hydrochemistry and land use. Our results showed that the groundwater microbiome has a higher spatial differentiation potential than hydrochemistry.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Starke:17,

title = {Candidate Brocadiales dominates C, N and S cycling in anoxic groundwater of a pristine limestone-fracture aquifer},

author = {Robert Starke and Martina Müller and Michael Gaspar and Manja Marz and Kirsten Küsel and Kai Uwe Totsche and Martin Bergen and Nico Jehmlich},

doi = {10.1016/j.jprot.2016.11.003},

year  = {2016},

date = {2016-11-10},

urldate = {2016-11-10},

journal = {J Proteomics},

volume = {152},

pages = {153--160},

abstract = {Groundwater-associated microorganisms are known to play an important role in the biogeochemical C, N and S cycling. Metaproteomics was applied to characterize the diversity and the activity of microbes to identify key species in major biogeochemical processes in the anoxic groundwater of a pristine karstic aquifer located in Hainich, central Germany. Sampling was achieved by pumping 1000L water from two sites of the upper aquifer assemblage and filtration on 0.3μm glass filters. In total, 3808 protein groups were identified. Interestingly, the two wells (H4/2 and H5/2) differed not only in microbial density but also in the prevalence of different C, N and S cycling pathways. The well H5/2 was dominated by the anaerobic ammonia-oxidizing (anammox) candidate Brocadiales (31%) while other orders such as Burkholderiales (2%) or Nitrospirales (3%) were less abundant. Otherwise, the well H4/2 featured only low biomass and remarkably fewer proteins (391 to 3631 at H5/2). Candidate Brocadiales was affiliated to all major carbon fixation strategies, and to the cycling of N and S implying a major role in biogeochemical processes of groundwater aquifers. The findings of our study support functions which can be linked to the ecosystem services provided by the microbial communities present in aquifers. Subsurface environments especially the groundwater ecosystems represent a large habitat for microbial activity. Microbes are responsible for energy and nutrient cycling and are massively involved in the planet's sustainability. Microbial diversity is tremendous and the central question in current microbial ecology is "Who eats what, where and when?". In this study, we characterize a natural aquifer inhabiting microbial community to obtain evidence for the phylogenetic diversity and the metabolic activity by protein abundance and we highlight important biogeochemical cycling processes. The aquifer was dominated by Candidatus Brocadiales while other phylotypes such as Burkholderiales, Caulobacterales and Nitrospirales were less abundant. The candidate comprised all major carbon fixation strategies, ammonification, anammox and denitrification as well as assimilatory sulfate reduction. Our findings have broad implications for the understanding of microbial activities in this aquifer and consequently specific functions can be linked to the ecosystem services provided by the microbial communities present in aquifers.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mostajo:20,

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

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

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

doi = {10.1093/nargab/lqz006},

year  = {2019},

date = {2019-09-30},

urldate = {2019-09-30},

journal = {NAR Genomics Bioinf},

volume = {2},

number = {1},

pages = {lqz006},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Hoelzer:16,

title = {Differential transcriptional responses to Ebola and Marburg virus infection in bat and human cells},

author = {Martin Hölzer and Verena Krähling and Fabian Amman and Emanuel Barth and Stephan H. Bernhart and Victor A. O. Carmelo and Maximilian Collatz and Gero Doose and Florian Eggenhofer and Jan Ewald and Jörg Fallmann and Lasse M. Feldhahn and Markus Fricke and Juliane Gebauer and Andreas J. Gruber and Franziska Hufsky and Henrike Indrischek and Sabina Kanton and Jörg Linde and Nelly F. Mostajo and Roman Ochsenreiter and Konstantin Riege and Lorena Rivarola-Duarte and Abdullah H. Sahyoun and Sita J. Saunders and Stefan E. Seemann and Andrea Tanzer and Bertram Vogel and Stefanie Wehner and Michael T. Wolfinger and Rolf Backofen and Jan Gorodkin and Ivo Grosse and Ivo Hofacker and Steve Hoffmann and Christoph Kaleta and Peter F. Stadler and Stephan Becker and Manja Marz},

doi = {10.1038/srep34589},

year  = {2016},

date = {2016-10-07},

urldate = {2016-10-07},

journal = {Sci Rep},

volume = {6},

pages = {34589},

abstract = {The unprecedented outbreak of Ebola in West Africa resulted in over 28,000 cases and 11,000 deaths, underlining the need for a better understanding of the biology of this highly pathogenic virus to develop specific counter strategies. Two filoviruses, the Ebola and Marburg viruses, result in a severe and often fatal infection in humans. However, bats are natural hosts and survive filovirus infections without obvious symptoms. The molecular basis of this striking difference in the response to filovirus infections is not well understood. We report a systematic overview of differentially expressed genes, activity motifs and pathways in human and bat cells infected with the Ebola and Marburg viruses, and we demonstrate that the replication of filoviruses is more rapid in human cells than in bat cells. We also found that the most strongly regulated genes upon filovirus infection are chemokine ligands and transcription factors. We observed a strong induction of the JAK/STAT pathway, of several genes encoding inhibitors of MAP kinases (DUSP genes) and of PPP1R15A, which is involved in ER stress-induced cell death. We used comparative transcriptomics to provide a data resource that can be used to identify cellular responses that might allow bats to survive filovirus infections.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Mock:20,

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

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

editor = {Jinbo Xu},

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

doi = {10.1093/bioinformatics/btaa705},

year  = {2020},

date = {2020-08-10},

urldate = {2020-08-10},

journal = {Bioinformatics},

volume = {37},

number = {3},

pages = {318–325},

publisher = {Oxford University Press (OUP)},

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

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

keywords = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Jordan-Paiz:20,

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

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

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

year  = {2020},

date = {2020-10-14},

urldate = {2020-01-01},

journal = {J Virol},

volume = {94},

number = {21},

publisher = {American Society for Microbiology},

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

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Madhugiri:18,

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

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

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

year  = {2017},

date = {2017-12-06},

urldate = {2017-12-06},

journal = {Virology},

volume = {517},

pages = {44--55},

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

keywords = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Desiro:18,

title = {SilentMutations (SIM): a tool for analyzing long-range RNA-RNA interactions in viral genomes and structured RNAs},

author = {Daniel Desiro and Martin Hölzer and Bashar Ibrahim and Manja Marz},

url = {https://github.com/desiro/silentMutations},

doi = {10.1016/j.virusres.2018.11.005},

year  = {2018},

date = {2018-11-12},

urldate = {2018-11-12},

journal = {Virus Res},

volume = {260},

pages = {135-141},

abstract = {A single nucleotide change in the coding region can alter the amino acid sequence of a protein. In consequence, natural or artificial sequence changes in viral RNAs may have various effects not only on protein stability, function and structure but also on viral replication. In recent decades, several tools have been developed to predict the effect of mutations in structured RNAs such as viral genomes or non-coding RNAs. Some tools use multiple point mutations and also take coding regions into account. However, none of these tools was designed to specifically simulate the effect of mutations on viral long-range interactions. Here, we developed SilentMutations (SIM), an easy-to-use tool to analyze the effect of multiple point mutations on the secondary structures of two interacting viral RNAs. The tool can simulate disruptive and compensatory mutants of two interacting single-stranded RNAs. This allows a fast and accurate assessment of key regions potentially involved in functional long-range RNA-RNA interactions and will eventually help virologists and RNA-experts to design appropriate experiments. SIM only requires two interacting single-stranded RNA regions as input. The output is a plain text file containing the most promising mutants and a graphical representation of all interactions. We applied our tool on two experimentally validated influenza A virus and hepatitis C virus interactions and we were able to predict potential double mutants for in vitro validation experiments. The source code and documentation of SIM are freely available at github.com/desiro/silentMutations.},

keywords = {},

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 = {},

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 = {},

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 = {},

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 = {},

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 = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{Viehweger:19a,

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

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

doi = {10.1101/gr.247064.118},

year  = {2019},

date = {2019-08-22},

urldate = {2019-08-22},

journal = {Genome Res},

volume = {29},

pages = {1545-1554},

publisher = {Cold Spring Harbor Laboratory},

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

keywords = {},

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 = {},

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 = {},

pubstate = {published},

tppubtype = {article}

}

@article{nokey,

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

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

doi = {10.3390/cells11091588},

year  = {2022},

date = {2022-05-09},

journal = {Cells},

volume = {11},

issue = {9},

pages = {1588},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Morales-Prieto:19,

title = {Identification of miRNAs and associated pathways regulated by Leukemia Inhibitory Factor in trophoblastic cell lines.},

author = {Diana M. Morales-Prieto and Emanuel Barth and Jose Martín Murrieta-Coxca and Rodolfo R. Favaro and Ruby N. Gutiérrez-Samudio and Wittaya Chaiwangyen and Stephanie Ospina-Prieto and Bernd Gruhn and Ekkehard Schleußner and Manja Marz and Udo R. Markert},

doi = {10.1016/j.placenta.2019.09.005},

year  = {2019},

date = {2019-09-12},

urldate = {2019-09-12},

journal = {Placenta},

volume = {88},

pages = {20--27},

abstract = {Leukemia Inhibitory Factor (LIF) regulates behavior of trophoblast cells and their interaction with immune and endothelial cells. In vitro, trophoblast cell response to LIF may vary depending on the cell model. Reported differences in the miRNA profile of trophoblastic cells may be responsible for these observations. Therefore, miRNA expression was investigated in four trophoblastic cell lines under LIF stimulation followed by in silico analysis of altered miRNAs and their associated pathways. Low density TaqMan miRNA assays were used to quantify levels of 762 mature miRNAs under LIF stimulation in three choriocarcinoma-derived (JEG-3, ACH-3P and AC1-M59) and a trophoblast immortalized (HTR-8/SVneo) cell lines. Expression of selected miRNAs was confirmed in primary trophoblast cells and cell lines by qPCR. Targets and associated pathways of the differentially expressed miRNAs were inferred from the miRTarBase followed by a KEGG Pathway Enrichment Analysis. HTR-8/SVneo and JEG-3 cells were transfected with miR-21-mimics and expression of miR-21 targets was assessed by qPCR. A similar number of miRNAs changed in each tested cell line upon LIF stimulation, however, low coincidence of individual miRNA species was observed and occurred more often among choriocarcinoma-derived cells (complete data set at http://www.ncbi.nlm.nih.gov/geo/ under GEO accession number GSE130489). Altered miRNAs were categorized into pathways involved in human diseases, cellular processes and signal transduction. Six cascades were identified as significantly enriched, including JAK/STAT and TGFB-SMAD. Upregulation of miR-21-3p was validated in all cell lines and primary cells and STAT3 was confirmed as its target. Dissimilar miRNA responses may be involved in differences of LIF effects on trophoblastic cell lines.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Dukhovny:19,

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

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

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

year  = {2019},

date = {2019-07-30},

urldate = {2019-07-30},

journal = {J Virol},

volume = {93},

number = {16},

publisher = {American Society for Microbiology Journals},

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

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Chaiwangyen:17,

title = {KL 5 Trophoblast-immune cell communication via microRNA transported in extracellular vesicles},

author = {Wittaya Chaiwangyen and Ruby N. Gutiérrez-Samudio and Udo R. Markert and Manja Marz and Diana M. Morales-Prieto and Stephanie Ospina-Prieto},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

journal = {Pregnancy Hypertens},

volume = {9},

pages = {5},

publisher = {Elsevier},

keywords = {},

pubstate = {published},

tppubtype = {article}

}