@article{MeierKruseButtlaretal.2016, author = {Meier, Doreen and Kruse, Janis and Buttlar, Jann and Friedrich, Michael and Zenk, Fides and Boesler, Benjamin and Forstner, Konrad U. and Hammann, Christian and Nellen, Wolfgang}, title = {Analysis of the Microprocessor in Dictyostelium: The Role of RbdB, a dsRNA Binding Protein}, series = {PLoS Genetics}, volume = {12}, journal = {PLoS Genetics}, number = {6}, doi = {10.1371/journal.pgen.1006057}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-166687}, pages = {e1006057}, year = {2016}, abstract = {We identified the dsRNA binding protein RbdB as an essential component in miRNA processing in Dictyostelium discoideum. RbdB is a nuclear protein that accumulates, together with Dicer B, in nucleolar foci reminiscent of plant dicing bodies. Disruption of rbdB results in loss of miRNAs and accumulation of primary miRNAs. The phenotype can be rescued by ectopic expression of RbdB thus allowing for a detailed analysis of domain function. The lack of cytoplasmic dsRBD proteins involved in miRNA processing, suggests that both processing steps take place in the nucleus thus resembling the plant pathway. However, we also find features e.g. in the domain structure of Dicer which suggest similarities to animals. Reduction of miRNAs in the rbdB- strain and their increase in the Argonaute A knock out allowed the definition of new miRNAs one of which appears to belong to a new non-canonical class.}, language = {en} } @article{YuVogelFoerstner2018, author = {Yu, Sung-Huan and Vogel, J{\"o}rg and F{\"o}rstner, Konrad U.}, title = {ANNOgesic: a Swiss army knife for the RNA-seq based annotation of bacterial/archaeal genomes}, series = {GigaScience}, volume = {7}, journal = {GigaScience}, doi = {10.1093/gigascience/giy096}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-178942}, year = {2018}, abstract = {To understand the gene regulation of an organism of interest, a comprehensive genome annotation is essential. While some features, such as coding sequences, can be computationally predicted with high accuracy based purely on the genomic sequence, others, such as promoter elements or noncoding RNAs, are harder to detect. RNA sequencing (RNA-seq) has proven to be an efficient method to identify these genomic features and to improve genome annotations. However, processing and integrating RNA-seq data in order to generate high-resolution annotations is challenging, time consuming, and requires numerous steps. We have constructed a powerful and modular tool called ANNOgesic that provides the required analyses and simplifies RNA-seq-based bacterial and archaeal genome annotation. It can integrate data from conventional RNA-seq and differential RNA-seq and predicts and annotates numerous features, including small noncoding RNAs, with high precision. The software is available under an open source license (ISCL) at https://pypi.org/project/ANNOgesic/.}, language = {en} } @article{SharanFoerstnerEulalioetal.2017, author = {Sharan, Malvika and F{\"o}rstner, Konrad U. and Eulalio, Ana and Vogel, J{\"o}rg}, title = {APRICOT: an integrated computational pipeline for the sequence-based identification and characterization of RNA-binding proteins}, series = {Nucleic Acids Research}, volume = {45}, journal = {Nucleic Acids Research}, number = {11}, doi = {10.1093/nar/gkx137}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-157963}, pages = {e96}, year = {2017}, abstract = {RNA-binding proteins (RBPs) have been established as core components of several post-transcriptional gene regulation mechanisms. Experimental techniques such as cross-linking and co-immunoprecipitation have enabled the identification of RBPs, RNA-binding domains (RBDs) and their regulatory roles in the eukaryotic species such as human and yeast in large-scale. In contrast, our knowledge of the number and potential diversity of RBPs in bacteria is poorer due to the technical challenges associated with the existing global screening approaches. We introduce APRICOT, a computational pipeline for the sequence-based identification and characterization of proteins using RBDs known from experimental studies. The pipeline identifies functional motifs in protein sequences using position-specific scoring matrices and Hidden Markov Models of the functional domains and statistically scores them based on a series of sequence-based features. Subsequently, APRICOT identifies putative RBPs and characterizes them by several biological properties. Here we demonstrate the application and adaptability of the pipeline on large-scale protein sets, including the bacterial proteome of Escherichia coli. APRICOT showed better performance on various datasets compared to other existing tools for the sequence-based prediction of RBPs by achieving an average sensitivity and specificity of 0.90 and 0.91 respectively. The command-line tool and its documentation are available at https://pypi.python.org/pypi/bio-apricot.}, language = {en} } @inproceedings{FoerstnerHagedornKoltzenburgetal.2011, author = {F{\"o}rstner, Konrad and Hagedorn, Gregor and Koltzenburg, Claudia and Kubke, Fabiana and Mietchen, Daniel}, title = {Collaborative platforms for streamlining workflows in Open Science}, series = {Proceedings of the 6th Open Knowledge Conference}, booktitle = {Proceedings of the 6th Open Knowledge Conference}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-101678}, year = {2011}, abstract = {Despite the internet's dynamic and collaborative nature, scientists continue to produce grant proposals, lab notebooks, data files, conclusions etc. that stay in static formats or are not published online and therefore not always easily accessible to the interested public. Because of limited adoption of tools that seamlessly integrate all aspects of a research project (conception, data generation, data evaluation, peerreviewing and publishing of conclusions), much effort is later spent on reproducing or reformatting individual entities before they can be repurposed independently or as parts of articles. We propose that workflows - performed both individually and collaboratively - could potentially become more efficient if all steps of the research cycle were coherently represented online and the underlying data were formatted, annotated and licensed for reuse. Such a system would accelerate the process of taking projects from conception to publication stages and allow for continuous updating of the data sets and their interpretation as well as their integration into other independent projects. A major advantage of such work ows is the increased transparency, both with respect to the scientific process as to the contribution of each participant. The latter point is important from a perspective of motivation, as it enables the allocation of reputation, which creates incentives for scientists to contribute to projects. Such work ow platforms offering possibilities to fine-tune the accessibility of their content could gradually pave the path from the current static mode of research presentation into a more coherent practice of open science.}, language = {en} } @phdthesis{Foerstner2008, author = {F{\"o}rstner, Konrad Ulrich}, title = {Computational analysis of metagenomic data: delineation of compositional features and screens for desirable enzymes}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-33577}, school = {Universit{\"a}t W{\"u}rzburg}, year = {2008}, abstract = {The topic of my doctorial research was the computational analysis of metagenomic data. A metagenome comprises the genomic information from all the microorganisms within a certain environment. The currently available metagenomic data sets cover only parts of these usually huge metagenomes due to the high technical and financial effort of such sequencing endeavors. During my thesis I developed bioinformatic tools and applied them to analyse genomic features of different metagenomic data sets and to search for enzymes of importance for biotechnology or pharmaceutical applications in those sequence collections. In these studies nine metagenomic projects (with up to 41 subsamples) were analysed. These samples originated from diverse environments like farm soil, acid mine drainage, microbial mats on whale bones, marine water, fresh water, water treatment sludges and the human gut flora. Additionally, data sets of conventionally retrieved sequence data were taken into account and compared with each other}, subject = {Bioinformatik}, language = {en} } @article{FanLiChaoetal.2015, author = {Fan, Ben and Li, Lei and Chao, Yanjie and F{\"o}rstner, Konrad and Vogel, J{\"o}rg and Borriss, Rainer and Wu, Xiao-Qin}, title = {dRNA-Seq Reveals Genomewide TSSs and Noncoding RNAs of Plant Beneficial Rhizobacterium Bacillus amyloliquefaciens FZB42}, series = {PLoS One}, volume = {10}, journal = {PLoS One}, number = {11}, doi = {10.1371/journal.pone.0142002}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-138369}, pages = {e0142002}, year = {2015}, abstract = {Bacillus amyloliquefaciens subsp. plantarum FZB42 is a representative of Gram-positive plant-growth-promoting rhizobacteria (PGPR) that inhabit plant root environments. In order to better understand the molecular mechanisms of bacteria-plant symbiosis, we have systematically analyzed the primary transcriptome of strain FZB42 grown under rhizospheremimicking conditions using differential RNA sequencing (dRNA-seq). Our analysis revealed 4,877 transcription start sites for protein-coding genes, identified genes differentially expressed under different growth conditions, and corrected many previously mis-annotated genes. We also identified a large number of riboswitches and cis-encoded antisense RNAs, as well as trans-encoded small noncoding RNAs that may play important roles in the gene regulation of Bacillus. Overall, our analyses provided a landscape of Bacillus primary transcriptome and improved the knowledge of rhizobacteria-host interactions.}, language = {en} } @article{DingemansMonsieursYuetal.2016, author = {Dingemans, Josef and Monsieurs, Pieter and Yu, Sung-Huan and Crabb{\´e}, Aur{\´e}lie and F{\"o}rstner, Konrad U. and Malfroot, Anne and Cornelis, Pierre and Van Houdt, Rob}, title = {Effect of Shear Stress on Pseudomonas aeruginosa Isolated from the Cystic Fibrosis Lung}, series = {mBio}, volume = {7}, journal = {mBio}, number = {4}, doi = {10.1128/mBio.00813-16}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-165821}, pages = {e00813-16}, year = {2016}, abstract = {Chronic colonization of the lungs by Pseudomonas aeruginosa is one of the major causes of morbidity and mortality in cystic fibrosis (CF) patients. To gain insights into the characteristic biofilm phenotype of P. aeruginosa in the CF lungs, mimicking the CF lung environment is critical. We previously showed that growth of the non-CF-adapted P. aeruginosa PAO1 strain in a rotating wall vessel, a device that simulates the low fluid shear (LS) conditions present in the CF lung, leads to the formation of in-suspension, self-aggregating biofilms. In the present study, we determined the phenotypic and transcriptomic changes associated with the growth of a highly adapted, transmissible P. aeruginosa CF strain in artificial sputum medium under LS conditions. Robust self-aggregating biofilms were observed only under LS conditions. Growth under LS conditions resulted in the upregulation of genes involved in stress response, alginate biosynthesis, denitrification, glycine betaine biosynthesis, glycerol metabolism, and cell shape maintenance, while genes involved in phenazine biosynthesis, type VI secretion, and multidrug efflux were downregulated. In addition, a number of small RNAs appeared to be involved in the response to shear stress. Finally, quorum sensing was found to be slightly but significantly affected by shear stress, resulting in higher production of autoinducer molecules during growth under high fluid shear (HS) conditions. In summary, our study revealed a way to modulate the behavior of a highly adapted P. aeruginosa CF strain by means of introducing shear stress, driving it from a biofilm lifestyle to a more planktonic lifestyle.}, language = {en} } @article{BabskiHaasNaetherSchindleretal.2016, author = {Babski, Julia and Haas, Karina A. and N{\"a}ther-Schindler, Daniela and Pfeiffer, Friedhelm and F{\"o}rstner, Konrad U. and Hammelmann, Matthias and Hilker, Rolf and Becker, Anke and Sharma, Cynthia M. and Marchfelder, Anita and Soppa, J{\"o}rg}, title = {Genome-wide identification of transcriptional start sites in the haloarchaeon Haloferax volcanii based on differential RNA-Seq (dRNA-Seq)}, series = {BMC Genomics}, volume = {17}, journal = {BMC Genomics}, number = {629}, doi = {10.1186/s12864-016-2920-y}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-164553}, year = {2016}, abstract = {Background Differential RNA-Seq (dRNA-Seq) is a recently developed method of performing primary transcriptome analyses that allows for the genome-wide mapping of transcriptional start sites (TSSs) and the identification of novel transcripts. Although the transcriptomes of diverse bacterial species have been characterized by dRNA-Seq, the transcriptome analysis of archaeal species is still rather limited. Therefore, we used dRNA-Seq to characterize the primary transcriptome of the model archaeon Haloferax volcanii. Results Three independent cultures of Hfx. volcanii grown under optimal conditions to the mid-exponential growth phase were used to determine the primary transcriptome and map the 5′-ends of the transcripts. In total, 4749 potential TSSs were detected. A position weight matrix (PWM) was derived for the promoter predictions, and the results showed that 64 \% of the TSSs were preceded by stringent or relaxed basal promoters. Of the identified TSSs, 1851 belonged to protein-coding genes. Thus, fewer than half (46 \%) of the 4040 protein-coding genes were expressed under optimal growth conditions. Seventy-two percent of all protein-coding transcripts were leaderless, which emphasized that this pathway is the major pathway for translation initiation in haloarchaea. A total of 2898 of the TSSs belonged to potential non-coding RNAs, which accounted for an unexpectedly high fraction (61 \%) of all transcripts. Most of the non-coding TSSs had not been previously described (2792) and represented novel sequences (59 \% of all TSSs). A large fraction of the potential novel non-coding transcripts were cis-antisense RNAs (1244 aTSSs). A strong negative correlation between the levels of antisense transcripts and cognate sense mRNAs was found, which suggested that the negative regulation of gene expression via antisense RNAs may play an important role in haloarchaea. The other types of novel non-coding transcripts corresponded to internal transcripts overlapping with mRNAs (1153 iTSSs) and intergenic small RNA (sRNA) candidates (395 TSSs). Conclusion This study provides a comprehensive map of the primary transcriptome of Hfx. volcanii grown under optimal conditions. Fewer than half of all protein-coding genes have been transcribed under these conditions. Unexpectedly, more than half of the detected TSSs belonged to several classes of non-coding RNAs. Thus, RNA-based regulation appears to play a more important role in haloarchaea than previously anticipated.}, language = {en} } @article{ČuklinaHahnImakaevetal.2016, author = {Čuklina, Jelena and Hahn, Julia and Imakaev, Maxim and Omasits, Ulrich and F{\"o}rstner, Konrad U. and Ljubimov, Nikolay and Goebel, Melanie and Pessi, Gabriella and Fischer, Hans-Martin and Ahrens, Christian H. and Gelfand, Mikhail S. and Evguenieva-Hackenberg, Elena}, title = {Genome-wide transcription start site mapping of Bradyrhizobium japonicum grown free-living or in symbiosis - a rich resource to identify new transcripts, proteins and to study gene regulation}, series = {BMC Genomics}, volume = {17}, journal = {BMC Genomics}, doi = {10.1186/s12864-016-2602-9}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-164565}, pages = {302}, year = {2016}, abstract = {Background Differential RNA-sequencing (dRNA-seq) is indispensable for determination of primary transcriptomes. However, using dRNA-seq data to map transcriptional start sites (TSSs) and promoters genome-wide is a bioinformatics challenge. We performed dRNA-seq of Bradyrhizobium japonicum USDA 110, the nitrogen-fixing symbiont of soybean, and developed algorithms to map TSSs and promoters. Results A specialized machine learning procedure for TSS recognition allowed us to map 15,923 TSSs: 14,360 in free-living bacteria, 4329 in symbiosis with soybean and 2766 in both conditions. Further, we provide proteomic evidence for 4090 proteins, among them 107 proteins corresponding to new genes and 178 proteins with N-termini different from the existing annotation (72 and 109 of them with TSS support, respectively). Guided by proteomics evidence, previously identified TSSs and TSSs experimentally validated here, we assign a score threshold to flag 14 \% of the mapped TSSs as a class of lower confidence. However, this class of lower confidence contains valid TSSs of low-abundant transcripts. Moreover, we developed a de novo algorithm to identify promoter motifs upstream of mapped TSSs, which is publicly available, and found motifs mainly used in symbiosis (similar to RpoN-dependent promoters) or under both conditions (similar to RpoD-dependent promoters). Mapped TSSs and putative promoters, proteomic evidence and updated gene annotation were combined into an annotation file. Conclusions The genome-wide TSS and promoter maps along with the extended genome annotation of B. japonicum represent a valuable resource for future systems biology studies and for detailed analyses of individual non-coding transcripts and ORFs. Our data will also provide new insights into bacterial gene regulation during the agriculturally important symbiosis between rhizobia and legumes.}, language = {en} } @article{SassVanAckerFoerstneretal.2015, author = {Sass, Andrea M. and Van Acker, Heleen and F{\"o}rstner, Konrad U. and Van Nieuwerburgh, Filip and Deforce, Dieter and Vogel, J{\"o}rg and Coenye, Tom}, title = {Genome-wide transcription start site profiling in biofilm-grown Burkholderia cenocepacia J2315}, series = {BMC Genomics}, volume = {16}, journal = {BMC Genomics}, number = {775}, doi = {10.1186/s12864-015-1993-3}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-139748}, year = {2015}, abstract = {Background: Burkholderia cenocepacia is a soil-dwelling Gram-negative Betaproteobacterium with an important role as opportunistic pathogen in humans. Infections with B. cenocepacia are very difficult to treat due to their high intrinsic resistance to most antibiotics. Biofilm formation further adds to their antibiotic resistance. B. cenocepacia harbours a large, multi-replicon genome with a high GC-content, the reference genome of strain J2315 includes 7374 annotated genes. This study aims to annotate transcription start sites and identify novel transcripts on a whole genome scale. Methods: RNA extracted from B. cenocepacia J2315 biofilms was analysed by differential RNA-sequencing and the resulting dataset compared to data derived from conventional, global RNA-sequencing. Transcription start sites were annotated and further analysed according to their position relative to annotated genes. Results: Four thousand ten transcription start sites were mapped over the whole B. cenocepacia genome and the primary transcription start site of 2089 genes expressed in B. cenocepacia biofilms were defined. For 64 genes a start codon alternative to the annotated one was proposed. Substantial antisense transcription for 105 genes and two novel protein coding sequences were identified. The distribution of internal transcription start sites can be used to identify genomic islands in B. cenocepacia. A potassium pump strongly induced only under biofilm conditions was found and 15 non-coding small RNAs highly expressed in biofilms were discovered. Conclusions: Mapping transcription start sites across the B. cenocepacia genome added relevant information to the J2315 annotation. Genes and novel regulatory RNAs putatively involved in B. cenocepacia biofilm formation were identified. These findings will help in understanding regulation of B. cenocepacia biofilm formation.}, language = {en} }