@conference {947, title = {Chatbot Explorer: Towards an understanding of knowledge bases of chatbot systems}, booktitle = {30th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2022}, year = {2022}, abstract = {A chatbot can automatically process a user{\textquoteright}s request, e.g. to provide a requested information. In doing so, the user starts a conversation with the chatbot and can specify the request by further inquiry. Due to the developments in the field of NLP in recent years, algorithmic text comprehension has been significantly improved. As a result, chatbots are increasingly used by companies and other institutions for various tasks such as order processes or service requests. Knowledge bases are often used to answer users queries, but these are usually curated manually in various text files, prone to errors. Visual methods can help the expert to identify common problems in the knowledge base and can provide an overview of the chatbot system. In this paper, we present Chatbot Explorer, a system to visually assist the expert to understand, explore, and manage a knowledge base of different chatbot systems. For this purpose, we provide a tree-based visualization of the knowledge base as an overview. For a detailed analysis, the expert can use appropriate visualizations to drill down the analysis to the level of individual elements of a specific story to identify problems within the knowledge base. We support the expert with automatic detection of possible problems, which can be visually highlighted. Additionally, the expert can also change the order of the queries to optimize the conversation lengths and it is possible to add new content. To develop our solution, we have conducted an iterative design process with domain experts and performed two user evaluations. The evaluations and the feedback from our domain experts have shown that our solution can significantly improve the maintainability of chatbot knowledge bases.}, author = {Alrik Hausdorf and Lydia M{\"u}ller and Gerik Scheuermann and Andreas Niekler and Daniel Wiegreffe} } @conference {948, title = {An Interactive Decision Support System for Analyzing and Linkage of Weather-Related Restrictions of Opencast Lignite Mines}, booktitle = {LEVIA{\textquoteright}22: Leipzig Symposium on Visualization in Applications 2022}, year = {2022}, author = {Yves Annanias and Jonah Windolph and Robert Wehlitz and Daniel Wiegreffe} } @article {945, title = {An Interactive Decision Support System for Land Reuse Tasks}, journal = {IEEE Computer Graphics and Applications}, volume = {42}, year = {2022}, month = {11/2022}, chapter = {72-83}, issn = {1558-1756}, doi = {10.1109/MCG.2022.3175604}, author = {Yves Annanias and Dirk Zeckzer and Gerik Scheuermann and Daniel Wiegreffe} } @article {946, title = {MDsrv: visual sharing and analysis of molecular dynamics simulations}, journal = {Nucleic Acids Research}, year = {2022}, abstract = {Molecular dynamics simulation is a proven technique for computing and visualizing the time-resolved motion of macromolecules at atomic resolution. The MDsrv is a tool that streams MD trajectories and displays them interactively in web browsers without requiring advanced skills, facilitating interactive exploration and collaborative visual analysis. We have now enhanced the MDsrv to further simplify the upload and sharing of MD trajectories and improve their online viewing and analysis. With the new instance, the MDsrv simplifies the creation of sessions, which allows the exchange of MD trajectories with preset representations and perspectives. An important innovation is that the MDsrv can now access and visualize trajectories from remote datasets, which greatly expands its applicability and use, as the data no longer needs to be accessible on a local server. In addition, initial analyses such as sequence or structure alignments, distance measurements, or RMSD calculations have been implemented, which optionally support visual analysis. Finally, based on Mol*, MDsrv now provides faster and more efficient visualization of even large trajectories compared to its predecessor tool NGL.}, doi = {10.1093/nar/gkac398}, author = {Michelle Kampfrath and Ren{\'e} Staritzbichler and Guillermo P{\'e}rez Hern{\'a}ndez and Alexander S Rose and Johanna K S Tiemann and Gerik Scheuermann and Daniel Wiegreffe and Peter W Hildebrand} } @conference {950, title = {Visualizing Similarities between American Rap-Artists}, booktitle = {EuroVis 2022 - Posters}, year = {2022}, doi = {10.2312/evp.20221129}, author = {Christofer Meinecke and Jeremias Schebera and Jakob Eschrich and Daniel Wiegreffe} } @conference {949, title = {Visualizing Similarities between American Rap-Artists based on Text Reuse}, booktitle = {LEVIA 2022: Leipzig Symposium on Visualization in Applications}, year = {2022}, author = {Christofer Meinecke and Jeremias Schebera and Jakob Eschrich and Daniel Wiegreffe} } @conference {915, title = {Report on the Correction of Erroneous Geometry Data in Land Reuse Project}, booktitle = {Workshop on Systems to Support Renaturation Projects (SyRePro 2021) }, year = {2021}, abstract = {Land Reuse processes are large planning and decision-making processes based on a large amount of geographic data. Therefore, it is essential that this data is as accurate as possible. However, errors can occur during the creation of the data and not all of them are directly noticeable. We report here what errors we have encountered while working with this geographic data, what problems they can cause, and how we have fixed them. Since the correction can be very time-consuming with the enormous amount of data, we have focused on an automatic correction. Not all of this data can be corrected this way, for the rest, we briefly indicate a procedure to support and simplify the manual correction.}, author = {Yves Annanias and Marc Wahsner and Gerik Scheuermann and Daniel Wiegreffe} } @conference {914, title = {Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning}, booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)}, year = {2021}, abstract = {Open pit mines left many regions worldwide inhospitable or uninhabitable. Many sites are left behind in a hazardous or contaminated state, show remnants of waste, or have other restrictions imposed upon them, eg, for the protection of human or nature. Such information has to be permanently managed in order to reuse those areas in the future. In this work we present and evaluate an automated workflow for supporting the post-mining management of former lignite open pit mines in the eastern part of Germany, where prior to any planned land reuse, aforementioned information has to be acquired to ensure the safety and validity of such an endeavor. Usually, this information is found in expert reports, either in the form of paper documents, or in the best case as digitized unstructured text{\textemdash}all of them in German language. However, due to the size and complexity of these documents, any inquiry is tedious and time-consuming, thereby slowing down or even obstructing the reuse of related areas. Since no training data is available, we employ active learning in order to perform multi-label sentence classification for two categories of restrictions and seven categories of topics. The final system integrates optical character recognition (OCR), active-learning-based text classification, and geographic information system visualization in order to effectively extract, query, and visualize this information for any area of interest. Active learning and text classification results are twofold: Whereas the restriction categories were reasonably accurate (> 0.85 F1), the seven topic-oriented categories seemed to be complex even for human annotators and achieved {\textellipsis}}, author = {Christopher Schr{\"o}der and Kim B{\"u}rgl and Yves Annanias and Andreas Niekler and Lydia M{\"u}lller and Daniel Wiegreffe and Christian Bender and Christoph Mengs and Gerik Scheuermann and Gerhard Heyer} } @conference {845, title = {Einsatz von K{\"u}nstlicher Intelligenz (KI) f{\"u}r die Optimierung von Planungsprozessen im Wasserbau}, booktitle = {43. Dresdner Wasserbaukolloquium 2020}, year = {2020}, author = {Patrycja-Jadwiga Sankowska and Nina Kumbruck and Christian Leyh and Andreas Niekler and Daniel Wiegreffe} } @proceedings {840, title = {LocalCompanies: Visual Analytics of spatial aligned regional companies}, year = {2020}, address = {Leipzig}, doi = {10.31219/osf.io/tsdfh}, url = {osf.io/tsdfh}, author = {Alrik Hausdorf and Andreas Niekler and Daniel Wiegreffe} } @article {879, title = {Masakari: visualization supported statistical analysis of genome segmentations}, journal = {BMC Bioinformatics}, volume = {21}, year = {2020}, month = {10/2020}, chapter = {437}, abstract = {Background In epigenetics, the change of the combination of histone modifications at the same genomic location during cell differentiation is of great interest for understanding the function of these modifications and their combinations. Besides analyzing them locally for individual genomic locations or globally using correlations between different cells types, intermediate level analyses of these changes are of interest. More specifically, the different distributions of these combinations for different cell types, respectively, are compared to gain new insights. Results and discussion We propose a new tool called {\textquoteleft}Masakari{\textquoteright} that allows segmenting genomes based on lists of ranges having a certain property, e.g., peaks describing histone modifications. It provides a graphical user interface allowing to select all data sets and setting all parameters needed for the segmentation process. Moreover, the graphical user interface provides statistical graphics allowing to assess the quality and suitability of the segmentation and the selected data. Conclusion Masakari provides statistics based visualizations and thus fosters insights into the combination of histone modification marks on genome ranges, and the differences of the distribution of these combinations between different cell types.}, doi = {10.1186/s12859-020-03761-6}, url = {https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-03761-6}, author = {Dirk Zeckzer and Alrik Hausdorf and Nicole Hinzmann and Lydia M{\"u}ller and Daniel Wiegreffe} } @article {791, title = {Big Data Competence Center ScaDS Dresden/Leipzig: Overview and selected research activities}, journal = {Datenbank-Spektrum}, volume = {19}, year = {2019}, month = {03/2019}, pages = {5-16}, type = {Schwerpunktbeitrag}, issn = {1610-1995}, doi = {10.1007/s13222-018-00303-6}, url = {https://link.springer.com/article/10.1007\%2Fs13222-018-00303-6}, author = {Erhard Rahm and Wolfgang E. Nagel and Eric Peukert and Ren{\'e} J{\"a}kel and Fabian G{\"a}rtner and Peter F. Stadler and Daniel Wiegreffe and Dirk Zeckzer and Wolfgang Lehner} } @article {772, title = {RNApuzzler: Efficient Outerplanar Drawing of RNA-Secondary Structures}, journal = {Bioinformatics}, volume = {35}, year = {2019}, month = {09/2018}, pages = {1342-1349}, doi = {10.1093/bioinformatics/bty817}, url = {https://doi.org/10.1093/bioinformatics/bty817}, author = {Daniel Wiegreffe and Daniel Alexander and Peter F. Stadler and Dirk Zeckzer} } @article {769, title = {Analyzing Histone Modifications Using Tiled Binned Clustering and 3D Scatter Plots}, journal = {Journal of WSCG}, volume = {26}, year = {2018}, month = {05/2018}, pages = {1-10}, chapter = {1}, issn = {1213-6972}, doi = {10.24132/JWSCG.2018.26.1.1}, url = {http://wscg.zcu.cz/DL/wscg_DL.htm}, author = {Dirk Zeckzer and Daniel Wiegreffe and Lydia M{\"u}ller} } @article {771, title = {The Sierra Platinum Service for generating peak-calls for replicated ChIP-seq experiments}, journal = {BMC Research Notes}, year = {2018}, month = {07/2018}, type = {Research Note}, abstract = { Objective Sierra Platinum is a fast and robust peak-caller for replicated ChIP-seq experiments with visual quality-control and -steering. The required computing resources are optimized but still may exceed the resources available to researchers at biological research institutes. Results Sierra Platinum Service provides the full functionality of Sierra Platinum: using a web interface, a new instance of the service can be generated. Then experimental data is uploaded and the computation of the peaks is started. Upon completion, the results can be inspected interactively and then downloaded for further analysis, at which point the service terminates. }, keywords = {ChIP-seq, Histone modifications, Peak-caller, Replicate analysis}, doi = {https://doi.org/10.1186/s13104-018-3633-x}, url = {https://bmcresnotes.biomedcentral.com/articles/10.1186/s13104-018-3633-x}, author = {Daniel Wiegreffe and Lydia M{\"u}ller and Jens Steuck and Dirk Zeckzer and Peter F. Stadler} } @proceedings {719, title = {iDotter - an interactive dot plot viewer}, year = {2017}, month = {08/2017}, pages = {117-124}, address = {Pilsen, Czech Republic}, abstract = {Bioinformaticians judge the likelihood of the overall RNA secondary structure based on comparing its base pair probabilities. These probabilities can be calculated by various tools and are frequently displayed using dot plots for further analysis. However, most tools produce only static dot plot images which restricts possible interactions to the capabilities of the respective viewers (mostly PostScript-viewers). Moreover, this approach does not scale well with larger RNAs since most PostScript viewers are not designed to show a huge number of elements and have only legacy support for PostScript. Therefore, we developed iDotter, an interactive tool for analyzing RNA secondary structures. iDotter overcomes the previously described limitations providing multiple interaction mech- anisms facilitating the interactive analysis of the displayed data. According to the biologists and bioinformaticians that regularly use out interactive dot plot viewer, iDotter is superior to all previous approaches with respect to facilitating dot plot based analysis of RNA secondary structures.}, keywords = {Bioinformatics Visualization, Dot Plots, Tabular Data, User Interfaces}, isbn = {978-80-86943-49-7}, author = {Daniel Wiegreffe and Alrik Hausdorf and Sebastian Z{\"a}nker and Dirk Zeckzer} } @proceedings {708, title = {Analyzing Histone Modifications in iPS Cells Using Tiled Binned 3D Scatter Plots}, year = {2016}, month = {11/2016}, pages = {1--8}, publisher = {International Symposium on Big Data Visual Analytics}, address = {Sydney, Australia}, abstract = {Epigenetics data is very important for understand- ing the differentiation of cells into different cell types. More- over, the amount of epigenetic data available was and still is considerably increasing. To cope with this big amount of data, statistical or visual analysis is used. Usually, biologists analyze epigenetic data using statistical methods like correlations on a high level. However, this does not allow to analyze the fate of histone modifications in detail during cell specification or to compare histone modifications in different cell lines. Tiled binned scatter plot matrices proved to be very useful for this type of analysis showing binary relationships. We adapted the idea of tiling and binning scatter plots from 2D to 3D, such that ternary relationships can be depicted. Comparing tiled binned 3D scatter plots{\textemdash}the new method{\textemdash}to tiled binned 2D scatter plot matrices showed, that many relations that are difficult or impossible to find using tiled binned 2D scatter plot matrices can easily be observed using the new approach. We found that using our approach, changes in the distribution of the marks over time (different cell types) or differences between different replicates of the same cell sample are easy to detect. Tiled binned 3D scatter plots proved superior compared to the previously used method due to the reduced amount of overplotting leading to less interaction necessary for gaining similar insights.}, doi = {10.1109/BDVA.2016.7787042}, author = {Dirk Zeckzer and Daniel Wiegreffe and Lydia M{\"u}ller} } @article {674, title = {A consensus network of gene regulatory factors in the human frontal lobe}, journal = {Frontiers in Genetics}, year = {2016}, abstract = {Cognitive abilities, such as memory, learning, language, problem solving, and planning, involve the frontal lobe and other brain areas. Not much is known yet about the molecular basis of cognitive abilities, but it seems clear that cognitive abilities are determined by the interplay of many genes. One approach for analyzing the genetic networks involved in cognitive functions is to study the coexpression networks of genes with known importance for proper cognitive functions, such as genes that have been associated with cognitive disorders like intellectual disability (ID) or autism spectrum disorders (ASD). Because many of these genes are gene regulatory factors (GRFs) we aimed to provide insights into the gene regulatory networks active in the human frontal lobe. Using genome wide human frontal lobe expression data from 10 independent data sets, we first derived 10 individual coexpression networks for all GRFs including their potential target genes. We observed a high level of variability among these 10 independently derived networks, pointing out that relying on results from a single study can only provide limited biological insights. To instead focus on the most confident information from these 10 networks we developed a method for integrating such independently derived networks into a consensus network. This consensus network revealed robust GRF interactions that are conserved across the frontal lobes of different healthy human individuals. Within this network, we detected a strong central module that is enriched for 166 GRFs known to be involved in brain development and/or cognitive disorders. Interestingly, several hubs of the consensus network encode for GRFs that have not yet been associated with brain functions. Their central role in the network suggests them as excellent new candidates for playing an essential role in the regulatory network of the human frontal lobe, which should be investigated in future studies. }, author = {Stefano Berto and Alvaro Perdomo-Sabogal and Daniel Wiegreffe and Jing Qin and Katja Nowick} } @article {695, title = {Sierra platinum: a fast and robust peak-caller for replicated ChIP-seq experiments with visual quality-control and -steering}, journal = {BMC Bioinformatics}, volume = {17}, year = {2016}, month = {09/2016}, pages = {1--13}, chapter = {1}, abstract = {Histone modifications play an important role in gene regulation. Their genomic locations are of great interest. Usually, the location is measured by ChIP-seq and analyzed with a peak-caller. Replicated ChIP-seq experiments become more and more available. However, their analysis is based on single-experiment peak-calling or on tools like PePr which allows peak-calling of replicates but whose underlying model might not be suitable for the conditions under which the experiments are performed.}, issn = {1471-2105}, doi = {10.1186/s12859-016-1248-6}, url = {http://dx.doi.org/10.1186/s12859-016-1248-6}, author = {Lydia M{\"u}ller and Daniel Wiegreffe and Mariam Farman and Dirk Zeckzer} } @conference {609, title = { Analyzing Chromatin Using Tiled Binned Scatterplot Matrices}, booktitle = {4th Symposium on Biologial Data Visualization}, year = {2014}, month = {07/2014}, address = {Boston, MA, USA}, author = {Dirk Zeckzer and Daniel Wiegreffe and Lydia Steiner and Sonja J. Prohaska} } @proceedings {666, title = {ChromatinVis: a tool for analyzing epigenetic data}, year = {2014}, author = {Daniel Wiegreffe and Dirk Zeckzer and Lydia M{\"u}ller and Sonja J. Prohaska} } @proceedings {667, title = {Using Significant Word Co-occurences for the Lexical Access Problem}, year = {2014}, author = {Rico Feist and Daniel Wiegreffe and Manuel Konrad and Georg Richter and Thomas Eckart and Dirk Goldhahn and Uwe Quasthoff} }