@article{ReidelbachFerrerWeber2023, author = {Reidelbach, Marco and Ferrer, Eloi and Weber, Marcus}, title = {MaRDMO Plugin}, volume = {1}, journal = {Proceedings of the Conference on Research Data Infrastructure}, publisher = {TIB Open Publishing}, issn = {2941-296X}, doi = {10.52825/cordi.v1i.254}, year = {2023}, abstract = {MaRDMO, a plugin for the Research Data Management Organiser, was developed in the Mathematical Research Data Initiative to document interdisciplinary workflows using a standardised scheme. Interdisciplinary workflows recorded this way are published directly on the MaRDI portal. In addition, central information is integrated into the MaRDI knowledge graph. Next to the documentation, MaRDMO offers the possibility to retrieve existing interdisciplinary workflows from the MaRDI Knowledge Graph to allow the reproduction of the initial work and to provide scientists with new researchimpulses. Thus, MaRDMO creates a community-driven knowledge loop that could help to overcome the replication crisis.}, language = {en} } @misc{Peter2023, type = {Master Thesis}, author = {Peter, Clea}, title = {Improving the Realism of Synthetic Cryogenic Electron Micrographs Using Generative Adversarial Networks}, year = {2023}, abstract = {This thesis addresses the problem of synthetic-to-real image refinement applied to tilt series of cryogenic electron micrographs. It explores the possibility of improving the realism of synthesized micrographs using generative adversarial networks, which could help to improve the automatic segmentation of cellular structures based on deep learning methods. For image refinement, three image-to-image translation networks were used to transfer the appearance of real micrographs to synthetic micrographs while preserving their original content, including the location and shape of particles. The first model, called SimGAN, was unable to produce any meaningful refinement. Instead, the content of the synthetic micrographs was corrupted by the addition of extensive noise, making SimGAN unsuitable for the problem of this thesis. As a result, CycleGAN was introduced and its refinement of synthetic micrographs matches the appearance of real micrographs very well. However, structural changes in the position and shape of particles were observed after translation. To avoid this behavior, CUT was used as a third model on an exploratory basis but its performance was inferior to that of CycleGAN. In conclusion, CycleGAN proved to be the most promising image-to-image translation model for the images presented, although it does not solve the main problem of this thesis. In order to do so, further modifications, such as the addition of a structural constraint during translation, are required.}, language = {en} } @inproceedings{WeimannConrad2023, author = {Weimann, Kuba and Conrad, Tim}, title = {Predicting Coma Recovery After Cardiac Arrest With Residual Neural Networks}, volume = {50}, booktitle = {Computing in Cardiology (CinC) 2023}, publisher = {IEEE}, doi = {10.22489/CinC.2023.093}, year = {2023}, abstract = {Aims: Interpretation of continuous EEG is a demanding task that requires the expertise of trained neurologists. However, these experts are not always available in many medical centers. As part of the 2023 George B. Moody PhysioNet Challenge, we developed a deep learning based method for analyzing EEG data of comatose patients and predicting prognosis following cardiac arrest. Methods: Our approach is a two-step pipeline that consists of a prediction model and a decision-making strategy. The prediction model is a residual neural network (ResNet-18) that extracts features and makes a prediction based on a short 5-minute EEG recording. In the second step, a majority vote over multiple predictions made for several EEG recordings of a patient determines the final prognosis. Results: Based on 10-fold cross-validation on the training set, we achieved a true positive rate (TPR) of 0.41 for predicting poor outcome while keeping the false positive rate below 0.05 at 72 hours after recovery of spontaneous circulation. On the official challenge leaderboard, our team ZIB_Visual scored 0.426 TPR. Conclusion: Our approach, while simple to implement and execute, faced overfitting challenges during the official competition phase. In this paper, we discuss our implementation and potential improvements to address these issues.}, language = {de} } @article{AnteghiniMartinsdosSantosSaccenti2023, author = {Anteghini, Marco and Martins dos Santos, Vitor AP and Saccenti, Edoardo}, title = {PortPred: Exploiting deep learning embeddings of amino acid sequences for the identification of transporter proteins and their substrates}, volume = {124}, journal = {Journal of Cellular Biochemistry}, number = {11}, doi = {10.1002/jcb.30490}, pages = {1665 -- 1885}, year = {2023}, abstract = {The physiology of every living cell is regulated at some level by transporter proteins which constitute a relevant portion of membrane-bound proteins and are involved in the movement of ions, small and macromolecules across bio-membranes. The importance of transporter proteins is unquestionable. The prediction and study of previously unknown transporters can lead to the discovery of new biological pathways, drugs and treatments. Here we present PortPred, a tool to accurately identify transporter proteins and their substrate starting from the protein amino acid sequence. PortPred successfully combines pre-trained deep learning-based protein embeddings and machine learning classification approaches and outperforms other state-of-the-art methods. In addition, we present a comparison of the most promising protein sequence embeddings (Unirep, SeqVec, ProteinBERT, ESM-1b) and their performances for this specific task.}, language = {en} } @article{BleichLinnemannJaidietal.2023, author = {Bleich, Amnon and Linnemann, Antje and Jaidi, Benjamin and Diem, Bjoern H and Conrad, Tim}, title = {Enhancing ECG Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification}, volume = {5}, journal = {Machine Learning and Knowledge Extraction}, number = {4}, publisher = {MDPI}, doi = {10.3390/make5040077}, year = {2023}, abstract = {Implantable Cardiac Monitor (ICM) devices are demonstrating as of today, the fastest-growing market for implantable cardiac devices. As such, they are becoming increasingly common in patients for measuring heart electrical activity. ICMs constantly monitor and record a patient's heart rhythm and when triggered - send it to a secure server where health care professionals (denote HCPs from here on) can review it. These devices employ a relatively simplistic rule-based algorithm (due to energy consumption constraints) to alert for abnormal heart rhythms. This algorithm is usually parameterized to an over-sensitive mode in order to not miss a case (resulting in a relatively high false-positive rate) and this, combined with the device's nature of constantly monitoring the heart rhythm and its growing popularity, results in HCPs having to analyze and diagnose an increasingly growing amount of data. In order to reduce the load on the latter, automated methods for ECG analysis are nowadays becoming a great tool to assist HCPs in their analysis. While state-of-the-art algorithms are data-driven rather than rule-based, training data for ICMs often consist of specific characteristics that make its analysis unique and particularly challenging. This study presents the challenges and solutions in automatically analyzing ICM data and introduces a method for its classification that outperforms existing methods on such data. It does so by combining high-frequency noise detection (which often occurs in ICM data) with a semi-supervised learning pipeline that allows for re-labeling of training episodes, and by using segmentation and dimension reduction techniques that are robust to morphology variations of the sECG signal (which are typical to ICM data). As a result, it performs better than state-of-the-art techniques on such data with e.g. F1 score of 0.51 vs. 0.38 of our baseline state-of-the-art technique in correctly calling Atrial Fibrilation in ICM data. As such, it could be used in numerous ways such as aiding HCPs in the analysis of ECGs originating from ICMs by, e.g., suggesting a rhythm type.}, language = {en} } @inproceedings{SchubotzFerrerStegmuelleretal.2023, author = {Schubotz, Moritz and Ferrer, Eloi and Stegm{\"u}ller, Johannes and Mietchen, Daniel and Teschke, Olaf and Pusch, Larissa and Conrad, Tim}, title = {Bravo MaRDI: A Wikibase Knowledge Graph on Mathematics}, booktitle = {Proceedings of the 4th Wikidata Workshop 2022 co-located with the 22st International Semantic Web Conference (ISWC2023)}, year = {2023}, abstract = {Mathematical world knowledge is a fundamental component of Wikidata. However, to date, no expertly curated knowledge graph has focused specifically on contemporary mathematics. Addressing this gap, the Mathematical Research Data Initiative (MaRDI) has developed a comprehensive knowledge graph that links multimodal research data in mathematics. This encompasses traditional research data items like datasets, software, and publications and includes semantically advanced objects such as mathematical formulae and hypotheses. This paper details the abilities of the MaRDI knowledge graph, which is based on Wikibase, leading up to its inaugural public release, codenamed Bravo, available on https://portal.mardi4nfdi.de.}, language = {de} } @incollection{AnteghiniMartinsDosSantos2023, author = {Anteghini, Marco and Martins Dos Santos, Vitor}, title = {Computational Approaches for Peroxisomal Protein Localization}, volume = {2643}, booktitle = {Peroxisomes}, publisher = {Humana, New York}, isbn = {978-1-0716-3047-1}, doi = {10.1007/978-1-0716-3048-8_29}, pages = {405 -- 411}, year = {2023}, abstract = {Computational approaches are practical when investigating putative peroxisomal proteins and for sub-peroxisomal protein localization in unknown protein sequences. Nowadays, advancements in computational methods and Machine Learning (ML) can be used to hasten the discovery of novel peroxisomal proteins and can be combined with more established computational methodologies. Here, we explain and list some of the most used tools and methodologies for novel peroxisomal protein detection and localization.}, language = {de} } @article{KiewiszBaumMuellerReichertetal.2023, author = {Kiewisz, Robert and Baum, Daniel and M{\"u}ller-Reichert, Thomas and Fabig, Gunar}, title = {Serial-section electron tomography and quantitative analysis of the microtubule organization in 3D-reconstructed mitotic spindles}, volume = {13}, journal = {Bio-protocol}, number = {20}, doi = {10.21769/BioProtoc.4849}, year = {2023}, language = {en} } @article{LongrenEigenShubitidzeetal.2023, author = {Longren, Luke L. and Eigen, Lennart and Shubitidze, Ani and Lieschnegg, Oliver and Baum, Daniel and Nyakatura, John A. and Hildebrandt, Thomas and Brecht, Michael}, title = {Dense Reconstruction of Elephant Trunk Musculature}, volume = {33}, journal = {Current Biology}, doi = {10.1016/j.cub.2023.09.007}, pages = {1 -- 8}, year = {2023}, abstract = {The elephant trunk operates as a muscular hydrostat and is actuated by the most complex musculature known in animals. Because the number of trunk muscles is unclear, we performed dense reconstructions of trunk muscle fascicles, elementary muscle units, from microCT scans of an Asian baby elephant trunk. Muscle architecture changes markedly across the trunk. Trunk tip and finger consist of about 8,000 extraordinarily filigree fascicles. The dexterous finger consists exclusively of microscopic radial fascicles pointing to a role of muscle miniaturization in elephant dexterity. Radial fascicles also predominate (at 82\% volume) the remainder of the trunk tip and we wonder if radial muscle fascicles are of particular significance for fine motor control of the dexterous trunk tip. By volume, trunk-shaft muscles comprise one-third of the numerous, small radial muscle fascicles, two-thirds of the three subtypes of large longitudinal fascicles (dorsal longitudinals, ventral outer obliques, and ventral inner obliques), and a small fraction of transversal fascicles. Shaft musculature is laterally, but not radially, symmetric. A predominance of dorsal over ventral radial muscles and of ventral over dorsal longitudinal muscles may result in a larger ability of the shaft to extend dorsally than ventrally and to bend inward rather than outward. There are around 90,000 trunk muscle fascicles. While primate hand control is based on fine control of contraction by the convergence of many motor neurons on a small set of relatively large muscles, evolution of elephant grasping has led to thousands of microscopic fascicles, which probably outnumber facial motor neurons.}, language = {en} } @article{WagendorfNahlesVachetal.2023, author = {Wagendorf, Oliver and Nahles, Susanne and Vach, Kirstin and Kernen, Florian and Zachow, Stefan and Heiland, Max and Fl{\"u}gge, Tabea}, title = {The impact of teeth and dental restorations on gray value distribution in cone-beam computer tomography - a pilot study}, volume = {9}, journal = {International Journal of Implant Dentistry}, number = {27}, doi = {10.1186/s40729-023-00493-z}, year = {2023}, abstract = {Purpose: To investigate the influence of teeth and dental restorations on the facial skeleton's gray value distributions in cone-beam computed tomography (CBCT). Methods: Gray value selection for the upper and lower jaw segmentation was performed in 40 patients. In total, CBCT data of 20 maxillae and 20 mandibles, ten partial edentulous and ten fully edentulous in each jaw, respectively, were evaluated using two different gray value selection procedures: manual lower threshold selection and automated lower threshold selection. Two sample t tests, linear regression models, linear mixed models, and Pearson's correlation coefficients were computed to evaluate the influence of teeth, dental restorations, and threshold selection procedures on gray value distributions. Results: Manual threshold selection resulted in significantly different gray values in the fully and partially edentulous mandible. (p = 0.015, difference 123). In automated threshold selection, only tendencies to different gray values in fully edentulous compared to partially edentulous jaws were observed (difference: 58-75). Significantly different gray values were evaluated for threshold selection approaches, independent of the dental situation of the analyzed jaw. No significant correlation between the number of teeth and gray values was assessed, but a trend towards higher gray values in patients with more teeth was noted. Conclusions: Standard gray values derived from CT imaging do not apply for threshold-based bone segmentation in CBCT. Teeth influence gray values and segmentation results. Inaccurate bone segmentation may result in ill-fitting surgical guides produced on CBCT data and misinterpreting bone density, which is crucial for selecting surgical protocols.}, language = {en} } @inproceedings{SiqueiraRodriguesNyakaturaZachowetal.2023, author = {Siqueira Rodrigues, Lucas and Nyakatura, John and Zachow, Stefan and Israel, Johann Habakuk}, title = {Design Challenges and Opportunities of Fossil Preparation Tools and Methods}, booktitle = {Proceedings of the 20th International Conference on Culture and Computer Science: Code and Materiality}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3623462.3623470}, year = {2023}, abstract = {Fossil preparation is the activity of processing paleontological specimens for research and exhibition purposes. In addition to traditional mechanical extraction of fossils, preparation presently comprises non-destructive digital methods that are part of a relatively new field, namely virtual paleontology. Despite significant technological advances, both traditional and digital preparation remain cumbersome and time-consuming endeavors. However, this field has received scarce attention from a human-computer interaction perspective. The present study aims to elucidate the state-of-the-art for paleontological fossil preparation in order to determine its main challenges and start a conversation regarding opportunities for creating novel designs that tackle the field's current issues. We conducted a qualitative study involving both technical preparators and virtual paleontologists. The study was divided into two parts: First, we assembled technical preparators and paleontology researchers in a focus group session to discuss their workflows, obtain a preliminary understanding of their issues, and ideate solutions based on their counterparts' workflows. Next, we conducted a series of contextual inquiries involving direct observation and semi-structured in-depth interviews. We transcribed our recordings and examined the data through theoretical and inductive thematic analysis, clustering emerging themes and applying concepts from human-computer interaction and related fields. Our findings report on challenges faced by traditional and digital fossil preparators and potential opportunities to improve their tools and workflows. We contribute with a novel analysis of fossil preparation from an HCI perspective.}, language = {en} } @inproceedings{SiqueiraRodriguesRiehmZachowetal.2023, author = {Siqueira Rodrigues, Lucas and Riehm, Felix and Zachow, Stefan and Israel, Johann Habakuk}, title = {VoxSculpt: An Open-Source Voxel Library for Tomographic Volume Sculpting in Virtual Reality}, booktitle = {2023 9th International Conference on Virtual Reality (ICVR), Xianyang, China, 2023}, doi = {10.1109/ICVR57957.2023.10169420}, pages = {515 -- 523}, year = {2023}, abstract = {Manual processing of tomographic data volumes, such as interactive image segmentation in medicine or paleontology, is considered a time-consuming and cumbersome endeavor. Immersive volume sculpting stands as a potential solution to improve its efficiency and intuitiveness. However, current open-source software solutions do not yield the required performance and functionalities. We address this issue by contributing a novel open-source game engine voxel library that supports real-time immersive volume sculpting. Our design leverages GPU instancing, parallel computing, and a chunk-based data structure to optimize collision detection and rendering. We have implemented features that enable fast voxel interaction and improve precision. Our benchmark evaluation indicates that our implementation offers a significant improvement over the state-of-the-art and can render and modify millions of visible voxels while maintaining stable performance for real-time interaction in virtual reality.}, language = {en} } @inproceedings{HarthBastTroidletal.2023, author = {Harth, Philipp and Bast, Arco and Troidl, Jakob and Meulemeester, Bjorge and Pfister, Hanspeter and Beyer, Johanna and Oberlaender, Marcel and Hege, Hans-Christian and Baum, Daniel}, title = {Rapid Prototyping for Coordinated Views of Multi-scale Spatial and Abstract Data: A Grammar-based Approach}, booktitle = {Eurographics Workshop on Visual Computing for Biology and Medicine (VCBM)}, doi = {10.2312/vcbm.20231218}, year = {2023}, abstract = {Visualization grammars are gaining popularity as they allow visualization specialists and experienced users to quickly create static and interactive views. Existing grammars, however, mostly focus on abstract views, ignoring three-dimensional (3D) views, which are very important in fields such as natural sciences. We propose a generalized interaction grammar for the problem of coordinating heterogeneous view types, such as standard charts (e.g., based on Vega-Lite) and 3D anatomical views. An important aspect of our web-based framework is that user interactions with data items at various levels of detail can be systematically integrated and used to control the overall layout of the application workspace. With the help of a concise JSON-based specification of the intended workflow, we can handle complex interactive visual analysis scenarios. This enables rapid prototyping and iterative refinement of the visual analysis tool in collaboration with domain experts. We illustrate the usefulness of our framework in two real-world case studies from the field of neuroscience. Since the logic of the presented grammar-based approach for handling interactions between heterogeneous web-based views is free of any application specifics, it can also serve as a template for applications beyond biological research.}, language = {en} }