@article{MuellerPaltraRehmannetal.2023, author = {M{\"u}ller, Sebastian and Paltra, Sydney and Rehmann, Jakob and Nagel, Kai and Conrad, Tim}, title = {Explicit modeling of antibody levels for infectious disease simulations in the context of SARS-CoV-2}, volume = {26}, journal = {iScience}, number = {9}, doi = {10.1016/j.isci.2023.107554}, year = {2023}, abstract = {Measurable levels of immunoglobulin G antibodies develop after infections with and vaccinations against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). These antibody levels are dynamic: due to waning, antibody levels will drop over time. During the COVID-19 pandemic, multiple models predicting infection dynamics were used by policymakers to support the planning of public health policies. Explicitly integrating antibody and waning effects into the models is crucial for reliable calculations of individual infection risk. However, only few approaches have been suggested that explicitly treat these effects. This paper presents a methodology that explicitly models antibody levels and the resulting protection against infection for individuals within an agent-based model. The model was developed in response to the complexity of different immunization sequences and types and is based on neutralization titer studies. This approach allows complex population studies with explicit antibody and waning effects. We demonstrate the usefulness of our model in two use cases.}, 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{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} } @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} } @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} } @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} } @article{SenguptaBartoli2025, author = {Sengupta, Agniva and Bartoli, Adrien}, title = {Convex Solutions to SfT and NRSfM under Algebraic Deformation Models}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, doi = {10.1109/TPAMI.2025.3635039}, year = {2025}, abstract = {We present nonlinear formulations to Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) faithfully exploiting the isometric, conformal and equiareal deformation models. Existing work uses relaxations such as inextensibility or requires knowing the optic flow field around the correspondences, an impractical assumption. In contrast, the proposed formulations only require point correspondences and resolve all ambiguities using the notions of maximal depth and maximal isometry heuristics. We propose solution methods using Semi-Definite Programming (SDP) for all formulations. We show that straightforward SDP models conflict with the usual maximal depth heuristic and propose an adapted opposite-depth parameterisation demonstrating a lesser relaxation gap. Experimental results on many real-world benchmark datasets demonstrate superior accuracy over existing methods.}, language = {en} } @inproceedings{ManogueSchangKuşetal.2025, author = {Manogue, Kevin and Schang, Tomasz and Ku{\c{s}}, Dilara and M{\"u}ller, Jonas and Zachow, Stefan and Sengupta, Agniva}, title = {Generalizing Shape-from-Template to Topological Changes}, booktitle = {Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference}, publisher = {The Eurographics Association}, isbn = {978-3-03868-296-7}, arxiv = {http://arxiv.org/abs/2511.03459}, doi = {10.2312/stag.20251322}, year = {2025}, abstract = {Reconstructing the surfaces of deformable objects from correspondences between a 3D template and a 2D image is well studied under Shape-from-Template (SfT) methods; however, existing approaches break down when topological changes accompany the deformation. We propose a principled extension of SfT that enables reconstruction in the presence of such changes. Our approach is initialized with a classical SfT solution and iteratively adapts the template by partitioning its spatial domain so as to minimize an energy functional that jointly encodes physical plausibility and reprojection consistency. We demonstrate that the method robustly captures a wide range of practically relevant topological events including tears and cuts on bounded 2D surfaces, thereby establishing the first general framework for topological-change-aware SfT. Experiments on both synthetic and real data confirm that our approach consistently outperforms baseline methods.}, language = {en} } @article{PuschConrad2025, author = {Pusch, Larissa and Conrad, Tim}, title = {Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Biomedical Question Answering}, volume = {5}, journal = {BioMedInformatics}, doi = {10.3390/biomedinformatics5040070}, year = {2025}, abstract = {Advancements in natural language processing (NLP), particularly Large Language Models (LLMs), have greatly improved how we access knowledge. However, in critical domains like biomedicine, challenges like hallucinations—where language models generate infor- mation not grounded in data—can lead to dangerous misinformation. This paper presents a hybrid approach that combines LLMs with Knowledge Graphs (KGs) to improve the accuracy and reliability of question-answering systems in the biomedical field. Our method, implemented using the LangChain framework, includes a query-checking algorithm that checks and, where possible, corrects LLM-generated Cypher queries, which are then exe- cuted on the Knowledge Graph, grounding answers in the KG and reducing hallucinations in the evaluated cases. We evaluated several LLMs, including several GPT models and Llama 3.3:70b, on a custom benchmark dataset of 50 biomedical questions. GPT-4 Turbo achieved 90\% query accuracy, outperforming most other models. We also evaluated prompt engineering, but found little statistically significant improvement compared to the standard prompt, except for Llama 3:70b, which improved with few-shot prompting. To enhance usability, we developed a web-based interface that allows users to input natural language queries, view generated and corrected Cypher queries, and inspect results for accuracy. This framework improves reliability and accessibility by accepting natural language questions and returning verifiable answers directly from the knowledge graph, enabling inspection and reproducibility. The source code for generating the results of this paper and for the user- interface can be found in our Git repository: https://git.zib.de/lpusch/cyphergenkg-gui, accessed on 1 November 2025.}, language = {en} } @article{PfeufferBielowWeinetal.2024, author = {Pfeuffer, Julianus and Bielow, Chris and Wein, Samuel and Jeong, Kyowon and Netz, Eugen and Walter, Axel and Alka, Oliver and Nilse, Lars and Colaianni, Pasquale Domenico and McCloskey, Douglas and Kim, Jihyung and Rosenberger, George and Bichmann, Leon and Walzer, Mathias and Veit, Johannes and Boudaud, Bertrand and Bernt, Matthias and Patikas, Nikolaos and Pilz, Matteo and Startek, Michał Piotr and Kutuzova, Svetlana and Heumos, Lukas and Charkow, Joshua and Sing, Justin Cyril and Feroz, Ayesha and Siraj, Arslan and Weisser, Hendrik and Dijkstra, Tjeerd M. H. and Perez-Riverol, Yasset and R{\"o}st, Hannes and Kohlbacher, Oliver and Sachsenberg, Timo}, title = {OpenMS 3 enables reproducible analysis of large-scale mass spectrometry data}, volume = {21}, journal = {Nature Methods}, number = {3}, publisher = {Springer Science and Business Media LLC}, issn = {1548-7091}, doi = {10.1038/s41592-024-02197-7}, pages = {365 -- 367}, year = {2024}, language = {en} } @article{WeimannConrad2024, author = {Weimann, Kuba and Conrad, Tim}, title = {Federated Learning with Deep Neural Networks: A Privacy-Preserving Approach to Enhanced ECG Classification}, volume = {28}, journal = {IEEE Journal of Biomedical and Health Informatics}, number = {11}, doi = {10.1109/JBHI.2024.3427787}, year = {2024}, language = {en} } @misc{HajarolasvadiBaum2024, author = {Hajarolasvadi, Noushin and Baum, Daniel}, title = {Data for Training the DeepOrientation Model: Simulated cryo-ET tomogram patches}, doi = {10.12752/9686}, year = {2024}, abstract = {A major restriction to applying deep learning methods in cryo-electron tomography is the lack of annotated data. Many large learning-based models cannot be applied to these images due to the lack of adequate experimental ground truth. One appealing alternative solution to the time-consuming and expensive experimental data acquisition and annotation is the generation of simulated cryo-ET images. In this context, we exploit a public cryo-ET simulator called PolNet to generate three datasets of two macromolecular structures, namely the ribosomal complex 4v4r and Thermoplasma acidophilum 20S proteasome, 3j9i. We select these two specific particles to test whether our models work for macromolecular structures with and without rotational symmetry. The three datasets contain 50, 150, and 450 tomograms with a voxel size of 10 ̊A, respectively. Here, we publish patches of size 40 × 40 × 40 extracted from the medium-sized dataset with 26,703 samples of 4v4r and 40,671 samples of 3j9i. The original tomograms from which the samples were extracted are of size 500 × 500 × 250. Finally, it should be noted that the currently published test dataset is employed for reporting the results of our paper titled "DeepOrientation: Deep Orientation Estimation of Macromolecules in Cryo-electron tomography" paper.}, language = {en} } @article{MaierWeiserConrad2025, author = {Maier, Kristina and Weiser, Martin and Conrad, Tim}, title = {Hybrid PDE-ODE Models for Efficient Simulation of Infection Spread in Epidemiology}, volume = {481}, journal = {Proceedings of the Royal Society A}, number = {2306}, publisher = {Royal Society}, arxiv = {http://arxiv.org/abs/2405.12938}, doi = {10.1098/rspa.2024.0421}, year = {2025}, abstract = {This paper introduces a novel hybrid model combining Partial Differential Equations (PDEs) and Ordinary Differential Equations (ODEs) to simulate infectious disease dynamics across geographic regions. By leveraging the spatial detail of PDEs and the computational efficiency of ODEs, the model enables rapid evaluation of public health interventions. Applied to synthetic environments and real-world scenarios in Lombardy, Italy, and Berlin, Germany, the model highlights how interactions between PDE and ODE regions affect infection dynamics, especially in high-density areas. Key findings reveal that the placement of model boundaries in densely populated regions can lead to inaccuracies in infection spread, suggesting that boundaries should be positioned in areas of lower population density to better reflect transmission dynamics. Additionally, regions with low population density hinder infection flow, indicating a need for incorporating, e.g., jumps in the model to enhance its predictive capabilities. Results indicate that the hybrid model achieves a balance between computational speed and accuracy, making it a valuable tool for policymakers in real-time decision-making and scenario analysis in epidemiology and potentially in other fields requiring similar modeling approaches.}, language = {en} }