TY - JOUR A1 - Conrad, Tim A1 - Bruckner, Sharon A1 - Kayser, Bastian T1 - Finding Modules in Networks with Non-modular Regions JF - Lecture Notes in Computer Science (Proceedings of SEA 2013) N2 - Most network clustering methods share the assumption that the network can be completely decomposed into modules, that is, every node belongs to (usually exactly one) module. Forcing this constraint can lead to misidentification of modules where none exist, while the true modules are drowned out in the noise, as has been observed e.g. for protein interaction networks. We thus propose a clustering model where networks contain both a modular region consisting of nodes that can be partitioned into modules, and a transition region containing nodes that lie between or outside modules. We propose two scores based on spectral properties to determine how well a network fits this model. We then evaluate three (partially adapted) clustering algorithms from the literature on random networks that fit our model, based on the scores and comparison to the ground truth. This allows to pinpoint the types of networks for which the different algorithms perform well. Y1 - 2013 U6 - https://doi.org/10.1007/978-3-642-38527-8_18 VL - 7933 SP - 188 EP - 199 ER - TY - JOUR A1 - Conrad, Tim A1 - Rath, Barbara A1 - Tief, Franziska A1 - Karsch, K. A1 - Muehlhans, S. A1 - Obermeier, Patrick A1 - Adamou, E. A1 - Chen, X. A1 - Seeber, L. A1 - Peiser, Ch. A1 - Hoppe, Christian A1 - von Kleist, Max A1 - Schweiger, Brunhilde T1 - Towards a personalized approach to managing of influenza infections in infants and children - food for thought and a note on oseltamivir JF - Infectious Disorders - Drug Targets Y1 - 2013 VL - 13 IS - 1 SP - 25 EP - 33 ER - TY - JOUR A1 - Conrad, Tim A1 - Leichtle, Alexander Benedikt A1 - Nuoffer, Jean-Marc A1 - Ceglarek, Uta A1 - Kase, Julia A1 - Witzigmann, Helmut A1 - Thiery, Joachim A1 - Fiedler, Georg Martin T1 - Serum amino acid profiles and their alterations in colorectal cancer JF - Metabolomics N2 - Mass spectrometry-based serum metabolic profiling is a promising tool to analyse complex cancer associated metabolic alterations, which may broaden our pathophysiological understanding of the disease and may function as a source of new cancer-associated biomarkers. Highly standardized serum samples of patients suffering from colon cancer (n = 59) and controls (n = 58) were collected at the University Hospital Leipzig. We based our investigations on amino acid screening profiles using electrospray tandem-mass spectrometry. Metabolic profiles were evaluated using the Analyst 1.4.2 software. General, comparative and equivalence statistics were performed by R 2.12.2. 11 out of 26 serum amino acid concentrations were significantly different between colorectal cancer patients and healthy controls. We found a model including CEA, glycine, and tyrosine as best discriminating and superior to CEA alone with an AUROC of 0.878 (95\% CI 0.815?0.941). Our serum metabolic profiling in colon cancer revealed multiple significant disease-associated alterations in the amino acid profile with promising diagnostic power. Further large-scale studies are necessary to elucidate the potential of our model also to discriminate between cancer and potential differential diagnoses. In conclusion, serum glycine and tyrosine in combination with CEA are superior to CEA for the discrimination between colorectal cancer patients and controls. Y1 - 2012 U6 - https://doi.org/10.1007/s11306-011-0357-5 ER - TY - JOUR A1 - Gupta, Pooja A1 - Conrad, Tim A1 - Spötter, Andreas A1 - Reinsch, Norbert A1 - Bienefeld, Kaspar T1 - Simulating a base population in honey bee for molecular genetic studies JF - Genetics Selection Evolution N2 - Over the past years, reports have indicated that honey bee populations are declining and that infestation by an ecto-parasitic mite (Varroa destructor) is one of the main causes. Selective breeding of resistant bees can help to prevent losses due to the parasite, but it requires that a robust breeding program and genetic evaluation are implemented. Genomic selection has emerged as an important tool in animal breeding programs and simulation studies have shown that it yields more accurate breeding values estimates, higher genetic gain and low rates of inbreeding. Since genomic selection relies on marker data, simulations conducted on a genomic dataset are a pre-requisite before selection can be implemented. Although genomic datasets have been simulated in other species undergoing genetic evaluation, simulation of a genomic dataset specific to the honey bee is required since this species has distinct genetic and reproductive biology characteristics. Our software program was aimed at constructing a base population by simulating a random mating honey bee population. A forward-time population simulation approach was applied since it allows modeling of genetic characteristics and reproductive behavior specific to the honey bee.  Results: Our software program yielded a genomic dataset for a base population in linkage disequilibrium. In addition, information was obtained on (1) the position of markers on each chromosome, (2) allele frequency, (3) ?2 statistics for Hardy- Weinberg equilibrium, (4) a sorted list of markers with a minor allele frequency less than or equal to the input value, (5) average r2 values of linkage disequilibrium between all simulated marker loci pair for all generations and (6) average r2 value of linkage disequilibrium in the last generation for selected markers with the highest minor allele frequency. Conclusion: We developed a software program that takes into account the genetic and reproductive biology characteristics specific to the honey bee and that can be used to constitute a genomic dataset compatible with the simulation studies necessary to optimize breeding programs. The source code together with an instruction file is freely accessible at http://msproteomics.org/Research/Misc/honeybeepopulationsimulator.html Y1 - 2012 U6 - https://doi.org/10.1186/1297-9686-44-14 ER - TY - JOUR A1 - Conrad, Tim T1 - New Appraches for Visualizing and Analyzing Metabolic Pathways JF - Proceedings of the Second Australian Undergraduate Students? Computing Conference N2 - Visualizing of metabolic pathways (or networks) has been done by many differentapproaches. In this work, we implemented and tested existing graph layout algorithms, and present a new approach to lay-out medium size metabolic pathways (500-20,000 vertices) by implementing and combining three well known graph lay-out algorithms (high dimension embedding, spring-embedder preprocessing, spring-embedder), through 3D space density analysis facilitated by the Octree technique. For the analysis of the results of metabolic pathways simulations we present two new techniques: rstly, a powerful technique to visualize pathways simulation data was created to unveil and understand concentration ows through metabolic pathways. This was achieved by mapping the color encoded concentration value of every substance from each time step of the simulation to its graphical representation in the layout. By combining all resulting images (from each time step) and displaying them as a movie, many characteristics such as subnetworks, alternative routes through the network, and differences between a modied pathway and its unmodied version can be revealed. Secondly, a new method to detect co-regulated substances in metabolic pathways and to recognize differences between two versions of a pathway, was established. To do this, we transformed the simulation data into a row-based representation, color-coded these rows, and reordered them with respect to similarity by using a Genetic Algorithm variant. From the arising discrete 2-dimensional matrix consisting of concentration values, a continuous 2-dimensional fourier row function was computed. This function can be used to measure properties, such as similarities in a pathway between time steps, or substances, or to detect and evaluate differences between modied versions of the same pathway. Y1 - 2004 ER - TY - THES A1 - Conrad, Tim T1 - Metabolic Pathways Y1 - 2004 UR - http://publications.imp.fu-berlin.de/10/ ER - TY - JOUR A1 - Vega, Iliusi A1 - Schütte, Christof A1 - Conrad, Tim T1 - Finding metastable states in real-world time series with recurrence networks JF - Physica A: Statistical Mechanics and its Applications N2 - In the framework of time series analysis with recurrence networks, we introduce a self-adaptive method that determines the elusive recurrence threshold and identifies metastable states in complex real-world time series. As initial step, we introduce a way to set the embedding parameters used to reconstruct the state space from the time series. We set them as the ones giving the maximum Shannon entropy of the diagonal line length distribution for the first simultaneous minima of recurrence rate and Shannon entropy. To identify metastable states, as well as the transitions between them, we use a soft partitioning algorithm for module finding which is specifically developed for the case in which a system shows metastability. We illustrate our method with a complex time series example. Finally, we show the robustness of our method for identifying metastable states. Our results suggest that our method is robust for identifying metastable states in complex time series, even when introducing considerable levels of noise and missing data points. Y1 - 2016 U6 - https://doi.org/10.1016/j.physa.2015.10.041 VL - 445 SP - 1 EP - 17 ER - TY - JOUR A1 - Conrad, Tim A1 - Genzel, Martin A1 - Cvetkovic, Nada A1 - Wulkow, Niklas A1 - Leichtle, Alexander Benedikt A1 - Vybiral, Jan A1 - Kytyniok, Gitta A1 - Schütte, Christof T1 - Sparse Proteomics Analysis – a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data JF - BMC Bioinfomatics N2 - Background: High-throughput proteomics techniques, such as mass spectrometry (MS)-based approaches, produce very high-dimensional data-sets. In a clinical setting one is often interested in how mass spectra differ between patients of different classes, for example spectra from healthy patients vs. spectra from patients having a particular disease. Machine learning algorithms are needed to (a) identify these discriminating features and (b) classify unknown spectra based on this feature set. Since the acquired data is usually noisy, the algorithms should be robust against noise and outliers, while the identified feature set should be as small as possible. Results: We present a new algorithm, Sparse Proteomics Analysis (SPA),based on thet heory of compressed sensing that allows us to identify a minimal discriminating set of features from mass spectrometry data-sets. We show (1) how our method performs on artificial and real-world data-sets, (2) that its performance is competitive with standard (and widely used) algorithms for analyzing proteomics data, and (3) that it is robust against random and systematic noise. We further demonstrate the applicability of our algorithm to two previously published clinical data-sets. Y1 - 2017 U6 - https://doi.org/10.1186/s12859-017-1565-4 VL - 18 IS - 160 ER - TY - GEN A1 - Vega, Iliusi A1 - Schütte, Christof A1 - Conrad, Tim T1 - SAIMeR: Self-adapted method for the identification of metastable states in real-world time series N2 - In the framework of time series analysis with recurrence networks, we introduce SAIMeR, a heuristic self-adapted method that determines the elusive recurrence threshold and identifies metastable states in complex time series. To identify metastable states as well as the transitions between them, we use graph theory concepts and a fuzzy partitioning clustering algorithm. We illustrate SAIMeR by applying it to three real-world time series and show that it is able to identify metastable states in real-world data with noise and missing data points. Finally, we suggest a way to choose the embedding parameters used to construct the state space in which this method is performed, based on the analysis of how the values of these parameters affect two recurrence quantitative measurements: recurrence rate and entropy. T3 - ZIB-Report - 14-16 KW - time series analysis KW - application in statistical physics KW - recurrence quantification analysis KW - threshold KW - metastability KW - non-linear dynamics Y1 - 2014 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-50130 SN - 1438-0064 ER - TY - GEN A1 - Schütte, Christof A1 - Conrad, Tim ED - Deuflhard, Peter ED - Grötschel, Martin ED - Hömberg, Dietmar ED - Horst, Ulrich ED - Kramer, Jürg ED - Mehrmann, Volker ED - Polthier, Konrad ED - Schmidt, Frank ED - Skutella, Martin ED - Sprekels, Jürgen T1 - Showcase 3: Information-based medicine T2 - MATHEON-Mathematics for Key Technologies Y1 - 2014 VL - 1 SP - 66 EP - 67 PB - European Mathematical Society ER - TY - JOUR A1 - Müller, Sebastian A1 - Paltra, Sydney A1 - Rehmann, Jakob A1 - Nagel, Kai A1 - Conrad, Tim T1 - Explicit modeling of antibody levels for infectious disease simulations in the context of SARS-CoV-2 JF - iScience N2 - 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. Y1 - 2023 U6 - https://doi.org/10.1016/j.isci.2023.107554 VL - 26 IS - 9 ER - TY - CHAP A1 - Weimann, Kuba A1 - Conrad, Tim T1 - Predicting Coma Recovery After Cardiac Arrest With Residual Neural Networks T2 - Computing in Cardiology (CinC) 2023 N2 - 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. Y1 - 2023 U6 - https://doi.org/10.22489/CinC.2023.093 VL - 50 PB - IEEE ER - TY - JOUR A1 - Bleich, Amnon A1 - Linnemann, Antje A1 - Jaidi, Benjamin A1 - Diem, Bjoern H A1 - Conrad, Tim T1 - Enhancing ECG Analysis of Implantable Cardiac Monitor Data: An Efficient Pipeline for Multi-Label Classification JF - Machine Learning and Knowledge Extraction N2 - 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. Y1 - 2023 U6 - https://doi.org/10.3390/make5040077 VL - 5 IS - 4 PB - MDPI ER - TY - CHAP A1 - Schubotz, Moritz A1 - Ferrer, Eloi A1 - Stegmüller, Johannes A1 - Mietchen, Daniel A1 - Teschke, Olaf A1 - Pusch, Larissa A1 - Conrad, Tim T1 - Bravo MaRDI: A Wikibase Knowledge Graph on Mathematics T2 - Proceedings of the 4th Wikidata Workshop 2022 co-located with the 22st International Semantic Web Conference (ISWC2023) N2 - 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. Y1 - 2023 ER - TY - JOUR A1 - Pusch, Larissa A1 - Conrad, Tim T1 - Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Biomedical Question Answering JF - BioMedInformatics N2 - 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. Y1 - 2025 U6 - https://doi.org/10.3390/biomedinformatics5040070 VL - 5 ER - TY - JOUR A1 - Conrad, Tim A1 - Ferrer, Eloi A1 - Mietchen, Daniel A1 - Pusch, Larissa A1 - Stegmuller, Johannes A1 - Schubotz, Moritz T1 - Making Mathematical Research Data FAIR: Pathways to Improved Data Sharing JF - Scientific Data Y1 - 2024 U6 - https://doi.org/10.1038/s41597-024-03480-0 VL - 11 ER - TY - JOUR A1 - Fürst, Steffen A1 - Conrad, Tim A1 - Jaeger, Carlo A1 - Wolf, Sarah T1 - Vahana.jl - A framework (not only) for large-scale agent-based models JF - Proceedings of Social Simulation Conference 2024 (SSC24) Y1 - 2024 ER - TY - JOUR A1 - Weimann, Kuba A1 - Conrad, Tim T1 - Federated Learning with Deep Neural Networks: A Privacy-Preserving Approach to Enhanced ECG Classification JF - IEEE Journal of Biomedical and Health Informatics Y1 - 2024 U6 - https://doi.org/10.1109/JBHI.2024.3427787 VL - 28 IS - 11 ER - TY - JOUR A1 - Maier, Kristina A1 - Weiser, Martin A1 - Conrad, Tim T1 - Hybrid PDE-ODE Models for Efficient Simulation of Infection Spread in Epidemiology JF - Proceedings of the Royal Society A N2 - 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. Y1 - 2025 U6 - https://doi.org/10.1098/rspa.2024.0421 VL - 481 IS - 2306 PB - Royal Society ER - TY - JOUR A1 - Weimann, Kuba A1 - Conrad, Tim T1 - FELRec: Efficient Handling of Item Cold-Start With Dynamic Representation Learning in Recommender Systems JF - International Journal of Data Science and Analytics Y1 - 2024 U6 - https://doi.org/10.1007/s41060-024-00635-5 IS - 2024 PB - Springer Nature ER - TY - JOUR A1 - Bostanci, Inan A1 - Conrad, Tim T1 - Integrating Agent-Based and Compartmental Models for Infectious Disease Modeling: A Novel Hybrid Approach JF - Journal of Artificial Societies and Social Simulation N2 - This study investigates the spatial integration of agent-based models (ABMs) and compartmental models for infectious disease modeling, presenting a novel hybrid approach and examining its implications. ABMs offer detailed insights by simulating interactions and decisions among individuals but are computationally expensive for large populations. Compartmental models capture population-level dynamics more efficiently but lack granular detail. We developed a hybrid model that aims to balance the granularity of ABMs with the computational efficiency of compartmental models, offering a more nuanced understanding of disease spread in diverse scenarios, including large populations. This model spatially couples discrete and continuous populations by integrating an ordinary differential equation model with a spatially explicit ABM. Our key objectives were to systematically assess the consistency of disease dynamics and the computational efficiency across various configurations. For this, we evaluated two experimental scenarios and varied the influence of each sub-model via spatial distribution. In the first, the ABM component modeled a homogeneous population; in the second, it simulated a heterogeneous population with landscape-driven movement. Results show that the hybrid model can significantly reduce computational costs but is sensitive to between-model differences, highlighting the importance of model equivalence in hybrid approaches. The code is available at: git.zib.de/ibostanc/hybrid_abm_ode. Y1 - 2025 U6 - https://doi.org/10.18564/jasss.5567 VL - 28 IS - 1 ER - TY - JOUR A1 - Paltra, Sydney A1 - Conrad, Tim T1 - Clinical Effectiveness of Ritonavir-Boosted Nirmatrelvir—A Literature Review JF - Advances in Respiratory Medicine N2 - Nirmatrelvir/Ritonavir is an oral treatment for mild to moderate COVID-19 cases with a high risk for a severe course of the disease. For this paper, a comprehensive literature review was performed, leading to a summary of currently available data on Nirmatrelvir/Ritonavir’s ability to reduce the risk of progressing to a severe disease state. Herein, the focus lies on publications that include comparisons between patients receiving Nirmatrelvir/Ritonavir and a control group. The findings can be summarized as follows: Data from the time when the Delta-variant was dominant show that Nirmatrelvir/Ritonavir reduced the risk of hospitalization or death by 88.9% for unvaccinated, non-hospitalized high-risk individuals. Data from the time when the Omicron variant was dominant found decreased relative risk reductions for various vaccination statuses: between 26% and 65% for hospitalization. The presented papers that differentiate between unvaccinated and vaccinated individuals agree that unvaccinated patients benefit more from treatment with Nirmatrelvir/Ritonavir. However, when it comes to the dependency of potential on age and comorbidities, further studies are necessary. From the available data, one can conclude that Nirmatrelvir/Ritonavir cannot substitute vaccinations; however, its low manufacturing cost and easy administration make it a valuable tool in fighting COVID-19, especially for countries with low vaccination rates. Y1 - 2024 U6 - https://doi.org/10.3390/arm92010009 VL - 92 IS - 1 ER - TY - JOUR A1 - Weimann, Kuba A1 - Conrad, Tim T1 - Self-supervised pre-training with joint-embedding predictive architecture boosts ECG classification performance JF - Computers in Biology and Medicine N2 - Accurate diagnosis of heart arrhythmias requires the interpretation of electrocardiograms (ECG), which capture the electrical activity of the heart. Automating this process through machine learning is challenging due to the need for large annotated datasets, which are difficult and costly to collect. To address this issue, transfer learning is often employed, where models are pre-trained on large datasets and fine-tuned for specific ECG classification tasks with limited labeled data. Self-supervised learning has become a widely adopted pre-training method, enabling models to learn meaningful representations from unlabeled datasets. In this work, we explore the joint-embedding predictive architecture (JEPA) for self-supervised learning from ECG data. Unlike invariance-based methods, JEPA does not rely on hand-crafted data augmentations, and unlike generative methods, it predicts latent features rather than reconstructing input data. We create a large unsupervised pre-training dataset by combining ten public ECG databases, amounting to over one million records. We pre-train Vision Transformers using JEPA on this dataset and fine-tune them on various PTB-XL benchmarks. Our results show that JEPA outperforms existing invariance-based and generative approaches, achieving an AUC of 0.945 on the PTB-XL all statements task. JEPA consistently learns the highest quality representations, as demonstrated in frozen evaluations, and proves advantageous for pre-training even in the absence of additional data. Y1 - 2025 U6 - https://doi.org/10.1016/j.compbiomed.2025.110809 SN - 0010-4825 VL - 196 PB - Elsevier BV ER - TY - CHAP A1 - Maignant, Elodie A1 - Conrad, Tim A1 - von Tycowicz, Christoph T1 - Tree inference with varifold distances T2 - Geometric Science of Information. GSI 2025 N2 - In this paper, we consider a tree inference problem motivated by the critical problem in single-cell genomics of reconstructing dynamic cellular processes from sequencing data. In particular, given a population of cells sampled from such a process, we are interested in the problem of ordering the cells according to their progression in the process. This is known as trajectory inference. If the process is differentiation, this amounts to reconstructing the corresponding differentiation tree. One way of doing this in practice is to estimate the shortest-path distance between nodes based on cell similarities observed in sequencing data. Recent sequencing techniques make it possible to measure two types of data: gene expression levels, and RNA velocity, a vector that predicts changes in gene expression. The data then consist of a discrete vector field on a (subset of a) Euclidean space of dimension equal to the number of genes under consideration. By integrating this velocity field, we trace the evolution of gene expression levels in each single cell from some initial stage to its current stage. Eventually, we assume that we have a faithful embedding of the differentiation tree in a Euclidean space, but which we only observe through the curves representing the paths from the root to the nodes. Using varifold distances between such curves, we define a similarity measure between nodes which we prove approximates the shortest-path distance in a tree that is isomorphic to the target tree. Y1 - 2025 U6 - https://doi.org/10.1007/978-3-032-03921-7_30 VL - 16034 ER - TY - JOUR A1 - Melnyk, Kateryna A1 - Weimann, Kuba A1 - Conrad, Tim T1 - Understanding microbiome dynamics via interpretable graph representation learning JF - Scientific Reports N2 - Large-scale perturbations in the microbiome constitution are strongly correlated, whether as a driver or a consequence, with the health and functioning of human physiology. However, understanding the difference in the microbiome profiles of healthy and ill individuals can be complicated due to the large number of complex interactions among microbes. We propose to model these interactions as a time-evolving graph whose nodes are microbes and edges are interactions among them. Motivated by the need to analyse such complex interactions, we develop a method that learns a low-dimensional representation of the time-evolving graph and maintains the dynamics occurring in the high-dimensional space. Through our experiments, we show that we can extract graph features such as clusters of nodes or edges that have the highest impact on the model to learn the low-dimensional representation. This information can be crucial to identify microbes and interactions among them that are strongly correlated with clinical diseases. We conduct our experiments on both synthetic and real-world microbiome datasets. Y1 - 2023 U6 - https://doi.org/10.1038/s41598-023-29098-7 VL - 13 SP - 2058 ER - TY - JOUR A1 - Liang, YongTian A1 - Piao, Chengji A1 - Beuschel, Christine B. A1 - Toppe, David A1 - Kollipara, Laxmikanth A1 - Bogdanow, Boris A1 - Maglione, Marta A1 - Lützkendorf, Janine A1 - See, Jason Chun Kit A1 - Huang, Sheng A1 - Conrad, Tim A1 - Kintscher, Ulrich A1 - Madeo, Frank A1 - Liu, Fan A1 - Sickmann, Albert A1 - Sigrist, Stephan J. T1 - eIF5A hypusination, boosted by dietary spermidine, protects from premature brain aging and mitochondrial dysfunction JF - Cell Reports Y1 - 2021 U6 - https://doi.org/10.1016/j.celrep.2021.108941 VL - 35 IS - 2 ER - TY - JOUR A1 - Melnyk, Kateryna A1 - Montavon, Grègoire A1 - Klus, Stefan A1 - Conrad, Tim T1 - Graph Kernel Koopman Embedding for Human Microbiome Analysis JF - Applied Network Science N2 - More and more diseases have been found to be strongly correlated with disturbances in the microbiome constitution, e.g., obesity, diabetes, or some cancer types. Thanks to modern high-throughput omics technologies, it becomes possible to directly analyze human microbiome and its influence on the health status. Microbial communities are monitored over long periods of time and the associations between their members are explored. These relationships can be described by a time-evolving graph. In order to understand responses of the microbial community members to a distinct range of perturbations such as antibiotics exposure or diseases and general dynamical properties, the time-evolving graph of the human microbial communities has to be analyzed. This becomes especially challenging due to dozens of complex interactions among microbes and metastable dynamics. The key to solving this problem is the representation of the time-evolving graphs as fixed-length feature vectors preserving the original dynamics. We propose a method for learning the embedding of the time-evolving graph that is based on the spectral analysis of transfer operators and graph kernels. We demonstrate that our method can capture temporary changes in the time-evolving graph on both synthetic data and real-world data. Our experiments demonstrate the efficacy of the method. Furthermore, we show that our method can be applied to human microbiome data to study dynamic processes. Y1 - 2020 U6 - https://doi.org/10.1007/s41109-020-00339-2 VL - 5 IS - 96 ER - TY - JOUR A1 - Iravani, Sahar A1 - Conrad, Tim T1 - An Interpretable Deep Learning Approach for Biomarker Detection in LC-MS Proteomics Data JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics N2 - Analyzing mass spectrometry-based proteomics data with deep learning (DL) approaches poses several challenges due to the high dimensionality, low sample size, and high level of noise. Additionally, DL-based workflows are often hindered to be integrated into medical settings due to the lack of interpretable explanation. We present DLearnMS, a DL biomarker detection framework, to address these challenges on proteomics instances of liquid chromatography-mass spectrometry (LC-MS) - a well-established tool for quantifying complex protein mixtures. Our DLearnMS framework learns the clinical state of LC-MS data instances using convolutional neural networks. Based on the trained neural networks, we show how biomarkers can be identified using layer-wise relevance propagation. This enables detecting discriminating regions of the data and the design of more robust networks. One of the main advantages over other established methods is that no explicit preprocessing step is needed in our DLearnMS framework. Our evaluation shows that DLearnMS outperforms conventional LC-MS biomarker detection approaches in identifying fewer false positive peaks while maintaining a comparable amount of true positives peaks. Y1 - 2023 U6 - https://doi.org/10.1109/tcbb.2022.3141656 VL - 20 IS - 1 SP - 151 EP - 161 ER - TY - JOUR A1 - Rams, Mona A1 - Conrad, Tim T1 - Dictionary learning allows model-free pseudotime estimation of transcriptomics data JF - BMC Genomics Y1 - 2022 U6 - https://doi.org/10.1186/s12864-021-08276-9 VL - 23 PB - BioMed Central ER - TY - JOUR A1 - Weimann, K. A1 - Conrad, Tim T1 - Transfer Learning for ECG Classification JF - Scientific Reports N2 - Remote monitoring devices, which can be worn or implanted, have enabled a more effective healthcare for patients with periodic heart arrhythmia due to their ability to constantly monitor heart activity. However, these devices record considerable amounts of electrocardiogram (ECG) data that needs to be interpreted by physicians. Therefore, there is a growing need to develop reliable methods for automatic ECG interpretation to assist the physicians. Here, we use deep convolutional neural networks (CNN) to classify raw ECG recordings. However, training CNNs for ECG classification often requires a large number of annotated samples, which are expensive to acquire. In this work, we tackle this problem by using transfer learning. First, we pretrain CNNs on the largest public data set of continuous raw ECG signals. Next, we finetune the networks on a small data set for classification of Atrial Fibrillation, which is the most common heart arrhythmia. We show that pretraining improves the performance of CNNs on the target task by up to 6.57%, effectively reducing the number of annotations required to achieve the same performance as CNNs that are not pretrained. We investigate both supervised as well as unsupervised pretraining approaches, which we believe will increase in relevance, since they do not rely on the expensive ECG annotations. The code is available on GitHub at https://github.com/kweimann/ecg-transfer-learning. Y1 - 2021 U6 - https://doi.org/10.1038/s41598-021-84374-8 VL - 11 ER - TY - JOUR A1 - Le Duc, Huy A1 - Conrad, Tim T1 - A light-weight and highly flexible software system for analyzing large bio-medical datasets JF - Future Generation Computer Systems Y1 - 2020 ER - TY - JOUR A1 - Juds, Carmen A1 - Schmidt, Johannes A1 - Weller, Michael A1 - Lange, Thorid A1 - Conrad, Tim A1 - Boerner, Hans T1 - Combining Phage Display and Next-generation Sequencing for Materials Sciences: A Case Study on Probing Polypropylene Surfaces JF - Journal of the American Chemical Society N2 - Phage display biopanning with Illumina next-generation sequencing (NGS) is applied to reveal insights into peptide-based adhesion domains for polypropylene (PP). One biopanning round followed by NGS selects robust PP-binding peptides that are not evident by Sanger sequencing. NGS provides a significant statistical base that enables motif analysis, statistics on positional residue depletion/enrichment, and data analysis to suppress false-positive sequences from amplification bias. The selected sequences are employed as water-based primers for PP?metal adhesion to condition PP surfaces and increase adhesive strength by 100\% relative to nonprimed PP. Y1 - 2020 U6 - https://doi.org/10.1021/jacs.0c03482 VL - 142 IS - 24 SP - 10624 EP - 10628 ER - TY - JOUR A1 - Cvetkovic, Nada A1 - Conrad, Tim A1 - Lie, Han Cheng T1 - A Convergent Discretisation Method for Transition Path Theory for Diffusion Processes JF - Multiscale Modeling & Simulation Y1 - 2021 U6 - https://doi.org/10.1137/20M1329354 VL - 19 IS - 1 SP - 242 EP - 266 PB - Society for Industrial and Applied Mathematics ER - TY - JOUR A1 - Tuncay, Erhun Giray A1 - Erdur, Rıza Cenk A1 - Conrad, Tim T1 - Parallel Exchange of Randomized SubGraphs for Optimization of Network Alignment: PERSONA JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics N2 - The aim of Network Alignment in Protein-Protein Interaction Networks is discovering functionally similar regions between compared organisms. One major compromise for solving a network alignment problem is the trade-off among multiple similarity objectives while applying an alignment strategy. An alignment may lose its biological relevance while favoring certain objectives upon others due to the actual relevance of unfavored objectives. One possible solution for solving this issue may be blending the stronger aspects of various alignment strategies until achieving mature solutions. This study proposes a parallel approach called PERSONA that allows aligners to share their partial solutions continuously while they progress. All these aligners pursue their particular heuristics as part of a particle swarm that searches for multi-objective solutions of the same alignment problem in a reactive actor environment. The actors use the stronger portion of a solution as a subgraph that they receive from leading or other actors and send their own stronger subgraphs back upon evaluation of those partial solutions. Moreover, the individual heuristics of each actor takes randomized parameter values at each cycle of parallel execution so that the problem search space can thoroughly be investigated. The results achieved with PERSONA are remarkably optimized and balanced for both topological and node similarity objectives. Y1 - 2023 U6 - https://doi.org/10.1109/TCBB.2022.3231489 VL - 20 IS - 3 SP - 2064 EP - 2077 ER - TY - JOUR A1 - Alchikh, Maren A1 - Conrad, Tim A1 - Obermeier, Patrick A1 - Ma, Xiaolin A1 - Schweiger, Brunhilde A1 - Opota, Onya A1 - Rath, Barbara T1 - Disease Burden and Inpatient Management of Children with Acute Respiratory Viral Infections during the Pre-COVID Era in Germany: A Cost-of-Illness Study JF - Viruses N2 - Respiratory viral infections (RVIs) are common reasons for healthcare consultations. The inpatient management of RVIs consumes significant resources. From 2009 to 2014, we assessed the costs of RVI management in 4776 hospitalized children aged 0–18 years participating in a quality improvement program, where all ILI patients underwent virologic testing at the National Reference Centre followed by detailed recording of their clinical course. The direct (medical or non-medical) and indirect costs of inpatient management outside the ICU (‘non-ICU’) versus management requiring ICU care (‘ICU’) added up to EUR 2767.14 (non-ICU) vs. EUR 29,941.71 (ICU) for influenza, EUR 2713.14 (non-ICU) vs. EUR 16,951.06 (ICU) for RSV infections, and EUR 2767.33 (non-ICU) vs. EUR 14,394.02 (ICU) for human rhinovirus (hRV) infections, respectively. Non-ICU inpatient costs were similar for all eight RVIs studied: influenza, RSV, hRV, adenovirus (hAdV), metapneumovirus (hMPV), parainfluenza virus (hPIV), bocavirus (hBoV), and seasonal coronavirus (hCoV) infections. ICU costs for influenza, however, exceeded all other RVIs. At the time of the study, influenza was the only RVI with antiviral treatment options available for children, but only 9.8% of influenza patients (non-ICU) and 1.5% of ICU patients with influenza received antivirals; only 2.9% were vaccinated. Future studies should investigate the economic impact of treatment and prevention of influenza, COVID-19, and RSV post vaccine introduction. Y1 - 2024 U6 - https://doi.org/10.3390/v16040507 VL - 16 IS - 4 ER - TY - JOUR A1 - Sherratt, Katharine A1 - Srivastava, Ajitesh A1 - Ainslie, Kylie A1 - Singh, David E. A1 - Cublier, Aymar A1 - Marinescu, Maria Cristina A1 - Carretero, Jesus A1 - Garcia, Alberto Cascajo A1 - Franco, Nicolas A1 - Willem, Lander A1 - Abrams, Steven A1 - Faes, Christel A1 - Beutels, Philippe A1 - Hens, Niel A1 - Müller, Sebastian A1 - Charlton, Billy A1 - Ewert, Ricardo A1 - Paltra, Sydney A1 - Rakow, Christian A1 - Rehmann, Jakob A1 - Conrad, Tim A1 - Schütte, Christof A1 - Nagel, Kai A1 - Abbott, Sam A1 - Grah, Rok A1 - Niehus, Rene A1 - Prasse, Bastian A1 - Sandmann, Frank A1 - Funk, Sebastian T1 - Characterising information gains and losses when collecting multiple epidemic model outputs JF - Epidemics N2 - Collaborative comparisons and combinations of epidemic models are used as policy-relevant evidence during epidemic outbreaks. In the process of collecting multiple model projections, such collaborations may gain or lose relevant information. Typically, modellers contribute a probabilistic summary at each time-step. We compared this to directly collecting simulated trajectories. We aimed to explore information on key epidemic quantities; ensemble uncertainty; and performance against data, investigating potential to continuously gain information from a single cross-sectional collection of model results. Methods We compared July 2022 projections from the European COVID-19 Scenario Modelling Hub. Five modelling teams projected incidence in Belgium, the Netherlands, and Spain. We compared projections by incidence, peaks, and cumulative totals. We created a probabilistic ensemble drawn from all trajectories, and compared to ensembles from a median across each model’s quantiles, or a linear opinion pool. We measured the predictive accuracy of individual trajectories against observations, using this in a weighted ensemble. We repeated this sequentially against increasing weeks of observed data. We evaluated these ensembles to reflect performance with varying observed data. Results. By collecting modelled trajectories, we showed policy-relevant epidemic characteristics. Trajectories contained a right-skewed distribution well represented by an ensemble of trajectories or a linear opinion pool, but not models’ quantile intervals. Ensembles weighted by performance typically retained the range of plausible incidence over time, and in some cases narrowed this by excluding some epidemic shapes. Conclusions. We observed several information gains from collecting modelled trajectories rather than quantile distributions, including potential for continuously updated information from a single model collection. The value of information gains and losses may vary with each collaborative effort’s aims, depending on the needs of projection users. Understanding the differing information potential of methods to collect model projections can support the accuracy, sustainability, and communication of collaborative infectious disease modelling efforts. Data availability All code and data available on Github: https://github.com/covid19-forecast-hub-europe/aggregation-info-loss KW - Virology KW - Infectious Diseases KW - Public Health, Environmental and Occupational Health KW - Microbiology KW - Parasitology KW - Epidemiology Y1 - 2024 U6 - https://doi.org/10.1016/j.epidem.2024.100765 SN - 1755-4365 VL - 47 PB - Elsevier BV ER - TY - JOUR A1 - Gaskin, Thomas A1 - Conrad, Tim A1 - Pavliotis, Grigorios A. A1 - Schütte, Christof T1 - Neural parameter calibration and uncertainty quantification for epidemic forecasting JF - PLOS ONE N2 - The recent COVID-19 pandemic has thrown the importance of accurately forecasting contagion dynamics and learning infection parameters into sharp focus. At the same time, effective policy-making requires knowledge of the uncertainty on such predictions, in order, for instance, to be able to ready hospitals and intensive care units for a worst-case scenario without needlessly wasting resources. In this work, we apply a novel and powerful computational method to the problem of learning probability densities on contagion parameters and providing uncertainty quantification for pandemic projections. Using a neural network, we calibrate an ODE model to data of the spread of COVID-19 in Berlin in 2020, achieving both a significantly more accurate calibration and prediction than Markov-Chain Monte Carlo (MCMC)-based sampling schemes. The uncertainties on our predictions provide meaningful confidence intervals e.g. on infection figures and hospitalisation rates, while training and running the neural scheme takes minutes where MCMC takes hours. We show convergence of our method to the true posterior on a simplified SIR model of epidemics, and also demonstrate our method's learning capabilities on a reduced dataset, where a complex model is learned from a small number of compartments for which data is available. Y1 - 2024 U6 - https://doi.org/10.1371/journal.pone.0306704 VL - 19 IS - 10 ER - TY - JOUR A1 - Obermeier, Patrick E A1 - Heim, Albert A1 - Biere, Barbara A1 - Hage, Elias A1 - Alchikh, Maren A1 - Conrad, Tim A1 - Schweiger, Brunhilde A1 - Rath, Barbara A T1 - Linking digital surveillance and in-depth virology to study clinical patterns of viral respiratory infections in vulnerable patient populations JF - iScience N2 - To improve the identification and management of viral respiratory infections, we established a clinical and virologic surveillance program for pediatric patients fulfilling pre-defined case criteria of influenza-like illness and viral respiratory infections. The program resulted in a cohort comprising 6,073 patients (56% male, median age 1.6 years, range 0–18.8 years), where every patient was assessed with a validated disease severity score at the point-of-care using the ViVI ScoreApp. We used machine learning and agnostic feature selection to identify characteristic clinical patterns. We tested all patients for human adenoviruses, 571 (9%) were positive. Adenovirus infections were particularly common and mild in children ≥1 month of age but rare and potentially severe in neonates: with lower airway involvement, disseminated disease, and a 50% mortality rate (n = 2/4). In one fatal case, we discovered a novel virus … Y1 - 2022 U6 - https://doi.org/10.1016/j.isci.2022.104276 VL - 25 IS - 5 PB - Cell Press ER - TY - JOUR A1 - Zhang, Wei A1 - Klus, Stefan A1 - Conrad, Tim A1 - Schütte, Christof T1 - Learning chemical reaction networks from trajectory data JF - SIAM Journal on Applied Dynamical Systems (SIADS) N2 - We develop a data-driven method to learn chemical reaction networks from trajectory data. Modeling the reaction system as a continuous-time Markov chain and assuming the system is fully observed,our method learns the propensity functions of the system with predetermined basis functions by maximizing the likelihood function of the trajectory data under l^1 sparse regularization. We demonstrate our method with numerical examples using synthetic data and carry out an asymptotic analysis of the proposed learning procedure in the infinite-data limit. Y1 - 2019 U6 - https://doi.org/10.1137/19M1265880 VL - 18 IS - 4 SP - 2000 EP - 2046 ER - TY - CHAP A1 - Iravani, Sahar A1 - Conrad, Tim ED - Holzinger, A. ED - Kieseberg, P. ED - Tjoa, A. ED - Weippl, E. T1 - Deep Learning for Proteomics Data for Feature Selection and Classification T2 - Machine Learning and Knowledge Extraction. CD-MAKE 2019 Y1 - 2019 U6 - https://doi.org/10.1007/978-3-030-29726-8_19 VL - 11713 PB - Springer, Cham ER -