@phdthesis{Conrad2004, author = {Conrad, Tim}, title = {Metabolic Pathways}, year = {2004}, language = {en} } @article{VegaSchuetteConrad2016, author = {Vega, Iliusi and Sch{\"u}tte, Christof and Conrad, Tim}, title = {Finding metastable states in real-world time series with recurrence networks}, volume = {445}, journal = {Physica A: Statistical Mechanics and its Applications}, doi = {10.1016/j.physa.2015.10.041}, pages = {1 -- 17}, year = {2016}, abstract = {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.}, language = {en} } @article{ConradGenzelCvetkovicetal.2017, author = {Conrad, Tim and Genzel, Martin and Cvetkovic, Nada and Wulkow, Niklas and Leichtle, Alexander Benedikt and Vybiral, Jan and Kytyniok, Gitta and Sch{\"u}tte, Christof}, title = {Sparse Proteomics Analysis - a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data}, volume = {18}, journal = {BMC Bioinfomatics}, number = {160}, doi = {10.1186/s12859-017-1565-4}, year = {2017}, abstract = {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.}, language = {en} } @misc{VegaSchuetteConrad2014, author = {Vega, Iliusi and Sch{\"u}tte, Christof and Conrad, Tim}, title = {SAIMeR: Self-adapted method for the identification of metastable states in real-world time series}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-50130}, year = {2014}, abstract = {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.}, language = {en} } @misc{SchuetteConrad2014, author = {Sch{\"u}tte, Christof and Conrad, Tim}, title = {Showcase 3: Information-based medicine}, volume = {1}, journal = {MATHEON-Mathematics for Key Technologies}, editor = {Deuflhard, Peter and Gr{\"o}tschel, Martin and H{\"o}mberg, Dietmar and Horst, Ulrich and Kramer, J{\"u}rg and Mehrmann, Volker and Polthier, Konrad and Schmidt, Frank and Skutella, Martin and Sprekels, J{\"u}rgen}, publisher = {European Mathematical Society}, pages = {66 -- 67}, year = {2014}, language = {en} } @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} } @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{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{ConradFerrerMietchenetal.2024, author = {Conrad, Tim and Ferrer, Eloi and Mietchen, Daniel and Pusch, Larissa and Stegmuller, Johannes and Schubotz, Moritz}, title = {Making Mathematical Research Data FAIR: Pathways to Improved Data Sharing}, volume = {11}, journal = {Scientific Data}, doi = {10.1038/s41597-024-03480-0}, year = {2024}, language = {en} } @article{FuerstConradJaegeretal.2024, author = {F{\"u}rst, Steffen and Conrad, Tim and Jaeger, Carlo and Wolf, Sarah}, title = {Vahana.jl - A framework (not only) for large-scale agent-based models}, journal = {Proceedings of Social Simulation Conference 2024 (SSC24)}, 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} } @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} } @article{WeimannConrad2024, author = {Weimann, Kuba and Conrad, Tim}, title = {FELRec: Efficient Handling of Item Cold-Start With Dynamic Representation Learning in Recommender Systems}, journal = {International Journal of Data Science and Analytics}, number = {2024}, publisher = {Springer Nature}, doi = {10.1007/s41060-024-00635-5}, year = {2024}, language = {en} } @article{BostanciConrad2025, author = {Bostanci, Inan and Conrad, Tim}, title = {Integrating Agent-Based and Compartmental Models for Infectious Disease Modeling: A Novel Hybrid Approach}, volume = {28}, journal = {Journal of Artificial Societies and Social Simulation}, number = {1}, doi = {10.18564/jasss.5567}, year = {2025}, abstract = {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.}, language = {en} } @article{BlaskovicConradKlusetal.2025, author = {Blaskovic, Filip and Conrad, Tim and Klus, Stefan and Djurdjevac Conrad, Natasa}, title = {Random walk based snapshot clustering for detecting community dynamics in temporal networks}, volume = {15}, journal = {Scientific Reports}, arxiv = {http://arxiv.org/abs/2412.12187}, doi = {10.1038/s41598-025-09340-0}, pages = {24414}, year = {2025}, abstract = {The evolution of many dynamical systems that describe relationships or interactions between objects can be effectively modeled by temporal networks, which are typically represented as a sequence of static network snapshots. In this paper, we introduce a novel random walk based approach that can identify clusters of time-snapshots in which network community structures are stable. This allows to detect significant structural shifts over time, such as the splitting, merging, birth, or death of communities. We also provide a low-dimensional representation of entire snapshots, placing those with similar community structure close to each other in the feature space. To validate our approach, we develop an agent-based algorithm that generates synthetic datasets with the desired characteristic properties, enabling thorough testing and benchmarking. We further demonstrate the effectiveness and broad applicability of our technique by testing it on various social dynamics models and real-world datasets and comparing its performance to several state-of-the-art algorithms. Our findings highlight the strength of our approach to correctly capture and analyze the dynamics of complex systems.}, language = {en} } @article{PaltraConrad2024, author = {Paltra, Sydney and Conrad, Tim}, title = {Clinical Effectiveness of Ritonavir-Boosted Nirmatrelvir—A Literature Review}, volume = {92}, journal = {Advances in Respiratory Medicine}, number = {1}, doi = {10.3390/arm92010009}, year = {2024}, abstract = {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.}, language = {de} } @article{WeimannConrad2025, author = {Weimann, Kuba and Conrad, Tim}, title = {Self-supervised pre-training with joint-embedding predictive architecture boosts ECG classification performance}, volume = {196}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier BV}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2025.110809}, year = {2025}, abstract = {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.}, language = {en} } @inproceedings{MaignantConradvonTycowicz2025, author = {Maignant, Elodie and Conrad, Tim and von Tycowicz, Christoph}, title = {Tree inference with varifold distances}, volume = {16034}, booktitle = {Geometric Science of Information. GSI 2025}, arxiv = {http://arxiv.org/abs/2507.11313}, doi = {10.1007/978-3-032-03921-7_30}, year = {2025}, abstract = {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.}, language = {en} } @article{MelnykWeimannConrad2023, author = {Melnyk, Kateryna and Weimann, Kuba and Conrad, Tim}, title = {Understanding microbiome dynamics via interpretable graph representation learning}, volume = {13}, journal = {Scientific Reports}, doi = {10.1038/s41598-023-29098-7}, pages = {2058}, year = {2023}, abstract = {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.}, language = {en} } @article{LiangPiaoBeuscheletal.2021, author = {Liang, YongTian and Piao, Chengji and Beuschel, Christine B. and Toppe, David and Kollipara, Laxmikanth and Bogdanow, Boris and Maglione, Marta and L{\"u}tzkendorf, Janine and See, Jason Chun Kit and Huang, Sheng and Conrad, Tim and Kintscher, Ulrich and Madeo, Frank and Liu, Fan and Sickmann, Albert and Sigrist, Stephan J.}, title = {eIF5A hypusination, boosted by dietary spermidine, protects from premature brain aging and mitochondrial dysfunction}, volume = {35}, journal = {Cell Reports}, number = {2}, doi = {10.1016/j.celrep.2021.108941}, year = {2021}, language = {de} } @article{MelnykMontavonKlusetal.2020, author = {Melnyk, Kateryna and Montavon, Gr{\`e}goire and Klus, Stefan and Conrad, Tim}, title = {Graph Kernel Koopman Embedding for Human Microbiome Analysis}, volume = {5}, journal = {Applied Network Science}, number = {96}, doi = {10.1007/s41109-020-00339-2}, year = {2020}, abstract = {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.}, language = {en} } @article{IravaniConrad2023, author = {Iravani, Sahar and Conrad, Tim}, title = {An Interpretable Deep Learning Approach for Biomarker Detection in LC-MS Proteomics Data}, volume = {20}, journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, number = {1}, doi = {10.1109/tcbb.2022.3141656}, pages = {151 -- 161}, year = {2023}, abstract = {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.}, language = {en} } @article{RamsConrad2022, author = {Rams, Mona and Conrad, Tim}, title = {Dictionary learning allows model-free pseudotime estimation of transcriptomics data}, volume = {23}, journal = {BMC Genomics}, publisher = {BioMed Central}, doi = {10.1186/s12864-021-08276-9}, year = {2022}, language = {en} } @article{WeimannConrad2021, author = {Weimann, K. and Conrad, Tim}, title = {Transfer Learning for ECG Classification}, volume = {11}, journal = {Scientific Reports}, doi = {10.1038/s41598-021-84374-8}, year = {2021}, abstract = {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.}, language = {en} } @article{LeDucConrad2020, author = {Le Duc, Huy and Conrad, Tim}, title = {A light-weight and highly flexible software system for analyzing large bio-medical datasets}, journal = {Future Generation Computer Systems}, year = {2020}, language = {en} } @article{JudsSchmidtWelleretal.2020, author = {Juds, Carmen and Schmidt, Johannes and Weller, Michael and Lange, Thorid and Conrad, Tim and Boerner, Hans}, title = {Combining Phage Display and Next-generation Sequencing for Materials Sciences: A Case Study on Probing Polypropylene Surfaces}, volume = {142}, journal = {Journal of the American Chemical Society}, number = {24}, doi = {10.1021/jacs.0c03482}, pages = {10624 -- 10628}, year = {2020}, abstract = {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.}, language = {en} } @article{CvetkovicConradLie2021, author = {Cvetkovic, Nada and Conrad, Tim and Lie, Han Cheng}, title = {A Convergent Discretisation Method for Transition Path Theory for Diffusion Processes}, volume = {19}, journal = {Multiscale Modeling \& Simulation}, number = {1}, publisher = {Society for Industrial and Applied Mathematics}, doi = {10.1137/20M1329354}, pages = {242 -- 266}, year = {2021}, language = {en} } @article{TuncayErdurConrad2023, author = {Tuncay, Erhun Giray and Erdur, R{\i}za Cenk and Conrad, Tim}, title = {Parallel Exchange of Randomized SubGraphs for Optimization of Network Alignment: PERSONA}, volume = {20}, journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, number = {3}, doi = {10.1109/TCBB.2022.3231489}, pages = {2064 -- 2077}, year = {2023}, abstract = {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.}, language = {de} } @article{AlchikhConradObermeieretal.2024, author = {Alchikh, Maren and Conrad, Tim and Obermeier, Patrick and Ma, Xiaolin and Schweiger, Brunhilde and Opota, Onya and Rath, Barbara}, title = {Disease Burden and Inpatient Management of Children with Acute Respiratory Viral Infections during the Pre-COVID Era in Germany: A Cost-of-Illness Study}, volume = {16}, journal = {Viruses}, number = {4}, doi = {10.3390/v16040507}, year = {2024}, abstract = {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.}, language = {en} } @article{SherrattSrivastavaAinslieetal.2024, author = {Sherratt, Katharine and Srivastava, Ajitesh and Ainslie, Kylie and Singh, David E. and Cublier, Aymar and Marinescu, Maria Cristina and Carretero, Jesus and Garcia, Alberto Cascajo and Franco, Nicolas and Willem, Lander and Abrams, Steven and Faes, Christel and Beutels, Philippe and Hens, Niel and M{\"u}ller, Sebastian and Charlton, Billy and Ewert, Ricardo and Paltra, Sydney and Rakow, Christian and Rehmann, Jakob and Conrad, Tim and Sch{\"u}tte, Christof and Nagel, Kai and Abbott, Sam and Grah, Rok and Niehus, Rene and Prasse, Bastian and Sandmann, Frank and Funk, Sebastian}, title = {Characterising information gains and losses when collecting multiple epidemic model outputs}, volume = {47}, journal = {Epidemics}, publisher = {Elsevier BV}, issn = {1755-4365}, doi = {10.1016/j.epidem.2024.100765}, year = {2024}, abstract = {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}, language = {en} } @article{GaskinConradPavliotisetal.2024, author = {Gaskin, Thomas and Conrad, Tim and Pavliotis, Grigorios A. and Sch{\"u}tte, Christof}, title = {Neural parameter calibration and uncertainty quantification for epidemic forecasting}, volume = {19}, journal = {PLOS ONE}, number = {10}, arxiv = {http://arxiv.org/abs/2312.03147}, doi = {10.1371/journal.pone.0306704}, year = {2024}, abstract = {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.}, language = {en} } @article{ObermeierHeimBiereetal.2022, author = {Obermeier, Patrick E and Heim, Albert and Biere, Barbara and Hage, Elias and Alchikh, Maren and Conrad, Tim and Schweiger, Brunhilde and Rath, Barbara A}, title = {Linking digital surveillance and in-depth virology to study clinical patterns of viral respiratory infections in vulnerable patient populations}, volume = {25}, journal = {iScience}, number = {5}, publisher = {Cell Press}, doi = {10.1016/j.isci.2022.104276}, year = {2022}, abstract = {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 …}, language = {en} } @article{ZhangKlusConradetal.2019, author = {Zhang, Wei and Klus, Stefan and Conrad, Tim and Sch{\"u}tte, Christof}, title = {Learning chemical reaction networks from trajectory data}, volume = {18}, journal = {SIAM Journal on Applied Dynamical Systems (SIADS)}, number = {4}, arxiv = {http://arxiv.org/abs/1902.04920}, doi = {10.1137/19M1265880}, pages = {2000 -- 2046}, year = {2019}, abstract = {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.}, language = {en} } @inproceedings{IravaniConrad2019, author = {Iravani, Sahar and Conrad, Tim}, title = {Deep Learning for Proteomics Data for Feature Selection and Classification}, volume = {11713}, booktitle = {Machine Learning and Knowledge Extraction. CD-MAKE 2019}, editor = {Holzinger, A. and Kieseberg, P. and Tjoa, A. and Weippl, E.}, publisher = {Springer, Cham}, doi = {10.1007/978-3-030-29726-8_19}, year = {2019}, language = {en} }