@article{KoltaiWuNoeetal.2018, author = {Koltai, Peter and Wu, Hao and No{\´e}, Frank and Sch{\"u}tte, Christof}, title = {Optimal data-driven estimation of generalized Markov state models for non-equilibrium dynamics}, volume = {6}, journal = {Computation}, number = {1}, publisher = {MDPI}, address = {Basel, Switzerland}, doi = {10.3390/computation6010022}, pages = {22}, year = {2018}, language = {en} } @article{DibakdelRazodeSanchoetal.2018, author = {Dibak, Manuel and del Razo, Mauricio J. and de Sancho, David and Sch{\"u}tte, Christof and No{\´e}, Frank}, title = {MSM/RD: Coupling Markov state models of molecular kinetics with reaction-diffusion simulations}, volume = {148}, journal = {Journal of Chemical Physics}, number = {21}, doi = {10.1063/1.5020294}, year = {2018}, abstract = {Molecular dynamics (MD) simulations can model the interactions between macromolecules with high spatiotemporal resolution but at a high computational cost. By combining high-throughput MD with Markov state models (MSMs), it is now possible to obtain long time-scale behavior of small to intermediate biomolecules and complexes. To model the interactions of many molecules at large length scales, particle-based reaction-diffusion (RD) simulations are more suitable but lack molecular detail. Thus, coupling MSMs and RD simulations (MSM/RD) would be highly desirable, as they could efficiently produce simulations at large time and length scales, while still conserving the characteristic features of the interactions observed at atomic detail. While such a coupling seems straightforward, fundamental questions are still open: Which definition of MSM states is suitable? Which protocol to merge and split RD particles in an association/dissociation reaction will conserve the correct bimolecular kinetics and thermodynamics? In this paper, we make the first step toward MSM/RD by laying out a general theory of coupling and proposing a first implementation for association/dissociation of a protein with a small ligand (A + B ⇌ C). Applications on a toy model and CO diffusion into the heme cavity of myoglobin are reported.}, language = {en} } @inproceedings{EstacioEhlkeTacketal.2021, author = {Estacio, Laura and Ehlke, Moritz and Tack, Alexander and Castro-Gutierrez, Eveling and Lamecker, Hans and Mora, Rensso and Zachow, Stefan}, title = {Unsupervised Detection of Disturbances in 2D Radiographs}, booktitle = {2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)}, doi = {10.1109/ISBI48211.2021.9434091}, pages = {367 -- 370}, year = {2021}, abstract = {We present a method based on a generative model for detection of disturbances such as prosthesis, screws, zippers, and metals in 2D radiographs. The generative model is trained in an unsupervised fashion using clinical radiographs as well as simulated data, none of which contain disturbances. Our approach employs a latent space consistency loss which has the benefit of identifying similarities, and is enforced to reconstruct X-rays without disturbances. In order to detect images with disturbances, an anomaly score is computed also employing the Frechet distance between the input X-ray and the reconstructed one using our generative model. Validation was performed using clinical pelvis radiographs. We achieved an AUC of 0.77 and 0.83 with clinical and synthetic data, respectively. The results demonstrated a good accuracy of our method for detecting outliers as well as the advantage of utilizing synthetic data.}, language = {en} } @article{SekuboyinaBayatHusseinietal.2020, author = {Sekuboyina, Anjany and Bayat, Amirhossein and Husseini, Malek E. and L{\"o}ffler, Maximilian and Li, Hongwei and Tetteh, Giles and Kukačka, Jan and Payer, Christian and Štern, Darko and Urschler, Martin and Chen, Maodong and Cheng, Dalong and Lessmann, Nikolas and Hu, Yujin and Wang, Tianfu and Yang, Dong and Xu, Daguang and Ambellan, Felix and Amiranashvili, Tamaz and Ehlke, Moritz and Lamecker, Hans and Lehnert, Sebastian and Lirio, Marilia and de Olaguer, Nicol{\´a}s P{\´e}rez and Ramm, Heiko and Sahu, Manish and Tack, Alexander and Zachow, Stefan and Jiang, Tao and Ma, Xinjun and Angerman, Christoph and Wang, Xin and Wei, Qingyue and Brown, Kevin and Wolf, Matthias and Kirszenberg, Alexandre and Puybareau, {\´E}lodie and Valentinitsch, Alexander and Rempfler, Markus and Menze, Bj{\"o}rn H. and Kirschke, Jan S.}, title = {VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images}, journal = {arXiv}, arxiv = {http://arxiv.org/abs/2001.09193}, year = {2020}, language = {en} } @article{WulkowConradDjurdjevacConradetal.2021, author = {Wulkow, Hanna and Conrad, Tim and Djurdjevac Conrad, Natasa and M{\"u}ller, Sebastian A. and Nagel, Kai and Sch{\"u}tte, Christof}, title = {Prediction of Covid-19 spreading and optimal coordination of counter-measures: From microscopic to macroscopic models to Pareto fronts}, volume = {16}, journal = {PLOS One}, number = {4}, publisher = {Public Library of Science}, doi = {10.1371/journal.pone.0249676}, year = {2021}, language = {en} } @article{BanischDjurdjevacConradSchuette2015, author = {Banisch, Ralf and Djurdjevac Conrad, Natasa and Sch{\"u}tte, Christof}, title = {Reactive flows and unproductive cycles for random walks on complex networks}, journal = {The European Physical Journal Special Topics, vol. 224, iss. 12 (2015) pp. 2369-2387}, doi = {10.1140/epjst/e2015-02417-8}, year = {2015}, language = {en} } @misc{BanischDjurdjevacConradSchuette2015, author = {Banisch, Ralf and Djurdjevac Conrad, Natasa and Sch{\"u}tte, Christof}, title = {Reactive flows and unproductive cycles for random walks on complex networks}, issn = {1438-0064}, doi = {10.1140/epjst/e2015-02417-8}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-54239}, year = {2015}, abstract = {We present a comprehensive theory for analysis and understanding of transition events between an initial set A and a target set B for general ergodic finite-state space Markov chains or jump processes, including random walks on networks as they occur, e.g., in Markov State Modelling in molecular dynamics. The theory allows us to decompose the probability flow generated by transition events between the sets A and B into the productive part that directly flows from A to B through reaction pathways and the unproductive part that runs in loops and is supported on cycles of the underlying network. It applies to random walks on directed networks and nonreversible Markov processes and can be seen as an extension of Transition Path Theory. Information on reaction pathways and unproductive cycles results from the stochastic cycle decomposition of the underlying network which also allows to compute their corresponding weight, thus characterizing completely which structure is used how often in transition events. The new theory is illustrated by an application to a Markov State Model resulting from weakly damped Langevin dynamics where the unproductive cycles are associated with periodic orbits of the underlying Hamiltonian dynamics.}, language = {en} } @article{WinkelmannSchuettevonKleist2014, author = {Winkelmann, Stefanie and Sch{\"u}tte, Christof and von Kleist, Max}, title = {Markov Control Processes with Rare State Observation: Theory and Application to Treatment Scheduling in HIV-1}, volume = {12}, journal = {Communications in Mathematical Sciences}, number = {5}, doi = {10.4310/CMS.2014.v12.n5.a4}, pages = {859 -- 877}, year = {2014}, abstract = {Markov Decision Processes (MDP) or Partially Observable MDPs (POMDP) are used for modelling situations in which the evolution of a process is partly random and partly controllable. These MDP theories allow for computing the optimal control policy for processes that can continuously or frequently be observed, even if only partially. However, they cannot be applied if state observation is very costly and therefore rare (in time). We present a novel MDP theory for rare, costly observations and derive the corresponding Bellman equation. In the new theory, state information can be derived for a particular cost after certain, rather long time intervals. The resulting information costs enter into the total cost and thus into the optimization criterion. This approach applies to many real world problems, particularly in the medical context, where the medical condition is examined rather rarely because examination costs are high. At the same time, the approach allows for efficient numerical realization. We demonstrate the usefulness of the novel theory by determining, from the national economic perspective, optimal therapeutic policies for the treatment of the human immunodeficiency virus (HIV) in resource-rich and resource-poor settings. Based on the developed theory and models, we discover that available drugs may not be utilized efficiently in resource-poor settings due to exorbitant diagnostic costs.}, language = {en} } @article{DjurdjevacConradBanischSchuette2015, author = {Djurdjevac Conrad, Natasa and Banisch, Ralf and Sch{\"u}tte, Christof}, title = {Modularity of Directed Networks: Cycle Decomposition Approach}, journal = {Journal of Computational Dynamics 2 (2015) pp. 1-24}, doi = {10.3934/jcd.2015.2.1}, year = {2015}, abstract = {The problem of decomposing networks into modules (or clusters) has gained much attention in recent years, as it can account for a coarsegrained description of complex systems, often revealing functional subunits of these systems. A variety of module detection algorithms have been proposed, mostly oriented towards finding hard partitionings of undirected networks. Despite the increasing number of fuzzy clustering methods for directed networks, many of these approaches tend to neglect important directional information. In this paper, we present a novel random walk based approach for finding fuzzy partitions of directed, weighted networks, where edge directions play a crucial role in defining how well nodes in a module are interconnected. We will show that cycle decomposition of a random walk process connects the notion of network modules and information transport in a network, leading to a new, symmetric measure of node communication. Finally, we will use this measure to introduce a communication graph, for which we will show that although being undirected it inherits all necessary information about modular structures from the original network.}, language = {en} } @misc{WangSchuette2014, author = {Wang, Han and Sch{\"u}tte, Christof}, title = {Building Markov State Models for Periodically Driven Non-Equilibrium Systems}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-53167}, year = {2014}, abstract = {Recent years have seen an increased interest in non-equilibrium molecular dynamics (NEMD) simulations, especially for molecular systems with periodic forcing by external fields, e.g., in the context of studying effects of electromagnetic radiation on the human body tissue. Lately, an NEMD methods with local thermostating has been proposed that allows for studying non-equilibrium processes in a statistically reliable and thermodynamically consistent way. In this article, we demonstrate how to construct Markov State Models (MSMs) for such NEMD simulations. MSM building has been well-established for systems in equilibrium where MSMs with just a few (macro-)states allow for accurate reproduction of the essential kinetics of the molecular system under consideration. Non-equilibrium MSMs have been lacking so far. The article presents how to construct such MSMs and illustrates their validity and usefulness for the case of conformation dynamics of alanine dipeptide in an external electric field.}, language = {en} } @misc{GulSchuetteBernhard2015, author = {Gul, Raheem and Sch{\"u}tte, Christof and Bernhard, Stefan}, title = {Mathematical modeling and sensitivity analysis of arterial anastomosis in arm arteries}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-54339}, year = {2015}, abstract = {Cardiovascular diseases are one of the major problems in medicine today and the number of patients increases worldwide. To find the most efficient treatment, prior knowledge about function and dysfunction of the cardiovas- cular system is required and methods need to be developed that identify the disease in an early stage. Mathematical modeling is a powerful tool for prediction and investigation of cardiovascular diseases. It has been shown that the Windkessel model, being based on an analogy between electrical circuits and fluid flow, is a simple but effective method to model the human cardiovascular system. In this paper, we have applied parametric local sensitivity analysis (LSA) to a linear elastic model of the arm arteries, to find and rank sensitive param- eters that may be helpful in clinical diagnosis. A computational model for end-to-side anastomosis (superior ulnar collateral anastomosis with posterior ulnar recurrent, SUC-PUR) is carried out to study the effects of some clinically relevant haemodynamic parameters like blood flow resistance and terminal re- sistance on pressure and flow at different locations of the arm artery. In this context, we also discuss the spatio-temporal dependency of local sensitivities. The sensitivities with respect to cardiovascular parameters reveal the flow resistance and diameter of the vessels as most sensitive parameters. These parameters play a key role in diagnosis of severe stenosis and aneurysms. In contrast, wall thickness and elastic modulus are found to be less sensitive.}, language = {en} } @inproceedings{Mukhopadhyay2016, author = {Mukhopadhyay, Anirban}, title = {Total Variation Random Forest: Fully automatic MRI segmentation in congenital heart disease}, volume = {LNCS 10129}, booktitle = {RAMBO 2016, HVSMR 2016: Reconstruction, Segmentation, and Analysis of Medical Images}, doi = {10.1007/978-3-319-52280-7_17}, pages = {165 -- 171}, year = {2016}, language = {en} } @inproceedings{MukhopadhyayMorilloZachowetal.2016, author = {Mukhopadhyay, Anirban and Morillo, Oscar and Zachow, Stefan and Lamecker, Hans}, title = {Robust and Accurate Appearance Models Based on Joint Dictionary Learning Data from the Osteoarthritis Initiative}, volume = {9993}, booktitle = {Lecture Notes in Computer Science, Patch-Based Techniques in Medical Imaging. Patch-MI 2016}, doi = {10.1007/978-3-319-47118-1_4}, pages = {25 -- 33}, year = {2016}, abstract = {Deformable model-based approaches to 3D image segmentation have been shown to be highly successful. Such methodology requires an appearance model that drives the deformation of a geometric model to the image data. Appearance models are usually either created heuristically or through supervised learning. Heuristic methods have been shown to work effectively in many applications but are hard to transfer from one application (imaging modality/anatomical structure) to another. On the contrary, supervised learning approaches can learn patterns from a collection of annotated training data. In this work, we show that the supervised joint dictionary learning technique is capable of overcoming the traditional drawbacks of the heuristic approaches. Our evaluation based on two different applications (liver/CT and knee/MR) reveals that our approach generates appearance models, which can be used effectively and efficiently in a deformable model-based segmentation framework.}, language = {en} } @article{SahuMukhopadhyaySzengeletal.2017, author = {Sahu, Manish and Mukhopadhyay, Anirban and Szengel, Angelika and Zachow, Stefan}, title = {Addressing multi-label imbalance problem of Surgical Tool Detection using CNN}, volume = {12}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {6}, publisher = {Springer}, doi = {10.1007/s11548-017-1565-x}, pages = {1013 -- 1020}, year = {2017}, abstract = {Purpose: A fully automated surgical tool detection framework is proposed for endoscopic video streams. State-of-the-art surgical tool detection methods rely on supervised one-vs-all or multi-class classification techniques, completely ignoring the co-occurrence relationship of the tools and the associated class imbalance. Methods: In this paper, we formulate tool detection as a multi-label classification task where tool co-occurrences are treated as separate classes. In addition, imbalance on tool co-occurrences is analyzed and stratification techniques are employed to address the imbalance during Convolutional Neural Network (CNN) training. Moreover, temporal smoothing is introduced as an online post-processing step to enhance run time prediction. Results: Quantitative analysis is performed on the M2CAI16 tool detection dataset to highlight the importance of stratification, temporal smoothing and the overall framework for tool detection. Conclusion: The analysis on tool imbalance, backed by the empirical results indicates the need and superiority of the proposed framework over state-of-the-art techniques.}, language = {en} } @article{KlusSchuette2016, author = {Klus, Stefan and Sch{\"u}tte, Christof}, title = {Towards tensor-based methods for the numerical approximation of the Perron-Frobenius and Koopman operator}, volume = {3}, journal = {Journal of Computational Dynamics}, number = {2}, doi = {10.3934/jcd.2016007}, pages = {139 -- 161}, year = {2016}, abstract = {The global behavior of dynamical systems can be studied by analyzing the eigenvalues and corresponding eigenfunctions of linear operators associated with the system. Two important operators which are frequently used to gain insight into the system's behavior are the Perron-Frobenius operator and the Koopman operator. Due to the curse of dimensionality, computing the eigenfunctions of high-dimensional systems is in general infeasible. We will propose a tensor-based reformulation of two numerical methods for computing finite-dimensional approximations of the aforementioned infinite-dimensional operators, namely Ulam's method and Extended Dynamic Mode Decomposition (EDMD). The aim of the tensor formulation is to approximate the eigenfunctions by low-rank tensors, potentially resulting in a significant reduction of the time and memory required to solve the resulting eigenvalue problems, provided that such a low-rank tensor decomposition exists. Typically, not all variables of a high-dimensional dynamical system contribute equally to the system's behavior, often the dynamics can be decomposed into slow and fast processes, which is also reflected in the eigenfunctions. Thus, the weak coupling between different variables might be approximated by low-rank tensor cores. We will illustrate the efficiency of the tensor-based formulation of Ulam's method and EDMD using simple stochastic differential equations.}, language = {en} } @article{KlusKoltaiSchuette2016, author = {Klus, Stefan and Koltai, Peter and Sch{\"u}tte, Christof}, title = {On the numerical approximation of the Perron-Frobenius and Koopman operator}, volume = {3}, journal = {Journal of Computational Dynamics}, number = {1}, doi = {10.3934/jcd.2016003}, pages = {51 -- 77}, year = {2016}, abstract = {Information about the behavior of dynamical systems can often be obtained by analyzing the eigenvalues and corresponding eigenfunctions of linear operators associated with a dynamical system. Examples of such operators are the Perron-Frobenius and the Koopman operator. In this paper, we will review di� fferent methods that have been developed over the last decades to compute � infinite-dimensional approximations of these in� finite-dimensional operators - in particular Ulam's method and Extended Dynamic Mode Decomposition (EDMD) - and highlight the similarities and di� fferences between these approaches. The results will be illustrated using simple stochastic di� fferential equations and molecular dynamics examples.}, language = {en} } @article{HuttaryGoubergritsSchuetteetal.2017, author = {Huttary, Rudolf and Goubergrits, Leonid and Sch{\"u}tte, Christof and Bernhard, Stefan}, title = {Simulation, Identification and Statistical Variation in Cardiovascular Analysis (SISCA) - a Software Framework for Multi-compartment Lumped Modeling}, volume = {87}, journal = {Computers in Biology and Medicine}, doi = {10.1016/j.compbiomed.2017.05.021}, pages = {104 -- 123}, year = {2017}, language = {en} } @misc{GuptaGramatkeEinspanieretal.2017, author = {Gupta, Pooja and Gramatke, Annika and Einspanier, Ralf and Sch{\"u}tte, Christof and von Kleist, Max and Sharbati, Jutta}, title = {In silicio cytotoxicity assessment on cultured rat intestinal cells deduced from cellular impedance measurements}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-62666}, year = {2017}, abstract = {Early and reliable identification of chemical toxicity is of utmost importance. At the same time, reduction of animal testing is paramount. Therefore, methods that improve the interpretability and usability of in vitro assays are essential. xCELLigence's real-time cell analyzer (RTCA) provides a novel, fast and cost effective in vitro method to probe compound toxicity. We developed a simple mathematical framework for the qualitative and quantitative assessment of toxicity for RTCA measurements. Compound toxicity, in terms of its 50\% inhibitory concentration IC_{50} on cell growth, and parameters related to cell turnover were estimated on cultured IEC-6 cells exposed to 10 chemicals at varying concentrations. Our method estimated IC50 values of 113.05, 7.16, 28.69 and 725.15 μM for the apparently toxic compounds 2-acetylamino-fluorene, aflatoxin B1, benzo-[a]-pyrene and chloramphenicol in the tested cell line, in agreement with literature knowledge. IC_{50} values of all apparent in vivo non-toxic compounds were estimated to be non-toxic by our method. Corresponding estimates from RTCA's in-built model gave false positive (toxicity) predictions in 5/10 cases. Taken together, our proposed method reduces false positive predictions and reliably identifies chemical toxicity based on impedance measurements. The source code for the developed method including instructions is available at https://git.zib.de/bzfgupta/toxfit/tree/master.}, language = {en} } @article{KlusNueskeKoltaietal.2018, author = {Klus, Stefan and N{\"u}ske, Feliks and Koltai, Peter and Wu, Hao and Kevrekidis, Ioannis and Sch{\"u}tte, Christof and No{\´e}, Frank}, title = {Data-driven model reduction and transfer operator approximation}, volume = {28}, journal = {Journal of Nonlinear Science}, number = {3}, doi = {10.1007/s00332-017-9437-7}, pages = {985 -- 1010}, year = {2018}, language = {en} } @article{KoltaiCiccottiSchuette2016, author = {Koltai, Peter and Ciccotti, Giovanni and Sch{\"u}tte, Christof}, title = {On Markov state models for non-equilibrium molecular dynamics}, volume = {145}, journal = {The Journal of Chemical Physics}, number = {174103}, doi = {10.1063/1.4966157}, year = {2016}, language = {en} } @article{ConradKarschObermeieretal.2015, author = {Conrad, Tim and Karsch, K. and Obermeier, Patrick and Seeber, L. and Chen, X. and Tief, Franziska and Muehlhans, S. and Hoppe, Christian and Boettcher, Sindy and Diedrich, S. and Rath, Barbara}, title = {Human Parechovirus Infections Associated with Seizures and Rash: A Syndromic Surveillance Study in Children}, volume = {34}, journal = {The Pediatric Infectious Disease Journal}, number = {10}, year = {2015}, language = {en} } @article{ConradMireles2015, author = {Conrad, Tim and Mireles, Victor}, title = {Minimum-overlap clusterings and the sparsity of overcomplete decompositions of binary matrics}, volume = {51}, journal = {Procedia Computer Science}, doi = {10.1016/j.procs.2015.05.500}, pages = {2967 -- 2971}, year = {2015}, abstract = {Given a set of n binary data points, a widely used technique is to group its features into k clusters. In the case where n {\ensuremath{<}} k, the question of how overlapping are the clusters becomes of interest. In this paper we approach the question through matrix decomposition, and relate the degree of overlap with the sparsity of one of the resulting matrices. We present analytical results regarding bounds on this sparsity, and a heuristic to estimate the minimum amount of overlap that an exact grouping of features into k clusters must have. As shown below, adding new data will not alter this minimum amount of overlap.}, language = {en} } @article{ConradShao2015, author = {Conrad, Tim and Shao, Borong}, title = {Are NoSQL data stores useful for bioinformatics researchers?}, volume = {3}, journal = {International Journal on Recent and Innovation Trends in Computing and Communication (IJRITCC)}, number = {3}, doi = {10.17762/ijritcc2321-8169.1503176}, pages = {1704 -- 1708}, year = {2015}, language = {en} } @article{ConradLeichtleCeglareketal.2013, author = {Conrad, Tim and Leichtle, Alexander Benedikt and Ceglarek, Uta and Weinert, P. and Nakas, C.T. and Nuoffer, Jean-Marc and Kase, Julia and Witzigmann, Helmut and Thiery, Joachim and Fiedler, Georg Martin}, title = {Pancreatic carcinoma, pancreatitis, and healthy controls - metabolite models in a three-class diagnostic dilemma}, volume = {9}, journal = {Metabolomics}, number = {3}, doi = {10.1007/s11306-012-0476-7}, pages = {677 -- 687}, year = {2013}, abstract = {Background: Metabolomics as one of the most rapidly growing technologies in the ?-omics?field denotes the comprehensive analysis of low molecular-weight compounds and their pathways. Cancer-specific alterations of the metabolome can be detected by high-throughput massspectrometric metabolite profiling and serve as a considerable source of new markers for the early differentiation of malignant diseases as well as their distinction from benign states. However, a comprehensive framework for the statistical evaluation of marker panels in a multi-class setting has not yet been established. Methods: We collected serum samples of 40 pancreatic carcinoma patients, 40 controls, and 23 pancreatitis patients according to standard protocols and generated amino acid profiles by routine mass-spectrometry. In an intrinsic three-class bioinformatic approach we compared these profiles, evaluated their selectivity and computed multi-marker panels combined with the conventional tumor marker CA 19-9. Additionally, we tested for non-inferiority and superiority to determine the diagnostic surplus value of our multi-metabolite marker panels.  Results: Compared to CA 19-9 alone, the combined amino acid-based metabolite panel had a superior selectivity for the discrimination of healthy controls, pancreatitis, and pancreatic carcinoma patients [Volume under ROC surface (VUS) = 0.891 (95\\% CI 0.794 - 0.968)]. Conclusions: We combined highly standardized samples, a three-class study design, a highthroughput mass-spectrometric technique, and a comprehensive bioinformatic framework to identify metabolite panels selective for all three groups in a single approach. Our results suggest that metabolomic profiling necessitates appropriate evaluation strategies and ?despite all its current limitations? can deliver marker panels with high selectivity even in multi-class settings.}, language = {en} } @article{GuptaReinschSpoetteretal.2013, author = {Gupta, Pooja and Reinsch, Norbert and Sp{\"o}tter, Andreas and Conrad, Tim and Bienefeld, Kaspar}, title = {Accuracy of the unified approach in maternally influenced traits - illustrated by a simulation study in the honey bee (Apis mellifera)}, volume = {14}, journal = {BMC Genetics}, number = {36}, doi = {10.1186/1471-2156-14-36}, year = {2013}, language = {en} } @article{ConradYou2016, author = {Conrad, Tim and You, Xintian}, title = {Acfs: accurate circRNA identification and quantification from NGS data}, volume = {6}, journal = {Nature Scientific Reports}, doi = {10.1038/srep38820}, year = {2016}, abstract = {Circular RNAs (circRNAs) are a group of single-stranded RNAs in closed circular form. They are splicing-generated, widely expressed in various tissues and have functional implications in development and diseases. To facilitate genome-wide characterization of circRNAs using RNA-Seq data, we present a freely available software package named acfs. Acfs allows de novo, accurate and fast identification and abundance quantification of circRNAs from single- and paired-ended RNA-Seq data. On simulated datasets, acfs achieved the highest F1 accuracy and lowest false discovery rate among current state-of-the-art tools. On real-world datasets, acfs efficiently identified more bona fide circRNAs. Furthermore, we demonstrated the power of circRNA analysis on two leukemia datasets. We identified a set of circRNAs that are differentially expressed between AML and APL samples, which might shed light on the potential molecular classification of complex diseases using circRNA profiles. Moreover, chromosomal translocation, as manifested in numerous diseases, could produce not only fusion transcripts but also fusion circRNAs of clinical relevance. Featured with high accuracy, low FDR and the ability to identify fusion circRNAs, we believe that acfs is well suited for a wide spectrum of applications in characterizing the landscape of circRNAs from non-model organisms to cancer biology.}, language = {en} } @article{HoppeObermeierMehlhansetal.2016, author = {Hoppe, Christian and Obermeier, Patrick and Mehlhans, S. and Alchikh, Maren and Seeber, L. and Tief, Franziska and Karsch, K. and Chen, X. and Boettcher, Sindy and Diedrich, S. and Conrad, Tim}, title = {Innovative Digital Tools and Surveillance Systems for the Timely Detection of Adverse Events at the Point of Care: A Proof-of-Concept Study}, volume = {39}, journal = {Drug Safety}, number = {10}, doi = {10.1007/s40264-016-0437-6}, pages = {977 -- 988}, year = {2016}, abstract = {Regulatory authorities often receive poorly structured safety reports requiring considerable effort to investigate potential adverse events post hoc. Automated question-and-answer systems may help to improve the overall quality of safety information transmitted to pharmacovigilance agencies. This paper explores the use of the VACC-Tool (ViVI Automated Case Classification Tool) 2.0, a mobile application enabling physicians to classify clinical cases according to 14 pre-defined case definitions for neuroinflammatory adverse events (NIAE) and in full compliance with data standards issued by the Clinical Data Interchange Standards Consortium. METHODS: The validation of the VACC-Tool 2.0 (beta-version) was conducted in the context of a unique quality management program for children with suspected NIAE in collaboration with the Robert Koch Institute in Berlin, Germany. The VACC-Tool was used for instant case classification and for longitudinal follow-up throughout the course of hospitalization. Results were compared to International Classification of Diseases , Tenth Revision (ICD-10) codes assigned in the emergency department (ED). RESULTS: From 07/2013 to 10/2014, a total of 34,368 patients were seen in the ED, and 5243 patients were hospitalized; 243 of these were admitted for suspected NIAE (mean age: 8.5 years), thus participating in the quality management program. Using the VACC-Tool in the ED, 209 cases were classified successfully, 69 \\% of which had been missed or miscoded in the ED reports. Longitudinal follow-up with the VACC-Tool identified additional NIAE. CONCLUSION: Mobile applications are taking data standards to the point of care, enabling clinicians to ascertain potential adverse events in the ED setting and during inpatient follow-up. Compliance with Clinical Data Interchange Standards Consortium (CDISC) data standards facilitates data interoperability according to regulatory requirements.}, language = {en} } @inproceedings{ShaoConrad2016, author = {Shao, Borong and Conrad, Tim}, title = {Epithelial Mesenchymal Transition Regulatory Network-based Feature Selection in Lung Cancer Prognosis Prediction}, volume = {9656}, booktitle = {Lecture Notes in Computer Science (LNCS)}, doi = {10.1007/978-3-319-31744-1_13}, pages = {1235 -- 146}, year = {2016}, abstract = {Feature selection technique is often applied in identifying cancer prognosis biomarkers. However, many feature selection methods are prone to over-fitting or poor biological interpretation when applied on biological high-dimensional data. Network-based feature selection and data integration approaches are proposed to identify more robust biomarkers. We conducted experiments to investigate the advantages of the two approaches using epithelial mesenchymal transition regulatory network, which is demonstrated as highly relevant to cancer prognosis. We obtained data from The Cancer Genome Atlas. Prognosis prediction was made using Support Vector Machine. Under our experimental settings, the results showed that network-based features gave significantly more accurate predictions than individual molecular features, and features selected from integrated data (RNA-Seq and micro-RNA data) gave significantly more accurate predictions than features selected from single source data (RNA-Seq data). Our study indicated that biological network-based feature transformation and data integration are two useful approaches to identify robust cancer biomarkers.}, language = {en} } @article{TiefHoppeSeeberetal.2016, author = {Tief, Franziska and Hoppe, Christian and Seeber, L. and Obermeier, Patrick and Chen, X. and Karsch, K. and Muehlhans, S. and Adamou, E. and Conrad, Tim and Schweiger, Brunhilde and Adam, T. and Rath, Barbara}, title = {An inception cohort study assessing the role of bacterial co-infections in children with influenza and ILI and a clinical decision model for stringent antibiotic use}, volume = {21}, journal = {Antiviral Therapy}, doi = {10.3851/IMP3034}, pages = {413 -- 424}, year = {2016}, abstract = {BACKGROUND: Influenza-like illness (ILI) is a common reason for paediatric consultations. Viral causes predominate, but antibiotics are used frequently. With regard to influenza, pneumococcal coinfections are considered major contributors to morbidity/mortality. METHODS: In the context of a perennial quality management (QM) programme at the Charit{\'e} Departments of Paediatrics and Microbiology in collaboration with the Robert Koch Institute, children aged 0-18 years presenting with signs and symptoms of ILI were followed from the time of initial presentation until hospital discharge (Charit{\'e} Influenza-Like Disease = ChILD Cohort). An independent QM team performed highly standardized clinical assessments using a disease severity score based on World Health Organization criteria for uncomplicated and complicated/progressive disease. Nasopharyngeal and pharyngeal samples were collected for viral reverse transcription polymerase chain reaction and bacterial culture/sensitivity and MaldiTOF analyses. The term 'detection' was used to denote any evidence of viral or bacterial pathogens in the (naso)pharyngeal cavity. With the ChILD Cohort data collected, a standard operating procedure (SOP) was created as a model system to reduce the inappropriate use of antibiotics in children with ILI. Monte Carlo simulations were performed to assess cost-effectiveness. RESULTS: Among 2,569 ChILD Cohort patients enrolled from 12/2010 to 04/2013 (55\\% male, mean age 3.2 years, range 0-18, 19\\% {\ensuremath{>}}5 years), 411 patients showed laboratory-confirmed influenza, with bacterial co-detection in 35\\%. Influenza and pneumococcus were detected simultaneously in 12/2,569 patients, with disease severity clearly below average. Pneumococcal vaccination rates were close to 90\\%. Nonetheless, every fifth patient was already on antibiotics upon presentation; new antibiotic prescriptions were issued in an additional 20\\%. Simulation of the model SOP in the same dataset revealed that the proposed decision model could have reduced the inappropriate use of antibiotics significantly (P{\ensuremath{<}}0.01) with an incremental cost-effectiveness ratio of -99.55?. CONCLUSIONS: Physicians should be made aware that in times of pneumococcal vaccination the prevalence and severity of influenza infections complicated by pneumococci may decline. Microbiological testing in combination with standardized disease severity assessments and review of vaccination records could be cost-effective, as well as promoting stringent use of antibiotics and a personalized approach to managing children with ILI.}, language = {en} } @article{ObermeierMuehlhansHoppeetal.2016, author = {Obermeier, Patrick and Muehlhans, S. and Hoppe, Christian and Karsch, K. and Tief, Franziska and Seeber, L. and Chen, X. and Conrad, Tim and Boettcher, Sindy and Diedrich, S. and Rath, Barbara}, title = {Enabling Precision Medicine With Digital Case Classification at the Point-of-Care}, volume = {4}, journal = {EBioMedicine}, doi = {10.1016/j.ebiom.2016.01.008}, pages = {191 -- 196}, year = {2016}, abstract = {Infectious and inflammatory diseases of the central nervous system are difficult to identify early. Case definitions for aseptic meningitis, encephalitis, myelitis, and acute disseminated encephalomyelitis (ADEM) are available, but rarely put to use. The VACC-Tool (Vienna Vaccine Safety Initiative Automated Case Classification-Tool) is a mobile application enabling immediate case ascertainment based on consensus criteria at the point-of-care. The VACC-Tool was validated in a quality management program in collaboration with the Robert-Koch-Institute. Results were compared to ICD-10 coding and retrospective analysis of electronic health records using the same case criteria. Of 68,921 patients attending the emergency room in 10/2010-06/2013, 11,575 were hospitalized, with 521 eligible patients (mean age: 7.6 years) entering the quality management program. Using the VACC-Tool at the point-of-care, 180/521 cases were classified successfully and 194/521 ruled out with certainty. Of the 180 confirmed cases, 116 had been missed by ICD-10 coding, 38 misclassified. By retrospective application of the same case criteria, 33 cases were missed. Encephalitis and ADEM cases were most likely missed or misclassified. The VACC-Tool enables physicians to ask the right questions at the right time, thereby classifying cases consistently and accurately, facilitating translational research. Future applications will alert physicians when additional diagnostic procedures are required.}, language = {en} } @article{ConradBrucknerKayser2013, author = {Conrad, Tim and Bruckner, Sharon and Kayser, Bastian}, title = {Finding Modules in Networks with Non-modular Regions}, volume = {7933}, journal = {Lecture Notes in Computer Science (Proceedings of SEA 2013)}, doi = {10.1007/978-3-642-38527-8_18}, pages = {188 -- 199}, year = {2013}, abstract = {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.}, language = {en} } @article{ConradRathTiefetal.2013, author = {Conrad, Tim and Rath, Barbara and Tief, Franziska and Karsch, K. and Muehlhans, S. and Obermeier, Patrick and Adamou, E. and Chen, X. and Seeber, L. and Peiser, Ch. and Hoppe, Christian and von Kleist, Max and Schweiger, Brunhilde}, title = {Towards a personalized approach to managing of influenza infections in infants and children - food for thought and a note on oseltamivir}, volume = {13}, journal = {Infectious Disorders - Drug Targets}, number = {1}, pages = {25 -- 33}, year = {2013}, language = {en} } @article{ConradLeichtleNuofferetal.2012, author = {Conrad, Tim and Leichtle, Alexander Benedikt and Nuoffer, Jean-Marc and Ceglarek, Uta and Kase, Julia and Witzigmann, Helmut and Thiery, Joachim and Fiedler, Georg Martin}, title = {Serum amino acid profiles and their alterations in colorectal cancer}, journal = {Metabolomics}, doi = {10.1007/s11306-011-0357-5}, year = {2012}, abstract = {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.}, language = {en} } @article{GuptaConradSpoetteretal.2012, author = {Gupta, Pooja and Conrad, Tim and Sp{\"o}tter, Andreas and Reinsch, Norbert and Bienefeld, Kaspar}, title = {Simulating a base population in honey bee for molecular genetic studies}, journal = {Genetics Selection Evolution}, doi = {10.1186/1297-9686-44-14}, year = {2012}, abstract = {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}, language = {en} } @article{Conrad2004, author = {Conrad, Tim}, title = {New Appraches for Visualizing and Analyzing Metabolic Pathways}, journal = {Proceedings of the Second Australian Undergraduate Students? Computing Conference}, year = {2004}, abstract = {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.}, language = {en} } @article{GelssMateraSchuette2016, author = {Gelß, Patrick and Matera, Sebastian and Sch{\"u}tte, Christof}, title = {Solving the master equation without kinetic Monte Carlo: Tensor train approximations for a CO oxidation model}, volume = {314}, journal = {Journal of Computational Physics}, doi = {10.1016/j.jcp.2016.03.025}, pages = {489 -- 502}, year = {2016}, abstract = {In multiscale modeling of heterogeneous catalytic processes, one crucial point is the solution of a Markovian master equation describing the stochastic reaction kinetics. Usually, this is too high-dimensional to be solved with standard numerical techniques and one has to rely on sampling approaches based on the kinetic Monte Carlo method. In this study we break the curse of dimensionality for the direct solution of the Markovian master equation by exploiting the Tensor Train Format for this purpose. The performance of the approach is demonstrated on a first principles based, reduced model for the CO oxidation on the RuO2(110) surface. We investigate the complexity for increasing system size and for various reaction conditions. The advantage over the stochastic simulation approach is illustrated by a problem with increased}, 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} } @article{GuptaGramatkeEinspanieretal.2017, author = {Gupta, Pooja and Gramatke, Annika and Einspanier, Ralf and Sch{\"u}tte, Christof and von Kleist, Max and Sharbati, Jutta}, title = {In silico cytotoxicity assessment on cultured rat intestinal cells deduced from cellular impedance measurements}, volume = {41}, journal = {Toxicology in Vitro}, issn = {1438-0064}, pages = {179 -- 188}, year = {2017}, abstract = {Early and reliable identification of chemical toxicity is of utmost importance. At the same time, reduction of animal testing is paramount. Therefore, methods that improve the interpretability and usability of in vitro assays are essential. xCELLigence's real-time cell analyzer (RTCA) provides a novel, fast and cost effective in vitro method to probe compound toxicity. We developed a simple mathematical framework for the qualitative and quantitative assessment of toxicity for RTCA measurements. Compound toxicity, in terms of its 50\% inhibitory concentration IC50 on cell growth, and parameters related to cell turnover were estimated on cultured IEC-6 cells exposed to 10 chemicals at varying concentrations. Our method estimated IC50 values of 113.05, 7.16, 28.69 and 725.15 μM for the apparently toxic compounds 2-acetylamino-fluorene, aflatoxin B1, benzo-[a]-pyrene and chloramphenicol in the tested cell line, in agreement with literature knowledge. IC50 values of all apparent in vivo non-toxic compounds were estimated to be non-toxic by our method. Corresponding estimates from RTCA's in-built model gave false positive (toxicity) predictions in 5/10 cases. Taken together, our proposed method reduces false positive predictions and reliably identifies chemical toxicity based on impedance measurements. The source code for the developed method including instructions is available at https://git.zib.de/bzfgupta/toxfit/tree/master.}, language = {en} } @article{WilsonAnglinAmbellanetal.2017, author = {Wilson, David and Anglin, Carolyn and Ambellan, Felix and Grewe, Carl Martin and Tack, Alexander and Lamecker, Hans and Dunbar, Michael and Zachow, Stefan}, title = {Validation of three-dimensional models of the distal femur created from surgical navigation point cloud data for intraoperative and postoperative analysis of total knee arthroplasty}, volume = {12}, journal = {International Journal of Computer Assisted Radiology and Surgery}, number = {12}, publisher = {Springer}, doi = {10.1007/s11548-017-1630-5}, pages = {2097 -- 2105}, year = {2017}, abstract = {Purpose: Despite the success of total knee arthroplasty there continues to be a significant proportion of patients who are dissatisfied. One explanation may be a shape mismatch between pre and post-operative distal femurs. The purpose of this study was to investigate a method to match a statistical shape model (SSM) to intra-operatively acquired point cloud data from a surgical navigation system, and to validate it against the pre-operative magnetic resonance imaging (MRI) data from the same patients. Methods: A total of 10 patients who underwent navigated total knee arthroplasty also had an MRI scan less than 2 months pre-operatively. The standard surgical protocol was followed which included partial digitization of the distal femur. Two different methods were employed to fit the SSM to the digitized point cloud data, based on (1) Iterative Closest Points (ICP) and (2) Gaussian Mixture Models (GMM). The available MRI data were manually segmented and the reconstructed three-dimensional surfaces used as ground truth against which the statistical shape model fit was compared. Results: For both approaches, the difference between the statistical shape model-generated femur and the surface generated from MRI segmentation averaged less than 1.7 mm, with maximum errors occurring in less clinically important areas. Conclusion: The results demonstrated good correspondence with the distal femoral morphology even in cases of sparse data sets. Application of this technique will allow for measurement of mismatch between pre and post-operative femurs retrospectively on any case done using the surgical navigation system and could be integrated into the surgical navigation unit to provide real-time feedback.}, language = {en} } @article{vonTycowiczAmbellanMukhopadhyayetal.2018, author = {von Tycowicz, Christoph and Ambellan, Felix and Mukhopadhyay, Anirban and Zachow, Stefan}, title = {An Efficient Riemannian Statistical Shape Model using Differential Coordinates}, volume = {43}, journal = {Medical Image Analysis}, number = {1}, doi = {10.1016/j.media.2017.09.004}, pages = {1 -- 9}, year = {2018}, abstract = {We propose a novel Riemannian framework for statistical analysis of shapes that is able to account for the nonlinearity in shape variation. By adopting a physical perspective, we introduce a differential representation that puts the local geometric variability into focus. We model these differential coordinates as elements of a Lie group thereby endowing our shape space with a non-Euclidean structure. A key advantage of our framework is that statistics in a manifold shape space becomes numerically tractable improving performance by several orders of magnitude over state-of-the-art. We show that our Riemannian model is well suited for the identification of intra-population variability as well as inter-population differences. In particular, we demonstrate the superiority of the proposed model in experiments on specificity and generalization ability. We further derive a statistical shape descriptor that outperforms the standard Euclidean approach in terms of shape-based classification of morphological disorders.}, language = {en} } @article{BennHiepenOsterlandetal.2017, author = {Benn, Andreas and Hiepen, Christian and Osterland, Marc and Sch{\"u}tte, Christof and Zwijsen, An and Knaus, Petra}, title = {Role of bone morphogenetic proteins in sprouting angiogenesis: differential BMP receptor-dependent signaling pathways balance stalk vs. tip cell competence}, volume = {31}, journal = {FASEB Journal}, number = {11}, doi = {10.1096/fj.201700193RR}, pages = {4720 -- 4733}, year = {2017}, abstract = {Before the onset of sprouting angiogenesis, the endothelium is prepatterned for the positioning of tip and stalk cells. Both cell identities are not static, as endothelial cells (ECs) constantly compete for the tip cell position in a dynamic fashion. Here, we show that both bone morphogenetic protein (BMP) 2 and BMP6 are proangiogenic in vitro and ex vivo and that the BMP type I receptors, activin receptor-like kinase (ALK)3 and ALK2, play crucial and distinct roles in this process. BMP2 activates the expression of tip cell-associated genes, such as DLL4 (delta-like ligand 4) and KDR (kinase insert domain receptor), and p38-heat shock protein 27 (HSP27)-dependent cell migration, thereby generating tip cell competence. Whereas BMP6 also triggers collective cell migration via the p38-HSP27 signaling axis, BMP6 induces in addition SMAD1/5 signaling, thereby promoting the expression of stalk cell-associated genes, such as HES1 (hairy and enhancer of split 1) and FLT1 (fms-like tyrosine kinase 1). Specifically, ALK3 is required for sprouting from HUVEC spheroids, whereas ALK2 represses sprout formation. We demonstrate that expression levels and respective complex formation of BMP type I receptors in ECs determine stalk vs. tip cell identity, thus contributing to endothelial plasticity during sprouting angiogenesis. As antiangiogenic monotherapies that target the VEGF or ALK1 pathways have not fulfilled efficacy objectives in clinical trials, the selective targeting of the ALK2/3 pathways may be an attractive new approach.}, language = {en} } @article{WinkelmannSchuette2017, author = {Winkelmann, Stefanie and Sch{\"u}tte, Christof}, title = {Hybrid models for chemical reaction networks: Multiscale theory and application to gene regulatory systems}, volume = {147}, journal = {The Journal of Chemical Physics}, number = {11}, doi = {10.1063/1.4986560}, pages = {114115-1 -- 114115-18}, year = {2017}, abstract = {Well-mixed stochastic chemical kinetics are properly modeled by the chemical master equation (CME) and associated Markov jump processes in molecule number space. If the reactants are present in large amounts, however, corresponding simulations of the stochastic dynamics become computationally expensive and model reductions are demanded. The classical model reduction approach uniformly rescales the overall dynamics to obtain deterministic systems characterized by ordinary differential equations, the well-known mass action reaction rate equations. For systems with multiple scales, there exist hybrid approaches that keep parts of the system discrete while another part is approximated either using Langevin dynamics or deterministically. This paper aims at giving a coherent overview of the different hybrid approaches, focusing on their basic concepts and the relation between them. We derive a novel general description of such hybrid models that allows expressing various forms by one type of equation. We also check in how far the approaches apply to model extensions of the CME for dynamics which do not comply with the central well-mixed condition and require some spatial resolution. A simple but meaningful gene expression system with negative self-regulation is analysed to illustrate the different approximation qualities of some of the hybrid approaches discussed. Especially, we reveal the cause of error in the case of small volume approximations.}, 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{KryvenRoeblitzSchuette2015, author = {Kryven, Ivan and R{\"o}blitz, Susanna and Sch{\"u}tte, Christof}, title = {Solution of the chemical master equation by radial basis functions approximation with interface tracking}, volume = {9}, journal = {BMC Systems Biology}, number = {67}, doi = {10.1186/s12918-015-0210-y}, pages = {1 -- 12}, year = {2015}, abstract = {Background. The chemical master equation is the fundamental equation of stochastic chemical kinetics. This differential-difference equation describes temporal evolution of the probability density function for states of a chemical system. A state of the system, usually encoded as a vector, represents the number of entities or copy numbers of interacting species, which are changing according to a list of possible reactions. It is often the case, especially when the state vector is high-dimensional, that the number of possible states the system may occupy is too large to be handled computationally. One way to get around this problem is to consider only those states that are associated with probabilities that are greater than a certain threshold level. Results. We introduce an algorithm that significantly reduces computational resources and is especially powerful when dealing with multi-modal distributions. The algorithm is built according to two key principles. Firstly, when performing time integration, the algorithm keeps track of the subset of states with significant probabilities (essential support). Secondly, the probability distribution that solves the equation is parametrised with a small number of coefficients using collocation on Gaussian radial basis functions. The system of basis functions is chosen in such a way that the solution is approximated only on the essential support instead of the whole state space. Discussion. In order to demonstrate the effectiveness of the method, we consider four application examples: a) the self-regulating gene model, b) the 2-dimensional bistable toggle switch, c) a generalisation of the bistable switch to a 3-dimensional tristable problem, and d) a 3-dimensional cell differentiation model that, depending on parameter values, may operate in bistable or tristable modes. In all multidimensional examples the manifold containing the system states with significant probabilities undergoes drastic transformations over time. This fact makes the examples especially challenging for numerical methods. Conclusions. The proposed method is a new numerical approach permitting to approximately solve a wide range of problems that have been hard to tackle until now. A full representation of multi-dimensional distributions is recovered. The method is especially attractive when dealing with models that yield solutions of a complex structure, for instance, featuring multi-stability. Electronic version: http://www.biomedcentral.com/1752-0509/9/67}, language = {en} } @incollection{LameckerZachow2016, author = {Lamecker, Hans and Zachow, Stefan}, title = {Statistical Shape Modeling of Musculoskeletal Structures and Its Applications}, volume = {23}, booktitle = {Computational Radiology for Orthopaedic Interventions}, publisher = {Springer}, isbn = {978-3-319-23481-6}, doi = {10.1007/978-3-319-23482-3}, pages = {1 -- 23}, year = {2016}, abstract = {Statistical shape models (SSM) describe the shape variability contained in a given population. They are able to describe large populations of complex shapes with few degrees of freedom. This makes them a useful tool for a variety of tasks that arise in computer-aided madicine. In this chapter we are going to explain the basic methodology of SSMs and present a variety of examples, where SSMs have been successfully applied.}, language = {en} } @inproceedings{MukhopadhyayOksuzBevilacquaetal.2015, author = {Mukhopadhyay, Anirban and Oksuz, Ilkay and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Data-Driven Feature Learning for Myocardial Segmentation of CP-BOLD MRI}, volume = {9126}, booktitle = {Functional Imaging and Modeling of the Heart}, publisher = {Springer}, doi = {10.1007/978-3-319-20309-6_22}, pages = {189 -- 197}, year = {2015}, abstract = {Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP- BOLD) MR is capable of diagnosing an ongoing ischemia by detecting changes in myocardial intensity patterns at rest without any contrast and stress agents. Visualizing and detecting these changes require significant post-processing, including myocardial segmentation for isolating the myocardium. But, changes in myocardial intensity pattern and myocardial shape due to the heart's motion challenge automated standard CINE MR myocardial segmentation techniques resulting in a significant drop of segmentation accuracy. We hypothesize that the main reason behind this phenomenon is the lack of discernible features. In this paper, a multi scale discriminative dictionary learning approach is proposed for supervised learning and sparse representation of the myocardium, to improve the myocardial feature selection. The technique is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canine subjects. The proposed method significantly outperforms standard cardiac segmentation techniques, including segmentation via registration, level sets and supervised methods for myocardial segmentation.}, language = {en} } @inproceedings{MukhopadhyayOksuzBevilacquaetal.2015, author = {Mukhopadhyay, Anirban and Oksuz, Ilkay and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Unsupervised myocardial segmentation for cardiac MRI}, volume = {LNCS 9351}, booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015}, doi = {10.1007/978-3-319-24574-4_2}, pages = {12 -- 20}, year = {2015}, abstract = {Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits of unsupervised techniques e.g., no need for large amount of training data and better potential of handling variability in anatomy and image contrast, is more evident with emerging cardiac MR modalities. For example, CP-BOLD is a new MRI technique that has been shown to detect ischemia without any contrast at stress but also at rest conditions. Although CP-BOLD looks similar to standard CINE, changes in myocardial intensity patterns and shape across cardiac phases, due to the heart's motion, BOLD effect and artifacts affect the underlying mechanisms of fully supervised segmentation techniques resulting in a significant drop in segmentation accuracy. In this paper, we present a fully unsupervised technique for segmenting myocardium from the background in both standard CINE MR and CP-BOLD MR. We combine appearance with motion information (obtained via Optical Flow) in a dictionary learning framework to sparsely represent important features in a low dimensional space and separate myocardium from background accordingly. Our fully automated method learns background-only models and one class classifier provides myocardial segmentation. The advantages of the proposed technique are demonstrated on a dataset containing CP-BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across 10 canine subjects, where our method outperforms state-of-the-art supervised segmentation techniques in CP-BOLD MR and performs at-par for standard CINE MR.}, language = {en} } @inproceedings{OksuzMukhopadhyayBevilacquaetal.2015, author = {Oksuz, Ilkay and Mukhopadhyay, Anirban and Bevilacqua, Marco and Dharmakumar, Rohan and Tsaftaris, Sotirios}, title = {Dictionary Learning Based Image Descriptor for Myocardial Registration of CP-BOLD MR}, volume = {9350}, booktitle = {Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015}, publisher = {Springer}, doi = {10.1007/978-3-319-24571-3_25}, pages = {205 -- 213}, year = {2015}, abstract = {Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP- BOLD) MRI is a new contrast agent- and stress-free imaging technique for the assessment of myocardial ischemia at rest. The precise registration among the cardiac phases in this cine type acquisition is essential for automating the analysis of images of this technique, since it can potentially lead to better specificity of ischemia detection. However, inconsistency in myocardial intensity patterns and the changes in myocardial shape due to the heart's motion lead to low registration performance for state- of-the-art methods. This low accuracy can be explained by the lack of distinguishable features in CP-BOLD and inappropriate metric defini- tions in current intensity-based registration frameworks. In this paper, the sparse representations, which are defined by a discriminative dictionary learning approach for source and target images, are used to improve myocardial registration. This method combines appearance with Gabor and HOG features in a dictionary learning framework to sparsely represent features in a low dimensional space. The sum of squared differences of these distinctive sparse representations are used to define a similarity term in the registration framework. The proposed descriptor is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canines.}, language = {en} } @misc{OsterlandBennProhaskaetal.2015, author = {Osterland, Marc and Benn, Andreas and Prohaska, Steffen and Sch{\"u}tte, Christof}, title = {Single Cell Tracking in Phase-Contrast Microscopy}, journal = {EMBL Symposium 2015 - Seeing is Believing - Imaging the Processes of Life}, year = {2015}, abstract = {In this work, we developed an automatic algorithm to analyze cell migration in chemotaxis assays, based on phase-contrast time-lapse microscopy. While manual approaches are still widely used in recent publications, our algorithm is able to track hundreds of single cells per frame. The extracted paths are analysed with traditional geometrical approaches as well as diffusion-driven Markov state models (MSM). Based on these models, a detailed view on spatial and temporal effects is possible. Using our new approach on experimental data, we are able to distinguish between directed migration (e.g. towards a VEGF gradient) and random migration without favored direction. A calculation of the committor probabilities reveals that cells of the whole image area are more likely to migrate directly towards the VEGF than away from it during the first four hours. However, in absence of a chemoattractant, cells migrate more likely to their nearest image border. These conclusions are supported by the spatial mean directions. In a next step, the cell-cell interaction during migration and the migration of cell clusters will be analyzed. Furthermore, we want to observe phenotypical changes during migration based on fluorescence microscopy and machine learning. The algorithm is part of a collaborative platform which brings the experimental expertise of scientists from life sciences and the analytical knowledge of computer scientists together. This platform is built using web-based technologies with a responsive real-time user interface. All data, including raw and metadata as well as the accompanying results, will be stored in a secure and scalable compute cluster. The compute cluster provides sufficient space and computational power for modern image-based experiments and their analyses. Specific versions of data and results can be tagged to keep immutable records for archival.}, language = {en} } @misc{KoltaiCiccottiSchuette2016, author = {Koltai, Peter and Ciccotti, Giovanni and Sch{\"u}tte, Christof}, title = {On metastability and Markov state models for non-stationary molecular dynamics}, volume = {174103}, journal = {The Journal of Chemical Physics}, edition = {145}, issn = {1438-0064}, doi = {10.1063/1.4966157}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-57869}, year = {2016}, abstract = {We utilize the theory of coherent sets to build Markov state models for non- equilibrium molecular dynamical systems. Unlike for systems in equilibrium, "meta- stable" sets in the non-equilibrium case may move as time evolves. We formalize this concept by relying on the theory of coherent sets, based on this we derive finite-time non-stationary Markov state models, and illustrate the concept and its main differences to equilibrium Markov state modeling on simple, one-dimensional examples.}, language = {en} } @article{DjurdjevacConradWeberSchuette2016, author = {Djurdjevac Conrad, Natasa and Weber, Marcus and Sch{\"u}tte, Christof}, title = {Finding dominant structures of nonreversible Markov processes}, volume = {14}, journal = {Multiscale Modeling and Simulation}, number = {4}, doi = {10.1137/15M1032272}, pages = {1319 -- 1340}, year = {2016}, language = {en} } @misc{MukhopadhyayKumarBhandarkar2016, author = {Mukhopadhyay, Anirban and Kumar, Arun and Bhandarkar, Suchendra}, title = {Joint Geometric Graph Embedding for Partial Shape Matching in Images}, journal = {IEEE Winter Conference on Applications of Computer Vision}, edition = {IEEE Winter Conference on Applications of Computer Vision (WACV)}, publisher = {IEEE}, pages = {1 -- 9}, year = {2016}, abstract = {A novel multi-criteria optimization framework for matching of partially visible shapes in multiple images using joint geometric graph embedding is proposed. The proposed framework achieves matching of partial shapes in images that exhibit extreme variations in scale, orientation, viewpoint and illumination and also instances of occlusion; conditions which render impractical the use of global contour-based descriptors or local pixel-level features for shape matching. The proposed technique is based on optimization of the embedding distances of geometric features obtained from the eigenspectrum of the joint image graph, coupled with regularization over values of the mean pixel intensity or histogram of oriented gradients. It is shown to obtain successfully the correspondences denoting partial shape similarities as well as correspondences between feature points in the images. A new benchmark dataset is proposed which contains disparate image pairs with extremely challenging variations in viewing conditions when compared to an existing dataset [18]. The proposed technique is shown to significantly outperform several state-of-the-art partial shape matching techniques on both datasets.}, language = {en} } @inproceedings{GuptaKrauseRikeitetal.2014, author = {Gupta, Pooja and Krause, Carola and Rikeit, Paul and R{\"o}blitz, Susanna and Knaus, Petra and Sch{\"u}tte, Christof}, title = {Modeling of the BMP mediated co-regulation of the Smad and Non-Smad pathways in the context of cell density}, booktitle = {10th International BMP conference, 2014, Berlin, Germany}, year = {2014}, language = {en} } @article{PeppertvonKleistSchuetteetal.2022, author = {Peppert, Felix and von Kleist, Max and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {On the Sufficient Condition for Solving the Gap-Filling Problem Using Deep Convolutional Neural Networks}, volume = {33}, journal = {IEEE Transactions on Neural Networks and Learning Systems}, number = {11}, doi = {10.1109/TNNLS.2021.3072746}, pages = {6194 -- 6205}, year = {2022}, abstract = {Deep convolutional neural networks (DCNNs) are routinely used for image segmentation of biomedical data sets to obtain quantitative measurements of cellular structures like tissues. These cellular structures often contain gaps in their boundaries, leading to poor segmentation performance when using DCNNs like the U-Net. The gaps can usually be corrected by post-hoc computer vision (CV) steps, which are specific to the data set and require a disproportionate amount of work. As DCNNs are Universal Function Approximators, it is conceivable that the corrections should be obsolete by selecting the appropriate architecture for the DCNN. In this article, we present a novel theoretical framework for the gap-filling problem in DCNNs that allows the selection of architecture to circumvent the CV steps. Combining information-theoretic measures of the data set with a fundamental property of DCNNs, the size of their receptive field, allows us to formulate statements about the solvability of the gap-filling problem independent of the specifics of model training. In particular, we obtain mathematical proof showing that the maximum proficiency of filling a gap by a DCNN is achieved if its receptive field is larger than the gap length. We then demonstrate the consequence of this result using numerical experiments on a synthetic and real data set and compare the gap-filling ability of the ubiquitous U-Net architecture with variable depths. Our code is available at https://github.com/ai-biology/dcnn-gap-filling.}, language = {en} } @article{LiPimentelSzengeletal.2021, author = {Li, Jianning and Pimentel, Pedro and Szengel, Angelika and Ehlke, Moritz and Lamecker, Hans and Zachow, Stefan and Estacio, Laura and Doenitz, Christian and Ramm, Heiko and Shi, Haochen and Chen, Xiaojun and Matzkin, Franco and Newcombe, Virginia and Ferrante, Enzo and Jin, Yuan and Ellis, David G. and Aizenberg, Michele R. and Kodym, Oldrich and Spanel, Michal and Herout, Adam and Mainprize, James G. and Fishman, Zachary and Hardisty, Michael R. and Bayat, Amirhossein and Shit, Suprosanna and Wang, Bomin and Liu, Zhi and Eder, Matthias and Pepe, Antonio and Gsaxner, Christina and Alves, Victor and Zefferer, Ulrike and von Campe, Cord and Pistracher, Karin and Sch{\"a}fer, Ute and Schmalstieg, Dieter and Menze, Bjoern H. and Glocker, Ben and Egger, Jan}, title = {AutoImplant 2020 - First MICCAI Challenge on Automatic Cranial Implant Design}, volume = {40}, journal = {IEEE Transactions on Medical Imaging}, number = {9}, issn = {0278-0062}, doi = {10.1109/TMI.2021.3077047}, pages = {2329 -- 2342}, year = {2021}, abstract = {The aim of this paper is to provide a comprehensive overview of the MICCAI 2020 AutoImplant Challenge. The approaches and publications submitted and accepted within the challenge will be summarized and reported, highlighting common algorithmic trends and algorithmic diversity. Furthermore, the evaluation results will be presented, compared and discussed in regard to the challenge aim: seeking for low cost, fast and fully automated solutions for cranial implant design. Based on feedback from collaborating neurosurgeons, this paper concludes by stating open issues and post-challenge requirements for intra-operative use.}, language = {en} } @article{DaiFuellgrabePfeufferetal.2021, author = {Dai, Chengxin and F{\"u}llgrabe, Anja and Pfeuffer, Julianus and Solovyeva, Elizaveta M. and Deng, Jingwen and Moreno, Pablo and Kamatchinathan, Selvakumar and Kundu, Deepti Jaiswal and George, Nancy and Fexovy, Silvie and Gr{\"u}ning, Bj{\"o}rn and F{\"o}ll, Melanie Christine and Griss, Johannes and Vaudel, Marc and Audain, Enrique and Locard-Paulet, Marie and Turewicz, Michael and Eisenacher, Martin and Uszkoreit, Julian and Van Den Bossche, Tim and Schw{\"a}mmle, Veit and Webel, Henry and Schulze, Stefan and Bouyssi{\´e}, David and Jayaram, Savita and Duggineni, Vinay Kumar and Samaras, Patroklos and Wilhelm, Mathias and Choi, Meena and Wang, Mingxun and Kohlbacher, Oliver and Brazma, Alvis and Papatheodorou, Irene and Bandeira, Nuno and Deutsch, Eric W. and Vizca{\´i}no, Juan Antonio and Bai, Mingze and Sachsenberg, Timo and Levitsky, Lev I. and Perez-Riverol, Yasset}, title = {A proteomics sample metadata representation for multiomics integration and big data analysis}, volume = {12}, journal = {Nature Communications}, number = {5854}, doi = {https://doi.org/10.1038/s41467-021-26111-3}, year = {2021}, abstract = {The amount of public proteomics data is rapidly increasing but there is no standardized format to describe the sample metadata and their relationship with the dataset files in a way that fully supports their understanding or reanalysis. Here we propose to develop the transcriptomics data format MAGE-TAB into a standard representation for proteomics sample metadata. We implement MAGE-TAB-Proteomics in a crowdsourcing project to manually curate over 200 public datasets. We also describe tools and libraries to validate and submit sample metadata-related information to the PRIDE repository. We expect that these developments will improve the reproducibility and facilitate the reanalysis and integration of public proteomics datasets.}, language = {en} } @article{UmerZhuPfeufferetal.2021, author = {Umer, Husen M. and Zhu, Yafeng and Pfeuffer, Julianus and Sachsenberg, Timo and Lehti{\"o}, Janne and Branca, Rui and Perez-Riverol, Yasset}, title = {Generation of ENSEMBL-based proteogenomics databases boosts the identification of non-canonical peptides}, journal = {Bioinformatics}, number = {5}, edition = {38}, publisher = {Oxford Academic}, pages = {1470 -- 1472}, year = {2021}, abstract = {We have implemented the pypgatk package and the pgdb workflow to create proteogenomics databases based on ENSEMBL resources. The tools allow the generation of protein sequences from novel protein-coding transcripts by performing a three-frame translation of pseudogenes, lncRNAs, and other non-canonical transcripts, such as those produced by alternative splicing events. It also includes exonic out-of-frame translation from otherwise canonical protein-coding mRNAs. Moreover, the tool enables the generation of variant protein sequences from multiple sources of genomic variants including COSMIC, cBioportal, gnomAD, and mutations detected from sequencing of patient samples. pypgatk and pgdb provide multiple functionalities for database handling, notably optimized target/decoy generation by the algorithm DecoyPyrat. Finally, we perform a reanalysis of four public datasets in PRIDE by generating cell-type specific databases for 65 cell lines using the pypgatk and pgdb workflow, revealing a wealth of non-canonical or cryptic peptides amounting to more than 10\% of the total number of peptides identified (43,501 out of 402,512).}, language = {en} } @article{TackAmbellanZachow2021, author = {Tack, Alexander and Ambellan, Felix and Zachow, Stefan}, title = {Towards novel osteoarthritis biomarkers: Multi-criteria evaluation of 46,996 segmented knee MRI data from the Osteoarthritis Initiative}, volume = {16}, journal = {PLOS One}, number = {10}, doi = {10.1371/journal.pone.0258855}, year = {2021}, abstract = {Convolutional neural networks (CNNs) are the state-of-the-art for automated assessment of knee osteoarthritis (KOA) from medical image data. However, these methods lack interpretability, mainly focus on image texture, and cannot completely grasp the analyzed anatomies' shapes. In this study we assess the informative value of quantitative features derived from segmentations in order to assess their potential as an alternative or extension to CNN-based approaches regarding multiple aspects of KOA. Six anatomical structures around the knee (femoral and tibial bones, femoral and tibial cartilages, and both menisci) are segmented in 46,996 MRI scans. Based on these segmentations, quantitative features are computed, i.e., measurements such as cartilage volume, meniscal extrusion and tibial coverage, as well as geometric features based on a statistical shape encoding of the anatomies. The feature quality is assessed by investigating their association to the Kellgren-Lawrence grade (KLG), joint space narrowing (JSN), incident KOA, and total knee replacement (TKR). Using gold standard labels from the Osteoarthritis Initiative database the balanced accuracy (BA), the area under the Receiver Operating Characteristic curve (AUC), and weighted kappa statistics are evaluated. Features based on shape encodings of femur, tibia, and menisci plus the performed measurements showed most potential as KOA biomarkers. Differentiation between non-arthritic and severely arthritic knees yielded BAs of up to 99\%, 84\% were achieved for diagnosis of early KOA. Weighted kappa values of 0.73, 0.72, and 0.78 were achieved for classification of the grade of medial JSN, lateral JSN, and KLG, respectively. The AUC was 0.61 and 0.76 for prediction of incident KOA and TKR within one year, respectively. Quantitative features from automated segmentations provide novel biomarkers for KLG and JSN classification and show potential for incident KOA and TKR prediction. The validity of these features should be further evaluated, especially as extensions of CNN- based approaches. To foster such developments we make all segmentations publicly available together with this publication.}, language = {en} } @misc{Krause2021, type = {Master Thesis}, author = {Krause, Jan}, title = {Investigation of Options to Handle 3D MRI Data via Convolutional Neural Networks Application in Knee Osteoarthritits Classification}, pages = {127}, year = {2021}, language = {en} } @misc{Shestakov2021, type = {Master Thesis}, author = {Shestakov, Alexey}, title = {A Deep Learning Method for Automated Detection of Meniscal Tears in Meniscal Sub-Regions in 3D MRI Data}, pages = {96}, year = {2021}, abstract = {This work presents a fully automated pipeline, centered around a deep neural network, as well as a method to train that network in an efficient manner, that enables accurate detection of lesions in meniscal anatomical subregions. The network architecture is based on a transformer encoder/decoder. It is trained on DESS and tuned on IW TSE 3D MRI scans sourced from the Osteoarthritis Initiative. Furthermore, it is trained in a multilabel, and multitask fashion, using an auxiliary detection head. The former enables implicit localisation of meniscal defects, that to the best of my knowledge, has not yet been reported elsewhere. The latter enables efficient learning on the entire 3D MRI volume. Thus, the proposed method does not require any expert knowledge at inference. Aggregated inference results from two datasets resulted in an overall AUCROC result of 0.90, 0.91 and 0.93 for meniscal lesion detection anywhere in the knee, in medial and in lateral menisci respectively. These results compare very well to the related work, even though only a fraction of the data has been utilized. Clinical applicability and benefit is yet to be determined.}, 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} } @article{AnteghiniMartinsdosSantosSaccenti2023, author = {Anteghini, Marco and Martins dos Santos, Vitor AP and Saccenti, Edoardo}, title = {PortPred: Exploiting deep learning embeddings of amino acid sequences for the identification of transporter proteins and their substrates}, volume = {124}, journal = {Journal of Cellular Biochemistry}, number = {11}, doi = {10.1002/jcb.30490}, pages = {1665 -- 1885}, year = {2023}, abstract = {The physiology of every living cell is regulated at some level by transporter proteins which constitute a relevant portion of membrane-bound proteins and are involved in the movement of ions, small and macromolecules across bio-membranes. The importance of transporter proteins is unquestionable. The prediction and study of previously unknown transporters can lead to the discovery of new biological pathways, drugs and treatments. Here we present PortPred, a tool to accurately identify transporter proteins and their substrate starting from the protein amino acid sequence. PortPred successfully combines pre-trained deep learning-based protein embeddings and machine learning classification approaches and outperforms other state-of-the-art methods. In addition, we present a comparison of the most promising protein sequence embeddings (Unirep, SeqVec, ProteinBERT, ESM-1b) and their performances for this specific task.}, language = {en} } @incollection{AnteghiniMartinsDosSantos2023, author = {Anteghini, Marco and Martins Dos Santos, Vitor}, title = {Computational Approaches for Peroxisomal Protein Localization}, volume = {2643}, booktitle = {Peroxisomes}, publisher = {Humana, New York}, isbn = {978-1-0716-3047-1}, doi = {10.1007/978-1-0716-3048-8_29}, pages = {405 -- 411}, year = {2023}, abstract = {Computational approaches are practical when investigating putative peroxisomal proteins and for sub-peroxisomal protein localization in unknown protein sequences. Nowadays, advancements in computational methods and Machine Learning (ML) can be used to hasten the discovery of novel peroxisomal proteins and can be combined with more established computational methodologies. Here, we explain and list some of the most used tools and methodologies for novel peroxisomal protein detection and localization.}, language = {de} } @inproceedings{SchubotzFerrerStegmuelleretal.2023, author = {Schubotz, Moritz and Ferrer, Eloi and Stegm{\"u}ller, Johannes and Mietchen, Daniel and Teschke, Olaf and Pusch, Larissa and Conrad, Tim}, title = {Bravo MaRDI: A Wikibase Knowledge Graph on Mathematics}, booktitle = {Proceedings of the 4th Wikidata Workshop 2022 co-located with the 22st International Semantic Web Conference (ISWC2023)}, year = {2023}, abstract = {Mathematical world knowledge is a fundamental component of Wikidata. However, to date, no expertly curated knowledge graph has focused specifically on contemporary mathematics. Addressing this gap, the Mathematical Research Data Initiative (MaRDI) has developed a comprehensive knowledge graph that links multimodal research data in mathematics. This encompasses traditional research data items like datasets, software, and publications and includes semantically advanced objects such as mathematical formulae and hypotheses. This paper details the abilities of the MaRDI knowledge graph, which is based on Wikibase, leading up to its inaugural public release, codenamed Bravo, available on https://portal.mardi4nfdi.de.}, language = {de} } @article{SenguptaBartoli2025, author = {Sengupta, Agniva and Bartoli, Adrien}, title = {Convex Solutions to SfT and NRSfM under Algebraic Deformation Models}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, doi = {10.1109/TPAMI.2025.3635039}, year = {2025}, abstract = {We present nonlinear formulations to Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) faithfully exploiting the isometric, conformal and equiareal deformation models. Existing work uses relaxations such as inextensibility or requires knowing the optic flow field around the correspondences, an impractical assumption. In contrast, the proposed formulations only require point correspondences and resolve all ambiguities using the notions of maximal depth and maximal isometry heuristics. We propose solution methods using Semi-Definite Programming (SDP) for all formulations. We show that straightforward SDP models conflict with the usual maximal depth heuristic and propose an adapted opposite-depth parameterisation demonstrating a lesser relaxation gap. Experimental results on many real-world benchmark datasets demonstrate superior accuracy over existing methods.}, language = {en} } @inproceedings{ManogueSchangKuşetal.2025, author = {Manogue, Kevin and Schang, Tomasz and Ku{\c{s}}, Dilara and M{\"u}ller, Jonas and Zachow, Stefan and Sengupta, Agniva}, title = {Generalizing Shape-from-Template to Topological Changes}, booktitle = {Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference}, publisher = {The Eurographics Association}, isbn = {978-3-03868-296-7}, arxiv = {http://arxiv.org/abs/2511.03459}, doi = {10.2312/stag.20251322}, year = {2025}, abstract = {Reconstructing the surfaces of deformable objects from correspondences between a 3D template and a 2D image is well studied under Shape-from-Template (SfT) methods; however, existing approaches break down when topological changes accompany the deformation. We propose a principled extension of SfT that enables reconstruction in the presence of such changes. Our approach is initialized with a classical SfT solution and iteratively adapts the template by partitioning its spatial domain so as to minimize an energy functional that jointly encodes physical plausibility and reprojection consistency. We demonstrate that the method robustly captures a wide range of practically relevant topological events including tears and cuts on bounded 2D surfaces, thereby establishing the first general framework for topological-change-aware SfT. Experiments on both synthetic and real data confirm that our approach consistently outperforms baseline methods.}, language = {en} } @article{PuschConrad2025, author = {Pusch, Larissa and Conrad, Tim}, title = {Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Biomedical Question Answering}, volume = {5}, journal = {BioMedInformatics}, doi = {10.3390/biomedinformatics5040070}, year = {2025}, abstract = {Advancements in natural language processing (NLP), particularly Large Language Models (LLMs), have greatly improved how we access knowledge. However, in critical domains like biomedicine, challenges like hallucinations—where language models generate infor- mation not grounded in data—can lead to dangerous misinformation. This paper presents a hybrid approach that combines LLMs with Knowledge Graphs (KGs) to improve the accuracy and reliability of question-answering systems in the biomedical field. Our method, implemented using the LangChain framework, includes a query-checking algorithm that checks and, where possible, corrects LLM-generated Cypher queries, which are then exe- cuted on the Knowledge Graph, grounding answers in the KG and reducing hallucinations in the evaluated cases. We evaluated several LLMs, including several GPT models and Llama 3.3:70b, on a custom benchmark dataset of 50 biomedical questions. GPT-4 Turbo achieved 90\% query accuracy, outperforming most other models. We also evaluated prompt engineering, but found little statistically significant improvement compared to the standard prompt, except for Llama 3:70b, which improved with few-shot prompting. To enhance usability, we developed a web-based interface that allows users to input natural language queries, view generated and corrected Cypher queries, and inspect results for accuracy. This framework improves reliability and accessibility by accepting natural language questions and returning verifiable answers directly from the knowledge graph, enabling inspection and reproducibility. The source code for generating the results of this paper and for the user- interface can be found in our Git repository: https://git.zib.de/lpusch/cyphergenkg-gui, accessed on 1 November 2025.}, language = {en} } @article{PfeufferBielowWeinetal.2024, author = {Pfeuffer, Julianus and Bielow, Chris and Wein, Samuel and Jeong, Kyowon and Netz, Eugen and Walter, Axel and Alka, Oliver and Nilse, Lars and Colaianni, Pasquale Domenico and McCloskey, Douglas and Kim, Jihyung and Rosenberger, George and Bichmann, Leon and Walzer, Mathias and Veit, Johannes and Boudaud, Bertrand and Bernt, Matthias and Patikas, Nikolaos and Pilz, Matteo and Startek, Michał Piotr and Kutuzova, Svetlana and Heumos, Lukas and Charkow, Joshua and Sing, Justin Cyril and Feroz, Ayesha and Siraj, Arslan and Weisser, Hendrik and Dijkstra, Tjeerd M. H. and Perez-Riverol, Yasset and R{\"o}st, Hannes and Kohlbacher, Oliver and Sachsenberg, Timo}, title = {OpenMS 3 enables reproducible analysis of large-scale mass spectrometry data}, volume = {21}, journal = {Nature Methods}, number = {3}, publisher = {Springer Science and Business Media LLC}, issn = {1548-7091}, doi = {10.1038/s41592-024-02197-7}, pages = {365 -- 367}, year = {2024}, language = {en} } @article{WeimannConrad2024, author = {Weimann, Kuba and Conrad, Tim}, title = {Federated Learning with Deep Neural Networks: A Privacy-Preserving Approach to Enhanced ECG Classification}, volume = {28}, journal = {IEEE Journal of Biomedical and Health Informatics}, number = {11}, doi = {10.1109/JBHI.2024.3427787}, year = {2024}, language = {en} } @misc{HajarolasvadiBaum2024, author = {Hajarolasvadi, Noushin and Baum, Daniel}, title = {Data for Training the DeepOrientation Model: Simulated cryo-ET tomogram patches}, doi = {10.12752/9686}, year = {2024}, abstract = {A major restriction to applying deep learning methods in cryo-electron tomography is the lack of annotated data. Many large learning-based models cannot be applied to these images due to the lack of adequate experimental ground truth. One appealing alternative solution to the time-consuming and expensive experimental data acquisition and annotation is the generation of simulated cryo-ET images. In this context, we exploit a public cryo-ET simulator called PolNet to generate three datasets of two macromolecular structures, namely the ribosomal complex 4v4r and Thermoplasma acidophilum 20S proteasome, 3j9i. We select these two specific particles to test whether our models work for macromolecular structures with and without rotational symmetry. The three datasets contain 50, 150, and 450 tomograms with a voxel size of 10 ̊A, respectively. Here, we publish patches of size 40 × 40 × 40 extracted from the medium-sized dataset with 26,703 samples of 4v4r and 40,671 samples of 3j9i. The original tomograms from which the samples were extracted are of size 500 × 500 × 250. Finally, it should be noted that the currently published test dataset is employed for reporting the results of our paper titled "DeepOrientation: Deep Orientation Estimation of Macromolecules in Cryo-electron tomography" paper.}, language = {en} } @article{MaierWeiserConrad2025, author = {Maier, Kristina and Weiser, Martin and Conrad, Tim}, title = {Hybrid PDE-ODE Models for Efficient Simulation of Infection Spread in Epidemiology}, volume = {481}, journal = {Proceedings of the Royal Society A}, number = {2306}, publisher = {Royal Society}, arxiv = {http://arxiv.org/abs/2405.12938}, doi = {10.1098/rspa.2024.0421}, year = {2025}, abstract = {This paper introduces a novel hybrid model combining Partial Differential Equations (PDEs) and Ordinary Differential Equations (ODEs) to simulate infectious disease dynamics across geographic regions. By leveraging the spatial detail of PDEs and the computational efficiency of ODEs, the model enables rapid evaluation of public health interventions. Applied to synthetic environments and real-world scenarios in Lombardy, Italy, and Berlin, Germany, the model highlights how interactions between PDE and ODE regions affect infection dynamics, especially in high-density areas. Key findings reveal that the placement of model boundaries in densely populated regions can lead to inaccuracies in infection spread, suggesting that boundaries should be positioned in areas of lower population density to better reflect transmission dynamics. Additionally, regions with low population density hinder infection flow, indicating a need for incorporating, e.g., jumps in the model to enhance its predictive capabilities. Results indicate that the hybrid model achieves a balance between computational speed and accuracy, making it a valuable tool for policymakers in real-time decision-making and scenario analysis in epidemiology and potentially in other fields requiring similar modeling approaches.}, language = {en} } @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{AnteghiniGualdiOliva2025, author = {Anteghini, Marco and Gualdi, Francesco and Oliva, Baldo}, title = {How did we get there? AI applications to biological networks and sequences}, volume = {190}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier BV}, issn = {0010-4825}, doi = {10.1016/j.compbiomed.2025.110064}, year = {2025}, abstract = {The rapidly advancing field of artificial intelligence (AI) has transformed numerous scientific domains, including biology, where a vast and complex volume of data is available for analysis. This paper provides a comprehensive overview of the current state of AI-driven methodologies in genomics, proteomics, and systems biology. We discuss how machine learning algorithms, particularly deep learning models, have enhanced the accuracy and efficiency of embedding sequences, motif discovery, and the prediction of gene expression and protein structure. Additionally, we explore the integration of AI in the embedding and analysis of biological networks, including protein-protein interaction networks and multi-layered networks. By leveraging large-scale biological data, AI techniques have enabled unprecedented insights into complex biological processes and disease mechanisms. This work underlines the potential of applying AI to complex biological data, highlighting current applications and suggesting directions for future research to further explore AI in this rapidly evolving field.}, language = {en} } @article{SenguptaZachow2025, author = {Sengupta, Agniva and Zachow, Stefan}, title = {Shape-from-Template with Generalised Camera}, volume = {162}, journal = {Image and Vision Computing}, doi = {10.1016/j.imavis.2025.105579}, year = {2025}, abstract = {This article presents a new method for non-rigidly registering a 3D shape to 2D keypoints observed by a constellation of multiple cameras. Non-rigid registration of a 3D shape to observed 2D keypoints, i.e., Shape-from-Template (SfT), has been widely studied using single images, but SfT with information from multiple-cameras jointly opens new directions for extending the scope of known use-cases such as 3D shape registration in medical imaging and registration from hand-held cameras, to name a few. We represent such multi-camera setup with the generalised camera model; therefore any collection of perspective or orthographic cameras observing any deforming object can be registered. We propose multiple approaches for such SfT: the first approach where the corresponded keypoints lie on a direction vector from a known 3D point in space, the second approach where the corresponded keypoints lie on a direction vector from an unknown 3D point in space but with known orientation w.r.t some local reference frame, and a third approach where, apart from correspondences, the silhouette of the imaged object is also known. Together, these form the first set of solutions to the SfT problem with generalised cameras. The key idea behind SfT with generalised camera is the improved reconstruction accuracy from estimating deformed shape while utilising the additional information from the mutual constraints between multiple views of a deformed object. The correspondence-based approaches are solved with convex programming while the silhouette-based approach is an iterative refinement of the results from the convex solutions. We demonstrate the accuracy of our proposed methods on many synthetic and real data.}, language = {en} } @misc{Bautz2023, type = {Master Thesis}, author = {Bautz, Lisa}, title = {Unsupervised Shape Correspondence Estimation for Anatomical Shapes}, pages = {83}, year = {2023}, abstract = {The concept of shape correspondence describes a relation between two or more shapes of the same class. It often consists of a mapping between points on semantically similar locations of all shapes. One possible application for shape correspondence in medicine is the automatic location of anatomical landmarks. Another popular application is the construction of statistical shape models. These models are an established way to represent geometric variation of anatomical shapes in a compact way. Possible applications range from the generation of shapes and reconstruction tasks to disease classification. This thesis aims to investigate unsupervised methods that can be used to estimate such a correspondence on anatomical shapes. While most methods used in the medical domain focus on classical optimization algorithms to establish correspondence, the broader computer vision domain developed a versatile field of data-driven methods. Recently, the new shape model FlowSSM was introduced, which does not require predefined correspondences for training as it generates them itself. As the performance of the shape model is quite competitive, it is natural to assume that the generated correspondences are of high quality as well. For this reason, we evaluate the quality of the correspondences generated by FlowSSM within this thesis. Furthermore, we modify the method by adding a second loss term that minimizes geodesic distortions. This is done to favor isometric deformations which can lead to better correspondences. We compare the results with two established methods from the medical domain, LDDMM and Meshmonk. Furthermore, we investigate the performance of a fourth method called Neuromoph. This data-driven method comes from the wider computer vision field and was not tested on anatomical data yet. All methods are evaluated with a set of different metrics. This includes metrics to assess the quality of the resulting meshes, a sparse correspondence error on anatomical landmarks, and metrics to measure the quality of the resulting shape models. Furthermore, we test all methods on three datasets with different degrees of geometric variation, namely liver, distal femur and face. We show that FlowSSM produces correspondences with state-of-the-art quality. Moreover, our modification further improved the quality of correspondences at a global level. Nevertheless, there is no clear ranking between all methods, as the results differ between metrics and datasets. Thereby, we can show that there are different qualities to a proper correspondence which are reflected in the different metrics. It is therefore strongly recommendable to choose a correspondence estimation method specifically for the problem at hand.}, language = {en} } @article{FogalliPeresLineBaum2023, author = {Fogalli, Giovani Bressan and Peres Line, S{\´e}rgio Roberto and Baum, Daniel}, title = {Segmentation of tooth enamel microstructure images using classical image processing and U-Net approaches}, volume = {2}, journal = {Frontiers in Imaging}, doi = {10.3389/fimag.2023.1215764}, year = {2023}, abstract = {Tooth enamel is the hardest tissue in human organism, formed by prism layers in regularly alternating directions. These prisms form the Hunter-Schreger Bands (HSB) pattern when under side illumination, which is composed of light and dark stripes resembling fingerprints. We have shown in previous works that HSB pattern is highly variable, seems to be unique for each tooth and can be used as a biometric method for human identification. Since this pattern cannot be acquired with sensors, the HSB region in the digital photograph must be identified and correctly segmented from the rest of the tooth and background. Although these areas can be manually removed, this process is not reliable as excluded areas can vary according to the individual's subjective impression. Therefore, the aim of this work was to develop an algorithm that automatically selects the region of interest (ROI), thus, making the entire biometric process straightforward. We used two different approaches: a classical image processing method which we called anisotropy-based segmentation (ABS) and a machine learning method known as U-Net, a fully convolutional neural network. Both approaches were applied to a set of extracted tooth images. U-Net with some post processing outperformed ABS in the segmentation task with an Intersection Over Union (IOU) of 0.837 against 0.766. Even with a small dataset, U-Net proved to be a potential candidate for fully automated in-mouth application. However, the ABS technique has several parameters which allow a more flexible segmentation with interactive adjustments specific to image properties.}, language = {en} } @article{BaiDengDaietal.2023, author = {Bai, Mingze and Deng, Jingwen and Dai, Chengxin and Pfeuffer, Julianus and Sachsenberg, Timo and Perez-Riverol, Yasset}, title = {LFQ-Based Peptide and Protein Intensity Differential Expression Analysis}, volume = {22}, journal = {J. Proteome Res.}, number = {6}, publisher = {American Chemical Society}, doi = {10.1021/acs.jproteome.2c00812}, pages = {2114 -- 2123}, year = {2023}, abstract = {Testing for significant differences in quantities at the protein level is a common goal of many LFQ-based mass spectrometry proteomics experiments. Starting from a table of protein and/or peptide quantities from a given proteomics quantification software, many tools and R packages exist to perform the final tasks of imputation, summarization, normalization, and statistical testing. To evaluate the effects of packages and settings in their substeps on the final list of significant proteins, we studied several packages on three public data sets with known expected protein fold changes. We found that the results between packages and even across different parameters of the same package can vary significantly. In addition to usability aspects and feature/compatibility lists of different packages, this paper highlights sensitivity and specificity trade-offs that come with specific packages and settings.}, language = {en} } @article{KontouWalterAlkaetal.2023, author = {Kontou, Eftychia E. and Walter, Axel and Alka, Oliver and Pfeuffer, Julianus and Sachsenberg, Timo and Mohite, Omkar and Nuhamunanda, Matin and Kohlbacher, Oliver and Weber, Tilmann}, title = {UmetaFlow: An untargeted metabolomics workflow for high-throughput data processing and analysis}, volume = {15}, journal = {Journal of Cheminformatics}, doi = {10.1186/s13321-023-00724-w}, year = {2023}, abstract = {Metabolomics experiments generate highly complex datasets, which are time and work-intensive, sometimes even error-prone if inspected manually. Therefore, new methods for automated, fast, reproducible, and accurate data processing and dereplication are required. Here, we present UmetaFlow, a computational workflow for untargeted metabolomics that combines algorithms for data pre-processing, spectral matching, molecular formula and structural predictions, and an integration to the GNPS workflows Feature-Based Molecular Networking and Ion Identity Molecular Networking for downstream analysis. UmetaFlow is implemented as a Snakemake workflow, making it easy to use, scalable, and reproducible. For more interactive computing, visualization, as well as development, the workflow is also implemented in Jupyter notebooks using the Python programming language and a set of Python bindings to the OpenMS algorithms (pyOpenMS). Finally, UmetaFlow is also offered as a web-based Graphical User Interface for parameter optimization and processing of smaller-sized datasets. UmetaFlow was validated with in-house LC-MS/MS datasets of actinomycetes producing known secondary metabolites, as well as commercial standards, and it detected all expected features and accurately annotated 76\% of the molecular formulas and 65\% of the structures. As a more generic validation, the publicly available MTBLS733 and MTBLS736 datasets were used for benchmarking, and UmetaFlow detected more than 90\% of all ground truth features and performed exceptionally well in quantification and discriminating marker selection.}, 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} } @phdthesis{Pfeuffer2023, author = {Pfeuffer, Julianus}, title = {Computational Methods for Protein Inference in Shotgun Proteomics Experiments}, year = {2023}, abstract = {Since the beginning of this millennium, the advent of high-throughput methods in numerous fields of the life sciences led to a shift in paradigms. A broad variety of technologies emerged that allow comprehensive quantification of molecules involved in biological processes. Simultaneously, a major increase in data volume has been recorded with these techniques through enhanced instrumentation and other technical advances. By supplying computational methods that automatically process raw data to obtain biological information, the field of bioinformatics plays an increasingly important role in the analysis of the ever-growing mass of data. Computational mass spectrometry in particular, is a bioinformatics field of research which provides means to gather, analyze and visualize data from high-throughput mass spectrometric experiments. For the study of the entirety of proteins in a cell or an environmental sample, even current techniques reach limitations that need to be circumvented by simplifying the samples subjected to the mass spectrometer. These pre-digested (so-called bottom-up) proteomics experiments then pose an even bigger computational burden during analysis since complex ambiguities need to be resolved during protein inference, grouping and quantification. In this thesis, we present several developments in the pursuit of our goal to provide means for a fully automated analysis of complex and large-scale bottom-up proteomics experiments. Firstly, due to prohibitive computational complexities in state-of-the-art Bayesian protein inference techniques, a refined, more stable technique for performing inference on sums of random variables was developed to enable a variation of standard Bayesian inference for the problem. nextflow and part of a set of standardized, well-tested, and community-maintained workflows by the nf-core collective. Our workflow runs on large-scale data with complex experimental designs and allows a one-command analysis of local and publicly available data sets with state-of-the-art accuracy on various high-performance computing environments or the cloud.}, language = {en} } @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} } @article{BartoliSengupta2025, author = {Bartoli, Adrien and Sengupta, Agniva}, title = {Camera Pose in SfT and NRSfM under Isometric and Weaker Deformation Models}, volume = {261}, journal = {Computer Vision and Image Understanding}, doi = {10.1016/j.cviu.2025.104488}, year = {2025}, abstract = {Camera pose is a very natural concept in 3D vision in the rigid setting. It is however much more difficult to work with in deformable settings. Consequently, numerous deformable reconstruction methods simply ignore camera pose. We analyse the concept of pose in deformable settings and prove that it is unconstrained with the existing formulations, properly justifying the existing pose-less methods reconstructing structure only. We explain this result intuitively by the impossibility to define an intrinsic coordinate frame to a general deforming object. The proposed analysis uses the isometric deformation model and extends to the weaker models including conformality and equiareality. We propose a novel prior to rescue camera pose estimation in deformable settings, which attributes the deforming object's dominant rigid-body motion to the camera. We show that adding this prior to any existing formulation fully constrains camera pose and leads to elegant two-step solution methods, involving deformable structure reconstruction using a base method in the first step, and absolute orientation or Procrustes analysis in the second step. We derive the proposed approach for the template-based and template-less settings, respectively implemented using Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) as base methods, and validate them experimentally, showing that the computed pose is qualitatively and quantitatively plausible.}, language = {en} } @phdthesis{Amiranashvili2025, author = {Amiranashvili, Tamaz}, title = {Universal and Expressive Statistical Shape Models for Anatomical Structures}, school = {Technische Universit{\"a}t M{\"u}nchen}, pages = {86}, year = {2025}, abstract = {Form and function of anatomical structures are intimately linked. Pathological changes in form can be associated with the loss of function. For example, diseases often cause characteristic shape changes, making shape a sensitive structural biomarker for medical diagnosis. If the link between form and function is causal, correcting a pathological shape can even restore the healthy function of an organ. Accurate shape reconstruction is then crucial for effective, patient-specific treatment planning. This demonstrates the importance of shape in clinical interventions and its potential to improve overall patient outcomes. Statistical shape models are computational methods that capture shape variations in a given population and enable precise shape analysis and generation. We focus on two key properties of a good statistical shape model. First, it should be easy to construct, and second, it should accurately represent the underlying shape distribution. Established existing approaches can only be constructed from surfaces with pre-defined dense correspondence. Such correspondence is tedious to obtain, can introduce undesired biases, and prevents training on partial or sparse observations. While correspondence-free methods exist, they struggle to accurately capture shape distributions with intricate details and large variations. In this thesis, we develop shape models that simplify training and improve accuracy over state-of-the-art. To achieve these goals, we build on approximately diffeomorphic neural deformations and implicit neural representations. First, our proposed methods are trainable on correspondence-free surfaces and even partial segmentations with large slice distances. This makes them universal since they can be trained on heterogeneous data, enabling scalability to large datasets and avoiding potential biases of pre-defined correspondence. Second, our methods are highly expressive, accurately capturing intricate shape details in complex distributions. We evaluate effectiveness of our models on multiple anatomical structures, outperforming established baselines in both generative and discriminative settings.}, language = {en} } @article{XieGruberCrampenetal.2025, author = {Xie, Kunpeng and Gruber, Lennart Johannes and Crampen, Martin and Li, Yao and Ferreira, Andr{\´e} and Tappeiner, Elias and Gillot, Maxime and Schepers, Jan and Xu, Jiangchang and Pankert, Tobias and Beyer, Michel and Shahamiri, Negar and ten Brink, Reinier and Dot, Gauthier and Weschke, Charlotte and van Nistelrooij, Niels and Verhelst, Pieter-Jan and Guo, Yan and Xu, Zhibin and Bienzeisler, Jonas and Rashad, Ashkan and Fl{\"u}gge, Tabea and Cotton, Ross and Vinayahalingam, Shankeeth and Ilesan, Robert and Raith, Stefan and Madsen, Dennis and Seibold, Constantin and Xi, Tong and Berg{\´e}, Stefaan and Nebelung, Sven and Kodym, Oldřich and Sundqvist, Osku and Thieringer, Florian and Lamecker, Hans and Coppens, Antoine and Potrusil, Thomas and Kraeima, Joep and Witjes, Max and Wu, Guomin and Chen, Xiaojun and Lambrechts, Adriaan and Cevidanes, Lucia H Soares and Zachow, Stefan and Hermans, Alexander and Truhn, Daniel and Alves, Victor and Egger, Jan and R{\"o}hrig, Rainer and H{\"o}lzle, Frank and Puladi, Behrus}, title = {Beyond Benchmarks: Towards Robust Artificial Intelligence Bone Segmentation in Socio-Technical Systems}, volume = {299}, journal = {Expert Systems With Applications}, number = {Part D}, doi = {10.1016/j.eswa.2025.130031}, year = {2025}, abstract = {Despite the advances in automated medical image segmentation, AI models still underperform in various clinical settings, challenging real-world integration. In this multicenter evaluation, we analyzed 20 state-of-the-art mandibular segmentation models across 19,218 segmentations of 1,000 clinically resampled CT/CBCT scans. We show that segmentation accuracy varies by up to 25\% depending on socio-technical factors such as voxel size, bone orientation, and patient conditions such as osteosynthesis or pathology. Higher sharpness, isotropic smaller voxels, and neutral orientation significantly improved results, while metallic osteosynthesis and anatomical complexity led to significant degradation. Our findings challenge the common view of AI models as "plug-and-play" tools and suggest evidence-based optimization recommendations for both clinicians and developers. This will in turn boost the integration of AI segmentation tools in routine healthcare.}, language = {en} } @article{SekuboyinaHusseiniBayatetal.2021, author = {Sekuboyina, Anjany and Husseini, Malek E. and Bayat, Amirhossein and L{\"o}ffler, Maximilian and Liebl, Hans and Li, Hongwei and Tetteh, Giles and Kukačka, Jan and Payer, Christian and Štern, Darko and Urschler, Martin and Chen, Maodong and Cheng, Dalong and Lessmann, Nikolas and Hu, Yujin and Wang, Tianfu and Yang, Dong and Xu, Daguang and Ambellan, Felix and Amiranashvili, Tamaz and Ehlke, Moritz and Lamecker, Hans and Lehnert, Sebastian and Lirio, Marilia and de Olaguer, Nicol{\´a}s P{\´e}rez and Ramm, Heiko and Sahu, Manish and Tack, Alexander and Zachow, Stefan and Jiang, Tao and Ma, Xinjun and Angerman, Christoph and Wang, Xin and Brown, Kevin and Kirszenberg, Alexandre and Puybareau, {\´E}lodie and Chen, Di and Bai, Yiwei and Rapazzo, Brandon H. and Yeah, Timyoas and Zhang, Amber and Xu, Shangliang and Hou, Feng and He, Zhiqiang and Zeng, Chan and Xiangshang, Zheng and Liming, Xu and Netherton, Tucker J. and Mumme, Raymond P. and Court, Laurence E. and Huang, Zixun and He, Chenhang and Wang, Li-Wen and Ling, Sai Ho and Huynh, L{\^e} Duy and Boutry, Nicolas and Jakubicek, Roman and Chmelik, Jiri and Mulay, Supriti and Sivaprakasam, Mohanasankar and Paetzold, Johannes C. and Shit, Suprosanna and Ezhov, Ivan and Wiestler, Benedikt and Glocker, Ben and Valentinitsch, Alexander and Rempfler, Markus and Menze, Bj{\"o}rn H. and Kirschke, Jan S.}, title = {VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images}, volume = {73}, journal = {Medical Image Analysis}, doi = {10.1016/j.media.2021.102166}, year = {2021}, abstract = {Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.}, language = {en} } @misc{Punjabi2021, type = {Master Thesis}, author = {Punjabi, Dev}, title = {Orientation-invariant Dense Correspondence using Graph Convolutional Neural Networks}, pages = {41}, year = {2021}, 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} } @misc{Şirin2023, type = {Master Thesis}, author = {Şirin, Ege}, title = {Probabilistic Image Segmentation With Continuous Shape Representations}, year = {2023}, language = {en} } @article{SeckerFackeldeyWeberetal.2023, author = {Secker, Christopher and Fackeldey, Konstantin and Weber, Marcus and Ray, Sourav and Gorgulla, Christoph and Sch{\"u}tte, Christof}, title = {Novel multi-objective affinity approach allows to identify pH-specific μ-opioid receptor agonists}, volume = {15}, journal = {Journal of Cheminformatics}, doi = {10.1186/s13321-023-00746-4}, year = {2023}, abstract = {Opioids are essential pharmaceuticals due to their analgesic properties, however, lethal side effects, addiction, and opioid tolerance are extremely challenging. The development of novel molecules targeting the μ-opioid receptor (MOR) in inflamed, but not in healthy tissue, could significantly reduce these unwanted effects. Finding such novel molecules can be achieved by maximizing the binding affinity to the MOR at acidic pH while minimizing it at neutral pH, thus combining two conflicting objectives. Here, this multi-objective optimal affinity approach is presented, together with a virtual drug discovery pipeline for its practical implementation. When applied to finding pH-specific drug candidates, it combines protonation state-dependent structure and ligand preparation with high-throughput virtual screening. We employ this pipeline to characterize a set of MOR agonists identifying a morphine-like opioid derivative with higher predicted binding affinities to the MOR at low pH compared to neutral pH. Our results also confirm existing experimental evidence that NFEPP, a previously described fentanyl derivative with reduced side effects, and recently reported β-fluorofentanyls and -morphines show an increased specificity for the MOR at acidic pH when compared to fentanyl and morphine. We further applied our approach to screen a >50K ligand library identifying novel molecules with pH-specific predicted binding affinities to the MOR. The presented differential docking pipeline can be applied to perform multi-objective affinity optimization to identify safer and more specific drug candidates at large scale.}, language = {en} } @article{GelssKlusSchusteretal.2021, author = {Gelss, Patrick and Klus, Stefan and Schuster, Ingmar and Sch{\"u}tte, Christof}, title = {Feature space approximation for kernel-based supervised learning}, volume = {221}, journal = {Knowledge-Based Sytems}, publisher = {Elsevier}, doi = {https://doi.org/10.1016/j.knosys.2021.106935}, year = {2021}, 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} }