@article{ThiesSunkaraRayetal.2023, author = {Thies, Arne and Sunkara, Vikram and Ray, Sourav and Wulkow, Hanna and Celik, M. {\"O}zg{\"u}r and Yerg{\"o}z, Fatih and Sch{\"u}tte, Christof and Stein, Christoph and Weber, Marcus and Winkelmann, Stefanie}, title = {Modelling altered signalling of G-protein coupled receptors in inflamed environment to advance drug design}, volume = {13}, journal = {Scientific Reports}, number = {607}, doi = {10.1038/s41598-023-27699-w}, year = {2023}, abstract = {We previously reported the successful design, synthesis and testing of the prototype opioid painkiller NFEPP that does not elicit adverse side effects. The design process of NFEPP was based on mathematical modelling of extracellular interactions between G-protein coupled receptors (GPCRs) and ligands, recognizing that GPCRs function differently under pathological versus healthy conditions. We now present an additional and novel stochastic model of GPCR function that includes intracellular dissociation of G-protein subunits and modulation of plasma membrane calcium channels and their dependence on parameters of inflamed and healthy tissue (pH, radicals). The model is validated against in vitro experimental data for the ligands NFEPP and fentanyl at different pH values and radical concentrations. We observe markedly reduced binding affinity and calcium channel inhibition for NFEPP at normal pH compared to lower pH, in contrast to the effect of fentanyl. For increasing radical concentrations, we find enhanced constitutive G-protein activation but reduced ligand binding affinity. Assessing the different effects, the results suggest that, compared to radicals, low pH is a more important determinant of overall GPCR function in an inflamed environment. Future drug design efforts should take this into account.}, language = {en} } @misc{RayThiesSunkaraetal.2021, author = {Ray, Sourav and Thies, Arne and Sunkara, Vikram and Wulkow, Hanna and Celik, {\"O}zg{\"u}r and Yerg{\"o}z, Fatih and Sch{\"u}tte, Christof and Stein, Christoph and Weber, Marcus and Winkelmann, Stefanie}, title = {Modelling altered signalling of G-protein coupled receptors in inflamed environment to advance drug design}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-82797}, year = {2021}, abstract = {Initiated by mathematical modelling of extracellular interactions between G-protein coupled receptors (GPCRs) and ligands in normal versus diseased (inflamed) environments, we previously reported the successful design, synthesis and testing of the prototype opioid painkiller NFEPP that does not elicit adverse side effects. Uniquely, this design recognised that GPCRs function differently under pathological versus healthy conditions. We now present a novel stochastic model of GPCR function that includes intracellular dissociation of G-protein subunits and modulation of plasma membrane calcium channels associated with parameters of inflamed tissue (pH, radicals). By means of molecular dynamics simulations, we also assessed qualitative changes of the reaction rates due to additional disulfide bridges inside the GPCR binding pocket and used these rates for stochastic simulations of the corresponding reaction jump process. The modelling results were validated with in vitro experiments measuring calcium currents and G-protein activation. We found markedly reduced G-protein dissociation and calcium channel inhibition induced by NFEPP at normal pH, and enhanced constitutive G-protein activation but lower probability of ligand binding with increasing radical concentrations. These results suggest that, compared to radicals, low pH is a more important determinant of overall GPCR function in an inflamed environment. Future drug design efforts should take this into account.}, 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{BirkRaharinirinaFackeldeyetal.2021, author = {Birk, Ralph and Raharinirina, N. Alexia and Fackeldey, Konstantin and Richter, Tonio Sebastian and Weber, Marcus}, title = {Inferring cultural and social processes based on patterns of statistical relationships between Synodal texts}, year = {2021}, abstract = {In this paper, we explore the relationship patterns between Ancient Egyptian texts of the corpus ``Synodal decrees'', which are originating between 243 and 185 BCE, during the Ptolemaic period. Particularly, we are interested in analyzing the grammatical features of the different texts. Conventional data analysis methods such as correspondence Analysis are very useful to explore the patterns of statistical interdependence between categories of variables. However, it is based on a PCA-like dimension-reduction method and turned out to be unsuitable for our dataset due to the high dimensionality of our data representations. Additionally, the similarity between pairs of texts and pairs of grammatical features is observed through the distance between their representation, but the degree of association between a particular grammatical feature and a text is not. Here, we applied a qualitative Euclidean embedding method that provides a new Euclidean representation of the categories of variables. This new representation of the categories is constructed in such a way that all the patterns of statistical interdependence, similarity, and association, are seen through the Euclidean distance between them. Nevertheless, the PCA-like dimension-reduction method also performed poorly on our new representation. Therefore, we obtained a two-dimensional visualization using non-linear methods such UMAP or t-SNE. Although these dimension-reduction methods reduced the interpretability of interpoint distances, we were still able to identify important similarity patterns between the Synodal text as well as their association patterns with the grammatical features.}, language = {en} } @article{RaharinirinaSunkaravonKleistetal.2024, author = {Raharinirina, Nomenjanahary Alexia and Sunkara, Vikram and von Kleist, Max and Fackeldey, Konstantin and Weber, Marcus}, title = {Multi-Input data ASsembly for joint Analysis (MIASA): A framework for the joint analysis of disjoint sets of variables}, volume = {19}, journal = {PLOS ONE}, number = {5}, publisher = {Public Library of Science}, doi = {10.1371/journal.pone.0302425}, pages = {26}, year = {2024}, language = {en} } @article{VuHanSchettinoWeissetal.2024, author = {Vu-Han, Tu-Lan and Schettino, Rodrigo Bermudez and Weiß, Claudia and Perka, Carsten and Winkler, Tobias and Sunkara, Vikram and Pumberger, Matthias}, title = {An interpretable data-driven prediction model to anticipate scoliosis in spinal muscular atrophy in the era of (gene-) therapies}, volume = {14}, journal = {Scientific Reports}, number = {11838}, doi = {10.1038/s41598-024-62720-w}, year = {2024}, abstract = {5q-spinal muscular atrophy (SMA) is a neuromuscular disorder (NMD) that has become one of the first 5\% treatable rare diseases. The efficacy of new SMA therapies is creating a dynamic SMA patient landscape, where disease progression and scoliosis development play a central role, however, remain difficult to anticipate. New approaches to anticipate disease progression and associated sequelae will be needed to continuously provide these patients the best standard of care. Here we developed an interpretable machine learning (ML) model that can function as an assistive tool in the anticipation of SMA-associated scoliosis based on disease progression markers. We collected longitudinal data from 86 genetically confirmed SMA patients. We selected six features routinely assessed over time to train a random forest classifier. The model achieved a mean accuracy of 0.77 (SD 0.2) and an average ROC AUC of 0.85 (SD 0.17). For class 1 'scoliosis' the average precision was 0.84 (SD 0.11), recall 0.89 (SD 0.22), F1-score of 0.85 (SD 0.17), respectively. Our trained model could predict scoliosis using selected disease progression markers and was consistent with the radiological measurements. During post validation, the model could predict scoliosis in patients who were unseen during training. We also demonstrate that rare disease data sets can be wrangled to build predictive ML models. Interpretable ML models can function as assistive tools in a changing disease landscape and have the potential to democratize expertise that is otherwise clustered at specialized centers.}, language = {en} } @article{KostreDjurdjevacConradSchuetteetal.2024, author = {Kostr{\´e}, Margarita and Djurdjevac Conrad, Natasa and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {Exploration of Particle Swarm Optimisation Algorithm with Divergent Parameters}, journal = {Natural Computing}, year = {2024}, language = {en} } @article{Vu‐HanSunkaraBermudez‐Schettinoetal.2025, author = {Vu-Han, Tu-Lan and Sunkara, Vikram and Bermudez-Schettino, Rodrigo and Schwechten, Jakob and Runge, Robin and Perka, Carsten and Winkler, Tobias and Pokutta, Sebastian and Weiß, Claudia and Pumberger, Matthias}, title = {Feature Engineering for the Prediction of Scoliosis in 5q-Spinal Muscular Atrophy}, volume = {16}, journal = {Journal of Cachexia, Sarcopenia and Muscle}, number = {1}, doi = {10.1002/jcsm.13599}, pages = {e13599}, year = {2025}, language = {en} } @article{RegenyiMashreghiSchuetteetal.2024, author = {Reg{\´e}nyi, Enikő and Mashreghi, Mir-Farzin and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {Exploring transcription modalities from bimodal, single-cell RNA sequencing data}, volume = {6}, journal = {NAR Genomics and Bioinformatics}, number = {4}, publisher = {Oxford University Press (OUP)}, issn = {2631-9268}, doi = {10.1093/nargab/lqae179}, year = {2024}, abstract = {Abstract There is a growing interest in generating bimodal, single-cell RNA sequencing (RNA-seq) data for studying biological pathways. These data are predominantly utilized in understanding phenotypic trajectories using RNA velocities; however, the shape information encoded in the two-dimensional resolution of such data is not yet exploited. In this paper, we present an elliptical parametrization of two-dimensional RNA-seq data, from which we derived statistics that reveal four different modalities. These modalities can be interpreted as manifestations of the changes in the rates of splicing, transcription or degradation. We performed our analysis on a cell cycle and a colorectal cancer dataset. In both datasets, we found genes that are not picked up by differential gene expression analysis (DGEA), and are consequently unnoticed, yet visibly delineate phenotypes. This indicates that, in addition to DGEA, searching for genes that exhibit the discovered modalities could aid recovering genes that set phenotypes apart. For communities studying biomarkers and cellular phenotyping, the modalities present in bimodal RNA-seq data broaden the search space of genes, and furthermore, allow for incorporating cellular RNA processing into regulatory analyses.}, language = {en} } @inproceedings{ChaukairSchuetteSunkara2023, author = {Chaukair, Mustafa and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {On the Activation Space of ReLU Equipped Deep Neural Networks}, volume = {222}, booktitle = {Procedia Computer Science}, doi = {10.1016/j.procs.2023.08.200}, pages = {624 -- 635}, year = {2023}, abstract = {Modern Deep Neural Networks are getting wider and deeper in their architecture design. However, with an increasing number of parameters the decision mechanisms becomes more opaque. Therefore, there is a need for understanding the structures arising in the hidden layers of deep neural networks. In this work, we present a new mathematical framework for describing the canonical polyhedral decomposition in the input space, and in addition, we introduce the notions of collapsing- and preserving patches, pertinent to understanding the forward map and the activation space they induce. The activation space can be seen as the output of a layer and, in the particular case of ReLU activations, we prove that this output has the structure of a polyhedral complex.}, language = {en} } @article{CoomberChewleSeckeretal.2025, author = {Coomber, Celvic and Chewle, Surahit and Secker, Christopher and Fackeldey, Konstantin and Weber, Marcus and Winkelmann, Stefanie and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {Investigating Endogenous Opioids Unravels the Mechanisms Behind Opioid-Induced Constipation, a Mathematical Modeling Approach}, volume = {26}, journal = {International Journal of Molecular Sciences}, number = {13}, doi = {10.3390/ijms26136207}, year = {2025}, abstract = {Endogenous opioids, such as Endomorphin-2, are not typically associated with severe constipation, unlike pharmaceutical opioids, which induce opioid-induced constipation (OIC) by activating μ-opioid receptors in the gastrointestinal tract. In this study, we present a mathematical model, which integrates the serotonergic and opioid pathways, simulating the interaction between serotonin and opioid signaling within the enteric nervous system (ENS). The model explores the mechanisms underlying OIC, with a focus on the change in adenylyl cyclase (AC) activity, cAMP accumulation, and the distinct functionalities of Endomorphin-2 compared to commonly used pharmaceutical opioids. We study the effects of Morphine, Fentanyl, and Methadone and contrast them with Endomorphin-2. Our findings reveal that opioids do not perturb the signaling of serotonin, but only the activity of AC, suggesting that serotonin levels have no influence on improving opioid-induced constipation. Furthermore, this study reveals that the primary difference between endogenous and pharmaceutical opioids is their degradation rates. This finding shows that modulating opioid degradation rates significantly improves cAMP recovery. In conclusion, our insights steer towards exploring opioid degrading enzymes, localized to the gut, as a strategy for mitigating OIC.}, language = {en} } @article{RaharinirinaPeppertvonKleistetal.2021, author = {Raharinirina, Alexia N. and Peppert, Felix and von Kleist, Max and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {Inferring gene regulatory networks from single-cell RNA-seq temporal snapshot data requires higher-order moments}, volume = {2}, journal = {Patterns}, number = {9}, doi = {10.1016/j.patter.2021.100332}, year = {2021}, abstract = {Single-cell RNA sequencing (scRNA-seq) has become ubiquitous in biology. Recently, there has been a push for using scRNA-seq snapshot data to infer the underlying gene regulatory networks (GRNs) steering cellular function. To date, this aspiration remains unrealized due to technical and computational challenges. In this work we focus on the latter, which is under-represented in the literature. We took a systemic approach by subdividing the GRN inference into three fundamental components: data pre-processing, feature extraction, and inference. We observed that the regulatory signature is captured in the statistical moments of scRNA-seq data and requires computationally intensive minimization solvers to extract it. Furthermore, current data pre-processing might not conserve these statistical moments. Although our moment-based approach is a didactic tool for understanding the different compartments of GRN inference, this line of thinking—finding computationally feasible multi-dimensional statistics of data—is imperative for designing GRN inference methods.}, language = {en} } @article{SunkaraHeinzHeinrichetal.2021, author = {Sunkara, Vikram and Heinz, Gitta A. and Heinrich, Frederik F. and Durek, Pawel and Mobasheri, Ali and Mashreghi, Mir-Farzin and Lang, Annemarie}, title = {Combining segmental bulk- and single-cell RNA-sequencing to define the chondrocyte gene expression signature in the murine knee joint}, volume = {29}, journal = {Osteoarthritis and Cartilage}, number = {6}, doi = {10.1016/j.joca.2021.03.007}, pages = {905 -- 914}, year = {2021}, language = {en} } @article{SunkaraHeinzHeinrichetal.2020, author = {Sunkara, Vikram and Heinz, Gitta A. and Heinrich, Frederik F. and Durek, Pawel and Mobasheri, Ali and Mashreghi, Mir-Farzin and Lang, Annemarie}, title = {Combining segmental bulk- and single-cell RNA-sequencing to define the chondrocyte gene expression signature in the murine knee joint}, journal = {bioarxiv (Accepted in Osteoarthr. Cartil.)}, doi = {10.1101/2020.06.13.148056}, year = {2020}, language = {en} } @article{LangHelfmeierStefanowskietal.2020, author = {Lang, Annemarie and Helfmeier, Sarah and Stefanowski, Jonathan and Kuppe, Aditi and Sunkara, Vikram and Pfeiffenberger, Moritz and Wolter, Angelique and Damerau, Alexandra and Hemmati-Sadeghi, Shabnam and Ringe, Jochen and Haag, Rainer and Hauser, Anja E. and L{\"o}hning, Max and Perka, Carsten and Duda, Georg and Hoff, Paula and Schmidt-Bleek, Katharina and Gaber, Timo and Buttgereit, Frank}, title = {HIF-stabilization prevents delayed fracture healing}, journal = {bioarxiv}, doi = {10.1101/2020.07.02.182832}, year = {2020}, language = {en} } @article{LaydonSunkaraBoelenetal.2020, author = {Laydon, Daniel J. and Sunkara, Vikram and Boelen, Lies and Bangham, Charles R. M. and Asquith, Becca}, title = {The relative contributions of infectious and mitotic spread to HTLV-1 persistence}, journal = {PLOS Computational Biology}, doi = {10.1371/journal.pcbi.1007470}, year = {2020}, language = {en} } @article{SunkaraLewisNguyenetal.2022, author = {Sunkara, Vikram and Lewis, Angus and Nguyen, Giang T. and O'Reilly, Malgorzata M. and Bean, Nigel}, title = {A discontinuous Galerkin method for approximating the stationary distribution of stochastic fluid-fluid processes}, journal = {Methodology and Computing in Applied Probability}, doi = {10.1007/s11009-022-09945-2}, year = {2022}, language = {en} } @article{LangVesterFerreiraGomesetal.2022, author = {Lang, Annemarie and Vester, Antja and Ferreira-Gomes, M. and Guerra, G.M. and Heinrich, Fredrich R. and G{\"o}tzke, C.C. and Kurmies, Sebastian and Sunkara, Vikram and Durek, Pawel and Boerckel, Joel D. and Mashreghi, Mir-Farzin}, title = {PIPELINE FOR SINGLE CELL SEQUENCING OF HUMAN CHONDROCYTE PELLET CULTURES TO DELINEATE IL-1β MODULATED CHANGES IN CELL HETEROGENEITY}, volume = {30}, journal = {Osteoarthritis and Cartilage}, number = {Supplement 1}, doi = {10.1016/j.joca.2022.02.112}, pages = {S90}, year = {2022}, language = {en} } @article{SchulzePeppertSchuetteetal.2025, author = {Schulze, Kenrick and Peppert, Felix and Sch{\"u}tte, Christof and Sunkara, Vikram}, title = {Chimeric U-Net - Modifying the standard U-Net towards Explainability}, volume = {338}, journal = {Artificial Intelligence}, doi = {10.1016/j.artint.2024.104240}, year = {2025}, abstract = {Healthcare guided by semantic segmentation has the potential to improve our quality of life through early and accurate disease detection. Convolutional Neural Networks, especially the U-Net-based architectures, are currently the state-of-the-art learning-based segmentation methods and have given unprecedented performances. However, their decision-making processes are still an active field of research. In order to reliably utilize such methods in healthcare, explainability of how the segmentation was performed is mandated. To date, explainability is studied and applied heavily in classification tasks. In this work, we propose the Chimeric U-Net, a U-Net architecture with an invertible decoder unit, that inherently brings explainability into semantic segmentation tasks. We find that having the restriction of an invertible decoder does not hinder the performance of the segmentation task. However, the invertible decoder helps to disentangle the class information in the latent space embedding and to construct meaningful saliency maps. Furthermore, we found that with a simple k-Nearest-Neighbours classifier, we could predict the Intersection over Union scores of unseen data, demonstrating that the latent space, constructed by the Chimeric U-Net , encodes an interpretable representation of the segmentation quality. Explainability is an emerging field, and in this work, we propose an alternative approach, that is, rather than building tools for explaining a generic architecture, we propose constraints on the architecture which induce explainability. With this approach, we could peer into the architecture to reveal its class correlations and local contextual dependencies, taking an insightful step towards trustworthy and reliable AI. Code to build and utilize the Chimeric U-Net is made available under: https://github.com/kenrickschulze/Chimeric-UNet---Half-invertible-UNet-in-Pytorch}, language = {en} } @article{KostreSunkaraSchuetteetal.2022, author = {Kostr{\´e}, Margarita and Sunkara, Vikram and Sch{\"u}tte, Christof and Djurdjevac Conrad, Natasa}, title = {Understanding the Romanization Spreading on Historical Interregional Networks in Northern Tunisia}, volume = {7}, journal = {Applied Network Science}, publisher = {Springer Nature}, doi = {10.1007/s41109-022-00492-w}, pages = {18}, year = {2022}, abstract = {Spreading processes are important drivers of change in social systems. To understand the mechanisms of spreading it is fundamental to have information about the underlying contact network and the dynamical parameters of the process. However, in many real-wold examples, this information is not known and needs to be inferred from data. State-of-the-art spreading inference methods have mostly been applied to modern social systems, as they rely on availability of very detailed data. In this paper we study the inference challenges for historical spreading processes, for which only very fragmented information is available. To cope with this problem, we extend existing network models by formulating a model on a mesoscale with temporal spreading rate. Furthermore, we formulate the respective parameter inference problem for the extended model. We apply our approach to the romanization process of Northern Tunisia, a scarce dataset, and study properties of the inferred time-evolving interregional networks. As a result, we show that (1) optimal solutions consist of very different network structures and spreading rate functions; and that (2) these diverse solutions produce very similar spreading patterns. Finally, we discuss how inferred dominant interregional connections are related to available archaeological traces. Historical networks resulting from our approach can help understanding complex processes of cultural change in ancient times.}, language = {en} } @inproceedings{KostreSunkaraDjurdjevacConrad2021, author = {Kostre, Margarita and Sunkara, Vikram and Djurdjevac Conrad, Natasa}, title = {Inference of historical influence networks}, booktitle = {International Conference on Complex Networks \& Their Applications Proceedings}, edition = {International Conference on Complex Networks \& Their Applications}, doi = {10.12752/8558}, pages = {110 -- 113}, year = {2021}, abstract = {We study the romanization process of northern Africa from 50 BC till 300 AD. Our goal is to infer the communication strength between different subregions, based on the evolution of the status of cities. Herefore, we use the general inverse infection model, that infers the weights of a known underlying network, given observations of the spreading on this network. As infection process we choose the SI metapopulation model, where I stands for a city with a Roman status. To solve the minimization problem we use the particle swarm optimization algorithm with a specific choice of parameters.}, language = {de} } @misc{KostreSunkaraSchuetteetal.2022, author = {Kostr{\´e}, Margarita and Sunkara, Vikram and Sch{\"u}tte, Christof and Djurdjevac Conrad, Nataša}, title = {Understanding the Romanization Spreading on Historical Interregional Networks in Northern Tunisia}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-86764}, year = {2022}, abstract = {Spreading processes are important drivers of change in social systems. To understand the mechanisms of spreading it is fundamental to have information about the underlying contact network and the dynamical parameters of the process. However, in many real-wold examples, this information is not known and needs to be inferred from data. State-of-the-art spreading inference methods have mostly been applied to modern social systems, as they rely on availability of very detailed data. In this paper we study the inference challenges for historical spreading processes, for which only very fragmented information is available. To cope with this problem, we extend existing network models by formulating a model on a mesoscale with temporal spreading rate. Furthermore, we formulate the respective parameter inference problem for the extended model. We apply our approach to the romanization process of Northern Tunisia, a scarce dataset, and study properties of the inferred time-evolving interregional networks. As a result, we show that (1) optimal solutions consist of very different network structures and spreading rate functions; and that (2) these diverse solutions produce very similar spreading patterns. Finally, we discuss how inferred dominant interregional connections are related to available archaeological traces. Historical networks resulting from our approach can help understanding complex processes of cultural change in ancient times.}, language = {en} } @article{HajarolasvadiSunkaraKhavnekaretal.2022, author = {Hajarolasvadi, Noushin and Sunkara, Vikram and Khavnekar, Sagar and Beck, Florian and Brandt, Robert and Baum, Daniel}, title = {Volumetric macromolecule identification in cryo-electron tomograms using capsule networks}, volume = {23}, journal = {BMC Bioinformatics}, number = {360}, doi = {10.1186/s12859-022-04901-w}, year = {2022}, abstract = {Background: Despite recent advances in cellular cryo-electron tomography (CET), developing automated tools for macromolecule identification in submolecular resolution remains challenging due to the lack of annotated data and high structural complexities. To date, the extent of the deep learning methods constructed for this problem is limited to conventional Convolutional Neural Networks (CNNs). Identifying macromolecules of different types and sizes is a tedious and time-consuming task. In this paper, we employ a capsule-based architecture to automate the task of macro- molecule identification, that we refer to as 3D-UCaps. In particular, the architecture is composed of three components: feature extractor, capsule encoder, and CNN decoder. The feature extractor converts voxel intensities of input sub-tomograms to activities of local features. The encoder is a 3D Capsule Network (CapsNet) that takes local features to generate a low-dimensional representation of the input. Then, a 3D CNN decoder reconstructs the sub-tomograms from the given representation by upsampling. Results: We performed binary and multi-class localization and identification tasks on synthetic and experimental data. We observed that the 3D-UNet and the 3D-UCaps had an F1-score mostly above 60\% and 70\%, respectively, on the test data. In both network architectures, we observed degradation of at least 40\% in the F1-score when identifying very small particles (PDB entry 3GL1) compared to a large particle (PDB entry 4D8Q). In the multi-class identification task of experimental data, 3D-UCaps had an F1-score of 91\% on the test data in contrast to 64\% of the 3D-UNet. The better F1-score of 3D-UCaps compared to 3D-UNet is obtained by a higher precision score. We speculate this to be due to the capsule network employed in the encoder. To study the effect of the CapsNet-based encoder architecture further, we performed an ablation study and perceived that the F1-score is boosted as network depth is increased which is in contrast to the previously reported results for the 3D-UNet. To present a reproducible work, source code, trained models, data as well as visualization results are made publicly available. Conclusion: Quantitative and qualitative results show that 3D-UCaps successfully perform various downstream tasks including identification and localization of macro- molecules and can at least compete with CNN architectures for this task. Given that the capsule layers extract both the existence probability and the orientation of the molecules, this architecture has the potential to lead to representations of the data that are better interpretable than those of 3D-UNet.}, language = {en} } @article{KresseSikorskiChewleetal.2026, author = {Kresse, Jakob and Sikorski, Alexander and Chewle, Surahit and Sunkara, Vikram and Weber, Marcus}, title = {Revealing the Atomistic Mechanism of Rare Events in Molecular Dynamics}, volume = {22}, journal = {Journal of Chemical Theory and Computation}, number = {5}, arxiv = {http://arxiv.org/abs/2511.15514}, doi = {10.1021/acs.jctc.5c01906}, pages = {2380 -- 2389}, year = {2026}, abstract = {Interpretable reaction coordinates are essential for understanding rare conformational transitions in molecular dynamics. The Atomistic Mechanism Of Rare Events in Molecular Dynamics (AMORE-MD) framework enhances interpretability of deep-learned reaction coordinates by connecting them to atomistic mechanisms, without requiring any a priori knowledge of collective variables, pathways, or endpoints. Here, AMORE-MD employs the ISOKANN algorithm to learn a neural membership function χ representing the dominant slow process, from which transition pathways are reconstructed as minimum-energy paths aligned with the gradient of χ, and atomic contributions are quantified through gradient-based sensitivity analysis. Iterative enhanced sampling further enriches transition regions and improves coverage of rare events enabling recovery of known mechanisms and chemically interpretable structural rearrangements at atomic resolution for the M{\"u}ller-Brown potential, alanine dipeptide, and the elastin-derived hexapeptide VGVAPG.}, language = {en} } @inproceedings{SunkaraRostamivonTycowiczetal.2026, author = {Sunkara, Vikram and Rostami, Atefe and von Tycowicz, Christoph and Sch{\"u}tte, Christof}, title = {Stop throwing away your Decoder; extract the learnt local coordinate system using Latent-XAI}, booktitle = {The 4th World Conference on Explainable Artificial Intelligence (XAI-2026)}, year = {2026}, language = {en} }