index.json

[{"authors":["florian-buettner"],"categories":null,"content":"Florian Buettner is a professor at Goethe-University Frankfurt and the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). Having earned his PhD in physics he spent several years as a postdoc and principal investigator at the Helmholtz Center for environmental health Munich and the European Bioinformatics Institute, Cambridge. Prior to joining Frankfurt University, he worked as a guest scientist at the Helmholtz Center Munich, in addition to his appointment as senior scientist for industrial AI and probabilistic machine learning at Siemens AG. His research interests are focused on the intersection of multi-omics bioinformatics, machine learning and oncology.\n","date":1759307784,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1770759595,"objectID":"07ca172c550ccbfbc610047047ef1573","permalink":"https://mlo-lab.github.io/author/florian-buettner/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/florian-buettner/","section":"authors","summary":"Florian Buettner is a professor at Goethe-University Frankfurt and the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). Having earned his PhD in physics he spent several years as a postdoc and principal investigator at the Helmholtz Center for environmental health Munich and the European Bioinformatics Institute, Cambridge.","tags":null,"title":"Florian Buettner","type":"authors"},{"authors":["arber-qoku"],"categories":null,"content":"Arber Qoku is a doctoral candidate in bioinformatics. His research focus includes developing statistically sound and computationally efficient latent variable models for comprehensible and scalable integration of multi-omics data. During his studies of Data Science (M.Sc.) at LMU Munich, he joined the Machine Intelligence Research Group at Siemens AG where he was exposed to an array of data science projects in the domain of information retrieval. This collaboration was finalised with a master thesis in the topology optimisation of tensor-based decompositions, where he developed compression methods for significantly reducing the memory usage of deep neural networks while maintaining the expressive power of the model.\n","date":1749586260,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193380,"objectID":"3a62786f613b7ae2bd43670b5b611a44","permalink":"https://mlo-lab.github.io/author/arber-qoku/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/arber-qoku/","section":"authors","summary":"Arber Qoku is a doctoral candidate in bioinformatics. His research focus includes developing statistically sound and computationally efficient latent variable models for comprehensible and scalable integration of multi-omics data. During his studies of Data Science (M.","tags":null,"title":"Arber Qoku","type":"authors"},{"authors":null,"categories":null,"content":"Andreas Kopf is a postdoctoral researcher for computational biology in the MLO-Lab. His research interests include developing application- and collaboration-driven machine learning methods to solve real world problems in life sciences and translational medicine. In his PhD, he studied the uptake of cholesterol into liver cells, how DMF treatment affects the immune profile of multiple sclerosis patients to identify immunological biomarkers, and developed a deep probabilistic generative model for clustering and similarity-based representation learning. Before joining ETH Zürich for his doctoral studies, he studied Biomathematics at the TU Munich (M.Sc.), Mathematics at the OTH Regensburg (B.Sc.), and did an apprenticeship as technician toolmaker at Grammer AG.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"3b7747d5a7cd64eafe405ddecb846493","permalink":"https://mlo-lab.github.io/author/andreas-kopf/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/andreas-kopf/","section":"authors","summary":"Andreas Kopf is a postdoctoral researcher for computational biology in the MLO-Lab. His research interests include developing application- and collaboration-driven machine learning methods to solve real world problems in life sciences and translational medicine.","tags":null,"title":"Andreas Kopf","type":"authors"},{"authors":["helong-gary-zhao"],"categories":null,"content":"Gary Zhao obtained his PhD of Biomedical Sciences at Ohio State University, and carried out postdoctoral training in Genetics and Hematology at University of Utah. He is an adjunct assistant professor at Medical College of Wisconsin. As a translational scientist, Gary is working on using machine learning tools to improve the diagnosis and clinical care of hematological abnormalities. He is collaborating with Prof. Dr. Florian Buettner on using explainable artificial intellegence (XAI) in characterizing cells of clonal hematopoiesis.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"f6450290a70d5626e764cac932a4c578","permalink":"https://mlo-lab.github.io/author/helong-gary-zhao/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/helong-gary-zhao/","section":"authors","summary":"Gary Zhao obtained his PhD of Biomedical Sciences at Ohio State University, and carried out postdoctoral training in Genetics and Hematology at University of Utah. He is an adjunct assistant professor at Medical College of Wisconsin.","tags":null,"title":"Helong Gary Zhao","type":"authors"},{"authors":["sebastian-gruber"],"categories":null,"content":"Sebastian Gruber is a doctoral candidate in bioinformatics. His research mostly revolves around Deep Learning topics with a strong theoretical background leading to trustworthier predictions of AI systems deployed in the real world. During his studies of Statistics (M.Sc. and B.Sc.) at LMU Munich, he joined the Machine Intelligence Research Group at Siemens AG as a working student where he co-authored a scientific paper regarding trustworthy AI. This paper was later published at the AI conference CVPR 2021. The work at Siemens was finalised with a master thesis combining Meta-Learning with Knowledge Distillation, where he developed an algorithm extracting knowledge of multiple models such a new task can be learned efficiently.\n","date":1749588361,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193382,"objectID":"31c62d491e5929f496863f9e173e4039","permalink":"https://mlo-lab.github.io/author/sebastian-gruber/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sebastian-gruber/","section":"authors","summary":"Sebastian Gruber is a doctoral candidate in bioinformatics. His research mostly revolves around Deep Learning topics with a strong theoretical background leading to trustworthier predictions of AI systems deployed in the real world.","tags":null,"title":"Sebastian Gruber","type":"authors"},{"authors":["adrien-jolly"],"categories":null,"content":"Adrien Jolly is a postdoctoral researcher who completed his PhD at the German Cancer Research Center (DKFZ) in Heidelberg under the supervision of Prof. Thomas Höfer.\nHe is working on quantification of pathological and normal human blood cell development using omics data. His project is co-hosted by the labs of Prof. Büttner and Prof. Michael Rieger from the Universitätsklinikum Frankfurt and is funded by the Mildred-Scheel-Nachwuchszentrum Frankfurt.\n","date":1749587769,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1749587769,"objectID":"20a68708cb13f3282cd5d047fb9b1958","permalink":"https://mlo-lab.github.io/author/adrien-jolly/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/adrien-jolly/","section":"authors","summary":"Adrien Jolly is a postdoctoral researcher who completed his PhD at the German Cancer Research Center (DKFZ) in Heidelberg under the supervision of Prof. Thomas Höfer.\nHe is working on quantification of pathological and normal human blood cell development using omics data.","tags":null,"title":"Adrien Jolly","type":"authors"},{"authors":["ali-yavuz-cakir"],"categories":null,"content":"Yavuz Cakir is a research scientist at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). He received his master degree in Bioengineering mainly focusing on genomics variant calling pipelines, tools, and databases for hereditary cancers. During his MSc, he was involved in a research project at the University of Ferrara under the supervision of Prof. Stefano Volinia for a research visit. He worked as a bioinformatician in the industry and dealt with different kinds of clinical variant calling strategies and methods, mostly collaborating with medical doctors to interpret it. His research interest is especially concentrated on developing pipelines for divergent single-cell sequencing data in oncological studies.\n","date":1749587769,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1749587769,"objectID":"c80f85d4f1155fad9f27be87bc8aaea5","permalink":"https://mlo-lab.github.io/author/ali-yavuz-cak%C4%B1r/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/ali-yavuz-cak%C4%B1r/","section":"authors","summary":"Yavuz Cakir is a research scientist at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). He received his master degree in Bioengineering mainly focusing on genomics variant calling pipelines, tools, and databases for hereditary cancers.","tags":null,"title":"Ali Yavuz Çakır","type":"authors"},{"authors":["zahra-moslehi"],"categories":null,"content":"Zahra Moslehi is a postdoctoral researcher at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). She received her Ph.D. degree in Artificial Intelligence under supervision of Prof. Abdolreza Mirzaei from Isfahan University of Technology, Iran. During her doctoral studies, she made two research visits at the University of Geneva under supervision of Prof. Alexandros Kalousis and University of Sheffield under supervision of Prof. Neil D. Lawrence. After her Ph.D., she continued her research and teaching experiences at Isfahan University of Technology, University of Isfahan, and Shahid Beheshti University, Iran. Then she joined Gioele La Manno’s lab at EPFL as a postdoctoral researcher to develop pipelines for the integration of single cell RNA-seq and single cell ATAC-seq datasets for clustering purposes and to build robust prediction models of transitions between cellular states. Her research interests are in the multidisciplinary field of machine learning and bioinformatics specially on probabilistic modeling, metric learning, and integration of multi-omics data.\n","date":1755011469,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193377,"objectID":"03a079f9b6509da65922153b33b9eec4","permalink":"https://mlo-lab.github.io/author/zahra-moslehi/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/zahra-moslehi/","section":"authors","summary":"Zahra Moslehi is a postdoctoral researcher at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). She received her Ph.D. degree in Artificial Intelligence under supervision of Prof. Abdolreza Mirzaei from Isfahan University of Technology, Iran.","tags":null,"title":"Zahra Moslehi","type":"authors"},{"authors":["lukas-kuhn"],"categories":null,"content":"Lukas Kuhn is a Research Scientist working on predictive multimodal learning, world models, and clinical AI. His research focuses on learning structured latent representations from images, language, and other heterogeneous data sources, with the goal of enabling robust prediction, temporal modeling, and decision-making. More broadly, he is interested in self-supervised and non-contrastive learning, multimodal foundation models, and the development of reliable AI systems for high-impact real-world applications.\n","date":1751982072,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193377,"objectID":"0c42241403df05119d67fb550122ae67","permalink":"https://mlo-lab.github.io/author/lukas-kuhn/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/lukas-kuhn/","section":"authors","summary":"Lukas Kuhn is a Research Scientist working on predictive multimodal learning, world models, and clinical AI. His research focuses on learning structured latent representations from images, language, and other heterogeneous data sources, with the goal of enabling robust prediction, temporal modeling, and decision-making.","tags":null,"title":"Lukas Kuhn","type":"authors"},{"authors":["achim-hekler"],"categories":null,"content":"Achim Hekler received his degree in computer science from the Karlsruhe Institute of Technology (KIT). From 2019 to 2023, he was the head of the multicenter Skin Classification Project in the Brinker junior research group at the German Cancer Research Center (DKFZ). In this project, it was demonstrated under research conditions that AI-based systems have the potential to serve as valuable tools in supporting skin cancer diagnosis. However, for a successful translation of these systems into clinical practice, it is crucial to address other aspects beyond performance, particularly the system\u0026rsquo;s ability to communicate when it is uncertain or lacks sufficient knowledge, to build trust among users and patients.\nSince 2023, Achim Hekler has been part of Florian Büttner\u0026rsquo;s research group, where he focuses on addressing these translation gaps. His work focuses on uncertainty estimation, with particular emphasis on the calibration of neural networks to ensure that predictions are not only accurate but also reliable. In particular, he investigates this under the characteristics of real-world datasets such as data scarcity, distribution shifts, and class imbalance. Tackling these challenges is essential for ensuring the effective and safe deployment of AI systems in real-world practice.\n","date":1749588361,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193380,"objectID":"c4bff2d7bfcba2731619657629887674","permalink":"https://mlo-lab.github.io/author/achim-hekler/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/achim-hekler/","section":"authors","summary":"Achim Hekler received his degree in computer science from the Karlsruhe Institute of Technology (KIT). From 2019 to 2023, he was the head of the multicenter Skin Classification Project in the Brinker junior research group at the German Cancer Research Center (DKFZ).","tags":null,"title":"Achim Hekler","type":"authors"},{"authors":["giuseppe-serra"],"categories":null,"content":"Giuseppe Serra is a postdoctoral researcher at the Goethe University Hospital, Frankfurt. Prior to joining the group, he was granted a Marie Skłodowska-Curie Actions-ITN fellowship for his industrial doctorate in Computer Science at the University of Birmingham (Birmingham, UK) under the supervision of Prof. Peter Tino and Prof. Xin Yao. During this period, he was a full-time early-stage researcher at NEC Labs Europe (Heidelberg, Germany) in the Machine Learning group led by Prof. Mathias Niepert. His research goal was to develop and discover new approaches and methods for increasing the interpretability of representation learning techniques and black-box models. He is now working on developing trustworthy solutions in a federated continual learning setting. His project is part of the OpenFLaaS (Open Federated Learning as a Service) consortium including several partners across Germany and funded by BMWk (Bundesministerium für Wirtschaft und Klimaschutz).\n","date":1749588361,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193377,"objectID":"77d79bd96ae134e17850d1ccf4a8ffca","permalink":"https://mlo-lab.github.io/author/giuseppe-serra/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/giuseppe-serra/","section":"authors","summary":"Giuseppe Serra is a postdoctoral researcher at the Goethe University Hospital, Frankfurt. Prior to joining the group, he was granted a Marie Skłodowska-Curie Actions-ITN fellowship for his industrial doctorate in Computer Science at the University of Birmingham (Birmingham, UK) under the supervision of Prof.","tags":null,"title":"Giuseppe Serra","type":"authors"},{"authors":["sareh-ameri-far"],"categories":null,"content":"Sareh Ameri Far is a Ph.D. candidate in bioinformatics at the Goethe University Hospital, Frankfurt. She holds a BSc. in computer science and an MSc. in bioinformatics. During her master’s program, she developed an R package (ftrCOOL) that extracts various features from biological sequences. This package is published in the CRAN repository. Also, she has published a paper based on this study in the “Briefings in Bioinformatics” journal. Her research interests are multi-omics data analysis, machine learning, and oncology.\n","date":1749586260,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1749586260,"objectID":"26d90bb8e78741fdab2d77c314cfd77c","permalink":"https://mlo-lab.github.io/author/sareh-ameri-far/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sareh-ameri-far/","section":"authors","summary":"Sareh Ameri Far is a Ph.D. candidate in bioinformatics at the Goethe University Hospital, Frankfurt. She holds a BSc. in computer science and an MSc. in bioinformatics. During her master’s program, she developed an R package (ftrCOOL) that extracts various features from biological sequences.","tags":null,"title":"Sareh Ameri Far","type":"authors"},{"authors":["sarmad-ahmad-khan"],"categories":null,"content":"Sarmad Ahmad Khan is a doctoral student for machine learning in oncology at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). He received his master’s degree with honors (Red Diploma in Russia) in biotechnology (specialization in bioinformatics) from Moscow Institute of Physics and Technology (MIPT), Russia. During his masters, his research focused on omics integration to predict the presence of DNA G-Quadruplexes in a specific string of DNA, which play an important role in cancer proliferation. He is the winner of doctoral track in the subject area of chemistry, 2021 and prize-winner of in the subject area of biology and biotechnology, 2019 of Open Doors Russian Olympiad. His research interest is in bioinformatics specifically focusing on the multi-omics integration and predictive models based on the omics data helping in oncological studies.\n","date":1758722109,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758722109,"objectID":"b60d7d745922bbf649ebedb0b9d2b319","permalink":"https://mlo-lab.github.io/author/sarmad-ahmad-khan/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/sarmad-ahmad-khan/","section":"authors","summary":"Sarmad Ahmad Khan is a doctoral student for machine learning in oncology at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). He received his master’s degree with honors (Red Diploma in Russia) in biotechnology (specialization in bioinformatics) from Moscow Institute of Physics and Technology (MIPT), Russia.","tags":null,"title":"Sarmad Ahmad Khan","type":"authors"},{"authors":["tyra-stickel"],"categories":null,"content":"Tyra Stickel is a Ph.D. candidate in Bioinformatics. She holds a Bachelor and Master degree in Medical Informatics from the University of Tübingen. During her studies, she was a team member of a research group developing the Personal Health Train (PHT) - a distributed machine learning framework for medical data analysis. In her Master thesis, she worked with Gaussian Processes for confounder detection in distributed machine learning scenarios. Her research focuses on multi-omics data analysis, personalized oncology and machine learning.\n","date":1749587769,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1749587769,"objectID":"0eac91e5aa4f5840f298ef59b49ba812","permalink":"https://mlo-lab.github.io/author/tyra-stickel/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/tyra-stickel/","section":"authors","summary":"Tyra Stickel is a Ph.D. candidate in Bioinformatics. She holds a Bachelor and Master degree in Medical Informatics from the University of Tübingen. During her studies, she was a team member of a research group developing the Personal Health Train (PHT) - a distributed machine learning framework for medical data analysis.","tags":null,"title":"Tyra Stickel","type":"authors"},{"authors":["kevin-de-azevedo"],"categories":null,"content":"Kevin De Azevedo is a doctoral candidate in bioinformatics. His research involves multi-omics data integration with probabilistic programming. After his MSc, he worked in two cancer research institutes, the Gustave Roussy Institute and then the Curie Institute, as a bioinformatician. There he coded pipelines for the analysis of bulk and single cell RNA-seq, siRNA screens as well as targeted sequencing. He also handled various types of clinical and omics data in the context of intra and inter sites data sharing project using relational databases.\n","date":1751328e3,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758193377,"objectID":"d902de8656ead8d9a2a3736222ef1cab","permalink":"https://mlo-lab.github.io/author/kevin-de-azevedo/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/kevin-de-azevedo/","section":"authors","summary":"Kevin De Azevedo is a doctoral candidate in bioinformatics. His research involves multi-omics data integration with probabilistic programming. After his MSc, he worked in two cancer research institutes, the Gustave Roussy Institute and then the Curie Institute, as a bioinformatician.","tags":null,"title":"Kevin De Azevedo","type":"authors"},{"authors":["yihao-liu"],"categories":null,"content":"Yihao Liu is a doctoral candidate in bioinformatics. His research focuses on developing statistical methods and tools to explore the bone marrow microenvironment. During his master\u0026rsquo;s study at ETH Zürich, he concentrated on analyzing the tumor microenvironment using single-cell sequencing and developed methods for human brain organoids imaging data analysis combining machine learning and graph theory. In the meanwhile, he worked as a Research Assistant in the Klause Eyer’s lab at ETH Zürich improving the droplet tracking project by optimizing visualization and algorithms.\n","date":1758722109,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1758722109,"objectID":"77775a7f5ab7c6963fb5ab3b9f8a20ae","permalink":"https://mlo-lab.github.io/author/yihao-liu/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/yihao-liu/","section":"authors","summary":"Yihao Liu is a doctoral candidate in bioinformatics. His research focuses on developing statistical methods and tools to explore the bone marrow microenvironment. During his master\u0026rsquo;s study at ETH Zürich, he concentrated on analyzing the tumor microenvironment using single-cell sequencing and developed methods for human brain organoids imaging data analysis combining machine learning and graph theory.","tags":null,"title":"Yihao Liu","type":"authors"},{"authors":["nassim-walha"],"categories":null,"content":"Nassim Walha is a doctoral candidate in machine learning. His current research, in collaboration with the Data Analytics \u0026amp; Artificial Intelligence department at Siemens AG, focuses on uncertainty quantification and robustness in generative AI. During his studies, he joined various teams in academia and industry to work on topics related to machine learning and deep learning, both on the theoretical and practical side. His bachelor thesis focused on a mathematical proof of the double descent phenomenon, which explains why deep neural networks do not overfit despite being overparametrized. During his master studies, he joined Huawei Technologies to work on privacy in large language models. His master\u0026rsquo;s thesis on privacy-preserving text rewriting resulted in a paper at the Safe Generative AI workshop at NeurIPS 2024.\n","date":1763299097,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1764863150,"objectID":"5a18733a5c865f986c2e1d88ed110fc6","permalink":"https://mlo-lab.github.io/author/nassim-walha/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/nassim-walha/","section":"authors","summary":"Nassim Walha is a doctoral candidate in machine learning. His current research, in collaboration with the Data Analytics \u0026amp; Artificial Intelligence department at Siemens AG, focuses on uncertainty quantification and robustness in generative AI.","tags":null,"title":"Nassim Walha","type":"authors"},{"authors":["dustin-eisenhardt"],"categories":null,"content":"Dustin Eisenhardt is a Ph.D. student with a strong background in artificial intelligence and applied machine learning. He received his B.Sc. degree from the University of Applied Sciences Darmstadt. During both his B.Sc. and M.Sc. studies, he gained practical experience in the development of autonomous systems using deep learning through his work at Continental. He subsequently specialized in artificial intelligence and obtained his M.Sc. degree in Computer Science from Goethe University Frankfurt. His current research interests include active learning and multimodal learning.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"7d265d4c29c7004ed440a7a3c37c329e","permalink":"https://mlo-lab.github.io/author/dustin-eisenhardt/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/dustin-eisenhardt/","section":"authors","summary":"Dustin Eisenhardt is a Ph.D. student with a strong background in artificial intelligence and applied machine learning. He received his B.Sc. degree from the University of Applied Sciences Darmstadt. During both his B.","tags":null,"title":"Dustin Eisenhardt","type":"authors"},{"authors":["yusuf-berk-oruc"],"categories":null,"content":"Yusuf Berk Oruc is a doctoral student for machine learning in oncology at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). His research focuses on the interpretable probabilistic ML models for multimodal data integration. Specifically, he is applying these techniques to a project on novel mRNA technology applications for colorectal and pancreatic cancer. He received his master’s degree from Georg-August University of Göttingen. During his masters, his research focused on the development of a particle picking models for Cryo-ET that required no manually labeled data. Instead, it derived all its supervised signals from simulated data and unsupervised signals from real data. This strategy had the capacity to reduce the annotation burden drastically, enabling the analysis of unlabeled cryo-ET data with deep learning techniques that perform on par with fully supervised models.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"aee7082e03b46227cb1ecfe58214d25b","permalink":"https://mlo-lab.github.io/author/yusuf-berk-oruc/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/yusuf-berk-oruc/","section":"authors","summary":"Yusuf Berk Oruc is a doctoral student for machine learning in oncology at the German Cancer Consortium (DKTK)/German Cancer Research Center (DKFZ). His research focuses on the interpretable probabilistic ML models for multimodal data integration.","tags":null,"title":"Yusuf Berk Oruc","type":"authors"},{"authors":["hendrik-mehrtens"],"categories":null,"content":"Hendrik Mehrtens is a shared doctoral candidate between the \u0026lsquo;Machine Learning in Oncology Lab\u0026rsquo; led by Prof. Florian Büttner and the \u0026lsquo;Computational Genomics\u0026rsquo; department of Prof. Oliver Stegle at the DKFZ. His research focuses on reliable machine learning methods integrating large-scale EHR data with multimodal data like genomics data, with a focus on causality and uncertainty estimation. He obtained a bachelor\u0026rsquo;s in computer science at the Georg-August Universität Göttingen, before completing his master\u0026rsquo;s in Visual Computing (Computer Science) at the TU Darmstadt. Before starting his PhD, Hendrik worked as a staff scientist at the lab of Dr. Titus Brinker, focusing on uncertainty estimation and explainability in the clinical application of machine learning models for dermatology and histopathology. His research interests include uncertainty estimation and probabilistic modelling in machine learning, evaluating and assuring robustness of machine learning systems to changing conditions, and research into causal ML.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"bb5a5f3b7ba5151051903b5f02ae1972","permalink":"https://mlo-lab.github.io/author/hendrik-mehrtens/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/hendrik-mehrtens/","section":"authors","summary":"Hendrik Mehrtens is a shared doctoral candidate between the \u0026lsquo;Machine Learning in Oncology Lab\u0026rsquo; led by Prof. Florian Büttner and the \u0026lsquo;Computational Genomics\u0026rsquo; department of Prof. Oliver Stegle at the DKFZ.","tags":null,"title":"Hendrik Mehrtens","type":"authors"},{"authors":["azza-jenane"],"categories":null,"content":"Azza Jenane is a doctoral candidate in machine learning in oncology at the German Cancer Research Center (DKFZ). During her master\u0026rsquo;s studies at the Technical University of Munich and EPFL, she gained practical experience in applied machine learning and large language model engineering. Her master’s thesis at CARIAD investigated efficient fine-tuning of small language models for on-edge deployment and the generation of high-quality synthetic data in resource-constrained environments. Her current research at DKFZ focuses on uncertainty quantification and estimation for trustworthy AI.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"b5ff671731011f074fd6a21b36e3990a","permalink":"https://mlo-lab.github.io/author/azza-jenane/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/azza-jenane/","section":"authors","summary":"Azza Jenane is a doctoral candidate in machine learning in oncology at the German Cancer Research Center (DKFZ). During her master\u0026rsquo;s studies at the Technical University of Munich and EPFL, she gained practical experience in applied machine learning and large language model engineering.","tags":null,"title":"Azza Jenane","type":"authors"},{"authors":["rashika-jakhmola"],"categories":null,"content":"Rashika is a doctoral researcher in the MLO Lab. Her research interests span probabilistic machine learning for multi-omic data integration and foundation-model approaches for single-cell representation learning. She wrote her master thesis in the Theis Lab at Helmholtz Zentrum Munich, where she built a benchmarking pipeline for a continual learning–based autoencoder framework to construct a comparative single-cell cancer atlas. She also gained experience in single-cell data analysis at the University Medical Center Mainz and spent one and a half years as a research assistant at the German Research Centre for Artificial Intelligence (DFKI), contributing to biologically informed neural network models for cancer research.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"1cc5399db9b5ba342e3ca035712ef95f","permalink":"https://mlo-lab.github.io/author/rashika-jakhmola/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/rashika-jakhmola/","section":"authors","summary":"Rashika is a doctoral researcher in the MLO Lab. Her research interests span probabilistic machine learning for multi-omic data integration and foundation-model approaches for single-cell representation learning. She wrote her master thesis in the Theis Lab at Helmholtz Zentrum Munich, where she built a benchmarking pipeline for a continual learning–based autoencoder framework to construct a comparative single-cell cancer atlas.","tags":null,"title":"Rashika Jakhmola","type":"authors"},{"authors":["leo-luety"],"categories":null,"content":"Leo Lüty is a shared doctoral candidate between Prof. Katharina Imkeller’s group ‘Computational Immunology’ and the ‘Machine Learning in Oncology’ group led by Prof. Florian Büttner. Their research focuses on integration and interpretation of spatial transcriptomics and spatial proteomics data. In particular, they investigate the effect of a combined immunotherapy on glioblastoma based on spatial multi-omics data. Leo holds a B.Sc. in Molecular Medicine from University of Freiburg and received their master’s degree in Biomedical Informatics and Data Science from Technical University of Applied Sciences Mannheim. During their masters, their research focused on developing a pipeline for somatic variant calling at single cell resolution and mutational signatures analysis at cell type resolution. Meanwhile, they worked as a software engineer to establish interoperable workflows and corresponding software for radiology information systems.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"e0d55e6ef11dd3c0d187b6f8c01b1d87","permalink":"https://mlo-lab.github.io/author/leo-luty/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/leo-luty/","section":"authors","summary":"Leo Lüty is a shared doctoral candidate between Prof. Katharina Imkeller’s group ‘Computational Immunology’ and the ‘Machine Learning in Oncology’ group led by Prof. Florian Büttner. Their research focuses on integration and interpretation of spatial transcriptomics and spatial proteomics data.","tags":null,"title":"Leo Lüty","type":"authors"},{"authors":["bernhard-hellmann"],"categories":null,"content":"Bernhard Hellmann is a scientific project coordinator at the German Cancer Consortium (DKTK) / German Cancer Research Center (DKFZ). He holds a PhD in Nutritional Sciences and has experience in clinical data management, data analytics, and interdisciplinary biomedical research. Before joining the MLO Lab, he worked as a clinical data manager, supporting international biotech clients by overseeing clinical trial data, ensuring data integrity, and developing R Shiny dashboards to streamline internal data review processes. During his doctoral research at the University of Giessen, he investigated mitochondrial mechanisms of the medicinal fungus Hericium erinaceus in the context of Alzheimer’s disease. His academic path also included an international research stay at Jiangnan University in Wuxi, China, where he completed his master’s thesis and deepened his experience in interdisciplinary scientific work. Within the MLO Lab, he supports internal workflows, communication, and project coordination, and acts as a co-trainer for team processes.\n","date":1771923070,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":1772009470,"objectID":"aa8fdad8971107e7b0a2b4c8ca671820","permalink":"https://mlo-lab.github.io/author/bernhard-hellmann/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/bernhard-hellmann/","section":"authors","summary":"Bernhard Hellmann is a scientific project coordinator at the German Cancer Consortium (DKTK) / German Cancer Research Center (DKFZ). He holds a PhD in Nutritional Sciences and has experience in clinical data management, data analytics, and interdisciplinary biomedical research.","tags":null,"title":"Bernhard Hellmann","type":"authors"},{"authors":["mlo"],"categories":null,"content":"Our mission is the application and collaboration driven development of interpretable and statistically sound machine learning methods for understanding disease heterogeneity. As part of the DKTK/DKFZ and hosted by Frankfurt University we thrive to use machine learning for accelerating progress in personalised oncology.\nWe build on probabilistic machine learning to address computational challenges in three areas: translational single-cell genomics, computational proteomics and the integration of multi-omics data.\n","date":-62135596800,"expirydate":-62135596800,"kind":"term","lang":"en","lastmod":-62135596800,"objectID":"6a9a8b294a89e2ad039c3abe7556e9f8","permalink":"https://mlo-lab.github.io/author/mlo-lab/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/author/mlo-lab/","section":"authors","summary":"Our mission is the application and collaboration driven development of interpretable and statistically sound machine learning methods for understanding disease heterogeneity. As part of the DKTK/DKFZ and hosted by Frankfurt University we thrive to use machine learning for accelerating progress in personalised oncology.","tags":null,"title":"MLO Lab","type":"authors"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"Florian represented our lab at the 6th Rhein-Main Cancer Retreat in Glashütten (23–24 February), where he presented our latest advances in AI-based modelling of multi-omics data.His talk highlighted how integrative machine learning approaches can transform complex molecular datasets into clinically actionable insights. By combining heterogeneous omics layers, our models aim to improve patient stratification, enhance model interpretability, and support the translation of computational discoveries into clinical practice.\n","date":1771923070,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1772009470,"objectID":"8be8a669ff5449f30d2803b156902716","permalink":"https://mlo-lab.github.io/post/confernce-rmcr-2026/","publishdate":"2026-02-24T09:51:10+01:00","relpermalink":"/post/confernce-rmcr-2026/","section":"post","summary":"Florian represented our lab at the 6th Rhein-Main Cancer Retreat in Glashütten (23–24 February), where he presented our latest advances in AI-based modelling of multi-omics data.His talk highlighted how integrative machine learning approaches can transform complex molecular datasets into clinically actionable insights.","tags":[],"title":"Florian presents at the 6th Rhein-Main Cancer Retreat","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"On the 12th of February, we welcomed Ziqi Kang (PhD student, Färkkilä Lab, University of Helsinki) for an online guest talk on quantitative spatial analysis of the tumor microenvironment in high-grade serous ovarian cancer. Ziqi presented SPACEstat, a method tackling a key bottleneck in spatial biology: generating robust, comparable spatial measurements across slides and patient cohorts from multiplexed spatial proteomics data (e.g., tCyCIF). The framework quantifies spatial organization in biologically interpretable ways — tumor–stroma interface architecture, immune infiltration patterns, cellular neighborhoods, and cell–cell interaction networks — enabling single-cell–level comparisons across samples. The talk concluded with ongoing directions extending spatial analyses across multiple biological scales to better connect cellular interactions with tissue-level architecture.\nThank you, Ziqi, for the presentation and the lively discussion!\n","date":1770887620,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1770974020,"objectID":"68c9039840155a1cf3313a9840c6cf98","permalink":"https://mlo-lab.github.io/post/guest-talk-kang/","publishdate":"2026-02-12T10:13:40+01:00","relpermalink":"/post/guest-talk-kang/","section":"post","summary":"On the 12th of February, we welcomed Ziqi Kang (PhD student, Färkkilä Lab, University of Helsinki) for an online guest talk on quantitative spatial analysis of the tumor microenvironment in high-grade serous ovarian cancer.","tags":[],"title":"Guest Talk | Ziqi Kang – Quantitative Spatial Analysis of the Tumor Microenvironment","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"For our 2026 group retreat, the entire team gathered at Bildungshaus Kloster Schöntal 03–05 February. Set in the beautiful monastery surroundings, the retreat gave us dedicated time to discuss organizational topics, exchange ideas on science, and deepen our understanding of our wide range of research areas.\nBeyond the sessions, the retreat was also about connection, with lively conversations and a friendly (and competitive) round of table tennis in the evenings. Overall, it was a wonderful opportunity to come together as a team, strengthen collaboration, and return with renewed focus and a shared perspective.\n","date":1770277632,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1770364032,"objectID":"3a816f62fc7e67d855a449e8f1f5c3ee","permalink":"https://mlo-lab.github.io/post/retreat-2026/","publishdate":"2026-02-05T08:47:12+01:00","relpermalink":"/post/retreat-2026/","section":"post","summary":"For our 2026 group retreat, the entire team gathered at Bildungshaus Kloster Schöntal 03–05 February. Set in the beautiful monastery surroundings, the retreat gave us dedicated time to discuss organizational topics, exchange ideas on science, and deepen our understanding of our wide range of research areas.","tags":[],"title":"Group Retreat 2026","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"We hosted Dr. Marius Herr from the University of Tübingen, who presented FLAME — Federated Learning and Analyses in Medicine, a platform developed within the privateAIM initiative. He outlined how patient data can be analyzed in a privacy-preserving manner and demonstrated how our methods could be applied to clinical data through FLAME. The subsequent discussions provided practical insights into the requirements for clinically ready applications of such systems.\nWe warmly thank Dr. Herr for his visit and the constructive exchange. We look forward to staying in contact and exploring potential collaborations as FLAME moves toward national implementation.\n","date":1764853135,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1764853135,"objectID":"6055176adcdeca4ea6eda5875192d05a","permalink":"https://mlo-lab.github.io/post/flame-project-herr/","publishdate":"2025-12-04T13:58:55+01:00","relpermalink":"/post/flame-project-herr/","section":"post","summary":"We hosted Dr. Marius Herr from the University of Tübingen, who presented FLAME — Federated Learning and Analyses in Medicine, a platform developed within the privateAIM initiative. He outlined how patient data can be analyzed in a privacy-preserving manner and demonstrated how our methods could be applied to clinical data through FLAME.","tags":[],"title":"Insights into FLAME: Visit by Dr. Marius Herr","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"Azza joins our ML sub-team as a doctoral researcher working on uncertainty quantification and estimation for trustworthy AI. She brings experience in applied machine learning and language model engineering and will support our ongoing research on reliable ML methods in oncology.\n","date":1763372291,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1763372291,"objectID":"9812d4e7a393f265aa723dff486e340e","permalink":"https://mlo-lab.github.io/post/azza-welcome-to-the-team/","publishdate":"2025-11-17T10:38:11+01:00","relpermalink":"/post/azza-welcome-to-the-team/","section":"post","summary":"Azza joins our ML sub-team as a doctoral researcher working on uncertainty quantification and estimation for trustworthy AI. She brings experience in applied machine learning and language model engineering and will support our ongoing research on reliable ML methods in oncology.","tags":[],"title":"Welcome to our newest team member, Azza","type":"post"},{"authors":["Nassim Walha"],"categories":[],"content":"This work presents Spectral Uncertainty, a new way to decompose uncertainty in large language models. Using the Von Neumann entropy, the method distinguishes aleatoric from epistemic uncertainty and incorporates detailed semantic structure in model outputs. Across multiple benchmarks, it outperforms current approaches in estimating uncertainty.\n","date":1763299097,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1763299097,"objectID":"a277f1341c5f3eb1705ff24736f59fef","permalink":"https://mlo-lab.github.io/post/walha-uncertainty-decomposition/","publishdate":"2025-11-16T14:18:17+01:00","relpermalink":"/post/walha-uncertainty-decomposition/","section":"post","summary":"This work presents Spectral Uncertainty, a new way to decompose uncertainty in large language models. Using the Von Neumann entropy, the method distinguishes aleatoric from epistemic uncertainty and incorporates detailed semantic structure in model outputs.","tags":[],"title":"Our paper “Fine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approach” is now available at AAAI","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"A proud moment: Florian has been listed as a Highly Cited Researcher 2025, placing him among the top 1% of scientists worldwide. This recognition reflects the shared work, ideas, and energy that move our lab forward every day. Proud to have this team! Official Announcement\n","date":1763127664,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1763127664,"objectID":"f9b0cbf155725e8aca8df010a91e82b1","permalink":"https://mlo-lab.github.io/post/buettner-most-cited-2025/","publishdate":"2025-11-14T14:41:04+01:00","relpermalink":"/post/buettner-most-cited-2025/","section":"post","summary":"A proud moment: Florian has been listed as a Highly Cited Researcher 2025, placing him among the top 1% of scientists worldwide. This recognition reflects the shared work, ideas, and energy that move our lab forward every day.","tags":[],"title":"Florian named among the world’s most cited researchers — huge congrats to the whole MLO Lab team!","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"Rashika joins the MLO Lab as a doctoral researcher working on probabilistic machine learning for multi-omic data integration and foundation-model approaches for single-cell representation learning. She will contribute to our research on machine learning methods for cancer data analysis.\n","date":1762782210,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1762782210,"objectID":"f7e472c16fb4704be9670794a80e42fb","permalink":"https://mlo-lab.github.io/post/rashika-welcome-to-the-team/","publishdate":"2025-11-10T14:43:30+01:00","relpermalink":"/post/rashika-welcome-to-the-team/","section":"post","summary":"Rashika joins the MLO Lab as a doctoral researcher working on probabilistic machine learning for multi-omic data integration and foundation-model approaches for single-cell representation learning. She will contribute to our research on machine learning methods for cancer data analysis.","tags":[],"title":"Welcome to our newest team member, Rashika","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"Hendrik joins our ML sub-team, working on machine learning methods that combine large-scale EHR data with other data types such as genomics. He focuses on causality and uncertainty estimation and will support our ongoing methodological work.\n","date":1760776144,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1760776144,"objectID":"090b985219b55ba60892d7a477fd863e","permalink":"https://mlo-lab.github.io/post/hendrik-welcome-to-the-team/","publishdate":"2025-10-18T09:29:04+01:00","relpermalink":"/post/hendrik-welcome-to-the-team/","section":"post","summary":"Hendrik joins our ML sub-team, working on machine learning methods that combine large-scale EHR data with other data types such as genomics. He focuses on causality and uncertainty estimation and will support our ongoing methodological work.","tags":[],"title":"Welcome to the team, Hendrik","type":"post"},{"authors":["Bernhard Hellmann"],"categories":[],"content":"Leo joins our group as a shared doctoral researcher working on the integration and interpretation of spatial transcriptomics and spatial proteomics data. Their research focuses on spatial multi-omics analyses to study immunotherapy effects in glioblastoma.\n","date":1759394409,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1759394409,"objectID":"e40cb9fe3cd93d9c9dc155b0326cd07a","permalink":"https://mlo-lab.github.io/post/leo-welcome-to-the-team/","publishdate":"2025-10-02T09:40:09+01:00","relpermalink":"/post/leo-welcome-to-the-team/","section":"post","summary":"Leo joins our group as a shared doctoral researcher working on the integration and interpretation of spatial transcriptomics and spatial proteomics data. Their research focuses on spatial multi-omics analyses to study immunotherapy effects in glioblastoma.","tags":[],"title":"Welcome to our newest team member, Rashika","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"Yussuf joins our bioinformatics sub-team as a doctoral researcher working on interpretable probabilistic machine learning models for multimodal data integration. He applies these methods to projects on novel mRNA technologies for colorectal and pancreatic cancer and will support our ongoing research efforts.\n","date":1759307784,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1759307784,"objectID":"0da7fa4054fcea4b28c262baaef8f288","permalink":"https://mlo-lab.github.io/post/yusuf-welcome-to-the-team/","publishdate":"2025-10-01T09:36:24+01:00","relpermalink":"/post/yusuf-welcome-to-the-team/","section":"post","summary":"Yussuf joins our bioinformatics sub-team as a doctoral researcher working on interpretable probabilistic machine learning models for multimodal data integration. He applies these methods to projects on novel mRNA technologies for colorectal and pancreatic cancer and will support our ongoing research efforts.","tags":[],"title":"Welcome to the team, Yusuf","type":"post"},{"authors":["Sarmad Ahmad Khan","Yihao Liu"],"categories":[],"content":"Quantitative imaging in oncology combines advanced microscopy, image analysis and machine learning to study cancer in unprecedented detail. By extracting rich spatial and molecular information from tissues, we aim to better understand how tumors grow, respond to treatments and interact with their surroundings. In our lab, we have developed colocatome frameworks to map and quantify in situ cellular organization, revealing how microenvironments regulate cell behavior. In parallel, we extract reproducible radiomic features such as texture, intensity and shape, together with quantitative MRI metrics like relaxation times, and apply interpretable machine-learning models to link these imaging biomarkers to clinical outcomes. This enables precise tumor localization and non-invasive monitoring of disease progression.\nQuantitative Imaging and Spatial Analysis Our work focuses on developing computational frameworks to analyze high-resolution multiplex microscopy images of tissues such as bone marrow, generated by Quantitative Spatial Cancer Biology - Kokkaliaris lab. We specialize in extracting spatial and morphological features from complex, multi-modal image data.\nWe have developed a framework that enables the integration and analysis of multiple biological replicates with complementary information in a shared spatial reference space. Building on this, we established a pipeline to extract and quantify spatial remodeling of the cellular neighborhood during the aging process. These tools allow us to investigate how hematopoietic stem cells, blood vessels, megakaryocytes, adipocytes, and stromal components are spatially organized and how these patterns evolve with age or in response to treatment.\nRadiomics and Quantitative MRI Our imaging research also includes radiological data analysis, with a focus on transitioning from qualitative interpretation to quantitative, reproducible metrics. In radiomics, we extract features such as texture, intensity, and shape from defined regions of interest within MRI scans, and use machine learning models to link these features to clinical outcomes. We emphasize interpretability and robustness, testing models on controlled environments to avoid confounding due to real-patient variability and ethical exposure limitations.\nIn parallel, we employ quantitative MRI (qMRI) techniques to move beyond traditional contrast-based imaging. By measuring intrinsic physical properties of tissues, e.g. relaxation times, we obtain microstructural insights into tissue composition, particularly in brain imaging. Combining qMRI with machine learning enables precise localization of tumors and assessment of disease progression, further enhancing the clinical utility of radiological data.\n","date":1758722109,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758722109,"objectID":"991de063ebf72eda700167b94a3bb60b","permalink":"https://mlo-lab.github.io/project/medical-imaging/","publishdate":"2025-09-24T15:55:09+02:00","relpermalink":"/project/medical-imaging/","section":"project","summary":"Quantitative imaging in oncology uses advanced microscopy, image analysis, and machine learning to study cancer in unprecedented detail. By extracting rich spatial and molecular information from tissues, we aim to better understand how tumors grow, respond to treatments, and interact with their surroundings.","tags":["applied-bioinformatics","single-cell","medical-imaging"],"title":"Quantitative Imaging in Oncology","type":"project"},{"authors":["Zahra Moslehi"],"categories":[],"content":"We present a unified framework that combines expressive neural embeddings with interpretable multi-output Gaussian processes for single-cell genomics. Joint representations of cells and genes reveal meaningful links between cell clusters and their marker genes via an interpretable gene-relevance map. Published in Nucleic Acids Research.\n","date":1755011469,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1755011469,"objectID":"75d9d43c69cbe09899f5cbd691a5b09c","permalink":"https://mlo-lab.github.io/post/moslehi-multioutput-gp/","publishdate":"2025-08-12T16:11:09+01:00","relpermalink":"/post/moslehi-multioutput-gp/","section":"post","summary":"We present a unified framework that combines expressive neural embeddings with interpretable multi-output Gaussian processes for single-cell genomics. Joint representations of cells and genes reveal meaningful links between cell clusters and their marker genes via an interpretable gene-relevance map.","tags":[],"title":"Our paper “Learning interpretable representations of single-cell multi-omics data with multi-output Gaussian processes” has been published in Nucleic Acids Research.","type":"post"},{"authors":["Lukas Kuhn"],"categories":[],"content":"We introduce ModelAuditor, a self-reflective agent that simulates clinically relevant distribution shifts and produces interpretable reports on likely failure modes. Across multiple medical imaging domains, it recovers up to 25% of performance lost under shift while providing actionable deployment insights.\n","date":1751982072,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1751982072,"objectID":"9d319dbab5e2646ad9a365edc3e56e9f","permalink":"https://mlo-lab.github.io/post/kuhn-autonomous-agent-clinical-ai/","publishdate":"2025-07-08T14:41:12+01:00","relpermalink":"/post/kuhn-autonomous-agent-clinical-ai/","section":"post","summary":"We introduce ModelAuditor, a self-reflective agent that simulates clinically relevant distribution shifts and produces interpretable reports on likely failure modes. Across multiple medical imaging domains, it recovers up to 25% of performance lost under shift while providing actionable deployment insights.","tags":[],"title":"An autonomous agent for auditing and improving the reliability of clinical AI models — now published.","type":"post"},{"authors":["Zahra Moslehi","Sareh AmeriFar","Kevin De Azevedo","Florian Buettner"],"categories":[],"content":"","date":1751328e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193377,"objectID":"6931daef2fe89c35db96a589163cecf3","permalink":"https://mlo-lab.github.io/publication/10-1093-nargkaf-630/","publishdate":"2025-09-18T11:02:57.249166Z","relpermalink":"/publication/10-1093-nargkaf-630/","section":"publication","summary":"Learning representations of single-cell genomics data is challenging due to the nonlinear and often multi-modal nature of the data on one hand and the need for interpretable representations on the other hand. Existing approaches tend to focus either on interpretability aspects via linear matrix factorization or on maximizing expressive power via neural network-based embeddings using black-box variational autoencoders or graph embedding approaches. We address this trade-off between expressive power and interpretability by introducing a novel approach that combines highly expressive representation learning via an embedding layer with interpretable multi-output Gaussian processes within a unified framework. In our model, we learn distinct representations for samples (cells) and features (genes) from multi-modal single-cell data. We demonstrate that even a few interpretable latent dimensions can effectively capture the underlying structure of the data. Our model yields interpretable relationships between groups of cells and their associated marker genes: leveraging a gene relevance map, we establish connections between cell clusters (e.g. specific cell types) and feature clusters (e.g. marker genes for those specific cell types) within the learned latent spaces of cells and features.","tags":[],"title":"Learning interpretable representations of single-cell multi-omics data with multi-output Gaussian processes","type":"publication"},{"authors":["Achim Hekler","Giuseppe Serra","Lukas Kuhn","Nassim Walha","Sebastian Gruber"],"categories":[],"content":"As machine learning becomes increasingly central to biomedical discovery and clinical decision-making, ensuring the reliability, fairness, and interpretability of these models is critical. In our lab, we are committed to developing and applying machine learning methods that are not only accurate but also trustworthy, meaning they are robust to noise, generalizable across datasets, transparent in their decision-making, and aligned with ethical and clinical standards.\nOur work spans multiple aspects of trustworthy ML, including uncertainty quantification, model calibration, interpretability, fairness in predictive models, and robustness to distributional shifts. These components are especially important in healthcare, where decisions influenced by models can have direct consequences for patients.\nIn the context of multi-omics data, single-cell analysis, and quantitative imaging, we embed trustworthiness principles throughout the model development pipeline, from data preprocessing and integration to prediction and interpretation. This ensures that our computational outputs can be confidently used to guide biological insight and translational applications.\nModel Calibration Under Distribution Shift Current-generation neural networks exhibit systematic underconfidence rather than the overconfidence reported in earlier models, and demonstrate improved calibration robustness under distribution shift. However, post-hoc calibration methods become less effective or even detrimental under severe shifts. Our analysis across ImageNet and biomedical datasets reveals that calibration insights from web-scraped benchmarks have limited transferability to specialized domains, where convolutional architectures consistently outperform transformers regardless of model generation. This work challenges established calibration paradigms and emphasizes the need for domain-specific architectural evaluation beyond standard benchmarks. [pdf, repo]\nUncertainty Quantification for Classification and Applications Reliably estimating the uncertainty of a prediction throughout the model lifecycle is crucial in many safety-critical applications. Since ML-based decision models are increasingly deployed in dynamic environments, understanding when and why a model might fail becomes as important as achieving accurate predictive performance. In our group, we focus on developing theoretically sounded methods for uncertainty quantification that remain robust across different applications, enabling more trustworthy and transparent AI systems. Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition (AISTATS 2023) Proper scoring rules (e.g., Brier score or negative log-likelihood) are commonly used as loss functions in machine learning, as they are designed to assign optimal predictions to the target distribution. However, it remains unclear how to decompose these scores in a way that a component capturing the model’s predictive uncertainty arises. To address this, we derive a general bias-variance decomposition for proper scoring rules, where the Bregman Information (BI) naturally emerges as the variance term. This new theoretical insight has practical implications for classification tasks: since the decomposition applies to the cross-entropy loss, it allows us to quantify predictive uncertainty directly in the logit space (the standard output of neural networks) without requiring a normalisation step. Extensive empirical results demonstrate the effectiveness and robustness of this method, particularly in out-of-distribution settings. [pdf, repo]\nHow to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning (TMLR 2025) In many real-world scenarios, we want models to continuously learn new information without forgetting what they already know. In memory-based online continual learning, a key challenge is managing a limited memory buffer to mitigate catastrophic forgetting (CF) — but what is the best strategy for selecting samples to store in the memory? Under an uncertainty lens, we investigate what characteristics make samples effective in alleviating CF. Starting from the examination of the properties and behaviours of popular uncertainty estimates, we identify that they mostly capture the irreducible aleatoric uncertainty and hypothesise that a better strategy should focus on the epistemic uncertainty instead. To this end, we propose using Bregman Information – derived from our general bias-variance decomposition of strictly proper scores – as an effective estimator of epistemic uncertainty, leading to improved memory population strategy and reduced forgetting. [pdf, repo]\nFederated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond (ICLR 2025) Federated Continual Learning (FCL) is a powerful paradigm that combines the privacy-preserving benefits of Federated Learning (FL) with the ability to learn sequentially over time, as in Continual Learning (CL). However, catastrophic forgetting still remains a major challenge. Most existing FCL methods rely on generative models, assuming an offline setting where all task data are available beforehand. But in real-world applications, data often arrives sequentially in small chunks — a challenge that remains largely unaddressed. To address this, we introduce a novel framework for online federated continual learning. To address scenarios where storing the full dataset locally is impractical, we propose an effective memory-based baseline that integrates uncertainty-aware updates — based on Bregman Information — with random replay to reduce catastrophic forgetting. Unlike generative approaches, our uncertainty-based solution is simple to implement and adaptable across different data modalities. [pdf, repo]\nUncertainty Quantification for Generative AI Generative AI models in general and large language models in particular have emerged as a disruptive technology that has been rapidly democratized. Their use in critical domains such as medicine, scientific research, and politics has raised serious concerns about reliability. Consequently, robust estimation of their uncertainty is essential to build trust and to prevent the potentially severe consequences of failures. We develop methods to quantify and calibrate their uncertainty across different modalities, while accounting for the specific characteristics of each modality. A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models (ICML 2024) This paper tackles a core gap in generative AI: there’s no unified, theory-grounded way to assess generalization and uncertainty across modalities or closed-source models. We introduce the first bias–variance–covariance decomposition for kernel scores, yielding kernel-based measures that can be estimated directly from generated samples, without access to the underlying model. Because kernels work from samples alone and are computed based on vector representations of these samples, the framework applies uniformly to images, audio, and language. In experiments, the approach explains generalization behavior (including mode collapse patterns) and delivers stronger uncertainty signals, even for closed-source LLMs.\n[pdf, repo]\n","date":1749588361,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1749588361,"objectID":"a6bc3bc069ac9ea116d9a1df662732a3","permalink":"https://mlo-lab.github.io/project/trustworthy-ml/","publishdate":"2025-06-10T22:46:01+02:00","relpermalink":"/project/trustworthy-ml/","section":"project","summary":"As machine learning becomes increasingly central to biomedical discovery and clinical decision-making, ensuring the reliability, fairness, and interpretability of these models is critical. In our lab, we are committed to developing and applying machine learning methods that are not only accurate but also trustworthy.","tags":["trustworthy-ml"],"title":"Trustworthy Machine Learning in Biomedical Research","type":"project"},{"authors":["Adrien Jolly","Ali Yavuz Çakır","Sarmad Ahmad Khan","Yihao Liu","Tyra Stickel"],"categories":[],"content":"Single-cell multi-omics data offer powerful opportunities to study disease at unprecedented resolution, but they also present significant challenges. The data are often sparse, noisy, and extremely high-dimensional, with technical differences between batches or donors that can obscure true biological signals. Our lab combines advanced computational methods with high-dimensional biological data to exludes technical artifacts and uncover mechanisms of disease progresssion and therapy response, with a particular emphasis on cancer and metabolic disorder.\nSingle-Cell Multi-Omics for Clinical Cohorts We specialize in the analysis of clinical single-cell multi-omics datasets, particularly from cancer and metabolic disease cohorts. Using state-of-the-art machine learning techniques, we analyze single-cell RNA sequencing and chromatin accessibility data to characterize cellular heterogeneity and regulatory dynamics. Our pipeline includes robust dimensionality reduction, clustering, and batch correction methods, allowing us to identify distinct cell populations and states across individuals. Through probabilistic graphical modeling and motif enrichment analysis, we reconstruct gene regulatory networks that govern disease-specific transcriptional programs. These approaches allow us to overcome the sparsity and noise inherent to single-cell data and extract biologically meaningful patterns that inform prognosis and therapeutic strategy.\nMulti-Omics for Mouse Models of Cancer Progression To explore tumor development and treatment effects in vivo, we analyze multi-omics data generated from mouse models, including xenografts and genetically induced cancers. These datasets are complex, encompassing multiple axes of variation such as treatment regimens, time points, and tumor subtypes. To disentangle these factors, we develop tailored probabilistic latent variable models (LVMs) that reveal how sources of variability interact and which molecular features are relevant to human disease. Recent projects:\n  Multi-Omics combined with lineage tracing technology now allow us to quantify the clonal connectivity between different cell populations and infer the temporal dynamics of cell populations. Using mechanistic modeling, we can uncover the directionality of differentiation trajectories and the dynamical properties of the clones [pdf].\n  Analyzing cancerous mouse models provides valuable insights for developing personalized oncology approaches. We will integrate patient data at an early stage in this process using a forward and reverse translation technique. This method ensures that the results are clinically relevant and enables us to identify patients who are eligible for a new treatment. For example, we are working on a TRR project that investigates how ubiquitination impacts DNA damage repair in AML in order to identify a new anticancer target [project].\n  ","date":1749587769,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1749587769,"objectID":"0f7627826e0068ea4f7a0fa29132cf8b","permalink":"https://mlo-lab.github.io/project/comp-medicine/","publishdate":"2025-06-10T22:36:09+02:00","relpermalink":"/project/comp-medicine/","section":"project","summary":" Single-cell multi-omics data present unique challenges. Our lab combines advanced computational methods with high-dimensional biological data to uncover mechanisms of disease, with a particular emphasis on cancer and metabolic disorders.","tags":["applied-bioinformatics","single-cell"],"title":"Computational Molecular Medicine","type":"project"},{"authors":["Arber Qoku","Kevin De Azevedo","Zahra Moslehi","Sareh Ameri Far","Tyra Stickel"],"categories":[],"content":"Understanding the complexity of cancer requires methods that can integrate equally complex biological data. In our lab, we are committed to developing probabilistic models that bring together multiple molecular layers, including genomics, epigenomics, transcriptomics, proteomics and metabolomics, to provide a holistic view of each patient. These models uncover hidden structure by capturing both shared and modality-specific variation, allowing us to reduce noise and reveal biologically meaningful patterns. By modeling system-level responses to perturbations such as drug treatments or environmental changes, we aim to generate representations that are not only statistically robust but also interpretable, enabling new biological insights that can be directly validated and translated into clinical understanding.\nMuVI MuVI is a general-purpose probabilistic latent variable model for multi-omics integration that incorporates prior biological knowledge into its structure. It uses pathway annotations, gene sets, or cell-type signatures to guide the discovery of latent factors that explain variation across different data types. Even when this prior knowledge is noisy or incomplete, MuVI is able to learn biologically relevant dimensions, enabling scientists to interpret the sources of variation in the data more clearly and to relate them to known mechanisms. MUSIC MUSIC (MUltiview baySIan tensor deComposition) extends probabilistic modeling to high-dimensional array data, such as time-series or condition-specific measurements. It jointly decomposes collections of heterogeneous tensors, e.g. patient × gene × time or patient × protein × condition, into shared and modality-specific components. With structured sparsity priors and efficient variational inference, MUSIC scales to large datasets, handles missing data, and yields interpretable embeddings. We have applied it to cancer drug-response studies and single-cell leukemia data, where it revealed meaningful molecular signatures associated with disease pathways.\nMOMO-GP MOMO-GP (Multi-Omic Multi-output Gaussian Processes) addresses the challenge of learning interpretable representations from single-cell multi-omics data, which are typically high-dimensional, sparse, and nonlinear. Unlike traditional methods that trade off interpretability for modeling power, MOMO-GP combines neural networks with Gaussian Processes to achieve both. It learns separate latent embeddings for cells and features, as well as shared and modality-specific components in the multi-view setting. By modeling gene relevance explicitly, MOMO-GP connects cell clusters to marker genes, making the learned structure readily interpretable in biological terms.\nJOANA JOANA is a probabilistic model for pathway enrichment analysis (PEA) that overcomes limitations of classical approaches like Over-Representation Analysis (ORA) and Functional Class Scoring (FCS). While methods such as GSEA work with continuous scores, they typically operate on a single omics layer and can yield overly broad sets of enriched pathways. JOANA improves on this by modeling enrichment scores across multiple omics layers using mixtures of beta distributions within a Bayesian framework. This allows it to estimate the probability of pathway enrichment both within and across modalities, yielding higher precision and more biologically relevant results.\nMOFAFLEX MOFAFLEX is our upcoming framework for flexible and interpretable multi-omics integration. Designed to generalize the principles behind models like MuVI and MUSIC, MOFAFLEX supports heterogeneous data types, modular priors, and scalable inference. Its architecture allows for tailored modeling of real-world datasets, balancing interpretability with modeling flexibility. MOFAFLEX is currently under active development and will provide a unified foundation for future applications in cancer biology and beyond. ","date":1749586260,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1749586260,"objectID":"42771e23be96567ffbc86857e673fb8c","permalink":"https://mlo-lab.github.io/project/multi-omics/","publishdate":"2025-06-10T22:11:00+02:00","relpermalink":"/project/multi-omics/","section":"project","summary":"Understanding the complexity of cancer requires making sense of equally complex biological data. In our lab, we develop probabilistic models for the integration of multi-omics datasets to uncover hidden structure in the data by capturing both shared and modality-specific sources of variation.","tags":["latent variable models","multi-omics","domain expertise","gaussian-process","tensor-decomposition","pathway analysis"],"title":"Interpretable Integration of Multi-Omics Data","type":"project"},{"authors":["Florian Buettner"],"categories":[],"content":"We present the first systematic framework for application-driven validation of posterior-based methods in inverse problems. Adapting concepts from object detection enables mode-centric validation with interpretable, application-focused metrics, demonstrated on multiple medical imaging use cases. Published in Medical Image Analysis.\n","date":1743516620,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1743516620,"objectID":"72c92c666d0ea2cb4d06a67b849c57be","permalink":"https://mlo-lab.github.io/post/buettner-posterior-inverse-problems/","publishdate":"2025-04-01T15:10:20+01:00","relpermalink":"/post/buettner-posterior-inverse-problems/","section":"post","summary":"We present the first systematic framework for application-driven validation of posterior-based methods in inverse problems. Adapting concepts from object detection enables mode-centric validation with interpretable, application-focused metrics, demonstrated on multiple medical imaging use cases.","tags":[],"title":"Application-driven validation of posteriors in inverse problems, published in Medical Image Analysis.","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"We introduce LVLM-Aided Visual Alignment (LVLM-VA), which aligns small vision models with human domain knowledge using large vision-language models. A bidirectional interface translates model behavior into natural language and expert instructions into image-level critiques, improving performance while reducing fine-grained feedback needs. Published at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment.\n","date":1741271696,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1741271696,"objectID":"76b9518224b3c5f509405d26ca3f7574","permalink":"https://mlo-lab.github.io/post/buettner-lvlm-aided-visiual-alignment/","publishdate":"2025-03-06T15:34:56+01:00","relpermalink":"/post/buettner-lvlm-aided-visiual-alignment/","section":"post","summary":"We introduce LVLM-Aided Visual Alignment (LVLM-VA), which aligns small vision models with human domain knowledge using large vision-language models. A bidirectional interface translates model behavior into natural language and expert instructions into image-level critiques, improving performance while reducing fine-grained feedback needs.","tags":[],"title":"Our paper on bidirectional human-AI visual alignment is out at the ICLR 2025 Workshop!","type":"post"},{"authors":["Giuseppe Serra"],"categories":[],"content":"We analyze how predictive uncertainty can guide memory management to mitigate catastrophic forgetting and introduce a generalized-variance–based uncertainty measure. Uncertainty-aware sampling improves retention across tasks. Published in the Journal of Transactions on Machine Learning Research.\n","date":1741098771,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1741098771,"objectID":"f2d0b3e9f091895a31620021bb193692","permalink":"https://mlo-lab.github.io/post/serra-predictive-uncertainty-catastrophic-forgetting/","publishdate":"2025-03-04T15:32:51+01:00","relpermalink":"/post/serra-predictive-uncertainty-catastrophic-forgetting/","section":"post","summary":"We analyze how predictive uncertainty can guide memory management to mitigate catastrophic forgetting and introduce a generalized-variance–based uncertainty measure. Uncertainty-aware sampling improves retention across tasks. Published in the Journal of Transactions on Machine Learning Research.","tags":[],"title":"Forget forgetting — our TMLR paper shows how uncertainty helps models keep their memory straight!","type":"post"},{"authors":["Alexander Koebler","Thomas Decker","Ingo Thon","Volker Tresp","Florian Buettner"],"categories":[],"content":"","date":1740787200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193376,"objectID":"c15aa2c1c3ba116747e7e39f264b146a","permalink":"https://mlo-lab.github.io/publication/pmlr-v-258-koebler-25-a/","publishdate":"2025-09-18T11:02:56.48879Z","relpermalink":"/publication/pmlr-v-258-koebler-25-a/","section":"publication","summary":"We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significant declines in accuracy. To address this, we propose Incremental Uncertainty-aware Performance Monitoring (IUPM), a novel label-free method that estimates performance changes by modeling gradual shifts using optimal transport. In addition, IUPM quantifies the uncertainty in the performance prediction and introduces an active labeling procedure to restore a reliable estimate under a limited labeling budget. Our experiments show that IUPM outperforms existing performance estimation baselines in various gradual shift scenarios and that its uncertainty awareness guides label acquisition more effectively compared to other strategies.","tags":["highlight"],"title":"Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention","type":"publication"},{"authors":["Florian Buettner"],"categories":[],"content":"We propose IUPM, a label-free method for tracking performance under gradual distribution shifts using optimal transport. IUPM quantifies uncertainty in its estimates and guides targeted labeling to restore reliability, outperforming existing baselines across scenarios. Published in the Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS).\n","date":1737557264,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1737557264,"objectID":"d0a5f8dc8f35bbb50dab2829cf663c62","permalink":"https://mlo-lab.github.io/post/buettner-iupm-intervention/","publishdate":"2025-01-22T15:47:44+01:00","relpermalink":"/post/buettner-iupm-intervention/","section":"post","summary":"We propose IUPM, a label-free method for tracking performance under gradual distribution shifts using optimal transport. IUPM quantifies uncertainty in its estimates and guides targeted labeling to restore reliability, outperforming existing baselines across scenarios.","tags":[],"title":"New at AISTATS: IUPM — a label-free method for reliable model monitoring under drift.","type":"post"},{"authors":["Giuseppe Serra"],"categories":[],"content":"We propose an uncertainty-aware memory-based approach for online Federated Continual Learning. Using a Bregman Information estimator to guide selective replay, the method reduces catastrophic forgetting across modalities while preserving privacy and communication efficiency. Presented at the Thirteenth International Conference on Learning Representations (ICLR).\n","date":1737555897,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1737555897,"objectID":"c8be7a507af2de51a84a3b826d8f1bed","permalink":"https://mlo-lab.github.io/post/serra-continous-learning-memory-managment/","publishdate":"2025-01-22T15:24:57+01:00","relpermalink":"/post/serra-continous-learning-memory-managment/","section":"post","summary":"We propose an uncertainty-aware memory-based approach for online Federated Continual Learning. Using a Bregman Information estimator to guide selective replay, the method reduces catastrophic forgetting across modalities while preserving privacy and communication efficiency.","tags":[],"title":"Our ICLR paper proves that not everything needs to be forgotten — tackling catastrophic forgetting head-on!","type":"post"},{"authors":["Lukas Kuhn"],"categories":[],"content":"We introduce an unsupervised framework to detect and mitigate shortcut learning in transformers. The method improves both worst-group and average accuracy while reducing annotation effort, offering interpretable insights for experts and running efficiently on consumer hardware.\n","date":1735740976,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1735740976,"objectID":"5c8bf5a7d2ef30ba4458ad1d8271bada","permalink":"https://mlo-lab.github.io/post/kuhn-unsupervised-shortcut-transformers/","publishdate":"2025-01-01T15:16:16+01:00","relpermalink":"/post/kuhn-unsupervised-shortcut-transformers/","section":"post","summary":"We introduce an unsupervised framework to detect and mitigate shortcut learning in transformers. The method improves both worst-group and average accuracy while reducing annotation effort, offering interpretable insights for experts and running efficiently on consumer hardware.","tags":[],"title":"Unsupervised and efficient — our latest work exposes and mitigates shortcut learning!","type":"post"},{"authors":["Lukas Kuhn","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193377,"objectID":"ab2cf9fd818cec640bbf440ce39e82bf","permalink":"https://mlo-lab.github.io/publication/kuhn-2025-autonomousagentauditingimproving/","publishdate":"2025-09-18T11:02:56.912807Z","relpermalink":"/publication/kuhn-2025-autonomousagentauditingimproving/","section":"publication","summary":"","tags":[],"title":"An autonomous agent for auditing and improving the reliability of clinical AI models","type":"publication"},{"authors":["Tim J Adler","Jan-Hinrich Nölke","Annika Reinke","Minu Dietlinde Tizabi","Sebastian Gruber","Dasha Trofimova","Lynton Ardizzone","Paul F Jaeger","Florian Buettner","Ullrich Köthe"," others"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193376,"objectID":"3170edbf9e9ca1332cc8b7047bfc0378","permalink":"https://mlo-lab.github.io/publication/adler-2025-application/","publishdate":"2025-09-18T11:02:56.13304Z","relpermalink":"/publication/adler-2025-application/","section":"publication","summary":"","tags":[],"title":"Application-driven validation of posteriors in inverse problems","type":"publication"},{"authors":["Mariano Ruz Jurado","David Rodriguez Morales","Elijah Genetzakis","Fatemeh Behjati Ardakani","Lukas Zanders","Ariane Fischer","Florian Buettner","Marcel H Schulz","Stefanie Dimmeler","David John"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1770759595,"objectID":"6bda721dc589e60a19525e0f07916773","permalink":"https://mlo-lab.github.io/publication/ruz-2025-decoding/","publishdate":"2026-02-10T21:39:54.809123Z","relpermalink":"/publication/ruz-2025-decoding/","section":"publication","summary":"","tags":[],"title":"Decoding heart failure subtypes with neural networks via differential explanation analysis","type":"publication"},{"authors":["Lukas Kuhn","Sari Sadiya","Jorg Schlotterer","Florian Buettner","Christin Seifert","Gemma Roig"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193377,"objectID":"eb40d4b65e89b5cbd72c4a675b9206f1","permalink":"https://mlo-lab.github.io/publication/kuhn-2025-efficientunsupervisedshortcutlearning/","publishdate":"2025-09-18T11:02:57.105803Z","relpermalink":"/publication/kuhn-2025-efficientunsupervisedshortcutlearning/","section":"publication","summary":"","tags":[],"title":"Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers","type":"publication"},{"authors":["Giuseppe Serra","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193377,"objectID":"a6d1e4383ce26b7abeaaa2028c78b174","permalink":"https://mlo-lab.github.io/publication/serra-2025-federated/","publishdate":"2025-09-18T11:02:57.466174Z","relpermalink":"/publication/serra-2025-federated/","section":"publication","summary":"","tags":[],"title":"Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond","type":"publication"},{"authors":["Nassim Walha","Sebastian G Gruber","Thomas Decker","Yinchong Yang","Alireza Javanmardi","Eyke Hüllermeier","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1764863150,"objectID":"597d34b8193d47d93a62b3d8daed7589","permalink":"https://mlo-lab.github.io/publication/walha-2025-fine/","publishdate":"2025-12-04T15:45:49.850021Z","relpermalink":"/publication/walha-2025-fine/","section":"publication","summary":"","tags":[],"title":"Fine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approach","type":"publication"},{"authors":["Giuseppe Serra","Ben Werner","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193377,"objectID":"e265267ae0d9ab1b2498c2bf8c9c9526","permalink":"https://mlo-lab.github.io/publication/serra-2025-how/","publishdate":"2025-09-18T11:02:57.672661Z","relpermalink":"/publication/serra-2025-how/","section":"publication","summary":"","tags":[],"title":"How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning","type":"publication"},{"authors":["Thomas Decker","Volker Tresp","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1770759594,"objectID":"8fcd8943cabbbbd890ecd2d45fd210d7","permalink":"https://mlo-lab.github.io/publication/decker-2025-improving/","publishdate":"2026-02-10T21:39:54.26336Z","relpermalink":"/publication/decker-2025-improving/","section":"publication","summary":"","tags":[],"title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","type":"publication"},{"authors":["Alexander Koebler","Christian Greisinger","Jan Paulus","Ingo Thon","Florian Buettner"],"categories":[],"content":"","date":1735689600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193376,"objectID":"536a7e32b696db39323aab1cdce3b0ab","permalink":"https://mlo-lab.github.io/publication/koebler-2025-towards/","publishdate":"2025-09-18T11:02:56.717643Z","relpermalink":"/publication/koebler-2025-towards/","section":"publication","summary":"","tags":[],"title":"Towards LVLM-Aided Alignment of Task-Specific Vision Models","type":"publication"},{"authors":["Florian Buettner"],"categories":[],"content":"We introduce GEMNA, a deep learning framework for mass spectrometry–based metabolomics that uses graph and edge embeddings with anomaly detection. GEMNA outperforms traditional tools in untargeted studies, producing clearer clusters and improved biological insights. Published in Scientific Reports\n","date":1732796773,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1732796773,"objectID":"8cc3b80196bd65a3e183987d9e08112e","permalink":"https://mlo-lab.github.io/post/buettner-metabolic-changes-graph-embeddings/","publishdate":"2024-11-28T13:26:13+01:00","relpermalink":"/post/buettner-metabolic-changes-graph-embeddings/","section":"post","summary":"We introduce GEMNA, a deep learning framework for mass spectrometry–based metabolomics that uses graph and edge embeddings with anomaly detection. GEMNA outperforms traditional tools in untargeted studies, producing clearer clusters and improved biological insights.","tags":[],"title":"Our latest work on deep learning for metabolomics just appeared in Scientific Reports!","type":"post"},{"authors":["Sebastian Gruber"],"categories":[],"content":"Our latest work presents a new approach to disentangle image generation performance by decomposing cosine similarity into cluster-level contributions using central kernel alignment. This allows us to quantify how different pixel regions contribute to overall image quality, enabling more fine-grained evaluation and improved explainability of generative models across real-world use cases. Published at the Interpretable AI: Past, Present and Future Workshop at NeurIPS 2024.\n","date":1725272872,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1725272872,"objectID":"ab364e5be0d23301d9e48d11df8b5771","permalink":"https://mlo-lab.github.io/post/gruber-diagnostic_image_generators/","publishdate":"2024-09-02T11:27:52+01:00","relpermalink":"/post/gruber-diagnostic_image_generators/","section":"post","summary":"Our latest work presents a new approach to disentangle image generation performance by decomposing cosine similarity into cluster-level contributions using central kernel alignment. This allows us to quantify how different pixel regions contribute to overall image quality, enabling more fine-grained evaluation and improved explainability of generative models across real-world use cases.","tags":[],"title":"Rounding out our research hat trick with new insights into interpretable image synthesis!","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"We introduce Explanatory Performance Estimation (XPE), a method that explains model behavior under feature shifts by linking performance changes to interpretable input characteristics using Optimal Transport and Shapley Values. This enables explanatory model monitoring across image, audio, and tabular data. Published in the Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.\n","date":1724507832,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1724507832,"objectID":"80ddb46fd3b0f19a2fb741a9b9fa1fb2","permalink":"https://mlo-lab.github.io/post/buettner-feature-shift-performance/","publishdate":"2024-08-24T14:57:12+01:00","relpermalink":"/post/buettner-feature-shift-performance/","section":"post","summary":"We introduce Explanatory Performance Estimation (XPE), a method that explains model behavior under feature shifts by linking performance changes to interpretable input characteristics using Optimal Transport and Shapley Values. This enables explanatory model monitoring across image, audio, and tabular data.","tags":[],"title":"Our framework for explanatory model monitoring was featured at KDD","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"We show how integrating human gaze information aligns human and machine attention, improving model robustness and explainability. Demonstrated on real-world visual quality inspection, the approach highlights the value of explicit human knowledge in training trustworthy AI. Published at the International Conference on Human-Computer Interaction.\n","date":1722259314,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1722259314,"objectID":"e87090c831d96b9ac4883edc70255da7","permalink":"https://mlo-lab.github.io/post/buettner-expert-eyes-algning-industrial-ai/","publishdate":"2024-07-29T14:21:54+01:00","relpermalink":"/post/buettner-expert-eyes-algning-industrial-ai/","section":"post","summary":"We show how integrating human gaze information aligns human and machine attention, improving model robustness and explainability. Demonstrated on real-world visual quality inspection, the approach highlights the value of explicit human knowledge in training trustworthy AI.","tags":[],"title":"Our latest paper at HCI explores how human gaze can make AI more interpretable and reliable!","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"We improve the quality of feature attributions by optimally combining multiple explanation methods. Our convex-combination strategy enhances robustness and faithfulness, consistently outperforming individual methods and baselines across architectures. Published at the International Conference on Machine Learning.\n","date":1720358060,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1720358060,"objectID":"f90347e45e1f2fb26b67c7a43b7011b7","permalink":"https://mlo-lab.github.io/post/buettner-provably-better-explanations/","publishdate":"2024-07-07T14:14:20+01:00","relpermalink":"/post/buettner-provably-better-explanations/","section":"post","summary":"We improve the quality of feature attributions by optimally combining multiple explanation methods. Our convex-combination strategy enhances robustness and faithfulness, consistently outperforming individual methods and baselines across architectures. Published at the International Conference on Machine Learning.","tags":[],"title":"New at ICML: improving the stability of feature attributions through optimal combinations!","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"This work compiles a domain-agnostic taxonomy of pitfalls in validation metrics, based on a multistage Delphi process and community feedback. It offers practical guidance to improve evaluation practices across application domains. Published in Nature Methods.\n","date":1707744263,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1707744263,"objectID":"f4eb5ada6b488a7f80a3d2b4fbf6b2e8","permalink":"https://mlo-lab.github.io/post/buettner-metric-related-pitfalls/","publishdate":"2024-02-12T14:24:23+01:00","relpermalink":"/post/buettner-metric-related-pitfalls/","section":"post","summary":"This work compiles a domain-agnostic taxonomy of pitfalls in validation metrics, based on a multistage Delphi process and community feedback. It offers practical guidance to improve evaluation practices across application domains.","tags":[],"title":"Advancing global understanding of evaluation metrics — now published in Nature Methods!","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"We present Metrics Reloaded, a comprehensive framework for problem-aware selection of evaluation metrics in biomedical image analysis. Developed through a large international Delphi process, it introduces the concept of a problem fingerprint to guide researchers toward meaningful and domain-relevant validation. Published in Nature Methods.\n","date":1707743416,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1707743416,"objectID":"9078a4d212925e99aae24f828abe4c61","permalink":"https://mlo-lab.github.io/post/buettner-metrics-reloaded-image-validation/","publishdate":"2024-02-12T14:10:16+01:00","relpermalink":"/post/buettner-metrics-reloaded-image-validation/","section":"post","summary":"We present Metrics Reloaded, a comprehensive framework for problem-aware selection of evaluation metrics in biomedical image analysis. Developed through a large international Delphi process, it introduces the concept of a problem fingerprint to guide researchers toward meaningful and domain-relevant validation.","tags":[],"title":"Metrics Reloaded — now published in Nature Methods.","type":"post"},{"authors":["Sebastian Gregor Gruber","Florian Buettner"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193378,"objectID":"5262dfb0cb82eb4af0e2e85286bd8e79","permalink":"https://mlo-lab.github.io/publication/gruber-2024-bias/","publishdate":"2025-09-18T11:02:58.721865Z","relpermalink":"/publication/gruber-2024-bias/","section":"publication","summary":"","tags":["highlight"],"title":"A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models","type":"publication"},{"authors":["Teodora Popordanoska","Sebastian Gregor Gruber","Aleksei Tiulpin","Florian Buettner","Matthew B Blaschko"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193379,"objectID":"38edf6fa74bc910215ef007530a68e61","permalink":"https://mlo-lab.github.io/publication/popordanoska-2024-consistent/","publishdate":"2025-09-18T11:02:59.298551Z","relpermalink":"/publication/popordanoska-2024-consistent/","section":"publication","summary":"","tags":[],"title":"Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors","type":"publication"},{"authors":["Sebastian G Gruber","Pascal Tobias Ziegler","Florian Buettner"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193378,"objectID":"1535b56ed5a0ea207fc2fa4fae2e2659","permalink":"https://mlo-lab.github.io/publication/gruber-2024-disentangling/","publishdate":"2025-09-18T11:02:58.50253Z","relpermalink":"/publication/gruber-2024-disentangling/","section":"publication","summary":"","tags":[],"title":"Disentangling Mean Embeddings for Better Diagnostics of Image Generators","type":"publication"},{"authors":["Thomas Decker","Alexander Koebler","Michael Lebacher","Ingo Thon","Volker Tresp","Florian Buettner"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193378,"objectID":"5c71471576e6644b0ed25caf99af64d0","permalink":"https://mlo-lab.github.io/publication/decker-2024-explanatory/","publishdate":"2025-09-18T11:02:58.293788Z","relpermalink":"/publication/decker-2024-explanatory/","section":"publication","summary":"","tags":[],"title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","type":"publication"},{"authors":["Edwin Alvarez-Mamani","Florian Buettner","Cesar A Beltran-Castanon","Alfredo J Ibanez"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193378,"objectID":"97fd7476e91707f365009ab20ef0da22","permalink":"https://mlo-lab.github.io/publication/alvarez-2024-exploratory/","publishdate":"2025-09-18T11:02:57.891874Z","relpermalink":"/publication/alvarez-2024-exploratory/","section":"publication","summary":"","tags":[],"title":"Exploratory analysis of metabolic changes using mass spectrometry data and graph embeddings","type":"publication"},{"authors":["Lena Maier-Hein","Annika Reinke","Patrick Godau","Minu D Tizabi","Florian Buettner","Evangelia Christodoulou","Ben Glocker","Fabian Isensee","Jens Kleesiek","Michal Kozubek"," others"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193379,"objectID":"a583f0ce9751cf3b27932bc0d65e459a","permalink":"https://mlo-lab.github.io/publication/maier-2024-metrics/","publishdate":"2025-09-18T11:02:59.146219Z","relpermalink":"/publication/maier-2024-metrics/","section":"publication","summary":"","tags":["highlight"],"title":"Metrics reloaded: recommendations for image analysis validation","type":"publication"},{"authors":["Thomas Decker","Ananta R Bhattarai","Jindong Gu","Volker Tresp","Florian Buettner"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193378,"objectID":"d8f235822bcc42275e1b2da3e950ad42","permalink":"https://mlo-lab.github.io/publication/decker-2024-provably/","publishdate":"2025-09-18T11:02:58.089498Z","relpermalink":"/publication/decker-2024-provably/","section":"publication","summary":"","tags":[],"title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","type":"publication"},{"authors":["Alexander Koebler","Christian Greisinger","Jan Paulus","Ingo Thon","Florian Buettner"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193379,"objectID":"d3d2ad2d2ea82cf6cfc00640b6efff66","permalink":"https://mlo-lab.github.io/publication/koebler-2024-through/","publishdate":"2025-09-18T11:02:58.926762Z","relpermalink":"/publication/koebler-2024-through/","section":"publication","summary":"","tags":[],"title":"Through the Eyes of the Expert: Aligning Human and Machine Attention for Industrial AI","type":"publication"},{"authors":["Annika Reinke","Minu D Tizabi","Michael Baumgartner","Matthias Eisenmann","Doreen Heckmann-Nötzel","A Emre Kavur","Tim Rädsch","Carole H Sudre","Laura Acion","Michela Antonelli"," others"],"categories":[],"content":"","date":1704067200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193379,"objectID":"c19c48c06594346dd68e86782c943076","permalink":"https://mlo-lab.github.io/publication/reinke-2024-understanding/","publishdate":"2025-09-18T11:02:59.468437Z","relpermalink":"/publication/reinke-2024-understanding/","section":"publication","summary":"","tags":[],"title":"Understanding metric-related pitfalls in image analysis validation","type":"publication"},{"authors":["Sebastian Gruber"],"categories":[],"content":"We present a general method for consistent and asymptotically unbiased estimation of proper calibration errors and refinement terms. Introducing the Kullback–Leibler calibration error, we reveal its connection to f-divergences and information monotonicity in neural networks. Published at the International Conference on Artificial Intelligence and Statistics.\n","date":1702548852,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1702548852,"objectID":"c21a26b71b39a0dabac78d4cb71dcb21","permalink":"https://mlo-lab.github.io/post/gruber-unbiased-calibration-errors/","publishdate":"2023-12-14T11:14:12+01:00","relpermalink":"/post/gruber-unbiased-calibration-errors/","section":"post","summary":"We present a general method for consistent and asymptotically unbiased estimation of proper calibration errors and refinement terms. Introducing the Kullback–Leibler calibration error, we reveal its connection to f-divergences and information monotonicity in neural networks.","tags":[],"title":"Bridging calibration and refinement — our latest work at AISTATS!","type":"post"},{"authors":["Sebastian Gruber"],"categories":[],"content":"Our latest work introduces the first bias–variance–covariance decomposition for kernel scores, providing a unified framework for uncertainty estimation in generative models. We show how kernel-based entropy and variance capture uncertainty across image, audio, and language generation — even in closed-source models. Published at the International Conference on Machine Learning.\n","date":1696844056,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1696844056,"objectID":"f518dbe674beb8c340dca4ce45937785","permalink":"https://mlo-lab.github.io/post/gruber-kernel-scores/","publishdate":"2023-10-09T10:34:16+01:00","relpermalink":"/post/gruber-kernel-scores/","section":"post","summary":"Our latest work introduces the first bias–variance–covariance decomposition for kernel scores, providing a unified framework for uncertainty estimation in generative models. We show how kernel-based entropy and variance capture uncertainty across image, audio, and language generation — even in closed-source models.","tags":[],"title":"Our kernel uncertainty framework is in at ICML!","type":"post"},{"authors":["Arber Qoku"],"categories":["publication"],"content":"Paper accepted! Our latest work on developing a versatile framework for rapid prototyping and training of a wide range of factor analysis models for multi-omics data got accepted at this year\u0026rsquo;s ICML workshop on computational biology!\n","date":1690316183,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1690316183,"objectID":"77c3d07a5d2737eefc271bb569770a83","permalink":"https://mlo-lab.github.io/post/qoku-cellij-icml-23/","publishdate":"2023-07-25T22:16:23+02:00","relpermalink":"/post/qoku-cellij-icml-23/","section":"post","summary":"Paper accepted! Our latest work on developing a versatile framework for rapid prototyping and training of a wide range of factor analysis models for multi-omics data got accepted at this year\u0026rsquo;s ICML workshop on computational biology!","tags":[],"title":"Paper accepted at ICML CompBio 2023!","type":"post"},{"authors":["Florian Buettner"],"categories":[],"content":"With 2 million Euros in funding from the European Research Council, we will be developing AI models to support doctors in the diagnosis and treatment of cancer. Read more!\n","date":1674396986,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1674396986,"objectID":"a686a411e76755aa97e630dde08a92de","permalink":"https://mlo-lab.github.io/post/buettner-erc-grant-23/","publishdate":"2023-01-22T16:16:26+02:00","relpermalink":"/post/buettner-erc-grant-23/","section":"post","summary":"With 2 million Euros in funding from the European Research Council, we will be developing AI models to support doctors in the diagnosis and treatment of cancer. Read more!","tags":[],"title":"ERC Consolidator Grant for Florian!","type":"post"},{"authors":["Sebastian Gruber"],"categories":["publication"],"content":"Paper accepted! Our latest work on a general bias-variance decomposition for proper scores got accepted at this year\u0026rsquo;s AISTATS conference!\n","date":1674224163,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1674224163,"objectID":"f98587f6a66f2bd2dd07d607fa6f1042","permalink":"https://mlo-lab.github.io/post/gruber-uncertainty-aistats-23/","publishdate":"2023-01-20T16:16:03+02:00","relpermalink":"/post/gruber-uncertainty-aistats-23/","section":"post","summary":"Paper accepted! Our latest work on a general bias-variance decomposition for proper scores got accepted at this year\u0026rsquo;s AISTATS conference!","tags":[],"title":"Paper accepted at AISTATS 2023!","type":"post"},{"authors":["Arber Qoku"],"categories":["publication"],"content":"Paper accepted! Our latest work on multi-view latent variable models with structured sparsity got accepted at this year\u0026rsquo;s AISTATS conference!\n","date":1674224147,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1674224147,"objectID":"f37c0759916b527b57909c1370da770d","permalink":"https://mlo-lab.github.io/post/qoku-encoding-aistats-23/","publishdate":"2023-01-20T16:15:47+02:00","relpermalink":"/post/qoku-encoding-aistats-23/","section":"post","summary":"Paper accepted! Our latest work on multi-view latent variable models with structured sparsity got accepted at this year\u0026rsquo;s AISTATS conference!","tags":[],"title":"Paper accepted at AISTATS 2023!","type":"post"},{"authors":["Florian Buettner"],"categories":["publication"],"content":"Paper accepted! Our latest work on quantifying uncertainty under real-world conditions got accepted at this year\u0026rsquo;s AAAI conference on artificial intelligence!\n","date":1673705705,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1673705705,"objectID":"a9a0a38a7781c390f8ec3eef9839f68d","permalink":"https://mlo-lab.github.io/post/hekler-test-aaai-23/","publishdate":"2023-01-14T16:15:05+02:00","relpermalink":"/post/hekler-test-aaai-23/","section":"post","summary":"Paper accepted! Our latest work on quantifying uncertainty under real-world conditions got accepted at this year\u0026rsquo;s AAAI conference on artificial intelligence!","tags":[],"title":"Paper accepted at AAAI 2023!","type":"post"},{"authors":["Arber Qoku","Florian Buettner"],"categories":[],"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193380,"objectID":"261e5e2d5c09b1405810a579d71be054","permalink":"https://mlo-lab.github.io/publication/qoku-2023-encoding/","publishdate":"2025-09-18T11:03:00.088158Z","relpermalink":"/publication/qoku-2023-encoding/","section":"publication","summary":"","tags":["highlight"],"title":"Encoding domain knowledge in multi-view latent variable models: A bayesian approach with structured sparsity","type":"publication"},{"authors":["Arber Qoku","Nikoletta Katsaouni","Nadine Flinner","Florian Buettner","Marcel H Schulz"],"categories":[],"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193380,"objectID":"3ecdc01b8ef17e9512bbb5d278c74088","permalink":"https://mlo-lab.github.io/publication/qoku-2023-multimodal/","publishdate":"2025-09-18T11:03:00.269951Z","relpermalink":"/publication/qoku-2023-multimodal/","section":"publication","summary":"","tags":[],"title":"Multimodal analysis methods in predictive biomedicine","type":"publication"},{"authors":["Achim Hekler","Titus J Brinker","Florian Buettner"],"categories":[],"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193380,"objectID":"47c98dcf9847d06392a3402af3b5da56","permalink":"https://mlo-lab.github.io/publication/hekler-2023-test/","publishdate":"2025-09-18T11:02:59.888782Z","relpermalink":"/publication/hekler-2023-test/","section":"publication","summary":"","tags":["highlight"],"title":"Test Time Augmentation Meets Post-hoc Calibration: Uncertainty Quantification under Real-World Conditions","type":"publication"},{"authors":["Sebastian Gruber","Florian Buettner"],"categories":[],"content":"","date":1672531200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193379,"objectID":"2a3144092ef32b5717661f5afa2c5311","permalink":"https://mlo-lab.github.io/publication/gruber-2023-uncertainty/","publishdate":"2025-09-18T11:02:59.672371Z","relpermalink":"/publication/gruber-2023-uncertainty/","section":"publication","summary":"","tags":[],"title":"Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition","type":"publication"},{"authors":["Florian Buettner"],"categories":["publication"],"content":"Paper accepted! Our latest work on boosting the expressive power in post-hoc uncertainty calibration got accepted at this year\u0026rsquo;s ECCV!\n","date":1657293229,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1657293229,"objectID":"32019fc16bec9d451041797f5133ea88","permalink":"https://mlo-lab.github.io/post/tomani-eccv-22/","publishdate":"2022-07-08T17:13:49+02:00","relpermalink":"/post/tomani-eccv-22/","section":"post","summary":"Paper accepted! Our latest work on boosting the expressive power in post-hoc uncertainty calibration got accepted at this year\u0026rsquo;s ECCV!","tags":[],"title":"Paper accepted at ECCV 2022!","type":"post"},{"authors":["Florian Buettner"],"categories":["publication"],"content":"Paper accepted! Our latest work on characterizing proteogenomic subtypes of AML got accepted at this year\u0026rsquo;s Cancer Cell!\n","date":1657290817,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1657290817,"objectID":"3663dcedab9c0aa6bd726d291c70cf1f","permalink":"https://mlo-lab.github.io/post/wolf-aml-cancercell-22/","publishdate":"2022-07-08T16:33:37+02:00","relpermalink":"/post/wolf-aml-cancercell-22/","section":"post","summary":"Paper accepted! Our latest work on characterizing proteogenomic subtypes of AML got accepted at this year\u0026rsquo;s Cancer Cell!","tags":[],"title":"Paper accepted at Cancer Cell 2022!","type":"post"},{"authors":["Sebastian Gruber","Florian Buettner"],"categories":[],"content":"","date":1640995200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193380,"objectID":"7b40e21973fa89f687ec47505fe1b908","permalink":"https://mlo-lab.github.io/publication/gruber-2022-better/","publishdate":"2025-09-18T11:03:00.684686Z","relpermalink":"/publication/gruber-2022-better/","section":"publication","summary":"","tags":[],"title":"Better uncertainty calibration via proper scores for classification and beyond","type":"publication"},{"authors":["Adele M Nicolas","Marina Pesic","Esther Engel","Paul K Ziegler","Markus Diefenhardt","Kilian B Kennel","Florian Buettner","Claire Conche","Valentina Petrocelli","Eiman Elwakeel"," others"],"categories":[],"content":"","date":1640995200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193381,"objectID":"9c8f947c36506c939420734145d01554","permalink":"https://mlo-lab.github.io/publication/nicolas-2022-inflammatory/","publishdate":"2025-09-18T11:03:01.094382Z","relpermalink":"/publication/nicolas-2022-inflammatory/","section":"publication","summary":"","tags":[],"title":"Inflammatory fibroblasts mediate resistance to neoadjuvant therapy in rectal cancer","type":"publication"},{"authors":["Fernando Anjos-Afonso","Florian Buettner","Syed A Mian","Hefin Rhys","Jimena Perez-Lloret","Manuel Garcia-Albornoz","Namrata Rastogi","Linda Ariza-McNaughton","Dominique Bonnet"],"categories":[],"content":"","date":1640995200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193380,"objectID":"0bf87206eb3d20733207971ebce6822b","permalink":"https://mlo-lab.github.io/publication/anjos-2022-single/","publishdate":"2025-09-18T11:03:00.484533Z","relpermalink":"/publication/anjos-2022-single/","section":"publication","summary":"","tags":[],"title":"Single cell analyses identify a highly regenerative and homogenous human CD34+ hematopoietic stem cell population","type":"publication"},{"authors":["Ashok Kumar Jayavelu","Sebastian Wolf","Florian Buettner","Gabriela Alexe","Björn Häupl","Federico Comoglio","Constanze Schneider","Carmen Doebele","Dominik C Fuhrmann","Sebastian Wagner"," others"],"categories":[],"content":"","date":1640995200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193381,"objectID":"45cf3f2f9a91e3e41f15d688d80c084b","permalink":"https://mlo-lab.github.io/publication/jayavelu-2022-proteogenomic/","publishdate":"2025-09-18T11:03:00.881881Z","relpermalink":"/publication/jayavelu-2022-proteogenomic/","section":"publication","summary":"","tags":[],"title":"The proteogenomic subtypes of acute myeloid leukemia","type":"publication"},{"authors":["Arber Qoku"],"categories":["publication"],"content":"Latent variable models are powerful statistical tools that can uncover relevant variation between patients or cells, by inferring unobserved hidden states from observable high-dimensional data. A major shortcoming of current methods, however, is their inability to learn sparse and interpretable hidden states. Additionally, in settings where partial knowledge on the latent structure of the data is readily available, a statistically sound integration of prior information into current methods is challenging. To address these issues, we propose spex-LVM, a factorial latent variable model with sparse priors to encourage the inference of explainable factors driven by domain-relevant information. spex-LVM utilizes existing knowledge of curated biomedical pathways to automatically assign annotated attributes to latent factors, yielding interpretable results tailored to the corresponding domain of interest. Evaluations on simulated and real single-cell RNA-seq datasets demonstrate that our model robustly identifies relevant structure in an inherently explainable manner, distinguishes technical noise from sources of biomedical variation, and provides data-driven adaptations of existing pathway annotations.\n","date":1626186604,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1626186604,"objectID":"a73f7168a2542cd00543b60cf13c496f","permalink":"https://mlo-lab.github.io/post/spexlvm-kdd/","publishdate":"2021-07-13T16:30:04+02:00","relpermalink":"/post/spexlvm-kdd/","section":"post","summary":"Latent variable models are powerful statistical tools that can uncover relevant variation between patients or cells, by inferring unobserved hidden states from observable high-dimensional data. A major shortcoming of current methods, however, is their inability to learn sparse and interpretable hidden states.","tags":[],"title":"Paper accepted at KDD 2021!","type":"post"},{"authors":["Florian Buettner"],"categories":["publication"],"content":"Paper accepted! Our latest work on multi-output Gaussian Process Latent Variable models got accepted at this year\u0026rsquo;s UAI!\n","date":1621522799,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1621522799,"objectID":"001f4cd90c3e82052b4129856f0785ae","permalink":"https://mlo-lab.github.io/post/paper-uai-yang/","publishdate":"2021-05-20T16:59:59+02:00","relpermalink":"/post/paper-uai-yang/","section":"post","summary":"Paper accepted! Our latest work on multi-output Gaussian Process Latent Variable models got accepted at this year\u0026rsquo;s UAI!","tags":[],"title":"Paper accepted at UAI!","type":"post"},{"authors":null,"categories":["Events"],"content":"We organize a workshop at this year\u0026rsquo;s KDD\nCheck out the workshop website here. Paper submission deadline is 10th May 2021.\nOverview Healthcare is, traditionally, a knowledge-driven enterprise with an enormous amount of data - both structured and unstructured. These data can impact positively on the development of data-driven health care including precision medicine and precision public health. In recent years, large scale medical/clinical datasets, such as “omics” data and radiology reports are increasingly available. We have also witnessed an increasing number of successful AI/ML applications using such datasets to address problems such as drug repurposing and preliminary screening of radiology reports. To facilitate the adoption of such AI/ML in practice, we have simultaneously witnessed an increasing adoption/innovation of using explainability methods to analyze/present AI for Health. In this deep learning era, What is the current status of AI/ML applications in healthcare? What are the standard methods of explaining such AI models for healthcare? What are the roles of causality in AI/ML practices? What are the state-of-the-art developments in causal AI in health and health care domains? What are the limitations and how are the different facets of trust and explanations (see figure 1 below) being addressed in practice? Can knowledge-backed AI lead to more robust and interpretable models? How do data scientists and physicians apply this knowledge in collaboration and via human-centered AI approaches to further the field and improve healthcare? How are regulatory requirements for transparency and trustworthiness of models and data privacy being defined and how can they be fulfilled? After witnessing so many great achievements from deep learning lately, we propose to invite world-leading experts from both data science and healthcare to discuss and debate the path forward for practical applications of AI/ML in healthcare, including demos, early work, and critiques on the current state and the path forward for explainability and trustworthiness in AI. More specifically, we plan to attract high-quality original research from emerging areas with significant implications in healthcare and invite open discussions on controversial yet crucial topics regarding healthcare transformation\nKey dates  Paper Submission opens: Apr 15, 2021 Paper Submission deadline: May 10, 2021 Acceptance Notice: Jun 10, 2021 Workshop Date: Aug 14, 2021  All deadlines correspond to 11:59 PM Hawaii Standard Time ( HST).\n","date":1618272e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1618272e3,"objectID":"13e6a3ff66cf703a79bfb563cc744c89","permalink":"https://mlo-lab.github.io/post/workshop/","publishdate":"2021-04-13T00:00:00Z","relpermalink":"/post/workshop/","section":"post","summary":"We organize a workshop at this year\u0026rsquo;s KDD\nCheck out the workshop website here. Paper submission deadline is 10th May 2021.\nOverview Healthcare is, traditionally, a knowledge-driven enterprise with an enormous amount of data - both structured and unstructured.","tags":null,"title":"Workshop on XAI and Trustworthiness in Healthcare at KDD 2021!","type":"post"},{"authors":["Xudong Sun","Florian Buettner"],"categories":[],"content":"","date":1609459200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193381,"objectID":"96038f1325dcb555eb8b5fccd97598ad","permalink":"https://mlo-lab.github.io/publication/sun-2021-hierarchical/","publishdate":"2025-09-18T11:03:01.278976Z","relpermalink":"/publication/sun-2021-hierarchical/","section":"publication","summary":"","tags":[],"title":"Hierarchical Domain Invariant Variational Auto-Encoding with weak domain supervision","type":"publication"},{"authors":["Yinchong Yang","Florian Buettner"],"categories":[],"content":"","date":1609459200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193382,"objectID":"46140514097e259ffb9795e28ccaaf97","permalink":"https://mlo-lab.github.io/publication/yang-2021-multi/","publishdate":"2025-09-18T11:03:01.968698Z","relpermalink":"/publication/yang-2021-multi/","section":"publication","summary":"","tags":[],"title":"Multi-output Gaussian Processes for uncertainty-aware recommender systems","type":"publication"},{"authors":["Christian Tomani","Daniel Cremers","Florian Buettner"],"categories":[],"content":"","date":1609459200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193381,"objectID":"c50670d510b9b6bdc4c1ba202de00574","permalink":"https://mlo-lab.github.io/publication/tomani-2021-parameterized/","publishdate":"2025-09-18T11:03:01.729261Z","relpermalink":"/publication/tomani-2021-parameterized/","section":"publication","summary":"","tags":[],"title":"Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration","type":"publication"},{"authors":["Christian Tomani","Florian Buettner"],"categories":[],"content":"","date":1609459200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193381,"objectID":"b69dd86c894ce43f841d1eaf0ec84f7e","permalink":"https://mlo-lab.github.io/publication/tomani-2021-towards/","publishdate":"2025-09-18T11:03:01.483392Z","relpermalink":"/publication/tomani-2021-towards/","section":"publication","summary":"","tags":[],"title":"Towards trustworthy predictions from deep neural networks with fast adversarial calibration","type":"publication"},{"authors":["Christian Tomani","Sebastian Gruber","Muhammed Ebrar Erdem","Daniel Cremers","Florian Buettner"],"categories":[],"content":"","date":1577836800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193382,"objectID":"beac4119a0020f9849411b0ab3eefc64","permalink":"https://mlo-lab.github.io/publication/tomani-post-hoc-2020/","publishdate":"2025-09-18T11:03:02.61415Z","relpermalink":"/publication/tomani-post-hoc-2020/","section":"publication","summary":"","tags":[],"title":"Post-hoc Uncertainty Calibration for Domain Drift Scenarios","type":"publication"},{"authors":["Anna SE Cuomo","Daniel D. Seaton","Davis J. McCarthy","Iker Martinez","Marc Jan Bonder","Jose Garcia-Bernardo","Shradha Amatya","Pedro Madrigal","Abigail Isaacson","Florian Buettner"],"categories":[],"content":"","date":1577836800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193382,"objectID":"5b61aef1beb93186333ee4573b000753","permalink":"https://mlo-lab.github.io/publication/cuomo-single-cell-2020/","publishdate":"2025-09-18T11:03:02.166023Z","relpermalink":"/publication/cuomo-single-cell-2020/","section":"publication","summary":"","tags":[],"title":"Single-cell RNA-sequencing of differentiating iPS cells reveals dynamic genetic effects on gene expression","type":"publication"},{"authors":["Yushan Liu","Markus M. Geipel","Christoph Tietz","Florian Buettner"],"categories":[],"content":"","date":1577836800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193382,"objectID":"28e5302dfa54e818730cf02dc502c206","permalink":"https://mlo-lab.github.io/publication/liu-timely-2020/","publishdate":"2025-09-18T11:03:02.384676Z","relpermalink":"/publication/liu-timely-2020/","section":"publication","summary":"","tags":[],"title":"TIMELY: Improving Labeling Consistency in Medical Imaging for Cell Type Classification","type":"publication"},{"authors":["Ben GL Vanneste","Florian Buettner","Michael Pinkawa","Philippe Lambin","Aswin L. Hoffmann"],"categories":[],"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"71be0fc2a912f0b8d855702713f239d5","permalink":"https://mlo-lab.github.io/publication/vanneste-ano-rectal-2019/","publishdate":"2025-09-18T11:03:03.374321Z","relpermalink":"/publication/vanneste-ano-rectal-2019/","section":"publication","summary":"","tags":[],"title":"Ano-rectal wall dose-surface maps localize the dosimetric benefit of hydrogel rectum spacers in prostate cancer radiotherapy","type":"publication"},{"authors":["Pankaj Gupta","Yatin Chaudhary","Florian Buettner","Hinrich Schütze"],"categories":[],"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"0cc769d3590fbe31ab1c363f00e8f891","permalink":"https://mlo-lab.github.io/publication/gupta-document-2019/","publishdate":"2025-09-18T11:03:03.027744Z","relpermalink":"/publication/gupta-document-2019/","section":"publication","summary":"","tags":[],"title":"Document informed neural autoregressive topic models with distributional prior","type":"publication"},{"authors":["Julia Tischler","Wolfram H. Gruhn","John Reid","Edward Allgeyer","Florian Buettner","Carsten Marr","Fabian Theis","Ben D. Simons","Lorenz Wernisch","M. Azim Surani"],"categories":[],"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"de1f01a1694ac862bb06c0e437922f27","permalink":"https://mlo-lab.github.io/publication/tischler-metabolic-2019/","publishdate":"2025-09-18T11:03:03.212221Z","relpermalink":"/publication/tischler-metabolic-2019/","section":"publication","summary":"","tags":[],"title":"Metabolic regulation of pluripotency and germ cell fate through α-ketoglutarate","type":"publication"},{"authors":["Ricard Argelaguet","Hisham Mohammed","Stephen J. Clark","L. Carine Stapel","Christel Krueger","Chantriolnt-Andreas Kapourani","Yunlong Xiang","Courtney Hanna","Sebastien Smallwood","Ximena Ibarra-Soria"],"categories":[],"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"1c865db93d392bef845a954dc53c626e","permalink":"https://mlo-lab.github.io/publication/argelaguet-single-2019/","publishdate":"2025-09-18T11:03:02.825388Z","relpermalink":"/publication/argelaguet-single-2019/","section":"publication","summary":"","tags":[],"title":"Single cell multi-omics profiling reveals a hierarchical epigenetic landscape during mammalian germ layer specification","type":"publication"},{"authors":null,"categories":null,"content":"Anbieter der Internetpräsenz Prof. Dr. Florian Buettner\nDeutsches Konsortium für Translationale Krebsforschung (DKTK)\nDeutsches Krebsforschungszentrum\nGoethe University Frankfurt\nTheodor-Stern-Kai 7\n60596 Frankfurt am Main\nKontakt Telefon: +49 696 30186212\nE-Mail: florian.buettner|dkfz-heidelberg.de\nStreitschlichtung Die Europäische Kommission stellt eine Plattform zur Online-Streitbeilegung (OS) bereit: https://ec.europa.eu/consumers/odr. Unsere E-Mail-Adresse finden Sie oben im Impressum.\nWir sind nicht bereit oder verpflichtet, an Streitbeilegungsverfahren vor einer Verbraucherschlichtungsstelle teilzunehmen.\nHaftung für Inhalte Als Diensteanbieter sind wir gemäß § 7 Abs.1 TMG für eigene Inhalte auf diesen Seiten nach den allgemeinen Gesetzen verantwortlich. Nach §§ 8 bis 10 TMG sind wir als Diensteanbieter jedoch nicht verpflichtet, übermittelte oder gespeicherte fremde Informationen zu überwachen oder nach Umständen zu forschen, die auf eine rechtswidrige Tätigkeit hinweisen.\nVerpflichtungen zur Entfernung oder Sperrung der Nutzung von Informationen nach den allgemeinen Gesetzen bleiben hiervon unberührt. Eine diesbezügliche Haftung ist jedoch erst ab dem Zeitpunkt der Kenntnis einer konkreten Rechtsverletzung möglich. Bei Bekanntwerden von entsprechenden Rechtsverletzungen werden wir diese Inhalte umgehend entfernen.\nHaftung für Links Unser Angebot enthält Links zu externen Websites Dritter, auf deren Inhalte wir keinen Einfluss haben. Deshalb können wir für diese fremden Inhalte auch keine Gewähr übernehmen. Für die Inhalte der verlinkten Seiten ist stets der jeweilige Anbieter oder Betreiber der Seiten verantwortlich. Die verlinkten Seiten wurden zum Zeitpunkt der Verlinkung auf mögliche Rechtsverstöße überprüft. Rechtswidrige Inhalte waren zum Zeitpunkt der Verlinkung nicht erkennbar.\nEine permanente inhaltliche Kontrolle der verlinkten Seiten ist jedoch ohne konkrete Anhaltspunkte einer Rechtsverletzung nicht zumutbar. Bei Bekanntwerden von Rechtsverletzungen werden wir derartige Links umgehend entfernen.\nUrheberrecht Die durch die Seitenbetreiber erstellten Inhalte und Werke auf diesen Seiten unterliegen dem deutschen Urheberrecht. Die Vervielfältigung, Bearbeitung, Verbreitung und jede Art der Verwertung außerhalb der Grenzen des Urheberrechtes bedürfen der schriftlichen Zustimmung des jeweiligen Autors bzw. Erstellers. Downloads und Kopien dieser Seite sind nur für den privaten, nicht kommerziellen Gebrauch gestattet.\nSoweit die Inhalte auf dieser Seite nicht vom Betreiber erstellt wurden, werden die Urheberrechte Dritter beachtet. Insbesondere werden Inhalte Dritter als solche gekennzeichnet. Sollten Sie trotzdem auf eine Urheberrechtsverletzung aufmerksam werden, bitten wir um einen entsprechenden Hinweis. Bei Bekanntwerden von Rechtsverletzungen werden wir derartige Inhalte umgehend entfernen.\n","date":1530140400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1530140400,"objectID":"9b10c1f64082d3869fd4cb1f85809430","permalink":"https://mlo-lab.github.io/terms/","publishdate":"2018-06-28T00:00:00+01:00","relpermalink":"/terms/","section":"","summary":"Anbieter der Internetpräsenz Prof. Dr. Florian Buettner\nDeutsches Konsortium für Translationale Krebsforschung (DKTK)\nDeutsches Krebsforschungszentrum\nGoethe University Frankfurt\nTheodor-Stern-Kai 7\n60596 Frankfurt am Main\nKontakt Telefon: +49 696 30186212\nE-Mail: florian.","tags":null,"title":"Impressum","type":"page"},{"authors":["Hubert S. Gabryś","Florian Buettner","Florian Sterzing","Henrik Hauswald","Mark Bangert"],"categories":[],"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"16c42fc9b13c5d8e17453d5055ef4676","permalink":"https://mlo-lab.github.io/publication/gabrys-design-2018/","publishdate":"2025-09-18T11:03:03.779721Z","relpermalink":"/publication/gabrys-design-2018/","section":"publication","summary":"","tags":[],"title":"Design and selection of machine learning methods using radiomics and dosiomics for normal tissue complication probability modeling of xerostomia","type":"publication"},{"authors":["Pankaj Gupta","Florian Buettner","Hinrich Schütze"],"categories":[],"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193384,"objectID":"7f93f5afe5eec27e600e20a03f414b10","permalink":"https://mlo-lab.github.io/publication/gupta-document-2018/","publishdate":"2025-09-18T11:03:03.985701Z","relpermalink":"/publication/gupta-document-2018/","section":"publication","summary":"","tags":[],"title":"Document informed neural autoregressive topic models","type":"publication"},{"authors":["Ricard Argelaguet","Britta Velten","Damien Arnol","Sascha Dietrich","Thorsten Zenz","John C. Marioni","Florian Buettner","Wolfgang Huber","Oliver Stegle"],"categories":[],"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193383,"objectID":"553faec625fca075413fb90c42e9892e","permalink":"https://mlo-lab.github.io/publication/argelaguet-multi-omics-2018/","publishdate":"2025-09-18T11:03:03.57801Z","relpermalink":"/publication/argelaguet-multi-omics-2018/","section":"publication","summary":"","tags":[],"title":"Multi-Omics Factor Analysis—a framework for unsupervised integration of multi-omics data sets","type":"publication"},{"authors":["Pankaj Gupta","Yatin Chaudhary","Florian Buettner","Hinrich Schütze"],"categories":[],"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193384,"objectID":"bf1b108d7b8d74f0bfce1146d9f69f11","permalink":"https://mlo-lab.github.io/publication/gupta-texttovec-2018-1/","publishdate":"2025-09-18T11:03:04.412995Z","relpermalink":"/publication/gupta-texttovec-2018-1/","section":"publication","summary":"","tags":[],"title":"texttovec: Deep contextualized neural autoregressive models of language with distributed compositional prior","type":"publication"},{"authors":["Pankaj Gupta","Yatin Chaudhary","Florian Buettner","Hinrich Schütze"],"categories":[],"content":"","date":1514764800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193384,"objectID":"c73df1383cf15c8c0aec6b65a41f7d07","permalink":"https://mlo-lab.github.io/publication/gupta-texttovec-2018/","publishdate":"2025-09-18T11:03:04.196963Z","relpermalink":"/publication/gupta-texttovec-2018/","section":"publication","summary":"","tags":[],"title":"Texttovec: Deep contextualized neural autoregressive topic models of language with distributed compositional prior","type":"publication"},{"authors":["Anne-Kristin Heninger","Anne Eugster","Denise Kuehn","Florian Buettner","Matthias Kuhn","Annett Lindner","Sevina Dietz","Sibille Jergens","Carmen Wilhelm","Andreas Beyerlein"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"e52b1ae7b080496d377bc451ec4513b0","permalink":"https://mlo-lab.github.io/publication/heninger-divergent-2017/","publishdate":"2025-09-18T11:03:05.740296Z","relpermalink":"/publication/heninger-divergent-2017/","section":"publication","summary":"","tags":[],"title":"A divergent population of autoantigen-responsive CD4+ T cells in infants prior to β cell autoimmunity","type":"publication"},{"authors":["Thomas Blasi","Florian Buettner","Michael K. Strasser","Carsten Marr","Fabian J. Theis"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193384,"objectID":"1ba60e8d518374a2bad278a545557f39","permalink":"https://mlo-lab.github.io/publication/blasi-cgcorrect-2017/","publishdate":"2025-09-18T11:03:04.620379Z","relpermalink":"/publication/blasi-cgcorrect-2017/","section":"publication","summary":"","tags":[],"title":"cgcorrect: a method to correct for confounding cell–cell variation due to cell growth in single-cell transcriptomics","type":"publication"},{"authors":["Florian Buettner","Naruemon Pratanwanich","Davis J. McCarthy","John C. Marioni","Oliver Stegle"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"8b2c6fcb0739e95efb6f2ccc982aba8d","permalink":"https://mlo-lab.github.io/publication/buettner-f-sclvm-2017/","publishdate":"2025-09-18T11:03:05.080624Z","relpermalink":"/publication/buettner-f-sclvm-2017/","section":"publication","summary":"","tags":[],"title":"f-scLVM: scalable and versatile factor analysis for single-cell RNA-seq","type":"publication"},{"authors":["Florian Buettner","Kyle Jay","Harry Wischnewski","Thomas Stadelmann","Shady Saad","Konstantins Jefimovs","Madina Mansurova","Juan Gerez","Claus M. Azzalin","Reinhard Dechant"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"60346720de66a2bb5c05223365329d66","permalink":"https://mlo-lab.github.io/publication/buettner-non-targeted-2017/","publishdate":"2025-09-18T11:03:04.825485Z","relpermalink":"/publication/buettner-non-targeted-2017/","section":"publication","summary":"","tags":[],"title":"Non-targeted metabolomic approach reveals two distinct types of metabolic responses to telomerase dysfunction in S. cerevisiae","type":"publication"},{"authors":["Hubert Szymon Gabryś","Florian Buettner","Florian Sterzing","Henrik Hauswald","Mark Bangert"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"e5f44b68ebc23456dc32ecf0a4c7bd7a","permalink":"https://mlo-lab.github.io/publication/gabrys-parotid-2017/","publishdate":"2025-09-18T11:03:05.597906Z","relpermalink":"/publication/gabrys-parotid-2017/","section":"publication","summary":"","tags":[],"title":"Parotid gland mean dose as a xerostomia predictor in low-dose domains","type":"publication"},{"authors":["Felix Buggenthin","Florian Buettner","Philipp S. Hoppe","Max Endele","Manuel Kroiss","Michael Strasser","Michael Schwarzfischer","Dirk Loeffler","Konstantinos D. Kokkaliaris","Oliver Hilsenbeck"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"ff8b3d64de2cb92a13f79bce8f785e45","permalink":"https://mlo-lab.github.io/publication/buggenthin-prospective-2017/","publishdate":"2025-09-18T11:03:05.291684Z","relpermalink":"/publication/buggenthin-prospective-2017/","section":"publication","summary":"","tags":[],"title":"Prospective identification of hematopoietic lineage choice by deep learning","type":"publication"},{"authors":["Nina Cabezas-Wallscheid","Florian Buettner","Pia Sommerkamp","Daniel Klimmeck","Luisa Ladel","Frederic B. Thalheimer","Daniel Pastor-Flores","Leticia P. Roma","Simon Renders","Petra Zeisberger"],"categories":[],"content":"","date":1483228800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193385,"objectID":"42f7a678ab9c762ff701e52a32017613","permalink":"https://mlo-lab.github.io/publication/cabezas-wallscheid-vitamin-2017/","publishdate":"2025-09-18T11:03:05.457665Z","relpermalink":"/publication/cabezas-wallscheid-vitamin-2017/","section":"publication","summary":"","tags":[],"title":"Vitamin A-retinoic acid signaling regulates hematopoietic stem cell dormancy","type":"publication"},{"authors":["Philipp Angerer","Laleh Haghverdi","Maren Büttner","Fabian J. Theis","Carsten Marr","Florian Buettner"],"categories":[],"content":"","date":1451606400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193386,"objectID":"493226c53c28c0ec46e59db029945369","permalink":"https://mlo-lab.github.io/publication/angerer-destiny-2016/","publishdate":"2025-09-18T11:03:05.916138Z","relpermalink":"/publication/angerer-destiny-2016/","section":"publication","summary":"","tags":[],"title":"destiny: diffusion maps for large-scale single-cell data in R","type":"publication"},{"authors":["Michael Laimighofer","J. A. N. Krumsiek","Florian Buettner","Fabian J. Theis"],"categories":[],"content":"","date":1451606400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193386,"objectID":"c4a49f742006203dfa1c2bbd4f94d2b9","permalink":"https://mlo-lab.github.io/publication/laimighofer-unbiased-2016/","publishdate":"2025-09-18T11:03:06.149575Z","relpermalink":"/publication/laimighofer-unbiased-2016/","section":"publication","summary":"","tags":[],"title":"Unbiased prediction and feature selection in high-dimensional survival regression","type":"publication"},{"authors":["Nicola K. Wilson","David G. Kent","Florian Buettner","Mona Shehata","Iain C. Macaulay","Fernando J. Calero-Nieto","Manuel Sánchez Castillo","Caroline A. Oedekoven","Evangelia Diamanti","Reiner Schulte"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193388,"objectID":"fdb94c32c293bf73cf4ae5a0007e0fda","permalink":"https://mlo-lab.github.io/publication/wilson-combined-2015/","publishdate":"2025-09-18T11:03:07.837686Z","relpermalink":"/publication/wilson-combined-2015/","section":"publication","summary":"","tags":[],"title":"Combined single-cell functional and gene expression analysis resolves heterogeneity within stem cell populations","type":"publication"},{"authors":["Florian Buettner","Kedar N. Natarajan","F. Paolo Casale","Valentina Proserpio","Antonio Scialdone","Fabian J. Theis","Sarah A. Teichmann","John C. Marioni","Oliver Stegle"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193386,"objectID":"81b9487e2a6f99eab73e8d573607527e","permalink":"https://mlo-lab.github.io/publication/buettner-computational-2015/","publishdate":"2025-09-18T11:03:06.542501Z","relpermalink":"/publication/buettner-computational-2015/","section":"publication","summary":"","tags":[],"title":"Computational analysis of cell-to-cell heterogeneity in single-cell RNA-sequencing data reveals hidden subpopulations of cells","type":"publication"},{"authors":["Antonio Scialdone","Kedar N. Natarajan","Luis R. Saraiva","Valentina Proserpio","Sarah A. Teichmann","Oliver Stegle","John C. Marioni","Florian Buettner"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193387,"objectID":"987a926d542a82a514c2dc5f1938dc74","permalink":"https://mlo-lab.github.io/publication/scialdone-computational-2015/","publishdate":"2025-09-18T11:03:07.433964Z","relpermalink":"/publication/scialdone-computational-2015/","section":"publication","summary":"","tags":[],"title":"Computational assignment of cell-cycle stage from single-cell transcriptome data","type":"publication"},{"authors":["Victoria Moignard","Steven Woodhouse","Laleh Haghverdi","Andrew J. Lilly","Yosuke Tanaka","Adam C. Wilkinson","Florian Buettner","Iain C. Macaulay","Wajid Jawaid","Evangelia Diamanti"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193387,"objectID":"74e33e184dbebd9e78114c156c8368de","permalink":"https://mlo-lab.github.io/publication/moignard-decoding-2015/","publishdate":"2025-09-18T11:03:06.954806Z","relpermalink":"/publication/moignard-decoding-2015/","section":"publication","summary":"","tags":[],"title":"Decoding the regulatory network of early blood development from single-cell gene expression measurements","type":"publication"},{"authors":["Laleh Haghverdi","Florian Buettner","Fabian J. Theis"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193386,"objectID":"cafe1b90369da744af1310f1e8c64355","permalink":"https://mlo-lab.github.io/publication/haghverdi-diffusion-2015/","publishdate":"2025-09-18T11:03:06.742738Z","relpermalink":"/publication/haghverdi-diffusion-2015/","section":"publication","summary":"","tags":[],"title":"Diffusion maps for high-dimensional single-cell analysis of differentiation data","type":"publication"},{"authors":["Ezio Bonifacio","Anette-G. Ziegler","Georgeanna Klingensmith","Edith Schober","Polly J. Bingley","Marietta Rottenkolber","Anke Theil","Anne Eugster","Ramona Puff","Claudia Peplow"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193386,"objectID":"9e8e89ab3acd7ace01a7e09ff1aa803b","permalink":"https://mlo-lab.github.io/publication/bonifacio-effects-2015/","publishdate":"2025-09-18T11:03:06.3407Z","relpermalink":"/publication/bonifacio-effects-2015/","section":"publication","summary":"","tags":[],"title":"Effects of high-dose oral insulin on immune responses in children at high risk for type 1 diabetes: the Pre-POINT randomized clinical trial","type":"publication"},{"authors":["Steffen Sass","Florian Buettner","Nikola S. Mueller","Fabian J. Theis"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193387,"objectID":"68d62b7225d305d22ca365a9acb4846b","permalink":"https://mlo-lab.github.io/publication/sass-ramona-2015/","publishdate":"2025-09-18T11:03:07.159573Z","relpermalink":"/publication/sass-ramona-2015/","section":"publication","summary":"","tags":[],"title":"RAMONA: a Web application for gene set analysis on multilevel omics data","type":"publication"},{"authors":["Jason CH Tsang","Yong Yu","Shannon Burke","Florian Buettner","Cui Wang","Aleksandra A. Kolodziejczyk","Sarah A. Teichmann","Liming Lu","Pentao Liu"],"categories":[],"content":"","date":1420070400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193387,"objectID":"c15201c1134557e74c1c292503a7ab2f","permalink":"https://mlo-lab.github.io/publication/tsang-single-cell-2015/","publishdate":"2025-09-18T11:03:07.629482Z","relpermalink":"/publication/tsang-single-cell-2015/","section":"publication","summary":"","tags":[],"title":"Single-cell transcriptomic reconstruction reveals cell cycle and multi-lineage differentiation defects in Bcl11a-deficient hematopoietic stem cells","type":"publication"},{"authors":["Christiane Winkler","Jan Krumsiek","Florian Buettner","Christof Angermüller","Eleni Z. Giannopoulou","Fabian J. Theis","Anette-Gabriele Ziegler","Ezio Bonifacio"],"categories":[],"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193388,"objectID":"df78f78a557f30ad1dc9269939ffd4f3","permalink":"https://mlo-lab.github.io/publication/winkler-feature-2014/","publishdate":"2025-09-18T11:03:08.753707Z","relpermalink":"/publication/winkler-feature-2014/","section":"publication","summary":"","tags":[],"title":"Feature ranking of type 1 diabetes susceptibility genes improves prediction of type 1 diabetes","type":"publication"},{"authors":["A. Mareike Schmidt","Stephan R. Fagerer","Konstantins Jefimovs","Florian Buettner","Christian Marro","Erdem C. Siringil","Karl L. Boehlen","Martin Pabst","Alfredo J. Ibáñez"],"categories":[],"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193388,"objectID":"55021eeaf4194a7123a462be09321ce1","permalink":"https://mlo-lab.github.io/publication/schmidt-molecular-2014/","publishdate":"2025-09-18T11:03:08.492926Z","relpermalink":"/publication/schmidt-molecular-2014/","section":"publication","summary":"","tags":[],"title":"Molecular phenotypic profiling of a Saccharomyces cerevisiae strain at the single-cell level","type":"publication"},{"authors":["Florian Buettner","Victoria Moignard","Berthold Göttgens","Fabian J. Theis"],"categories":[],"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193388,"objectID":"f8c9a0ed258624b58fd99879ad0e9814","permalink":"https://mlo-lab.github.io/publication/buettner-probabilistic-2014/","publishdate":"2025-09-18T11:03:08.044172Z","relpermalink":"/publication/buettner-probabilistic-2014/","section":"publication","summary":"","tags":[],"title":"Probabilistic PCA of censored data: accounting for uncertainties in the visualization of high-throughput single-cell qPCR data","type":"publication"},{"authors":["M. A. Ebert","S. L. Gulliford","F. Buettner","Kerwyn Foo","A. Haworth","A. Kennedy","D. J. Joseph","J. W. Denham"],"categories":[],"content":"","date":1388534400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193388,"objectID":"236b048284a991cd6518e6cf6d7ea055","permalink":"https://mlo-lab.github.io/publication/ebert-two-2014/","publishdate":"2025-09-18T11:03:08.261329Z","relpermalink":"/publication/ebert-two-2014/","section":"publication","summary":"","tags":[],"title":"Two non-parametric methods for derivation of constraints from radiotherapy dose–histogram data","type":"publication"},{"authors":["Steffen Sass","Florian Buettner","Nikola S. Mueller","Fabian J. Theis"],"categories":[],"content":"","date":1356998400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193389,"objectID":"41ce7b3daaadd94ffb16e8ff8352b3b5","permalink":"https://mlo-lab.github.io/publication/sass-modular-2013/","publishdate":"2025-09-18T11:03:09.078232Z","relpermalink":"/publication/sass-modular-2013/","section":"publication","summary":"","tags":[],"title":"A modular framework for gene set analysis integrating multilevel omics data","type":"publication"},{"authors":["Victoria Moignard","Iain C. Macaulay","Gemma Swiers","Florian Buettner","Judith Schütte","Fernando J. Calero-Nieto","Sarah Kinston","Anagha Joshi","Rebecca Hannah","Fabian J. Theis"],"categories":[],"content":"","date":1356998400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193389,"objectID":"f44724611c02c9b0bc93013fe08f01ff","permalink":"https://mlo-lab.github.io/publication/moignard-characterization-2013/","publishdate":"2025-09-18T11:03:08.932729Z","relpermalink":"/publication/moignard-characterization-2013/","section":"publication","summary":"","tags":[],"title":"Characterization of transcriptional networks in blood stem and progenitor cells using high-throughput single-cell gene expression analysis","type":"publication"},{"authors":["Florian Buettner","Fabian J. Theis"],"categories":[],"content":"","date":1325376e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193389,"objectID":"e523f0a006e102467c33ac723663e908","permalink":"https://mlo-lab.github.io/publication/buettner-novel-2012/","publishdate":"2025-09-18T11:03:09.650775Z","relpermalink":"/publication/buettner-novel-2012/","section":"publication","summary":"","tags":[],"title":"A novel approach for resolving differences in single-cell gene expression patterns from zygote to blastocyst","type":"publication"},{"authors":["Florian Buettner","Aisha B. Miah","Sarah L. Gulliford","Emma Hall","Kevin J. Harrington","Steve Webb","Mike Partridge","Christopher M. Nutting"],"categories":[],"content":"","date":1325376e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193389,"objectID":"02a0c7d20caccca66ab64b4a5cc8da96","permalink":"https://mlo-lab.github.io/publication/buettner-novel-2012-1/","publishdate":"2025-09-18T11:03:09.503034Z","relpermalink":"/publication/buettner-novel-2012-1/","section":"publication","summary":"","tags":[],"title":"Novel approaches to improve the therapeutic index of head and neck radiotherapy: an analysis of data from the PARSPORT randomised phase III trial","type":"publication"},{"authors":["Florian Buettner","Sarah L. Gulliford","Steve Webb","Matthew R. Sydes","David P. Dearnaley","Mike Partridge"],"categories":[],"content":"","date":1325376e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193389,"objectID":"894b120127363ddcc995ace65f3a7230","permalink":"https://mlo-lab.github.io/publication/buettner-doseresponse-2012/","publishdate":"2025-09-18T11:03:09.29006Z","relpermalink":"/publication/buettner-doseresponse-2012/","section":"publication","summary":"","tags":[],"title":"The dose–response of the anal sphincter region–an analysis of data from the MRC RT01 trial","type":"publication"},{"authors":["Florian Buettner","Sarah L. Gulliford","Steve Webb","Mike Partridge"],"categories":[],"content":"","date":129384e4,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193390,"objectID":"f7f7daf50e3960257ed250d322125e5c","permalink":"https://mlo-lab.github.io/publication/buettner-modeling-2011/","publishdate":"2025-09-18T11:03:09.879172Z","relpermalink":"/publication/buettner-modeling-2011/","section":"publication","summary":"","tags":[],"title":"Modeling late rectal toxicities based on a parameterized representation of the 3D dose distribution","type":"publication"},{"authors":["F. Buettner","S. L. Gulliford","S. Webb","M. Partridge"],"categories":[],"content":"","date":1262304e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193390,"objectID":"aed24f93d817b8823a1dacaba5aa60aa","permalink":"https://mlo-lab.github.io/publication/buettner-using-2010/","publishdate":"2025-09-18T11:03:10.07615Z","relpermalink":"/publication/buettner-using-2010/","section":"publication","summary":"","tags":[],"title":"Using Bayesian logistic regression to evaluate a new type of dosimetric constraint for prostate radiotherapy treatment planning","type":"publication"},{"authors":["Florian Buettner","Sarah L. Gulliford","Steve Webb","Matthew R. Sydes","David P. Dearnaley","Mike Partridge"],"categories":[],"content":"","date":1230768e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193390,"objectID":"d9e8f2d6ecc1ba59c9d3403d3bf385e9","permalink":"https://mlo-lab.github.io/publication/buettner-assessing-2009/","publishdate":"2025-09-18T11:03:10.493572Z","relpermalink":"/publication/buettner-assessing-2009/","section":"publication","summary":"","tags":[],"title":"Assessing correlations between the spatial distribution of the dose to the rectal wall and late rectal toxicity after prostate radiotherapy: an analysis of data from the MRC RT01 trial (ISRCTN 47772397)","type":"publication"},{"authors":["Florian Buettner","Sarah L. Gulliford","Steve Webb","Mike Partridge"],"categories":[],"content":"","date":1230768e3,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193390,"objectID":"c0217c283db2522f3d59cb56daa8143e","permalink":"https://mlo-lab.github.io/publication/buettner-using-2009/","publishdate":"2025-09-18T11:03:10.286824Z","relpermalink":"/publication/buettner-using-2009/","section":"publication","summary":"","tags":[],"title":"Using dose-surface maps to predict radiation-induced rectal bleeding: a neural network approach","type":"publication"},{"authors":["Joao Seco","Greg C. Sharp","Ziji Wu","David Gierga","Florian Buettner","Harald Paganetti"],"categories":[],"content":"","date":1199145600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193390,"objectID":"0c9ee52032b88065c044cf07e4f8ab15","permalink":"https://mlo-lab.github.io/publication/seco-dosimetric-2008/","publishdate":"2025-09-18T11:03:10.686367Z","relpermalink":"/publication/seco-dosimetric-2008/","section":"publication","summary":"","tags":[],"title":"Dosimetric impact of motion in free-breathing and gated lung radiotherapy: A 4D Monte Carlo study of intrafraction and interfraction effects","type":"publication"},{"authors":["Giovanni Volpe","Gajendra P. Singh","Florian Buettner","Anna M. Drets","Dmitri V. Petrov"],"categories":[],"content":"","date":1136073600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1758193391,"objectID":"381266498790a3f4dbfa87dc87e5fdbb","permalink":"https://mlo-lab.github.io/publication/volpe-optical-2006/","publishdate":"2025-09-18T11:03:10.949399Z","relpermalink":"/publication/volpe-optical-2006/","section":"publication","summary":"","tags":[],"title":"Optical trapping dynamics for cell identification","type":"publication"},{"authors":null,"categories":null,"content":"","date":-62135596800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":-62135596800,"objectID":"f26b5133c34eec1aa0a09390a36c2ade","permalink":"https://mlo-lab.github.io/admin/config.yml","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/admin/config.yml","section":"","summary":"","tags":null,"title":"","type":"wowchemycms"}]