@misc{OPUS4-2939, title = {781 - Gr{\"u}ndungsurkunde: Zentrum f{\"u}r Digitalisierung und Digitalit{\"a}t (ZDD) vom 14.04.2020}, address = {D{\"u}sseldorf}, organization = {Hochschule D{\"u}sseldorf}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-29392}, pages = {1}, year = {2021}, abstract = {mit Beschluss des Pr{\"a}sidiums vom 14.04.2021 wird das Zentrum f{\"u}r Digitalisierung und Digitalit{\"a}t (ZDD)}, language = {de} } @misc{OPUS4-2941, title = {782 - Satzung des Zentrums f{\"u}r Digitalisierung und Digitalit{\"a}t (ZDD) der Hochschule D{\"u}sseldorf vom 26.05.2021}, address = {D{\"u}sseldorf}, organization = {Hochschule D{\"u}sseldorf}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-29415}, pages = {7}, year = {2021}, abstract = {Aufgrund der \S\S 2 Abs. 4 S. 1, 29 Abs. 1 in Verbindung mit \S 16 Absatz 1 Satz 2 sowie \S 28 Absatz 1 Satz 2 des Gesetzes {\"u}ber die Hochschulen des Landes Nordrhein-Westfalen (Hochschulgesetz - HG) vom 16.09.2014 (GV. NRW. S. 547) in der aktuell g{\"u}ltigen Fassung hat die Hochschule D{\"u}sseldorf die folgende Satzung erlassen}, language = {de} } @misc{OPUS4-3355, title = {796 - Pr{\"u}fungsordnung f{\"u}r den Bachelorstudiengang Data Science, Al und Intelligente Systeme an der Hochschule D{\"u}sseldorf vom 16.09.2021}, address = {D{\"u}sseldorf}, organization = {Hochschule D{\"u}sseldorf}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-33551}, pages = {25}, year = {2021}, abstract = {Aufgrund der \S\S 2 Abs. 4, 64 Abs. 1 des Gesetzes {\"u}ber die Hochschulen des Landes Nordrhein-Westfalen (Hochschulgesetz - HG) vom 16.09.2014 (GV. NRW. S. 547) in der aktuell g{\"u}ltigen Fassung hat die Hochschule D{\"u}sseldorf die folgende Pr{\"u}fungsordnung als Satzung erlassen.}, subject = {Pr{\"u}fungsrecht}, language = {de} } @article{MullowneyDuncanElsayedetal.2023, author = {Mullowney, Michael W. and Duncan, Katherine R. and Elsayed, Somayah S. and Garg, Neha and van der Hooft, Justin J. J. and Martin, Nathaniel I. and Meijer, David and Terlouw, Barbara R. and Biermann, Friederike and Blin, Kai and Durairaj, Janani and Gorostiola Gonz{\´a}lez, Marina and Helfrich, Eric J. N. and Huber, Florian and Leopold-Messer, Stefan and Rajan, Kohulan and de Rond, Tristan and van Santen, Jeffrey A. and Sorokina, Maria and Balunas, Marcy J. and Beniddir, Mehdi A. and van Bergeijk, Doris A. and Carroll, Laura M. and Clark, Chase M. and Clevert, Djork-Arn{\´e} and Dejong, Chris A. and Du, Chao and Ferrinho, Scarlet and Grisoni, Francesca and Hofstetter, Albert and Jespers, Willem and Kalinina, Olga V. and Kautsar, Satria A. and Kim, Hyunwoo and Leao, Tiago F. and Masschelein, Joleen and Rees, Evan R. and Reher, Raphael and Reker, Daniel and Schwaller, Philippe and Segler, Marwin and Skinnider, Michael A. and Walker, Allison S. and Willighagen, Egon L. and Zdrazil, Barbara and Ziemert, Nadine and Goss, Rebecca J. M. and Guyomard, Pierre and Volkamer, Andrea and Gerwick, William H. and Kim, Hyun Uk and M{\"u}ller, Rolf and van Wezel, Gilles P. and van Westen, Gerard J. P. and Hirsch, Anna K. H. and Linington, Roger G. and Robinson, Serina L. and Medema, Marnix H.}, title = {Artificial intelligence for natural product drug discovery}, series = {Nature Reviews Drug Discovery}, volume = {22}, journal = {Nature Reviews Drug Discovery}, number = {11}, publisher = {Springer Nature}, issn = {1474-1776}, doi = {10.1038/s41573-023-00774-7}, pages = {895 -- 916}, year = {2023}, subject = {Maschinelles Lernen}, language = {en} } @inproceedings{GaudryHuberFlueckigeretal.2022, author = {Gaudry, Arnaud and Huber, Florian and Fl{\"u}ckiger, Julien and Quir{\´o}s, L and Rutz, Adriano and Kaiser, M and Grondin, A and Marcourt, Laurence and Ferreira Queiroz, E and Wolfender, Jean-Luc and Allard, Pierre-Marie}, title = {Short Lecture "Mass spectrometry-based sample vectorization for exploration of large chemodiverse datasets and efficient identification of new antiparasitic compounds"}, series = {Planta Medica}, volume = {88}, booktitle = {Planta Medica}, number = {15}, publisher = {Thieme}, issn = {1439-0221}, doi = {10.1055/s-0042-1758983}, year = {2022}, subject = {Massenspektrometrie}, language = {en} } @book{Huber2024, author = {Huber, Florian}, title = {Hands-on Introduction to Data Science with Python}, edition = {v0.21}, publisher = {Zenodo}, doi = {10.5281/zenodo.10074474}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-49548}, pages = {365}, year = {2024}, abstract = {In today's world, data is generated at an unprecedented pace, and our ability to harness it is changing the way we live, work, and even think. Data science, the interdisciplinary field that blends statistics, computer science, and domain-specific knowledge, empowers us to extract insights from this vast ocean of data. As data science becomes increasingly essential across various industries and sectors, there is a growing need for skilled professionals who can make sense of data and transform it into actionable information. This book is designed to give you a very broad and at the same time a very practical hands-on tour through the full spectrum of data science approaches}, subject = {Data Science}, language = {en} } @misc{OPUS4-4049, title = {872 - Erste Satzung zur {\"A}nderung der Pr{\"u}fungsordnung f{\"u}r den Bachelorstudiengang Data Science, Al und Intelligente Systeme an der Hochschule D{\"u}sseldorf vom 04.04.2023}, address = {D{\"u}sseldorf}, organization = {Hochschule D{\"u}sseldorf}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-40499}, pages = {2}, year = {2023}, abstract = {Aufgrund der \S\S 2 Abs. 4, 64 Abs. 1 des Gesetzes {\"u}ber die Hochschulen des Landes Nordrhein-Westfalen (Hochschulgesetz - HG) vom 16.09.2014 (GV. NRW. S. 547) in der aktuell g{\"u}ltigen Fassung hat die Hochschule D{\"u}sseldorf die folgende Ordnung als Satzung erlassen.}, language = {de} } @article{KamiloğluSunBosetal.2024, author = {Kamiloğlu, Roza G. and Sun, Rui and Bos, Patrick and Huber, Florian and Attema, Jisk Jakob and Sauter, Disa A.}, title = {Tickling induces a unique type of spontaneous laughter}, series = {Biology Letters}, volume = {20}, journal = {Biology Letters}, number = {11}, publisher = {The Royal Society}, issn = {1744-957X}, doi = {10.1098/rsbl.2024.0543}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-47446}, year = {2024}, abstract = {Laughing is ubiquitous in human life, yet what causes it and how it sounds is highly variable. Considering this diversity, we sought to test whether there are fundamentally different kinds of laughter. Here, we sampled spontaneous laughs (n = 887) from a wide range of everyday situations (e.g. comedic performances and playful pranks). Machine learning analyses showed that laughs produced during tickling are acoustically distinct from laughs triggered by other kinds of events (verbal jokes, watching something funny or witnessing someone else's misfortune). In a listening experiment (n = 201), participants could accurately identify tickling-induced laughter, validating that such laughter is not only acoustically but also perceptually distinct. A second listening study (n = 210) combined with acoustic analyses indicates that tickling-induced laughter involves less vocal control than laughter produced in other contexts. Together, our results reveal a unique acoustic and perceptual profile of laughter induced by tickling, an evolutionarily ancient play behaviour, distinguishing it clearly from laughter caused by other triggers. This study showcases the power of machine learning in uncovering patterns within complex behavioural phenomena, providing a window into the evolutionary significance of ticking-induced laughter.}, subject = {Lachen}, language = {en} } @article{MildauEhlersMeisenburgetal.2024, author = {Mildau, Kevin and Ehlers, Henry and Meisenburg, Mara and Del Pup, Elena and Koetsier, Robert A. and Torres Ortega, Laura Rosina and de Jonge, Niek F. and Singh, Kumar Saurabh and Ferreira, Dora and Othibeng, Kgalaletso and Tugizimana, Fidele and Huber, Florian and van der Hooft, Justin J. J.}, title = {Effective data visualization strategies in untargeted metabolomics}, series = {Natural Product Reports}, journal = {Natural Product Reports}, publisher = {Royal Society of Chemistry}, issn = {0265-0568}, doi = {10.1039/d4np00039k}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-47596}, pages = {38}, year = {2024}, abstract = {LC-MS/MS-based untargeted metabolomics is a rapidly developing research field spawning increasing numbers of computational metabolomics tools assisting researchers with their complex data processing, analysis, and interpretation tasks. In this article, we review the entire untargeted metabolomics workflow from the perspective of information visualization, visual analytics and visual data integration. Data visualization is a crucial step at every stage of the metabolomics workflow, where it provides core components of data inspection, evaluation, and sharing capabilities. However, due to the large number of available data analysis tools and corresponding visualization components, it is hard for both users and developers to get an overview of what is already available and which tools are suitable for their analysis. In addition, there is little cross-pollination between the fields of data visualization and metabolomics, leaving visual tools to be designed in a secondary and mostly ad hoc fashion. With this review, we aim to bridge the gap between the fields of untargeted metabolomics and data visualization. First, we introduce data visualization to the untargeted metabolomics field as a topic worthy of its own dedicated research, and provide a primer on cutting-edge visualization research into data visualization for both researchers as well as developers active in metabolomics. We extend this primer with a discussion of best practices for data visualization as they have emerged from data visualization studies. Second, we provide a practical roadmap to the visual tool landscape and its use within the untargeted metabolomics field. Here, for several computational analysis stages within the untargeted metabolomics workflow, we provide an overview of commonly used visual strategies with practical examples. In this context, we will also outline promising areas for further research and development. We end the review with a set of recommendations for developers and users on how to make the best use of visualizations for more effective and transparent communication of results.}, subject = {Metabolomik}, language = {en} } @article{GaudryHuberNothiasetal.2022, author = {Gaudry, Arnaud and Huber, Florian and Nothias, Louis-F{\´e}lix and Cretton, Sylvian and Kaiser, Marcel and Wolfender, Jean-Luc and Allard, Pierre-Marie}, title = {MEMO: Mass Spectrometry-Based Sample Vectorization to Explore Chemodiverse Datasets}, series = {Frontiers in Bioinformatics}, volume = {2}, journal = {Frontiers in Bioinformatics}, publisher = {Frontiers}, issn = {2673-7647}, doi = {10.3389/fbinf.2022.842964}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54660}, pages = {13}, year = {2022}, abstract = {In natural products research, chemodiverse extracts coming from multiple organisms are explored for novel bioactive molecules, sometimes over extended periods. Samples are usually analyzed by liquid chromatography coupled with fragmentation mass spectrometry to acquire informative mass spectral ensembles. Such data is then exploited to establish relationships among analytes or samples (e.g., via molecular networking) and annotate metabolites. However, the comparison of samples profiled in different batches is challenging with current metabolomics methods since the experimental variation—changes in chromatographical or mass spectrometric conditions - hinders the direct comparison of the profiled samples. Here we introduce MEMO—MS2 BasEd SaMple VectOrization—a method allowing to cluster large amounts of chemodiverse samples based on their LC-MS/MS profiles in a retention time agnostic manner. This method is particularly suited for heterogeneous and chemodiverse sample sets. MEMO demonstrated similar clustering performance as state-of-the-art metrics considering fragmentation spectra. More importantly, such performance was achieved without the requirement of a prior feature alignment step and in a significantly shorter computational time. MEMO thus allows the comparison of vast ensembles of samples, even when analyzed over long periods of time, and on different chromatographic or mass spectrometry platforms. This new addition to the computational metabolomics toolbox should drastically expand the scope of large-scale comparative analysis.}, subject = {Computational chemistry}, language = {en} } @article{SzwarcRutzLeeetal.2025, author = {Szwarc, Sarah and Rutz, Adriano and Lee, Kyungha and Mejri, Yassine and Bonnet, Olivier and Hazni, Hazrina and Jagora, Adrien and Mbeng Obame, Rany B. and Noh, Jin Kyoung and Otogo N'Nang, Elvis and Alaribe, Stephenie C. and Awang, Khalijah and Bernadat, Guillaume and Choi, Young Hae and Courdavault, Vincent and Frederich, Michel and Gaslonde, Thomas and Huber, Florian and Kam, Toh-Seok and Low, Yun Yee and Poupon, Erwan and van der Hooft, Justin J. J. and Kang, Kyo Bin and Le Pogam, Pierre and Beniddir, Mehdi A.}, title = {Translating community-wide spectral library into actionable chemical knowledge: a proof of concept with monoterpene indole alkaloids}, series = {Journal of Cheminformatics}, volume = {17}, journal = {Journal of Cheminformatics}, number = {1}, publisher = {Springer Nature}, issn = {1758-2946}, doi = {10.1186/s13321-025-01009-0}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54607}, pages = {15}, year = {2025}, abstract = {With over 3000 representatives, the monoterpene indole alkaloids (MIAs) class is among the most diverse families of plant natural products. The MS/MS spectral space exploration of these complex compounds using chemoinformatic and computational mass spectrometry tools offers a valuable opportunity to extract and share chemical insights from this emblematic family of natural products (NPs). In this work, we first present a substantially updated version of the MIADB, a database now containing 422 MS/MS spectra of MIAs that has been uploaded to the GNPS library versus 172 initial entries. We then introduce an innovative workflow that leverages hundreds of fragmentation spectra to support the FAIRification, extraction and dissemination of chemical knowledge. This workflow aims at the extraction of spectral patterns matching finely defined MIA skeletons. These extracted signatures can then be queried against complex biological extract datasets using MassQL. By applying this strategy to an LC-MS/MS dataset of 75 plant extracts, our results demonstrated the efficiency of this approach in identifying the diversity of MIA skeletons present in the analyzed samples. Additionally, our work enabled the digitization of structural data for diverse MIA skeletons by converting them into machine-readable formats and thereby enhancing their dissemination for the scientific community. Scientific contribution A comprehensive investigation of the monoterpene indole alkaloid chemical space, aiming to highlight skeleton-dependent fragmentation similarity trends and to generate valuable spectrometric signatures that could be used as queries.}, subject = {Computational chemistry}, language = {en} } @unpublished{HuberPollmann2025, author = {Huber, Florian and Pollmann, Julian}, title = {Count your bits: more subtle similarity measures using larger radius count vectors}, publisher = {bioRXiv}, doi = {10.1101/2025.06.16.659994}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54632}, pages = {29}, year = {2025}, abstract = {Quantifying molecular similarity is a cornerstone of cheminformatics, underpinning applications from virtual screening to chemical space visualization. A wide range of molecular fingerprints and similarity metrics, most notably Tanimoto scores, are employed, but their effectiveness is highly context-dependent. In this study, we systematically evaluate several 2D fingerprint types, including circular, path-based, and distance-encoded variants, using both binary and count representations. We highlight the consequences of fingerprint choice, vector folding, and similarity metric selection, revealing critical issues such as fingerprint duplication, mass dependent score biases, and high bit collision rates. Sparse and count-based fingerprints consistently outperform fixed-size binary vectors in preserving structural distinctions. Furthermore, we introduce percentile-based normalization, propose inverse-document-frequency (IDF) weighting, and benchmark all methods against graph-based MCES similarities. Our results offer practical guidance for selecting molecular similarity measures, emphasizing the need for conscious, task-aware fingerprinting choices in large-scale chemical analyses.}, subject = {Computational chemistry}, language = {en} } @article{KokHuberKalischetal.2025, author = {Kok, Maurits and Huber, Florian and Kalisch, Svenja-Marei and Dogterom, Marileen}, title = {EB3-informed dynamics of the microtubule stabilizing cap during stalled growth}, series = {Biophysical Journal}, volume = {124}, journal = {Biophysical Journal}, number = {2}, publisher = {Elsevier}, issn = {1542-0086}, doi = {10.1016/j.bpj.2024.11.3314}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-53164}, pages = {227 -- 244}, year = {2025}, abstract = {Microtubule stability is known to be governed by a stabilizing GTP/GDP-Pi cap, but the exact relation between growth velocity, GTP hydrolysis, and catastrophes remains unclear. We investigate the dynamics of the stabilizing cap through in vitro reconstitution of microtubule dynamics in contact with microfabricated barriers, using the plus-end binding protein GFP-EB3 as a marker for the nucleotide state of the tip. The interaction of growing microtubules with steric objects is known to slow down microtubule growth and accelerate catastrophes. We show that the lifetime distributions of stalled microtubules, as well as the corresponding lifetime distributions of freely growing microtubules, can be fully described with a simple phenomenological 1D model based on noisy microtubule growth and a single EB3-dependent hydrolysis rate. This same model is furthermore capable of explaining both the previously reported mild catastrophe dependence on microtubule growth rates and the catastrophe statistics during tubulin washout experiments.}, subject = {Mikrotubulus}, language = {en} } @unpublished{BushuievBushuievdeJongeetal.2025, author = {Bushuiev, Roman and Bushuiev, Anton and de Jonge, Niek F. and Young, Adamo and Kretschmer, Fleming and Samusevich, Raman and Heirman, Janne and Wang, Fei and Zhang, Luke and D{\"u}hrkop, Kai and Ludwig, Marcus and Haupt, Nils A. and Kalia, Apurva and Brungs, Corinna and Schmid, Robin and Greiner, Russell and Wang, Bo and Wishart, David S. and Liu, Li-Ping and Rousu, Juho and Bittremieux, Wout and R{\"o}st, Hannes and Mak, Tytus D. and Hassoun, Soha and Huber, Florian and van der Hooft, Justin J.J. and Stravs, Michael A. and B{\"o}cker, Sebastian and Sivic, Josef and Pluskal, Tom{\´a}š}, title = {MassSpecGym: A benchmark for the discovery and identification of molecules}, series = {arXiv}, journal = {arXiv}, edition = {v3}, publisher = {arXiv}, doi = {10.48550/arXiv.2410.23326}, pages = {49}, year = {2025}, abstract = {The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym -- the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at this https URL [https://github.com/pluskal-lab/MassSpecGym].}, subject = {Maschinelles Lernen}, language = {en} } @inproceedings{SteffensJoschkoGiangetal.2025, author = {Steffens, Jochen and Joschko, Marcel and Giang, Hien and Huber, Florian}, title = {Using machine learning to identify acoustic fingerprints of concert halls in classical audio recordings [Abstract]}, series = {DAS|DAGA 2025: 51st Annual Meeting on Acoustics, March 17-20, 2025, Copenhagen}, booktitle = {DAS|DAGA 2025: 51st Annual Meeting on Acoustics, March 17-20, 2025, Copenhagen}, publisher = {Deutsche Gesellschaft f{\"u}r Akustik e.V.}, address = {Berlin}, year = {2025}, subject = {Datenanalyse}, language = {en} } @article{deJongeHechtStrobeletal.2024, author = {de Jonge, Niek F. and Hecht, Helge and Strobel, Michael and Wang, Mingxun and van der Hooft, Justin J. J. and Huber, Florian}, title = {Reproducible MS/MS library cleaning pipeline in matchms}, series = {Journal of Cheminformatics}, volume = {16}, journal = {Journal of Cheminformatics}, number = {1}, publisher = {Springer Nature}, issn = {1758-2946}, doi = {10.1186/s13321-024-00878-1}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-46491}, year = {2024}, abstract = {Mass spectral libraries have proven to be essential for mass spectrum annotation, both for library matching and training new machine learning algorithms. A key step in training machine learning models is the availability of high-quality training data. Public libraries of mass spectrometry data that are open to user submission often suffer from limited metadata curation and harmonization. The resulting variability in data quality makes training of machine learning models challenging. Here we present a library cleaning pipeline designed for cleaning tandem mass spectrometry library data. The pipeline is designed with ease of use, flexibility, and reproducibility as leading principles.Scientific contributionThis pipeline will result in cleaner public mass spectral libraries that will improve library searching and the quality of machine-learning training datasets in mass spectrometry. This pipeline builds on previous work by adding new functionality for curating and correcting annotated libraries, by validating structure annotations. Due to the high quality of our software, the reproducibility, and improved logging, we think our new pipeline has the potential to become the standard in the field for cleaning tandem mass spectrometry libraries.}, subject = {Massenspektrometrie}, language = {en} }