@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{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{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} } @article{HunkeHuberSteffens2025, author = {Hunke, Til and Huber, Florian and Steffens, Jochen}, title = {The Evolution of Song Lyrics: An NLP-Based Analysis of Popular Music in Germany from 1954 to 2022}, series = {Music \& Science}, volume = {8}, journal = {Music \& Science}, publisher = {Sage Publications}, issn = {2059-2043}, doi = {10.1177/20592043251331155}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-52618}, pages = {20}, year = {2025}, abstract = {Music is an indispensable cultural product, reflecting changes in social, psychological, and cultural contexts. This study analyzes the historical evolution of topics and conveyed affect in popular music lyrics in Germany from 1954 to 2022, using LDA-based topic modeling and transformer-based sentiment analysis. These results show that Love \& Relationships is the most referenced topic, with Dreams \& Longings prominent until the mid-1960s and Society \& Status rising from 2017. The sentiment analysis reveals a significant decline in positive sentiment since the mid-1960s, accompanied by increases in negative, ambiguous, and neutral sentiments. These trends may reflect broader societal changes, including shifts in cultural values, rising individualism, and increasing mental health issues. The study highlights the evolving nature of popular music and its reflection of social dynamics.}, subject = {Popmusik}, 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{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} } @unpublished{deJongeJoasTruongetal.2024, author = {de Jonge, Niek F. and Joas, David and Truong, Lem-Joe and van der Hooft, Justin J.J. and Huber, Florian}, title = {Reliable cross-ion mode chemical similarity prediction between MS2 spectra}, series = {biorxiv}, journal = {biorxiv}, publisher = {Cold Spring Harbor Laboratory}, doi = {10.1101/2024.03.25.586580}, year = {2024}, abstract = {Mass spectrometry is commonly used to characterize metabolites in untargeted metabolomics. This can be done in positive and negative ionization mode, a choice typically guided by the fraction of metabolites a researcher is interested in. During analysis, mass spectral comparisons are widely used to enable annotation through reference libraries and to facilitate data organization through networking. However, until now, such comparisons between mass spectra were restricted to mass spectra of the same ionization mode, as the two modes generally result in very distinct fragmentation spectra. To overcome this barrier, here, we have implemented a machine learning model that can predict chemical similarity between spectra of different ionization modes. Hence, our new MS2DeepScore 2.0 model facilitates the seamless integration of positive and negative ionization mode mass spectra into one analysis pipeline. This creates entirely new options for data exploration, such as mass spectral library searching of negative ion mode spectra in positive ion mode libraries or cross-ionization mode molecular networking. Furthermore, to improve the reliability of predictions and better cope with unseen data, we have implemented a method to estimate the quality of prediction. This will help to avoid false predictions on spectra with low information content or spectra that substantially differ from the training data. We anticipate that the MS2DeepScore 2.0 model will extend our current capabilities in organizing and annotating untargeted metabolomics profiles.}, subject = {Massenspektrometrie}, 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} } @article{deJongeMildauMeijeretal.2022, author = {de Jonge, Niek F. and Mildau, Kevin and Meijer, David and Louwen, Joris J. R. and Bueschl, Christoph and Huber, Florian and van der Hooft, Justin J. J.}, title = {Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools}, series = {Metabolomics}, volume = {18}, journal = {Metabolomics}, number = {12}, publisher = {Springer Nature}, issn = {1573-3890}, doi = {10.1007/s11306-022-01963-y}, pages = {22}, year = {2022}, abstract = {Background Untargeted metabolomics approaches based on mass spectrometry obtain comprehensive profiles of complex biological samples. However, on average only 10\% of the molecules can be annotated. This low annotation rate hampers biochemical interpretation and effective comparison of metabolomics studies. Furthermore, de novo structural characterization of mass spectral data remains a complicated and time-intensive process. Recently, the field of computational metabolomics has gained traction and novel methods have started to enable large-scale and reliable metabolite annotation. Molecular networking and machine learning-based in-silico annotation tools have been shown to greatly assist metabolite characterization in diverse fields such as clinical metabolomics and natural product discovery. Aim of review We highlight recent advances in computational metabolite annotation workflows with a special focus on their evaluation and comparison with other tools. Whilst the progress is substantial and promising, we also argue that inconsistencies in benchmarking different tools hamper users from selecting the most appropriate and promising method for their research. We summarize benchmarking strategies of the different tools and outline several recommendations for benchmarking and comparing novel tools. Key scientific concepts of review This review focuses on recent advances in mass spectral library-based and machine learning-supported metabolite annotation workflows. We discuss large-scale library matching and analogue search, the current bloom of mass spectral similarity scores, and how molecular networking has changed the field. In addition, the potentials and challenges of machine learning-supported metabolite annotation workflows are highlighted. Overall, recent developments in computational metabolomics have started to fundamentally change metabolomics workflows, and we expect that as a community we will be able to overcome current method performance ambiguities and annotation bottlenecks.}, subject = {Metabolomik}, language = {en} }