TY - JOUR A1 - Mullowney, Michael W. A1 - Duncan, Katherine R. A1 - Elsayed, Somayah S. A1 - Garg, Neha A1 - van der Hooft, Justin J. J. A1 - Martin, Nathaniel I. A1 - Meijer, David A1 - Terlouw, Barbara R. A1 - Biermann, Friederike A1 - Blin, Kai A1 - Durairaj, Janani A1 - Gorostiola González, Marina A1 - Helfrich, Eric J. N. A1 - Huber, Florian A1 - Leopold-Messer, Stefan A1 - Rajan, Kohulan A1 - de Rond, Tristan A1 - van Santen, Jeffrey A. A1 - Sorokina, Maria A1 - Balunas, Marcy J. A1 - Beniddir, Mehdi A. A1 - van Bergeijk, Doris A. A1 - Carroll, Laura M. A1 - Clark, Chase M. A1 - Clevert, Djork-Arné A1 - Dejong, Chris A. A1 - Du, Chao A1 - Ferrinho, Scarlet A1 - Grisoni, Francesca A1 - Hofstetter, Albert A1 - Jespers, Willem A1 - Kalinina, Olga V. A1 - Kautsar, Satria A. A1 - Kim, Hyunwoo A1 - Leao, Tiago F. A1 - Masschelein, Joleen A1 - Rees, Evan R. A1 - Reher, Raphael A1 - Reker, Daniel A1 - Schwaller, Philippe A1 - Segler, Marwin A1 - Skinnider, Michael A. A1 - Walker, Allison S. A1 - Willighagen, Egon L. A1 - Zdrazil, Barbara A1 - Ziemert, Nadine A1 - Goss, Rebecca J. M. A1 - Guyomard, Pierre A1 - Volkamer, Andrea A1 - Gerwick, William H. A1 - Kim, Hyun Uk A1 - Müller, Rolf A1 - van Wezel, Gilles P. A1 - van Westen, Gerard J. P. A1 - Hirsch, Anna K. H. A1 - Linington, Roger G. A1 - Robinson, Serina L. A1 - Medema, Marnix H. T1 - Artificial intelligence for natural product drug discovery JF - Nature Reviews Drug Discovery KW - Maschinelles Lernen KW - Arzneimittelforschung KW - Deep learning KW - Omics-Technologie Y1 - 2023 U6 - https://doi.org/10.1038/s41573-023-00774-7 SN - 1474-1776 VL - 22 IS - 11 SP - 895 EP - 916 PB - Springer Nature ER - TY - JOUR A1 - de Jonge, Niek F. A1 - Mildau, Kevin A1 - Meijer, David A1 - Louwen, Joris J. R. A1 - Bueschl, Christoph A1 - Huber, Florian A1 - van der Hooft, Justin J. J. T1 - Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools JF - Metabolomics N2 - 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. KW - Metabolomik KW - Massenspektrometrie KW - Maschinelles Lernen KW - Benchmarking KW - Mass fragmentation spectra Y1 - 2022 U6 - https://doi.org/10.1007/s11306-022-01963-y SN - 1573-3890 VL - 18 IS - 12 PB - Springer Nature ER - TY - JOUR A1 - de Jonge, Niek F. A1 - Louwen, Joris J. R. A1 - Chekmeneva, Elena A1 - Camuzeaux, Stephane A1 - Vermeir, Femke J. A1 - Jansen, Robert S. A1 - Huber, Florian A1 - van der Hooft, Justin J. J. T1 - MS2Query: reliable and scalable MS2 mass spectra-based analogue search JF - Nature Communications N2 - Metabolomics-driven discoveries of biological samples remain hampered by the grand challenge of metabolite annotation and identification. Only few metabolites have an annotated spectrum in spectral libraries; hence, searching only for exact library matches generally returns a few hits. An attractive alternative is searching for so-called analogues as a starting point for structural annotations; analogues are library molecules which are not exact matches but display a high chemical similarity. However, current analogue search implementations are not yet very reliable and relatively slow. Here, we present MS2Query, a machine learning-based tool that integrates mass spectral embedding-based chemical similarity predictors (Spec2Vec and MS2Deepscore) as well as detected precursor masses to rank potential analogues and exact matches. Benchmarking MS2Query on reference mass spectra and experimental case studies demonstrate improved reliability and scalability. Thereby, MS2Query offers exciting opportunities to further increase the annotation rate of metabolomics profiles of complex metabolite mixtures and to discover new biology. KW - Metabolomik KW - Massenspektrometrie KW - Maschinelles Lernen KW - Reproduzierbarkeit KW - Metabolomics KW - Mass Spectrometry KW - Machine Learning KW - Complex Mixtures Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-46105 SN - 2041-1723 VL - 14 PB - Springer ER - TY - JOUR A1 - Kamiloğlu, Roza G. A1 - Sun, Rui A1 - Bos, Patrick A1 - Huber, Florian A1 - Attema, Jisk Jakob A1 - Sauter, Disa A. T1 - Tickling induces a unique type of spontaneous laughter JF - Biology Letters N2 - 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. KW - Lachen KW - Kitzel KW - Akustik KW - Maschinelles Lernen KW - Spontaneität KW - Evolutionsbiologie KW - Verhalten Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-47446 SN - 1744-957X VL - 20 IS - 11 PB - The Royal Society ER - TY - INPR A1 - de Jonge, Niek F. A1 - Joas, David A1 - Truong, Lem-Joe A1 - van der Hooft, Justin J.J. A1 - Huber, Florian T1 - Reliable cross-ion mode chemical similarity prediction between MS2 spectra T2 - biorxiv N2 - 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. KW - Massenspektrometrie KW - Metabolomik KW - Maschinelles Lernen Y1 - 2024 U6 - https://doi.org/10.1101/2024.03.25.586580 PB - Cold Spring Harbor Laboratory ER - TY - JOUR A1 - Hunke, Til A1 - Huber, Florian A1 - Steffens, Jochen T1 - The Evolution of Song Lyrics: An NLP-Based Analysis of Popular Music in Germany from 1954 to 2022 JF - Music & Science N2 - 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. KW - Popmusik KW - Maschinelles Lernen KW - Automatische Sprachanalyse Y1 - 2025 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-52618 SN - 2059-2043 VL - 8 PB - Sage Publications ER - TY - INPR A1 - Bushuiev, Roman A1 - Bushuiev, Anton A1 - de Jonge, Niek F. A1 - Young, Adamo A1 - Kretschmer, Fleming A1 - Samusevich, Raman A1 - Heirman, Janne A1 - Wang, Fei A1 - Zhang, Luke A1 - Dührkop, Kai A1 - Ludwig, Marcus A1 - Haupt, Nils A. A1 - Kalia, Apurva A1 - Brungs, Corinna A1 - Schmid, Robin A1 - Greiner, Russell A1 - Wang, Bo A1 - Wishart, David S. A1 - Liu, Li-Ping A1 - Rousu, Juho A1 - Bittremieux, Wout A1 - Röst, Hannes A1 - Mak, Tytus D. A1 - Hassoun, Soha A1 - Huber, Florian A1 - van der Hooft, Justin J.J. A1 - Stravs, Michael A. A1 - Böcker, Sebastian A1 - Sivic, Josef A1 - Pluskal, Tomáš T1 - MassSpecGym: A benchmark for the discovery and identification of molecules T2 - arXiv N2 - 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]. KW - Maschinelles Lernen KW - Benchmark KW - Computational chemistry KW - Massenspektrometrie KW - Molekülstruktur Y1 - 2025 U6 - https://doi.org/10.48550/arXiv.2410.23326 N1 - Open Review: https://web.archive.org/web/20250521010648/https://openreview.net/forum?id=AAo8zAShX3#discussion PB - arXiv ET - v3 ER - TY - CHAP A1 - Steffens, Jochen A1 - Joschko, Marcel A1 - Giang, Hien A1 - Huber, Florian T1 - Using machine learning to identify acoustic fingerprints of concert halls in classical audio recordings [Abstract] T2 - DAS|DAGA 2025: 51st Annual Meeting on Acoustics, March 17-20, 2025, Copenhagen KW - Datenanalyse KW - Maschinelles Lernen KW - Raumakustik KW - Konzertsaal Y1 - 2025 UR - https://pub.dega-akustik.de/DAS-DAGA_2025/konferenz-1559.html?article=348 PB - Deutsche Gesellschaft für Akustik e.V. CY - Berlin ER -