@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} } @article{deJongeLouwenChekmenevaetal.2023, author = {de Jonge, Niek F. and Louwen, Joris J. R. and Chekmeneva, Elena and Camuzeaux, Stephane and Vermeir, Femke J. and Jansen, Robert S. and Huber, Florian and van der Hooft, Justin J. J.}, title = {MS2Query: reliable and scalable MS2 mass spectra-based analogue search}, series = {Nature Communications}, volume = {14}, journal = {Nature Communications}, publisher = {Springer}, issn = {2041-1723}, doi = {10.1038/s41467-023-37446-4}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-46105}, pages = {12}, year = {2023}, abstract = {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.}, subject = {Metabolomik}, 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} } @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{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} } @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{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} }