@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{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} }