@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} } @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} }