20 May 2024 in Nature Protocols
20 September 2024 in Nature Protocols
23 May 2025 in Nature Biotechnology
Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we named Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas—a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.
15 September 2025 in Nature Methods
Untargeted high-resolution mass spectrometry is a key tool in clinical metabolomics, natural product discovery and exposomics, with compound identification remaining the major bottleneck. Currently, the standard workflow applies spectral library matching against tandem mass spectrometry (MS 2 ) fragmentation data. Multi-stage fragmentation (MS n ) yields more profound insights into substructures, enabling validation of fragmentation pathways; however, the community lacks open MS n reference data of diverse natural products and other chemicals. Here we describe MS n Lib, a machine learning-ready open resource of >2 million spectra in MS n trees of 30,008 unique small molecules, built with a high-throughput data acquisition and processing pipeline in the open-source software mzmine.
28 February 2025 in Nature Metabolism
6 May 2024 in Journal of the European Academy of Dermatology and Venereology
Tattooing has been part of the human culture for thousands of years, yet only in the past decades has it entered the mainstream of the society. With the rise in popularity, tattoos also gained attention among researchers, with the aim to better understand the health risks posed by their application. ‘A medical‐toxicological view of tattooing’—a work published in The Lancet almost a decade ago, resulted from the international collaboration of various experts in the field. Since then, much understanding has been achieved regarding adverse effects, treatment of complications, as well as their regulation for improving public health. Yet major knowledge gaps remain. This review article results from the Second International Conference on Tattoo Safety hosted by the German Federal Institute for Risk Assessment (BfR) and provides a glimpse from the medical‐toxicological perspective, regulatory strategies and advances in the analysis of tattoo inks.