Refine
Document Type
- Preprint (2)
Language
- English (2)
Is part of the Bibliography
- yes (2)
Keywords
- Maschinelles Lernen (2)
- Massenspektrometrie (2)
- Benchmark (1)
- Computational chemistry (1)
- Metabolomik (1)
- Molekülstruktur (1)
Department/institution
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.
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].