Roman Bushuiev, Anton Bushuiev, Niek F. de Jonge, Adamo Young, Fleming Kretschmer, Raman Samusevich, Janne Heirman, Fei Wang, Luke Zhang, Kai Dührkop, Marcus Ludwig, Nils A. Haupt, Apurva Kalia, Corinna Brungs, Robin Schmid, Russell Greiner, Bo Wang, David S. Wishart, Li-Ping Liu, Juho Rousu, Wout Bittremieux, Hannes Röst, Tytus D. Mak, Soha Hassoun, Florian Huber, Justin J.J. van der Hooft, Michael A. Stravs, Sebastian Böcker, Josef Sivic, Tomáš Pluskal
- 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 ofThe 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].…


Metadaten| Author: | Roman BushuievORCiD, Anton BushuievORCiD, Niek F. de JongeORCiD, Adamo Young, Fleming KretschmerORCiDGND, Raman SamusevichORCiD, Janne HeirmanORCiD, Fei WangORCiD, Luke Zhang, Kai DührkopORCiD, Marcus LudwigORCiD, Nils A. HauptORCiD, Apurva KaliaORCiD, Corinna BrungsORCiD, Robin SchmidORCiD, Russell GreinerORCiD, Bo WangORCiD, David S. WishartORCiD, Li-Ping LiuORCiD, Juho RousuORCiD, Wout BittremieuxORCiD, Hannes RöstORCiDGND, Tytus D. MakORCiD, Soha HassounORCiD, Florian HuberORCiDGND, Justin J.J. van der HooftORCiD, Michael A. StravsORCiDGND, Sebastian BöckerORCiDGND, Josef SivicORCiD, Tomáš PluskalORCiD |
|---|
| Qualitätssicherung: | peer reviewed |
|---|
| open access: | Green - Zweitveröffentlichung – meist in Form eines Manuskripts (z. B. Preprint oder Postprint) |
|---|
| Institutes: | Zentrum für Digitalisierung und Digitalität (ZDD) |
|---|
| Research fields: | Informationstechnologie / Künstliche Intelligenz und Big Data |
|---|
| Fachbereich/Einrichtung: | Hochschule Düsseldorf / Fachbereich - Medien |
|---|
| Document Type: | Preprint |
|---|
| Year of Completion: | 2025 |
|---|
| Language of Publication: | English |
|---|
| Publisher: | arXiv |
|---|
| Parent Title (English): | arXiv |
|---|
| Edition: | v3 |
|---|
| Page Number: | 49 |
|---|
| DOI: | https://doi.org/10.48550/arXiv.2410.23326 |
|---|
| GND Keyword: | Maschinelles LernenGND; BenchmarkGND; Computational chemistryGND; MassenspektrometrieGND; MolekülstrukturGND |
|---|
| Dewey Decimal Classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 006 Spezielle Computerverfahren |
|---|
| Licence (German): | keine Lizenz - nur Metadaten |
|---|
| Release Date: | 2025/07/15 |
|---|
| Note: | Open Review: https://web.archive.org/web/20250521010648/https://openreview.net/forum?id=AAo8zAShX3#discussion |
|---|