EUVIMEDEUVIMED entdecken
Crossref

SpecRoFormer: Relative Position-Aware Representation Learning for Small-Molecule MS/MS Spectra

Guoqing Zhu, Shiting Lai, Xinyi Cao, Keyu Hu, Luojun Lin iD, Yuanlong Yu iD

Analytical Chemistry · 30.10.2026

DOI: 10.1021/acs.analchem.6c03195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 30.10.2026. Verfasst von Guoqing Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Data Science, Fuzhou University, Fuzhou350108, China. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China (NSFC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spectrum retrieval in tandem mass spectrometry (MS/MS) relies on learning representations that accurately reflect molecular structural similarity. However, fragmentation variability across experimental conditions and instrument biases introduces significant distribution shifts in spectral data, making it difficult to learn representations that can generalize to different instruments. In this study, we propose SpecRoFormer, a Transformer-based framework that learns generalizable MS/MS representations through relative spectral modeling and fragmentation-aware augmentation. The approach captures structure-relevant relationships between peaks while improving robustness to fragmentation variability and distribution shifts. We train SpecRoFormer on the GNPS dataset and evaluate its generalization across multiple external benchmarks, including MoNA, MassBank, and MassSpecGym. Across these datasets, SpecRoFormer achieves the best overall retrieval performance against strong baselines such as MSBERT, DreaMS, and SpecEmbedding. Furthermore, evaluations on the large-scale simulated dataset SimMS-9M further verify the robustness of SpecRoFormer under broader distribution shifts, consistently outperforming competing methods. These results demonstrate that modeling relative spectral relationships together with fragmentation-aware robustness is critical for learning generalizable MS/MS representations, enabling reliable cross-instrument spectrum retrieval.

Schlagwörter

Stichwörter der Autor:innen

mass spectrum retrievalspectrum representation learningtandem mass spectrometry

Autor:innen und Institutionen

  • College of Computer and Data Science, Fuzhou University, Fuzhou350108, China.

ORCID-Profile: Luojun Lin, Yuanlong Yu

Förderung

  • National Natural Science Foundation of China (NSFC)

Zitieren

APA

Zhu, G., Lai, S., Cao, X., Hu, K., Lin, L., & Yu, Y. (2026). SpecRoFormer: Relative Position-Aware Representation Learning for Small-Molecule MS/MS Spectra. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.6c03195

Vancouver

Zhu G, Lai S, Cao X, Hu K, Lin L, Yu Y. SpecRoFormer: Relative Position-Aware Representation Learning for Small-Molecule MS/MS Spectra. Analytical Chemistry. 2026. doi:10.1021/acs.analchem.6c03195

BibTeX
@article{Zhu2026,
  author = {Zhu, Guoqing and Lai, Shiting and Cao, Xinyi and Hu, Keyu and Lin, Luojun and Yu, Yuanlong},
  title = {SpecRoFormer: Relative Position-Aware Representation Learning for Small-Molecule MS/MS Spectra},
  journal = {Analytical Chemistry},
  year = {2026},
  doi = {10.1021/acs.analchem.6c03195}
}
Kostenlos starten →