Hybrid Deep Learning Model for EI-MS Spectra Prediction
International Journal of Molecular Sciences · 05.02.2026 · 27 (3) · 1588
DOI: 10.3390/ijms27031588 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 05.02.2026. Verfasst von Bartosz Majewski und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Theoretical Physics and Quantum Information, Gdańsk University of Technology, Narutowicza 11/12, 80-233 Gdańsk, Poland. Hauptthemen laut MEDLINE: Deep Learning, Spectrometry, Mass, Electrospray Ionization. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research and the APC were funded by the Department of Theoretical Physics and Quantum Information at Gdansk University of Technology.
Abstract (Originalsprache)
Electron ionization (EI) mass spectrometry (MS) is a widely used technique for the compound identification and production of spectra. However, incomplete coverage of reference spectral libraries limits reliable analysis of newly characterized molecules. This study presents a hybrid deep learning model for predicting EI-MS spectra directly from molecular structure. The approach combines a graph neural network encoder with a residual neural network decoder, followed by refinement using cross-attention, bidirectional prediction, and probabilistic, chemistry-informed masks. Trained on the NIST14 EI-MS database (≤500 Da), the model achieves strong library matching performance (Recall@10 ≈ 80.8%) and high spectral similarity. The proposed hybrid GNN (Graph Neural Network)-ResNet (Residual Neural Network) model can generate high-quality synthetic EI-MS spectra to supplement existing libraries, potentially reducing the cost and effort of experimental spectrum acquisition. The obtained results demonstrate the potential of data-driven models to augment EI-MS libraries, while highlighting remaining challenges in generalization and spectral uniqueness.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Theoretical Physics and Quantum Information, Gdańsk University of Technology, Narutowicza 11/12, 80-233 Gdańsk, Poland.
- BioTechMed Center, Gdańsk University of Technology, Narutowicza 11/12, 80-233 Gdańsk, Poland.
ORCID-Profile: Bartosz Majewski, Marta Łabuda
Förderung
- This research and the APC were funded by the Department of Theoretical Physics and Quantum Information at Gdansk University of Technology
Zitieren
APA
Majewski, B., & Łabuda, M. (2026). Hybrid Deep Learning Model for EI-MS Spectra Prediction. International Journal of Molecular Sciences, 27(3), 1588. https://doi.org/10.3390/ijms27031588
Vancouver
Majewski B, Łabuda M. Hybrid Deep Learning Model for EI-MS Spectra Prediction. International Journal of Molecular Sciences. 2026;27(3):1588. doi:10.3390/ijms27031588
BibTeX
@article{Majewski2026,
author = {Majewski, Bartosz and Łabuda, Marta},
title = {Hybrid Deep Learning Model for EI-MS Spectra Prediction},
journal = {International Journal of Molecular Sciences},
year = {2026},
volume = {27},
number = {3},
pages = {1588},
doi = {10.3390/ijms27031588}
}
EUVIMED