EUVIMEDEUVIMED entdecken
Crossref

CoSpred: Machine Learning Workflow to Predict Tandem Mass Spectrum in Proteomics

Liang Xue iD, Shivani Tiwary, Mykola Bordyuh iD, Robert Stanton

PROTEOMICS · 2025

DOI: 10.1002/pmic.70004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PROTEOMICS, 2025. Verfasst von Liang Xue und 3 weiteren Autor:innen. Beteiligte Einrichtung: Machine Learning and Computational Sciences, Pfizer Worldwide R&D, Cambridge, Massachusetts, USA. Hauptthemen laut MEDLINE: Proteomics, Tandem Mass Spectrometry, Machine Learning, Software. Die Arbeit nennt 51 Literaturangaben. Gefördert von: Pfizer Postdoctoral Research Fund, Pfizer.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In mass spectrometry‐based proteomics, the use of deep learning algorithms can help improve the identification rates of peptides and proteins through the generation of high‐fidelity theoretical spectrum which can be used as the basis of a more complete spectral library than those presently available, especially for unobserved protein/genetic variants. Here we focus on providing an end‐to‐end user‐friendly machine learning workflow, which we call Co mplete S pectrum Pred ictor (CoSpred). Using CoSpred users can create their own machine learning compatible training dataset and then train a machine learning model to predict both backbone and non‐backbone ions. For the model a transformer encoder architecture is used to predict the complete MS/MS spectrum from a given peptide sequence. In addition to the transformer model provided in the package, the code is built modularly to allow for alternate ML models to be easily “plugged in,” allowing for spectrum prediction optimization given different experimental conditions. The CoSpred workflow (preprocessing→training→inference) provides a path for state‐of‐art ML capabilities to be more accessible to proteomics scientists.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteomicsTandem Mass SpectrometryMachine LearningSoftwareWorkflowAlgorithms

Stichwörter der Autor:innen

Machine LearningMass SpectrometryMass Spectrum PredictionTransformer

Autor:innen und Institutionen

  • Machine Learning and Computational Sciences, Pfizer Worldwide R&D, Cambridge, Massachusetts, USA.
  • Machine Learning and Computational Sciences, Pfizer Worldwide R&D, Berlin, Germany.

ORCID-Profile: Liang Xue, Mykola Bordyuh

Förderung

  • Pfizer Postdoctoral Research Fund
  • Pfizer

Zitieren

APA

Xue, L., Tiwary, S., Bordyuh, M., & Stanton, R. (2025). CoSpred: Machine Learning Workflow to Predict Tandem Mass Spectrum in Proteomics. PROTEOMICS. https://doi.org/10.1002/pmic.70004

Vancouver

Xue L, Tiwary S, Bordyuh M, Stanton R. CoSpred: Machine Learning Workflow to Predict Tandem Mass Spectrum in Proteomics. PROTEOMICS. 2025. doi:10.1002/pmic.70004

BibTeX
@article{Xue2025,
  author = {Xue, Liang and Tiwary, Shivani and Bordyuh, Mykola and Stanton, Robert},
  title = {CoSpred: Machine Learning Workflow to Predict Tandem Mass Spectrum in Proteomics},
  journal = {PROTEOMICS},
  year = {2025},
  doi = {10.1002/pmic.70004}
}
Kostenlos starten →