EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Deep Learning Methods for De Novo Peptide Sequencing

Wout Bittremieux iD, Varun Ananth, William E Fondrie, Carlo Melendez, Marina Pominova, Justin Sanders, Bo Wen, Melih Yilmaz, William S Noble iD

Mass Spectrometry Reviews · 2026-05 · 45 (3) · 507-526

DOI: 10.1002/mas.21919 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Mass Spectrometry Reviews, online erschienen am 29.11.2024. Verfasst von Wout Bittremieux und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Antwerp, Antwerp, Belgium. Hauptthemen laut MEDLINE: Deep Learning, Sequence Analysis, Protein, Peptides, Tandem Mass Spectrometry. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 116 Literaturangaben. Gefördert von: This work was funded by National Science Foundation award 2245300 to WSN. MP and WB acknowledge support by the University of Antwerp Research Fund (BOF 49083-D…, National Science Foundation, University of Antwerp Research Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Protein tandem mass spectrometry data are most often interpreted by matching observed mass spectra to a protein database derived from the reference genome of the sample being analyzed. In many application domains, however, a relevant protein database is unavailable or incomplete, and in such settings de novo sequencing is required. Since the introduction of the DeepNovo algorithm in 2017, the field of de novo sequencing has been dominated by deep learning methods, which use large amounts of labeled mass spectrometry data to train multi‐layer neural networks to translate from observed mass spectra to corresponding peptide sequences. Here, we describe these deep learning methods, outline procedures for evaluating their performance, and discuss the challenges in the field, both in terms of methods development and evaluation protocols.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSequence Analysis, ProteinPeptidesTandem Mass SpectrometryHumansAlgorithmsDatabases, ProteinNeural Networks, ComputerProteomics

Substanzen

Peptides

Autor:innen und Institutionen

  • Department of Computer Science, University of Antwerp, Antwerp, Belgium.
  • Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, Washington, USA.
  • Talus Bioscience, Seattle, Washington, USA.
  • Department of Genome Sciences, University of Washington, Seattle, Washington, USA.

ORCID-Profile: Wout Bittremieux, William S Noble

Förderung

  • This work was funded by National Science Foundation award 2245300 to WSN. MP and WB acknowledge support by the University of Antwerp Research Fund (BOF 49083-D…
  • National Science Foundation
  • University of Antwerp Research Fund
  • Division of Biological Infrastructure

Zitieren

APA

Bittremieux, W., Ananth, V., Fondrie, W. E., Melendez, C., Pominova, M., Sanders, J., Wen, B., Yilmaz, M., & Noble, W. S. (2026). Deep Learning Methods for De Novo Peptide Sequencing. Mass Spectrometry Reviews, 45(3), 507-526. https://doi.org/10.1002/mas.21919

Vancouver

Bittremieux W, Ananth V, Fondrie WE, Melendez C, Pominova M, Sanders J, et al. Deep Learning Methods for De Novo Peptide Sequencing. Mass Spectrometry Reviews. 2026;45(3):507-526. doi:10.1002/mas.21919

BibTeX
@article{Bittremieux2026,
  author = {Bittremieux, Wout and Ananth, Varun and Fondrie, William E and Melendez, Carlo and Pominova, Marina and Sanders, Justin and Wen, Bo and Yilmaz, Melih and Noble, William S},
  title = {Deep Learning Methods for De Novo Peptide Sequencing},
  journal = {Mass Spectrometry Reviews},
  year = {2026},
  volume = {45},
  number = {3},
  pages = {507--526},
  doi = {10.1002/mas.21919}
}
Kostenlos starten →