EUVIMEDEUVIMED entdecken
Crossref

EncNovo: De Novo Peptide Sequencing With an Encoder‐Only Architectures

Xinglong Zhu iD, Zejiang Chen, Zihao Huang, Haipeng Wang

Rapid Communications in Mass Spectrometry · 30.01.2027 · 41 (2)

DOI: 10.1002/rcm.70211 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Rapid Communications in Mass Spectrometry, online erschienen am 16.11.2026. Verfasst von Xinglong Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Shandong University of Technology, Zibo, China. Hauptthemen laut MEDLINE: Sequence Analysis, Protein, Tandem Mass Spectrometry, Peptides. Die Arbeit nennt 24 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rationale

De novo peptide sequencing enables interpretation of tandem mass spectrometry (MS/MS) data without relying on sequence databases and is valuable for analyzing proteins from unknown species. However, existing Transformer‐based approaches may not fully exploit interactions among precursor information, spectral features, and sequence prediction tokens, potentially limiting sequencing performance.

Methods

We developed EncNovo, a nonautoregressive de novo peptide sequencing model based on a BERT‐inspired encoder‐only Transformer architecture. Precursor attributes, spectral peaks, and sequence prediction tokens are jointly encoded within a unified encoder, enabling continuous interaction among the three throughout the encoding process. A residual attention mechanism and a peak mass‐difference inductive bias were further incorporated into the self‐attention framework to encode amino acid residue mass relationships between spectral peaks.

Results

Experimental results on the nine‐species benchmark dataset demonstrate that EncNovo improves peptide recall at 100% coverage by 5.10 and 4.18 percentage points on average compared with Casanovo and RefineNovo, respectively. The model also achieved higher amino acid recall and demonstrated faster convergence during training.

Conclusions

Experimental results demonstrate that the proposed encoder‐only framework, combined with residual attention and a peak mass‐difference inductive bias, effectively improves peptide recall and accelerates model convergence. Collectively, these advantages make EncNovo a reliable framework for de novo peptide sequencing in proteomics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sequence Analysis, ProteinTandem Mass SpectrometryPeptidesAnimalsProteomicsProteinsDatabases, ProteinAlgorithms

Stichwörter der Autor:innen

de novo peptide sequencingencoder‐only architecturepeak mass‐difference inductive biasresidual attentiontransformer

Substanzen

PeptidesProteins

Autor:innen und Institutionen

  • School of Computer Science and Technology, Shandong University of Technology, Zibo, China.

ORCID-Profile: Xinglong Zhu

Zitieren

APA

Zhu, X., Chen, Z., Huang, Z., & Wang, H. (2027). EncNovo: De Novo Peptide Sequencing With an Encoder‐Only Architectures. Rapid Communications in Mass Spectrometry, 41(2). https://doi.org/10.1002/rcm.70211

Vancouver

Zhu X, Chen Z, Huang Z, Wang H. EncNovo: De Novo Peptide Sequencing With an Encoder‐Only Architectures. Rapid Communications in Mass Spectrometry. 2027;41(2). doi:10.1002/rcm.70211

BibTeX
@article{Zhu2027,
  author = {Zhu, Xinglong and Chen, Zejiang and Huang, Zihao and Wang, Haipeng},
  title = {EncNovo: De Novo Peptide Sequencing With an Encoder‐Only Architectures},
  journal = {Rapid Communications in Mass Spectrometry},
  year = {2027},
  volume = {41},
  number = {2},
  doi = {10.1002/rcm.70211}
}
Kostenlos starten →