Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra
peer-reviewed · Journal of Proteome Research · 2025
| Date | 2025-06-02 |
| Type | peer-reviewed |
| Venue | Journal of Proteome Research |
| Publisher | American Chemical Society (ACS) |
| Contribution | algorithm |
| DOI | 10.1021/acs.jproteome.5c00063 |
| Citations (OpenAlex) | 2 |
| Venue 2-year citedness | 3.48 |
Preprint version: Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra (2025-03-28, bioRxiv)
Abstract
A fundamental challenge in mass spectrometry-based proteomics is determining which peptide generated a given MS2 spectrum. Peptide sequencing typically relies on matching spectra against a known sequence database, which in some applications is not available. Deep learning-based de novo sequencing can address this limitation by directly predicting peptide sequences from MS2 data. We have seen the application of the transformer architecture to de novo sequencing produce state-of-the-art results on the so-called nine-species benchmark. In this study, we propose an improved transformer encoder inspired by the heuristics used in the manual interpretation of spectra. We modify the attention mechanism with a learned bias based on pairwise mass differences, termed Pairwise Attention (PA). Adding PA improves average peptide precision at 100% coverage by 12.7% (5.9 percentage points) over our base transformer on the original nine-species benchmark. We have also achieved a 7.4% increase over the previously published model Casanovo. Our MS2 encoding strategy is largely orthogonal to other transformer-based models encoding MS2 spectra, enabling straightforward integration into existing deep-learning approaches. Our results show that integrating domain-specific knowledge into transformers boosts de novo sequencing performance.
Methods and tools
- Pairwise: Mass difference attention
Cites (12)
- MARLOWE: Taxonomic Characterization of Unknown Samples for Forensics Using De Novo Peptide Identification (2025) crossref
- Deep Learning Methods for De Novo Peptide Sequencing (2024) both
- Sequence-to-sequence translation from mass spectra to peptides with a transformer model (2024) both
- NovoBoard: a comprehensive framework for evaluating the false discovery rate and accuracy of de novo peptide sequencing (2024) crossref
- Introducing π-HelixNovo for practical large-scale de novo peptide sequencing (2024) crossref
- Introducing PandaNovo for practical large-scale de novo peptide sequencing (2023) semanticscholar
- Uncovering Hidden Members and Functions of the Soil Microbiome Using De Novo Metaproteomics (2022) both
- Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices (2021) both
- De novo peptide sequencing by deep learning (2017) both
- Recent Developments in Computational Methods for De Novo Peptide Sequencing from Tandem Mass Spectrometry (MS/MS) (2015) semanticscholar
- Novor: Real-Time Peptide de Novo Sequencing Software (2015) both
- De Novo Peptide Sequencing via Manual Interpretation of MS/MS Spectra (2002) both