kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Pairwise Attention: Leveraging Mass Differences to Enhance De Novo Sequencing of Mass Spectra
Computational Mass Spectrometry, TUM School of Life Sciences, Technical University of Munich, 85354 Freising, Germany.
KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Gene Technology. KTH, Centres, Science for Life Laboratory, SciLifeLab.ORCID iD: 0000-0002-3181-3800
Computational Mass Spectrometry, TUM School of Life Sciences, Technical University of Munich, 85354 Freising, Germany; Munich Data Science Institute, Technical University of Munich, 85748 Garching, Germany.ORCID iD: 0000-0002-9224-3258
KTH, Centres, Science for Life Laboratory, SciLifeLab. KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Gene Technology.ORCID iD: 0000-0001-5689-9797
2025 (English)In: Journal of Proteome Research, ISSN 1535-3893, E-ISSN 1535-3907, Vol. 24, no 7, p. 3722-3730Article in journal (Refereed) Published
Abstract [en]

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.

Place, publisher, year, edition, pages
American Chemical Society (ACS) , 2025. Vol. 24, no 7, p. 3722-3730
Keywords [en]
Attention, De novo sequencing, Mass spectrometry, MS2, Proteomics, Transformers
National Category
Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:kth:diva-364463DOI: 10.1021/acs.jproteome.5c00063ISI: 001500093400001PubMedID: 40454436Scopus ID: 2-s2.0-105007317018OAI: oai:DiVA.org:kth-364463DiVA, id: diva2:1968279
Funder
Knut and Alice Wallenberg Foundation, KAW 2022.0032
Note

QC 20260127

Available from: 2025-06-12 Created: 2025-06-12 Last updated: 2026-05-12Bibliographically approved
In thesis
1. Learning Representations for Tandem Mass Spectra: Self-Supervised Methods and Inductive Biases
Open this publication in new window or tab >>Learning Representations for Tandem Mass Spectra: Self-Supervised Methods and Inductive Biases
2026 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Mass spectrometry (MS) is central to modern proteomics, enabling analysis of proteins and peptides based on their mass-to-charge ratio. Tandem mass spectrometry (MS2) encodes peptide fragmentation patterns and forms the basis for sequence identification. While database search has long dominated this process, deep learning has opened new paths for the direct interpretation of spectra. This thesis investigates how neural networks can learn representations of MS2 spectra. Two complementary research directions are explored.

First, selected self-supervised pretraining strategies are evaluated through controlled downstream experiments using encoders pretrained on unlabeled MS2 corpora. Self-distillation yields global embeddings that implicitly encode aspects of peptide chemical properties, and masked autoencoding provides modest improvements in de novo optimization and accuracy. However, the resulting improvements fall short of state-of-the-art supervised de novo sequencing performance.

Second, we introduce Pairwise Attention, a transformer architecture that incorporates a domain-aligned relational inductive bias by conditioning attention on pairwise mass differences between peaks. This yields consistent performance improvements on standard de novo sequencing benchmarks and strong generalization across datasets.

Overall, the results show that self-supervised learning can recover meaningful structure from raw MS2 data, while architectural inductive biases currently offer the most robust and reliable gains for de novo peptide sequencing.

Abstract [sv]

Masspektrometrin (MS) är central inom modern proteomik och möjliggör analysav proteiner och peptider baserat på deras massa. Tandem-masspektrometri (MS2)kodar fragmenteringsmönster för peptider och utgör grunden för sekvensidentifiering. Även om databassökning länge har dominerat denna process har djupinlärning öppnat nya möjligheter för direkt tolkning av spektra.

Denna avhandling undersöker hur neurala nätverk kan lära sig representationer av MS2-spektra. Två kompletterande forskningsinriktningar studeras.

Först utvärderas utvalda självövervakade förträningsstrategier genom kontrollerade experiment med encoders som förtränats på oetiketterade MS2-korpusar. Självdistillation ger globala inbäddningar som implicit kodar aspekter av peptiders kemiska egenskaper, och masked autoencoding ger måttliga förbättringar i de novo-precision. De resulterande förbättringarna når dock inte upp till prestandan hos dagens state-of-the-art-metoder för övervakad de novo-sekvensering.

Sedan introduceras Pairwise Attention, en transformerarkitektur som inkorporerar en domänanpassad induktiv bias genom att villkora Attention på parvisa masskillnader mellan toppar. Detta ger prestandaförbättringar på etablerade de novo-sekvenseringsbenchmarkar samt stark generalisering över dataset.

Sammantaget visar resultaten att självövervakad inlärning kan återvinna meningsfull struktur ur råa MS2-data, medan induktiva biaser för närvarande erbjuder de mest robusta förbättringarna för de novo-peptidsekvensering.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2026. p. 45
Series
TRITA-CBH-FOU ; 2026:21
Keywords
Mass Spectrometry, Deep Learning, De Novo Sequencing, Self-Supervised Learning
National Category
Bioinformatics and Computational Biology
Research subject
Biotechnology
Identifiers
urn:nbn:se:kth:diva-378805 (URN)978-91-8106-586-2 (ISBN)
Presentation
2026-04-17, Pascal, Gamma-6, Tomtebodavägen 23, Solna, Stockholm, 13:15 (English)
Opponent
Supervisors
Note

QC 2026-03-27

Available from: 2026-03-27 Created: 2026-03-27 Last updated: 2026-03-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Nilsson, AlfredKäll, Lukas

Search in DiVA

By author/editor
Nilsson, AlfredWilhelm, MathiasKäll, Lukas
By organisation
Gene TechnologyScience for Life Laboratory, SciLifeLab
In the same journal
Journal of Proteome Research
Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 114 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf