Abstract
We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised representation learning that improves de novo sequencing of peptides. This invariance exploits the physical relationship between precursor properties (mass and charge) and fragment-ion evidence, without requiring peptide sequence labels. We introduce dIon, which adapts the DINO framework with two latent prediction tasks, both recovering a clean teacher representation: one from a spectrum mixture, using the precursor as a selection query, and one from a partial spectrum with the precursor withheld. The first associates precursor information with fragment-ion evidence; the second prevents representational collapse onto that information alone. Mechanistic probes support both effects, and ablations show that the full objective performs best. Under identical end-to-end training, dIon initialization improves de novo peptide precision over training from scratch by 5.5 and 8.4 percentage points on the held-out MassIVE-KB and Kingdoms test sets, and by 2.3 and 4.8 percentage points with a larger supervised training corpus. The resulting models surpass fully supervised state-of-the-art de novo sequencing models on the diverse, multi-species Kingdoms corpus under the same greedy-decoding protocol. Without peptide labels, dIon learns strong native peptide-similarity geometry compared with other learned models; with limited peptide-supervised adaptation, it achieves the best retrieval and pair-discrimination performance across all representation benchmarks.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Nilsson, A., Lapin, J., Payne, S. H., Wilhelm, M., & Käll, L. (2026). dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra. https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra
MLA 9
Nilsson, Alfred, et al. "dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra." https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra.
Chicago (author–date)
Nilsson, Alfred, Joel Lapin, Samuel H. Payne, Mathias Wilhelm, and Lukas Käll. 2026. "dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra." https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra.
Harvard
Nilsson, A., Lapin, J., Payne, S. H., Wilhelm, M. and Käll, L. (2026) 'dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra', Available at: https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra.
Vancouver
Nilsson A, Lapin J, Payne SH, Wilhelm M, Käll L. dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra. https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra
IEEE
A. Nilsson, J. Lapin, S. H. Payne, M. Wilhelm, and L. Käll, "dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra," https://omanscience.com/en/articles/dion-fragmentation-based-invariance-for-self-supervised-learning-of-tandem-mass-spectra.