dIon: Fragmentation-Based Invariance for Self-Supervised Learning of Tandem Mass Spectra

preprint · arXiv · 2026

preprint · arXiv · 2026. Alfred Nilsson et al. We introduce a novel invariance for peptide tandem mass spectrometry data, unlocking self-supervised…
Date 2026-10-05
Type preprint
Venue arXiv
Publisher arXiv
Contribution algorithm
DOI 10.48550/arXiv.2610.06282
Citations (OpenAlex) 0

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.

Authors

  1. Alfred Nilsson · KTH Royal Institute of Technology
  2. Joel Lapin · Technical University of Munich
  3. Samuel H. Payne · Brigham Young University
  4. Mathias Wilhelm · Technical University of Munich
  5. Lukas Käll · KTH Royal Institute of Technology

Methods and tools

  • dIon: Self-supervised DINO-style pretraining of a spectrum encoder, from a precursor-conditioned spectrum mixture and a partial spectrum with the precursor withheld; initialising a Casanovo-style de novo sequencer from it raises peptide precision over training from scratch.

Data deposited

Trained on

Evaluated on

Seen in the charts

Back to the full map

Back to top