SemiNovo: Learning Beyond Search-Identified Spectra for De Novo Peptide Sequencing

preprint · arXiv · 2026

preprint · arXiv · 2026. Pan Liu et al. Sensitive peptide identification is fundamental to protein characterization and novel protein discovery, for…
Date 2026-11-16
Type preprint
Venue arXiv
Publisher arXiv
Contribution algorithm
DOI 10.48550/arXiv.2611.21079

Abstract

Sensitive peptide identification is fundamental to protein characterization and novel protein discovery, for which de novo peptide sequencing (DNPS) from tandem mass spectra provides an important database-independent approach. Although deep learning has substantially advanced de novo sequencing, existing models are predominantly trained on high-confidence peptide-spectrum matches obtained through database search. This search-conditioned supervision excludes a large fraction of unidentified spectra, creating a distribution mismatch between the selectively labeled training data and the complete spectrum stream encountered at inference time, thereby limiting peptide identification performance. To address this challenge, we propose SemiNovo, a semi-supervised framework that learns jointly from identified and unlabeled spectra. SemiNovo first constructs DarkSpec, a large-scale quality-controlled corpus of unlabeled spectra collected from diverse public proteomics projects, thereby extending training beyond search-identified spectra and mitigating the resulting shift in DNPS supervision. It then combines stepwise mass-constrained autoregressive decoding with cumulative path confidence to derive reliable supervision from unlabeled spectra. Moreover, SemiNovo introduces head-wise chemical-evidence gating to improve spectral evidence aggregation under noisy and incomplete fragmentation. Experiments show that SemiNovo performs favorably against state-of-the-art methods on multiple benchmarks. Code and dataset are publicly available.

Authors

  1. Pan Liu · The Hong Kong University of Science and Technology (Guangzhou)
  2. Dongxin Lyu · Westlake University
  3. Yusen Tan · The Hong Kong University of Science and Technology (Guangzhou)
  4. Yifan Li · The Hong Kong University of Science and Technology (Guangzhou)
  5. Hai-tao Yu · The Hong Kong University of Science and Technology (Guangzhou)
  6. Yunhua Zhong · The University of Hong Kong
  7. Zikun Wang · The Hong Kong University of Science and Technology (Guangzhou)
  8. Tianze Ling · Beijing Institute of Lifeomics, National Center for Protein Sciences (Beijing), State Key Laboratory of Medical Proteomics, Tsinghua University
  9. Jun Xia · The Hong Kong University of Science and Technology, The Hong Kong University of Science and Technology (Guangzhou), Westlake University

Methods and tools

  • SemiNovo: Semi-supervised training on identified and 4.5 million unlabeled spectra (DarkSpec), pseudo-labelled by stepwise mass-constrained autoregressive decoding with cumulative path confidence, plus head-wise chemical-evidence gating of spectral attention.

Data deposited

Trained on

Evaluated on

Seen in the charts

Back to the full map

Back to top