False discovery rate control for trustworthy AI-based de novo peptide sequencing

preprint · bioRxiv · 2026

preprint · bioRxiv · 2026. Zhendong Liang et al. AI-based de novo peptide sequencing predicts peptide sequences from tandem mass spectra, enabling…
Date 2026-06-29
Type preprint
Venue bioRxiv
Publisher Cold Spring Harbor Laboratory
Contribution post-processor
DOI 10.64898/2026.06.29.735174
Citations (OpenAlex) 0

Abstract

AI-based de novo peptide sequencing predicts peptide sequences from tandem mass spectra, enabling identification beyond predefined databases but leaving prediction reliability difficult to assess, particularly with respect to false discovery rate (FDR). In database search, FDR control is provided by target-decoy competition over a finite search space, whereas de novo predictions are generated in open sequence space and lack naturally matched sequence-level decoys. Here we introduce Counterpart Calibration Theory (CCT), a theory-guided framework that reframes de novo FDR control as a four-group score-ranking and threshold-selection problem over target-side predictions and matched counterpart-side comparators. Implemented in {pi}-NovoQC, CCT provides dual-level FDR control at the peptide-spectrum match and peptide levels. Across models, datasets, instruments and acquisition modes, {pi}-NovoQC achieves stable FDR control while preserving identification yield. In large-scale proteomic applications, {pi}-NovoQC recovers low-abundance in-database peptides missed by database search and provides de novo-supported protein-group and variant evidence.

Authors

  1. Zhendong Liang · Peng Cheng Laboratory, Tsinghua University
  2. Chengxin Dai · Beijing Institute of Lifeomics, International Academy of Phronesis Medicine (Guangdong), State Key Laboratory of Medical Proteomics
  3. Tianze Ling · Beijing Institute of Lifeomics, State Key Laboratory of Medical Proteomics, Tsinghua University
  4. Tingpeng Yang · Peng Cheng Laboratory, Tsinghua Shenzhen International Graduate School, Tsinghua University
  5. Yun Yang · International Academy of Phronesis Medicine (Guangdong)
  6. Yeye Leng · International Academy of Phronesis Medicine (Guangdong)
  7. Linhai Xie · Beijing Institute of Lifeomics, International Academy of Phronesis Medicine (Guangdong), State Key Laboratory of Medical Proteomics
  8. Yonghong He · Peng Cheng Laboratory, Tsinghua University
  9. Fuchu He · Beijing Institute of Lifeomics, International Academy of Phronesis Medicine (Guangdong), National Center for Protein Sciences (Beijing), State Key Laboratory of Medical Proteomics
  10. Yu Wang · Peng Cheng Laboratory
  11. Cheng Chang · Beijing Institute of Lifeomics, International Academy of Phronesis Medicine (Guangdong), National Center for Protein Sciences (Beijing), State Key Laboratory of Medical Proteomics

Methods and tools

  • FDR control for AI-based de novo sequencing: FDR-control post-processing layer for the output of AI-based de novo peptide sequencers. Surfaces trustworthy identifications and calibrates confidence scores across models. Applicable to any deep-learning de novo pipeline.

Cites (16)

Seen in the charts

Back to the full map

Back to top