Prime-DiffNovo: Accurate Peptide De Novo Sequencing via Non-autoregressive Generation and Diffusion Refinement

peer-reviewed · Lecture Notes in Computer Science (ISBRA 2026) · 2026

peer-reviewed · Lecture Notes in Computer Science (ISBRA 2026) · 2026. Xuan Yu et al.
Date 2026-07-15
Type peer-reviewed
Venue Lecture Notes in Computer Science (ISBRA 2026)
Publisher Springer Nature Singapore
Contribution algorithm
DOI 10.1007/978-981-92-3719-7_16
Citations (OpenAlex) 0

Authors

  1. Xuan Yu · City University of Hong Kong
  2. Kunyi Li · City University of Hong Kong
  3. Lusheng Wang · City University of Hong Kong

Methods and tools

  • Prime-DiffNovo: Non-autoregressive Transformer de novo peptide sequencer with a diffusion-based refinement step at inference time: the NAR pass drafts a full sequence in parallel, and the diffusion loop iteratively corrects residue predictions to sharpen accuracy.

Data used

Cites (13)

Seen in the charts

Back to the full map

Back to top