FDR control for AI-based de novo sequencing
post-processor
FDR control for AI-based de novo sequencing: post-processor. FDR-control post-processing layer for the output of AI-based de novo peptide sequencers. Surfaces trustworthy identifications and calibrates confidence scores across…
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.
| Kind | post-processor |
| Deep learning | yes |
| Acquisition | DDA |
Data
What the papers describing this method trained it on and reported its results on, as each paper states it. A version is named only where the paper names one.
Trained on
- CPTAC CCRCC Discovery Study - DIA Proteome (as deposited)
- Deep Human Proteome Sequencing Enables Global Detection of Mutations and Alternative Splicing (as deposited)
- GraphNovo dataset and checkpoint (as deposited)
- MassIVE-KB (v1)
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-independent acquisition (as deposited)
Evaluated on
- CPTAC CCRCC Discovery Study - DIA Proteome (as deposited)
- Deep Human Proteome Sequencing Enables Global Detection of Mutations and Alternative Splicing (as deposited)
- GraphNovo dataset and checkpoint (as deposited)
- Nine-species benchmark (version not stated)
- Open-pFind enables precise, comprehensive and rapid peptide identification in shotgun proteomics, part 1 (as deposited)
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-independent acquisition (as deposited)
Paper describing it
- False discovery rate control for trustworthy AI-based de novo peptide sequencing (2026, bioRxiv, preprint)