Winnow
post-processor
Winnow: post-processor. NN rescoring + decoy-free FDR
NN rescoring + decoy-free FDR
| Kind | post-processor |
| Deep learning | yes |
| Acquisition | both |
Code
Live stars, open issues and last-push figures are on the Code activity chart.
Checkpoints
| Version | Trained on | Host | Licence | Size | Checked |
|---|---|---|---|---|---|
| hold-one-out calibrators | each training set minus the held-out one | figshare archival | CC-BY-4.0 | 167 KB | live 2026-10-03 |
| HeLa QC model | — | Hugging Face | CC-BY-NC-SA-4.0 | — | live 2026-10-02 |
A host marked archival has a DOI and keeps what it is given. The others can move or disappear, which is why they are checked rather than merely listed. verified means the bytes were fetched and hashed on the date shown; live means only that the host answered when last asked.
Paper describing it
- De novo peptide sequencing rescoring and FDR estimation with Winnow (2025, arXiv, preprint)
Paper using it
An application or evaluation that ran this method. It is not counted among its authors below.
- Generalizable Direct Protein Sequencing With InstaNexus (2026, Molecular & Cellular Proteomics, peer-reviewed)