Prosit
adjacent · CNN + RNN
Prosit: adjacent · CNN + RNN. Deep-learning (bidirectional RNN + attention) predictor of peptide fragment-ion intensities and retention times: widely used to validate and rescore de novo sequencing…
Deep-learning (bidirectional RNN + attention) predictor of peptide fragment-ion intensities and retention times: widely used to validate and rescore de novo sequencing candidates against predicted spectra.
| Kind | adjacent |
| Deep learning | yes |
| Acquisition | DDA |
| Family | CNN + RNN |
Code
Live stars, open issues and last-push figures are on the Code activity chart.
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.
Also used, purpose not recorded
- Expanding proteome coverage with CHarge Ordered Parallel Ion aNalysis (CHOPIN) combined with broad specificity proteolys (as deposited)
- HeLa proteome of 12,250 protein-coding genes (as deposited)
- Optimization of Experimental Parameters in Data-Independent Mass Spectrometry Significantly Increases Depth and Reproduc (as deposited)
- ProteomeTools (Parts I-III)
Paper describing it
- Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning (2019, Nature Methods, peer-reviewed)
Papers using it (2)
Applications and evaluations that ran this method. They are not counted among its authors below.
- ScopeNovo: a De Novo Peptide Sequencing Method Using Spectrum-Spectrum Similarity to Refine the Prediction Accuracy (2026, Bioinformatics, peer-reviewed)
- Beyond Best Guesses: A Multi-Level Confidence Assessment Framework for De Novo Peptide Sequencing Results (2026, HUPO 2026 World Congress, presentation)