MS2Rescore

adjacent

MS2Rescore: adjacent. Data-driven PSM rescoring framework that mixes search-engine scores with DL-predicted features (MS2PIP fragment intensities, DeepLC retention times, ion-mobility, etc.)…

Data-driven PSM rescoring framework that mixes search-engine scores with DL-predicted features (MS2PIP fragment intensities, DeepLC retention times, ion-mobility, etc.); used to boost de novo + database-search identification rates, including downstream of Casanovo / DeepNovo.

Kind	adjacent
Deep learning	yes
Acquisition	DDA

Code

• https://github.com/compomics/ms2rescore

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.

Deposited

• Code and data sets for “MS²Rescore: Data-driven rescoring dramatically boosts immunopeptide identification rates” (as deposited)
• MS²Rescore: Data-driven rescoring dramatically boosts immunopeptide identification rates (as deposited)

Also used, purpose not recorded

• Deep learning boosts immunopeptidomics one mass spectrum at a time (as deposited)
• Fully unsupervised identification of HLA-I motifs (as deposited)
• The pancreatic islet MHC-II peptidome identifies key features of autoimmune peptides (as deposited)

Paper describing it

• MS2Rescore: Data-Driven Rescoring Dramatically Boosts Immunopeptide Identification Rates (2022, Molecular & Cellular Proteomics, peer-reviewed)

Authors (7)

Arthur Declercq, Robbin Bouwmeester, Aurélie Hirschler, Christine Carapito, Sven Degroeve, Lennart Martens, Ralf Gabriels

Seen in the charts

• Code activity
• Models and the authors behind them

Back to the full map