Random Forest
2 methods · 2013–2023
Random Forest: Tree ensembles, used to predict fragment-ion intensities and to combine several sequencers’ output under a controlled error rate, rather than to sequence a spectrum directly.
Tree ensembles, used to predict fragment-ion intensities and to combine several sequencers’ output under a controlled error rate, rather than to sequence a spectrum directly.
The earliest of its 2 methods is MS2PIP (2013).
| Methods | 2 |
| Papers describing them | 4 |
| Authors | 12 |
| Active | 2013-09-27 to 2023-07-05 |
| Kinds | adjacent, post-processor |
| Acquisition | DDA (2) |
Methods (2)
Oldest first, by the paper that describes each one.
- MS2PIP (2013): Predictor of MS/MS fragment-ion peak intensities, used to rescore search-engine and de novo sequencing results. Introduced in 2013 as a random-forest model; the 2019 web-server update added models for further fragmentation methods, instruments and labelling techniques, and the 2023 update added tryptic, non-tryptic, immunopeptide and TMT models and proteome-wide predicted spectral libraries with DeepLC retention times.
- PostNovo (2018): FDR-controlled ensembling
Papers describing them (4)
- MS2PIP: a tool for MS/MS peak intensity prediction (2013, Bioinformatics, peer-reviewed)
- Postnovo: Postprocessing Enables Accurate and FDR-Controlled de Novo Peptide Sequencing (2018, Journal of Proteome Research, peer-reviewed)
- Updated MS²PIP web server delivers fast and accurate MS² peak intensity prediction for multiple fragmentation methods, instruments and labeling techniques (2019, Nucleic Acids Research, peer-reviewed)
- Updated MS²PIP web server supports cutting-edge proteomics applications (2023, Nucleic Acids Research, peer-reviewed)