Semi-supervised learning for peptide identification from shotgun proteomics datasets - PubMed (original) (raw)

doi: 10.1038/nmeth1113. Epub 2007 Oct 21.

Affiliations

Semi-supervised learning for peptide identification from shotgun proteomics datasets

Lukas Käll et al. Nat Methods. 2007 Nov.

Abstract

Shotgun proteomics uses liquid chromatography-tandem mass spectrometry to identify proteins in complex biological samples. We describe an algorithm, called Percolator, for improving the rate of confident peptide identifications from a collection of tandem mass spectra. Percolator uses semi-supervised machine learning to discriminate between correct and decoy spectrum identifications, correctly assigning peptides to 17% more spectra from a tryptic Saccharomyces cerevisiae dataset, and up to 77% more spectra from non-tryptic digests, relative to a fully supervised approach.

PubMed Disclaimer

Similar articles

Cited by

Publication types

MeSH terms

Substances

LinkOut - more resources