Nature Methods
- 4, 923 - 925 (2007)
Published online: 21 October 2007; | doi:10.1038/nmeth1113
Semi-supervised learning for peptide identification from shotgun proteomics datasetsLukas Käll1, Jesse D Canterbury1, Jason Weston2, William Stafford Noble1, 3 & Michael J MacCoss11
Department of Genome Sciences, University of Washington, 1705 NE Pacific St., William H. Foege Building, Seattle, Washington 98195, USA. 2
NEC Laboratories America, Inc., 4 Independence Way, Suite 200, Princeton, New Jersey 08540, USA. 3
Department of Computer Science and Engineering, University of Washington, AC101 Paul G. Allen Center, 185 Stevens Way, Seattle, Washington 98195, USA.
Correspondence should be addressed to Michael J MacCoss maccoss@u.washington.edu 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.
MORE ARTICLES LIKE THIS These links to content published by NPG are automatically generated.
|
