Semi-supervised learning for peptide identification from shotgun proteomics datasets
2007 (English)In: Nature Methods, ISSN 1548-7091, E-ISSN 1548-7105, Vol. 4, no 11, 923-925 p.Article in journal (Refereed) Published
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.
Place, publisher, year, edition, pages
2007. Vol. 4, no 11, 923-925 p.
Bioinformatics (Computational Biology)
IdentifiersURN: urn:nbn:se:kth:diva-48858DOI: 10.1038/nmeth1113ISI: 000250575700016PubMedID: 17952086OAI: oai:DiVA.org:kth-48858DiVA: diva2:458731
QC 201111242011-11-232011-11-232011-11-24Bibliographically approved