Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Semi-supervised learning for peptide identification from shotgun proteomics datasets.

Lukas Käll1, Jesse D Canterbury, Jason Weston

  • 1Department of Genome Sciences, University of Washington, 1705 NE Pacific St., William H. Foege Building, Seattle, Washington 98195, USA.

Nature Methods
|October 24, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Interlaboratory Comparison of a Glucagon and Oxyntomodulin Immuno-LC-MS/MS Assay: Implications for Diabetes Research.

Clinical chemistry·2026
Same author

Spontaneous Isomerization of Tau is Most Prevalent in Alzheimer's Disease.

NeuroMarkers·2026
Same author

Corona: A Virtual Mass Spectrometer for the Development of Real-Time Mass Spectrometry Software.

Analytical chemistry·2026
Same author

DORSSAA: Drug-target interactOmics Resource based on Stability/Solubility Alteration Assay.

Molecular & cellular proteomics : MCP·2026
Same author

Revisiting resonance-excitation collision-induced dissociation for data-independent acquisition.

bioRxiv : the preprint server for biology·2026
Same author

ToxBase: A Multidimensional ToxCast Reference Database for High-Throughput Human Exposome Analysis.

Environmental science & technology·2026

Percolator is a new algorithm that improves protein identification in shotgun proteomics. It uses machine learning to accurately identify more peptides from mass spectrometry data, especially for non-standard samples.

Area of Science:

  • Proteomics
  • Biochemistry
  • Computational Biology

Background:

  • Shotgun proteomics is a key technique for protein identification in biological samples.
  • Liquid chromatography-tandem mass spectrometry (LC-MS/MS) is commonly used in shotgun proteomics.
  • Accurate peptide identification is crucial for reliable protein identification.

Purpose of the Study:

  • To introduce Percolator, an algorithm designed to enhance confident peptide identifications from tandem mass spectra.
  • To improve the accuracy and yield of protein identification in shotgun proteomics workflows.

Main Methods:

  • Development of the Percolator algorithm.
  • Utilizing semi-supervised machine learning for discriminating correct from decoy spectrum identifications.

Related Experiment Videos

  • Application to tryptic and non-tryptic Saccharomyces cerevisiae datasets.

    • Main Results:

    • Percolator correctly assigns peptides to 17% more spectra in tryptic datasets.
    • Percolator identifies up to 77% more spectra in non-tryptic digests compared to fully supervised methods.
    • Demonstrates improved performance in identifying peptides from complex mass spectrometry data.

    Conclusions:

    • Percolator significantly enhances the rate of confident peptide identifications in shotgun proteomics.
    • The algorithm offers substantial improvements, particularly for challenging non-tryptic digests.
    • Percolator represents a valuable advancement for mass spectrometry-based proteomics analysis.