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

A machine learning approach to predicting peptide fragmentation spectra.

Randy J Arnold1, Narmada Jayasankar, Divya Aggarwal

  • 1Department of Chemistry, Indiana University, Bloomington, IN 47405, USA.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|November 11, 2006
PubMed
Summary

This study introduces a data-driven neural network approach to predict peptide fragmentation spectra in mass spectrometry. This method enhances peptide identification accuracy by learning complex fragmentation rules for improved proteomics research.

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

An integrated, scaled approach to resolve TSC2 variants of uncertain significance.

Nature communications·2026
Same author

Saturation Genome Editing reveals the functional impact of RAD51D <i>and</i> XRCC2 variants.

bioRxiv : the preprint server for biology·2026
Same author

Improving splice site usage prediction with SPLAIRE.

bioRxiv : the preprint server for biology·2026
Same author

Structural and functional characterization of thermostable EstS1 esterase for BHET degradation.

Journal of structural biology·2026
Same author

"AR"e We Ignoring the Role of Androgen Receptor (AR) in Breast Carcinomas?

International journal of surgical pathology·2026
Same author

Farber Lipogranulomatosis With Spinal Muscular Atrophy With Progressive Myoclonic Epilepsy: Expanding the Phenotypic Spectrum.

Journal of child neurology·2026

Area of Science:

  • Proteomics
  • Analytical Chemistry
  • Computational Biology

Background:

  • Accurate peptide identification via tandem mass spectrometry is crucial for proteomics.
  • Existing methods (e.g., Sequest, Mascot) face limitations in sensitivity and specificity due to non-uniform peptide fragmentation.
  • Improved de novo peptide fragmentation spectrum prediction is needed for more precise identification.

Purpose of the Study:

  • To develop a data-driven methodology for learning peptide fragmentation rules.
  • To enhance the accuracy of peptide identification in mass spectrometry.
  • To investigate fragmentation patterns across different ion and precursor types.

Main Methods:

  • Utilized a data-driven approach employing neural networks.
  • Learned peptide fragmentation rules as posterior probabilities.

Related Experiment Videos

  • Analyzed fragment-ion types for doubly and triply charged precursor ions.

    • Main Results:

    • The neural network methodology demonstrated useful accuracy for peptide database searches.
    • Identified significant differences in fragmentation rules across various ion and precursor types.
    • The approach provides a more robust understanding of peptide fragmentation.

    Conclusions:

    • A novel neural network-based method improves peptide identification accuracy in proteomics.
    • Understanding specific fragmentation rules is key to advancing mass spectrometry analysis.
    • This data-driven approach offers a promising direction for future proteomics studies.