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

An integrated machine learning system to computationally screen protein databases for protein binding peptide

Ling Zhang1, Chen Shao, Dexian Zheng

  • 1Proteomics Research Center, National Key Laboratory of Medical Molecular Biology, Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences/Peking Union Medical College, 5 Dong Dan San Tiao, 100005 Beijing, China.

Molecular & Cellular Proteomics : MCP
|April 1, 2006
PubMed
Summary

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

Henagliflozin promotes mitophagy in renal tubular cells by activating AMPK/ULK1 to alleviate the progression of diabetic kidney disease.

Histology and histopathology·2026
Same author

<b>Erratum: HAIFENG HAN, XIAOJIN XUE, ZHISHENG ZHANG & CHEN SHAO (2026) Morphology and molecular phylogeny of a new ciliate, <i>Hemiurosomoida sinica</i> sp. nov. (Ciliophora, Hypotrichia). <i>Zootaxa</i>, 5750 (2): 241-250.</b>

Zootaxa·2026
Same author

<b>Morphology and molecular phylogeny of a new ciliate, <i>Hemiurosomoida sinica</i> sp. nov. (Ciliophora, Hypotrichia)</b>.

Zootaxa·2026
Same author

Beyond classification metrics: a psychometric-aware benchmark for data augmentation in imbalanced student mental health surveys.

Frontiers in digital health·2026
Same author

School and family based myopia education associations with myopia prevalence in Hefei high school students in the post-COVID-19 period.

Scientific reports·2026
Same author

Comparative genomics of parasitic and symbiotic microeukaryotes: Phylogenomic insights into lifestyle transitions and co-evolutionary dynamics.

Molecular phylogenetics and evolution·2026

Computational methods can efficiently identify protein interactions, overcoming experimental limitations. This study developed machine learning models to predict peptide ligands for Src homology 3 (SH3) and PDZ domains, aiding future research.

Area of Science:

  • Molecular Biology
  • Bioinformatics
  • Computational Biology

Background:

  • Protein interactions are crucial for cellular functions and are often mediated by peptide-binding domains like SH2, SH3, and PDZ.
  • Experimental screening for protein-ligand interactions is labor-intensive and struggles with low-abundance species.
  • Existing computational predictors lack sufficient accuracy for large-scale database screening.

Purpose of the Study:

  • To develop and apply high-throughput computational approaches for identifying protein-protein interactions.
  • To screen protein sequence databases for potential peptide ligands of SH3 and PDZ domains.
  • To improve the accuracy and generalization capability of computational predictors for protein interaction studies.

Main Methods:

  • Integrated machine learning systems were developed using three novel coding methods.

Related Experiment Videos

  • Swiss-Prot and GenBank protein databases were screened for potential ligands.
  • The models were validated for their ability to predict interactions for 10 SH3 and three PDZ domains.

    • Main Results:

    • A significant number of predicted protein-ligand interactions were subsequently confirmed experimentally by independent research groups.
    • The developed machine learning systems demonstrated satisfying generalization capabilities.
    • The computational approach successfully identified potential ligands for SH3 and PDZ domains.

    Conclusions:

    • High-throughput computational screening is a viable and efficient strategy for identifying protein-protein interactions.
    • The developed machine learning models show promise for future applications in discovering novel protein interactions.
    • This work facilitates experimental validation by directing researchers toward the most promising peptide candidates.