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

Using product kernels to predict protein interactions.

Shawn Martin1, W Michael Brown, Jean-Loup Faulon

  • 1Computational Biology, Sandia National Laboratories, PO Box 5800, 87185-1316, Albuquerque, NM 87185-1316, USA. smartin@sandia.gov

Advances in Biochemical Engineering/Biotechnology
|October 9, 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

Active-learning-guided optimization of cell-free systems for genome-wide transcriptomic profiling reveals progressive layers of regulation.

Nature communications·2026
Same author

dAMN: a genome-scale neural-mechanistic hybrid model to predict bacterial growth dynamics.

Bioinformatics (Oxford, England)·2026
Same author

RetroRules 2026: an expanded database combining biochemical and organic reaction templates for pathway discovery.

Nucleic acids research·2025
Same author

Microbial computing: Review and Perspectives.

Biotechnology advances·2025
Same author

BioRGroup dataset: R-group expansion of ChEBI molecules referenced in the Rhea database.

Scientific data·2025
Same author

An AI-driven workflow for the accelerated optimization of cell-free protein synthesis.

iScience·2025
Same journal

Valorization of Agricultural Residues Through Nutrient Enrichment for Animal Farming.

Advances in biochemical engineering/biotechnology·2026
Same journal

Safety Aspects of Cell Culture-Derived Food for Human Consumption.

Advances in biochemical engineering/biotechnology·2026
Same journal

Correction to: Perspectives Towards AI and ML.

Advances in biochemical engineering/biotechnology·2026
Same journal

Valorization of Agricultural Residues for Biohydrogen Production via Dark Fermentation.

Advances in biochemical engineering/biotechnology·2026
Same journal

Composting of Agricultural Residues into Organic Fertilizers for Sustainable Agriculture.

Advances in biochemical engineering/biotechnology·2026
Same journal

Correction to: Theoretical Perspectives for Biomolecular Crystallization Prediction.

Advances in biochemical engineering/biotechnology·2026
See all related articles

Computational methods can predict protein interactions, including protein-protein, beta-strand, and protein-chemical interactions. Support Vector Machine product kernels offer a powerful approach for these predictions, complementing experimental identification methods.

Area of Science:

  • Biochemistry
  • Bioinformatics
  • Computational Biology

Background:

  • Numerous experimental methods exist for identifying protein interactions.
  • This has led to the development of diverse computational approaches for modeling and predicting these interactions.
  • Computational methods vary from detailed structure-based to broad statistical approaches.

Purpose of the Study:

  • To discuss the merits of various experimental and computational methods for identifying protein interactions.
  • To detail a specific computational method using Support Vector Machine (SVM) product kernels.
  • To demonstrate the application of this SVM method for predicting different types of molecular interactions.

Main Methods:

  • Discussion of existing experimental and computational techniques for protein interaction identification.

Related Experiment Videos

  • Application of Support Vector Machine (SVM) product kernels as a computational approach.
  • Detailed description and application of the SVM method for predicting protein-protein, beta-strand, and protein-chemical interactions.

    • Main Results:

    • The study highlights the diverse landscape of protein interaction identification methods.
    • It emphasizes the utility of Support Vector Machine (SVM) product kernels for computational prediction.
    • The SVM method is shown to be applicable for predicting protein-protein, beta-strand, and protein-chemical interactions.

    Conclusions:

    • Computational methods, particularly those using Support Vector Machine (SVM) product kernels, are valuable tools for predicting protein interactions.
    • The discussed SVM approach offers a versatile method for identifying various interaction types.
    • This work contributes to the field of bioinformatics by detailing and applying an effective computational strategy for molecular interaction prediction.