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

Improving domain-based protein interaction prediction using biologically significant negative datasets.

Xiao-Li Li1, Soon-Heng Tan, See-Kiong Ng

  • 1Knowledge Discovery Department, Institute For Infocomm Research, 21 Heng Mui Keng Terrace, Singapore 119613. xlli@i2r.a-star.edu.sg

International Journal of Data Mining and Bioinformatics
|April 11, 2008
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

Towards Accurate and Reliable ICU Outcome Prediction: A Multimodal Learning Framework Based on Belief Function Theory using Structured EHRs and Free-Text Notes.

Journal of healthcare informatics research·2026
Same author

Evaluating Large Language Models on Named Entity Recognition.

IEEE transactions on neural networks and learning systems·2026
Same author

Principled Multimodal Representation Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

MoEGAD: A Mixture-of-Experts Framework With Pseudo-Anomaly Generation for Graph-Level Anomaly Detection.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Bioactive Rosane and Podocarpane Diterpenoids From the Whole Plant of Jatropha curcas L.

Chemistry & biodiversity·2025
Same author

An innovative external drainage device for suprachoroidal fluid: the puncture needle with drainage groove.

International journal of ophthalmology·2025
Same journal

DiffGRN: differential gene regulatory network analysis.

International journal of data mining and bioinformatics·2019
Same journal

Integration of multi-omics data for integrative gene regulatory network inference.

International journal of data mining and bioinformatics·2018
Same journal

The development of non-coding RNA ontology.

International journal of data mining and bioinformatics·2016
Same journal

Learning multiple distributed prototypes of semantic categories for named entity recognition.

International journal of data mining and bioinformatics·2015
Same journal

Weighted fusion regularisation and predicting microbial interactions with vector autoregressive model.

International journal of data mining and bioinformatics·2015
Same journal

Application of consensus string matching in the diagnosis of allelic heterogeneity involving transposition mutation.

International journal of data mining and bioinformatics·2015
See all related articles

We developed a domain-based method to predict protein-protein interactions. Using carefully selected non-interacting protein pairs improves prediction accuracy, enhancing biological data analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Molecular Interactions

Background:

  • Protein-protein interactions (PPIs) are crucial for cellular functions.
  • Predicting PPIs is essential for understanding biological pathways.
  • Accurate negative datasets are vital for training reliable prediction models.

Purpose of the Study:

  • To propose a novel domain-based classification method for predicting protein-protein interactions.
  • To evaluate the impact of carefully generated negative training data on prediction performance.

Main Methods:

  • Utilized probabilities of putative interacting domain pairs.
  • Derived data from experimentally determined interacting protein pairs.
  • Incorporated carefully chosen non-interacting protein pairs as negative training data.

Related Experiment Videos

  • Performed multi-species comparative analysis for validation.

    • Main Results:

    • The proposed domain-based method demonstrated effectiveness in predicting protein-protein interactions.
    • The inclusion of biologically meaningful negative training data significantly improved classification performance.
    • Comparative analysis across multiple species confirmed the robustness of the approach.

    Conclusions:

    • Domain-based classification is a viable strategy for predicting protein-protein interactions.
    • The quality and biological relevance of negative training data are critical for enhancing prediction accuracy.
    • This method offers a valuable tool for advancing the study of molecular interactions.