Jove
Visualize
Contact Us

Related Concept Videos

Protein-protein Interfaces02:04

Protein-protein Interfaces

Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a polypeptide...
Protein-Protein Interfaces02:04

Protein-Protein Interfaces

Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a polypeptide...
Protein Networks02:26

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Protein Networks02:26

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

You might also read

Related Articles

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

Sort by
Same author

Inferring Gene Regulatory Networks from RNA-seq Data Using Kernel Classification.

Biology·2023
Same author

Detecting implicit cross-communities to which an active user belongs.

PloS one·2022
Same author

Personizing the prediction of future susceptibility to a specific disease.

PloS one·2021
Same author

Predicting protein functions by applying predicate logic to biomedical literature.

BMC bioinformatics·2019
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 Video

Updated: May 14, 2026

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay (PCA) in Living Cells
08:38

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay (PCA) in Living Cells

Published on: March 3, 2015

A Review and Experimental Analysis of Supervised Learning Systems and Methods for Protein-Protein Interaction

Kamal Taha1

  • 1Department of Computer Science, Khalifa University, Abu Dhabi P.O. Box 127788, United Arab Emirates.

International Journal of Molecular Sciences
|May 13, 2026
PubMed
Summary

This survey evaluates ten supervised learning models for protein-protein interaction (PPI) prediction. Graph Neural Networks (GNNs) and Deep Neural Networks (DNNs) offer the highest accuracy, while Extreme Learning Machines (ELM) and Naïve Bayes provide superior efficiency.

Keywords:
CNNELMGNNKNNPPISVMmachine learning modelsprotein–protein interactionsupervised learning

More Related Videos

Probing High-density Functional Protein Microarrays to Detect Protein-protein Interactions
08:07

Probing High-density Functional Protein Microarrays to Detect Protein-protein Interactions

Published on: August 2, 2015

Mapping Dysfunctional Protein-Protein Interactions in Disease
09:39

Mapping Dysfunctional Protein-Protein Interactions in Disease

Published on: October 24, 2025

Related Experiment Videos

Last Updated: May 14, 2026

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay (PCA) in Living Cells
08:38

Genome-wide Protein-protein Interaction Screening by Protein-fragment Complementation Assay (PCA) in Living Cells

Published on: March 3, 2015

Probing High-density Functional Protein Microarrays to Detect Protein-protein Interactions
08:07

Probing High-density Functional Protein Microarrays to Detect Protein-protein Interactions

Published on: August 2, 2015

Mapping Dysfunctional Protein-Protein Interactions in Disease
09:39

Mapping Dysfunctional Protein-Protein Interactions in Disease

Published on: October 24, 2025

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning in genomics

Background:

  • Protein-protein interactions (PPIs) are crucial for cellular functions and disease mechanisms.
  • Experimental PPI identification is resource-intensive and lacks scalability.
  • Computational prediction methods are essential for handling large-scale omics data.

Purpose of the Study:

  • To systematically evaluate ten supervised learning models for computational PPI prediction.
  • To provide a method-aware analysis integrating quantitative, observational, and experimental evaluations.
  • To offer practical guidance for deploying PPI prediction models in real-world scenarios.

Main Methods:

  • A tri-layered framework: Comparative Quantitative Analysis, Comparative Observational Analysis, and Experimental Evaluations.
  • Investigation of ten supervised learning models: ELM, CNNs, GNNs, DNNs, Naïve Bayes, Probabilistic Decision Tree, SVM, LS-SVM, KNN, and WKNN.
  • Empirical validation on benchmark datasets to assess predictive performance, interpretability, scalability, and efficiency.

Main Results:

  • GNNs and DNNs achieve the highest predictive accuracy by capturing complex relationships.
  • ELM and Naïve Bayes demonstrate superior computational efficiency.
  • SVM and LS-SVM exhibit robust stability in noisy data; CNNs excel in sequence-based tasks.
  • Instance-based methods (KNN, WKNN) show performance variations based on feature noise and dataset quality.

Conclusions:

  • The study provides a comprehensive, evidence-backed perspective on the strengths, weaknesses, and practical applicability of various PPI prediction models.
  • Findings clarify trade-offs between accuracy, efficiency, and scalability, guiding researchers in selecting appropriate methods.
  • Decision-grade guidance is offered, bridging theoretical knowledge with practical implementation for PPI detection.