Related Experiment Video
Updated: Apr 11, 2026
13:56
A Comparative Approach to Characterize the Landscape of Host-Pathogen Protein-Protein Interactions
Published on: July 18, 2013
11.7K
Improved Method for Predicting GPCR-GPCR Interaction Pairs
Aoi Fukushima1, Arina Ouma2, Hiroki Teruse3
1Master's Programs in Life Science and Engineering, Graduate School of Science and Engineering, Tokyo Denki University (TDU), Saitama, Japan.
Proteins
|April 10, 2026
Summary
This study enhances a tool to predict G protein-coupled receptor (GPCR) interactions, finding that interacting GPCRs are linked to diseases like schizophrenia and hypertension, aiding drug development.
Area of Science:
- Biochemistry and Molecular Biology
- Computational Biology and Cheminformatics
- Pharmacology and Drug Discovery
Background:
- G protein-coupled receptors (GPCRs) form oligomers, influencing signaling pathways and disease states (e.g., schizophrenia, hypertension).
- Understanding GPCR oligomerization is crucial for disease mechanism elucidation and therapeutic strategy development.
- Previous work established a GPCR-GPCR interaction pair predictor (GGIP) using Support Vector Machines (SVM).
Purpose of the Study:
- To improve the predictive accuracy of the GPCR-GPCR interaction pair predictor (GGIP).
- To explore novel feature generation and prediction algorithms for GPCR interaction prediction.
- To investigate the association between GPCR interaction pairs and disease-related gene expression.
Main Methods:
- Evaluated four methods combining two feature generation techniques (sequence segmentation, autoencoder) with two algorithms (SVM, gradient-boosting decision tree - GBDT).
- Assessed prediction performance using Area Under the Receiver Operating Characteristic curve (AUROC).
- Integrated improved prediction with disease-related gene expression variation data.
Main Results:
- The combination of segmentation-based feature generation and GBDT achieved the highest performance (AUROC > 0.98).
- Identified specific amino acid properties and structural arrangements as key predictive features for GPCR interaction.
- Demonstrated a significant association between GPCR interaction pairs and disease-related differentially expressed genes (DEGs), with ~90% of interaction pairs involving at least one DEG.
Conclusions:
- Enhanced GPCR-GPCR interaction prediction using segmentation-based features and GBDT significantly improves accuracy.
- GPCR interaction pairs are strongly linked to disease-related gene expression changes, highlighting their pathological relevance.
- This approach is vital for identifying disease-associated GPCR interactions and guiding the development of novel therapeutics.
More Related Videos
Related Concept Videos
02:04Protein-protein Interfaces
15.0K
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...
15.0K
02:26Protein Networks
4.7K
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,...
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,...
4.7K