Related Experiment Video
Updated: Sep 27, 2025

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins
Published on: July 8, 2025
iScore: An MPI supported software for ranking protein-protein docking models based on a random walk graph kernel and
Nicolas Renaud1, Yong Jung2, Vasant Honavar2,3
1Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, The Netherlands.
iScore software accurately ranks protein-protein docking models using graph kernel methods. This computational tool enhances the analysis of protein-protein interactions and structures.
Area of Science:
- Computational biology
- Structural bioinformatics
- Machine learning in bioinformatics
Background:
- Protein-protein interactions are crucial for cellular functions.
- Computational docking models 3D protein complex structures.
- Accurate scoring of docking models remains a challenge.
Purpose of the Study:
- To present the iScore software for scoring protein-protein docking models.
- To provide an automated workflow for computational docking analysis.
- To leverage graph kernels for improved model ranking.
Main Methods:
- Utilizes a novel graph kernel-based scoring function (iScore).
- Employs a support vector machine with random-walk graph kernels.
- Implements Message Passing Interface (MPI) and CUDA for distributed computing.
Main Results:
- iScore software automates the computational docking workflow.
- The software ranks models based on interface graph similarity.
- Enables distributed and GPU-accelerated analysis.
Conclusions:
- iScore software offers an efficient solution for the protein-protein docking scoring problem.
- The tool facilitates deeper insights into protein functions through structural analysis.
- Advanced computational techniques enhance the accuracy and scalability of docking predictions.
More Related Videos
Related Concept Videos
Protein-protein Interfaces
Protein-Protein Interfaces
Molecular Models
Protein Networks
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,...
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
Protein Folding Quality Check in the RER

