Related Experiment Video
Updated: Nov 30, 2025
Mapping Dysfunctional Protein-Protein Interactions in Disease
Published on: October 24, 2025
DPPN-SVM: Computational Identification of Mis-Localized Proteins in Cancers by Integrating Differential Gene
Guang-Ping Li1, Pu-Feng Du1, Zi-Ang Shen1
1College of Intelligence and Computing, Tianjin University, Tianjin, China.
Abstract:
Eukaryotic cells contain numerous components, which are known as subcellular compartments or subcellular organelles. Proteins must be sorted to proper subcellular compartments to carry out their molecular functions. Mis-localized proteins are related to various cancers. Identifying mis-localized proteins is important in understanding the pathology of cancers and in developing therapies. However, experimental methods, which are used to determine protein subcellular locations, are always costly and time-consuming. We tried to identify cancer-related mis-localized proteins in three different cancers using computational approaches. By integrating gene expression profiles and dynamic protein-protein interaction networks, we established DPPN-SVM (Dynamic Protein-Protein Network with Support Vector Machine), a predictive model using the SVM classifier with diffusion kernels. With this predictive model, we identified a number of mis-localized proteins. Since we introduced the dynamic protein-protein network, which has never been considered in existing works, our model is capable of identifying more mis-localized proteins than existing studies. As far as we know, this is the first study to incorporate dynamic protein-protein interaction network in identifying mis-localized proteins in cancers.
Insights
Identifying cancer-related mis-localized proteins is crucial for understanding cancer pathology and developing therapies. This study introduces a novel computational model, DPPN-SVM, to accurately identify these mis-localized proteins using dynamic protein-protein interaction networks.
Area of Science:
- Cell biology
- Bioinformatics
- Computational oncology
Background:
- Eukaryotic cells possess subcellular compartments essential for protein function.
- Mis-localization of proteins is implicated in the development of various cancers.
- Experimental methods for determining protein localization are resource-intensive.
Purpose of the Study:
- To computationally identify cancer-related mis-localized proteins.
- To develop a predictive model integrating gene expression and dynamic protein-protein interactions.
- To improve the identification of mis-localized proteins compared to existing methods.
Main Methods:
- Development of the DPPN-SVM (Dynamic Protein-Protein Network with Support Vector Machine) model.
- Integration of gene expression profiles and dynamic protein-protein interaction networks.
- Utilizing a Support Vector Machine (SVM) classifier with diffusion kernels for prediction.
Main Results:
- Identification of a significant number of mis-localized proteins associated with cancer.
- Demonstration of the DPPN-SVM model's enhanced capability in identifying mis-localized proteins.
- Establishment of a novel approach incorporating dynamic protein-protein interaction networks.
Conclusions:
- The DPPN-SVM model offers a powerful computational tool for identifying cancer-related mis-localized proteins.
- Incorporating dynamic protein-protein interaction networks significantly improves the accuracy of mis-localized protein identification.
- This approach holds promise for advancing cancer research and therapeutic development.
Related Concept Videos
02:26Protein 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,...
02:04Protein-protein Interfaces