Identification of DNA-binding and protein-binding proteins using enhanced graph wavelet features
Yuan Zhu1, Weiqiang Zhou2, Dao-Qing Dai3
1Guangdong University of Finance and Economics, Guangzhou and Sun Yat-Sen University, Guangzhou.
IEEE/ACM Transactions on Computational Biology and Bioinformatics
|December 17, 2013
Summary
This study introduces Enhanced Graph Wavelet Features (EGWF) for improved prediction of DNA-binding and protein-binding proteins. EGWF effectively captures neighborhood atom information, outperforming existing methods.
Area of Science:
- Computational Biology
- Bioinformatics
- Machine Learning
Background:
- Biomolecular interactions are crucial for biological processes.
- Existing machine learning methods for predicting binding proteins often overlook neighborhood atom information.
- Current feature representations focus on single atom properties.
Purpose of the Study:
- To propose a novel feature representation method for biomolecular interfaces.
- To enhance the characterization of interface features by incorporating physicochemical properties and graph wavelet theory.
- To improve the accuracy of predicting DNA-binding and protein-binding proteins.
Main Methods:
- Developed Enhanced Graph Wavelet Features (EGWF) by integrating physicochemical features with a graph wavelet formulation.
- Utilized graph wavelets to condense information around central atoms, enhancing feature discrimination.
- Applied EGWF to predict DNA-binding and protein-binding proteins.
Main Results:
- EGWF effectively characterizes biomolecular interface features.
- The method demonstrates enhanced discrimination of features in the feature space.
- Achieved effective performance in predicting DNA-binding and protein-binding proteins.
Conclusions:
- EGWF offers a superior approach for representing biomolecular interfaces.
- The proposed method significantly improves the prediction of binding proteins.
- EGWF shows strong performance metrics, including Matthew's correlation coefficient (MCC) and Area Under the Curve (AUC).
Related Concept Videos
01:15Western Blotting
14.3K
Western blotting is an analytical technique for protein identification. It has various applications in immunology and medicine, including detecting diseases like bovine spongiform encephalopathy, mad cow disease, and human and feline immunodeficiency virus from biological samples.
The technique begins with separating proteins from the sample using sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE), followed by protein transfer, immunoblotting, and finally, protein detection.
The technique begins with separating proteins from the sample using sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE), followed by protein transfer, immunoblotting, and finally, protein detection.
14.3K
02:26Protein Networks
3.7K
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,...
3.7K