Abstract
We introduce SVM-Net, a method for detecting multiprotein complexes. Detecting multiprotein complexes is becoming crucial to the study and understanding of system biology and it could be a way to reveal the biochemical functions of a protein. Most of the recently developed methods focus on topological information to detect multiprotein complexes. In this chapter, biological and topological features characterizing protein complexes are extracted and used in conjunction with support vector machines to detect multiprotein complexes from the protein-protein interaction network. SVM-Net was able to detect 76 functional complexes out of 81 reference complexes with high precision. In comparison with state-of-the-art methods, the evaluation results indicate that the SVM-Net has great potential in detecting multiprotein complexes.
Original language | English |
---|---|
Title of host publication | Emerging Trends in Applications and Infrastructures for Computational Biology, Bioinformatics, and Systems Biology |
Subtitle of host publication | Systems and Applications |
Publisher | Elsevier Inc. |
Pages | 305-315 |
Number of pages | 11 |
ISBN (Electronic) | 9780128042595 |
ISBN (Print) | 9780128042038 |
DOIs | |
Publication status | Published - Mar 22 2016 |
Keywords
- Biological process
- Cellular localization
- Multiclass SVM
- Network topological features
- Protein complex
ASJC Scopus subject areas
- Computer Science(all)