Universiti Teknologi Malaysia Institutional Repository

Predicting protein-protein interactions as a one-class classification problem

Alashwal, Hany and Deris, Safaai and Othman, Razib M. (2006) Predicting protein-protein interactions as a one-class classification problem. In: Proceedings of the Postgraduate Annual Research Seminar 2006 (PARS 2006), 24-25 May 2006, Postgraduate Studies Department FSKSM, UTM Skudai.

PDF - Published Version


Protein-protein interactions represent a key step in understanding proteins functions. This is due to the fact that proteins usually work in context of other proteins and rarely function alone. Machine learning techniques have been used to predict protein-protein interactions. However, most of these techniques address this problem as a binary classification problem. While it is easy to get a dataset of interacting protein as positive example, there is no experimentally confirmed non-interacting protein to be considered as a negative set. Therefore, in this paper we solve this problem as a one-class classification problem using One-Class SVM (OCSVM). Using only positive examples (interacting protein pairs) for training, the OCSVM achieves accuracy of 80%. These results imply that protein-protein interaction can be predicted using one-class classifier with reliable accuracy.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:One-Class Classifier, Support Vector Machine, Bioinformatics, Protein-Protein Interaction Prediction
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computer Science and Information System (Formerly known)
ID Code:4931
Deposited By: Tajul Ariffin Musa
Deposited On:16 Jan 2008 02:19
Last Modified:30 Aug 2017 01:25

Repository Staff Only: item control page