One-class support vector machines for protein-protein interactions prediction
Predicting 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 applied to predict protein-protein interactions. However,...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Academy of Science, Engineering and Technology
2006
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/8405/ http://eprints.utm.my/8405/1/8405.pdf |
| _version_ | 1848891680485277696 |
|---|---|
| author | Alashwal, H. Deris, Safaai Othman, M. R. |
| author_facet | Alashwal, H. Deris, Safaai Othman, M. R. |
| author_sort | Alashwal, H. |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | Predicting 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 applied to predict protein-protein interactions. However, most of these techniques address this problem as a binary classification problem. Although it is easy to get a dataset of interacting proteins as positive examples, there are no experimentally confirmed non-interacting proteins to be considered as negative examples. Therefore, in this paper we solve this problem as a one-class classification problem using one-class support vectormmachines (SVM). Using only positive examples (interacting protein pairs) in training phase, the one-class SVM achieves accuracy of about 80%. These results imply that proteinprotein interaction can be predicted using one-class classifier with comparable accuracy to the binary classifiers that use artificially constructed negative examples. |
| first_indexed | 2025-11-15T21:01:49Z |
| format | Article |
| id | utm-8405 |
| institution | Universiti Teknologi Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T21:01:49Z |
| publishDate | 2006 |
| publisher | World Academy of Science, Engineering and Technology |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utm-84052017-10-16T04:23:47Z http://eprints.utm.my/8405/ One-class support vector machines for protein-protein interactions prediction Alashwal, H. Deris, Safaai Othman, M. R. QA75 Electronic computers. Computer science Predicting 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 applied to predict protein-protein interactions. However, most of these techniques address this problem as a binary classification problem. Although it is easy to get a dataset of interacting proteins as positive examples, there are no experimentally confirmed non-interacting proteins to be considered as negative examples. Therefore, in this paper we solve this problem as a one-class classification problem using one-class support vectormmachines (SVM). Using only positive examples (interacting protein pairs) in training phase, the one-class SVM achieves accuracy of about 80%. These results imply that proteinprotein interaction can be predicted using one-class classifier with comparable accuracy to the binary classifiers that use artificially constructed negative examples. World Academy of Science, Engineering and Technology 2006 Article PeerReviewed application/pdf en http://eprints.utm.my/8405/1/8405.pdf Alashwal, H. and Deris, Safaai and Othman, M. R. (2006) One-class support vector machines for protein-protein interactions prediction. International Journal of Biological and Medical Sciences, 1 (2). pp. 120-127. ISSN 1307-7457 http://www.waset.org/ijbms/ |
| spellingShingle | QA75 Electronic computers. Computer science Alashwal, H. Deris, Safaai Othman, M. R. One-class support vector machines for protein-protein interactions prediction |
| title | One-class support vector machines for protein-protein interactions prediction |
| title_full | One-class support vector machines for protein-protein interactions prediction |
| title_fullStr | One-class support vector machines for protein-protein interactions prediction |
| title_full_unstemmed | One-class support vector machines for protein-protein interactions prediction |
| title_short | One-class support vector machines for protein-protein interactions prediction |
| title_sort | one-class support vector machines for protein-protein interactions prediction |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/8405/ http://eprints.utm.my/8405/ http://eprints.utm.my/8405/1/8405.pdf |