Predicting protein-protein interactions as a one-class classification problem
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...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2006
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/4931/ http://eprints.utm.my/4931/1/SafaaiDeris2006_Predictin_ProteinProteinInteractionsasaOneClass.pdf |
| _version_ | 1848890924503924736 |
|---|---|
| author | Alashwal, Hany Deris, Safaai Othman, Razib M. |
| author_facet | Alashwal, Hany Deris, Safaai Othman, Razib M. |
| author_sort | Alashwal, Hany |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-15T20:49:48Z |
| format | Conference or Workshop Item |
| id | utm-4931 |
| institution | Universiti Teknologi Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:49:48Z |
| publishDate | 2006 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utm-49312017-08-30T01:25:01Z http://eprints.utm.my/4931/ Predicting protein-protein interactions as a one-class classification problem Alashwal, Hany Deris, Safaai Othman, Razib M. QA75 Electronic computers. Computer science 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. 2006 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/4931/1/SafaaiDeris2006_Predictin_ProteinProteinInteractionsasaOneClass.pdf 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. |
| spellingShingle | QA75 Electronic computers. Computer science Alashwal, Hany Deris, Safaai Othman, Razib M. Predicting protein-protein interactions as a one-class classification problem |
| title | Predicting protein-protein interactions as a one-class classification problem |
| title_full | Predicting protein-protein interactions as a one-class classification problem |
| title_fullStr | Predicting protein-protein interactions as a one-class classification problem |
| title_full_unstemmed | Predicting protein-protein interactions as a one-class classification problem |
| title_short | Predicting protein-protein interactions as a one-class classification problem |
| title_sort | predicting protein-protein interactions as a one-class classification problem |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/4931/ http://eprints.utm.my/4931/1/SafaaiDeris2006_Predictin_ProteinProteinInteractionsasaOneClass.pdf |