A hybrid approach to extract protein-protein interactions
Motivation: Protein–protein interactions (PPIs) play an important role in understanding biological processes. Although recent research in text mining has achieved a significant progress in automatic PPI extraction from literature, performance of existing systems still needs to be improved. Results: I...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2014
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/96394 http://hdl.handle.net/10220/18848 |
| _version_ | 1826117250327773184 |
|---|---|
| author | Sloot, Peter M. A. Bui, Quoc-Chinh Katrenko, Sophia |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Sloot, Peter M. A. Bui, Quoc-Chinh Katrenko, Sophia |
| author_sort | Sloot, Peter M. A. |
| collection | NTU |
| description | Motivation: Protein–protein interactions (PPIs) play an important role in understanding biological processes. Although recent research in text mining has achieved a significant progress in automatic PPI extraction from literature, performance of existing systems still needs to be improved. Results: In this study, we propose a novel algorithm for extracting PPIs from literature which consists of two phases. First, we automatically categorize the data into subsets based on its semantic properties and extract candidate PPI pairs from these subsets. Second, we apply support vector machines (SVMs) to classify candidate PPI pairs using features specific for each subset. We obtain promising results on five benchmark datasets: AIMed, BioInfer, HPRD50, IEPA and LLL with F-scores ranging from 60% to 84%, which are comparable with the state-of-the-art PPI extraction systems. Furthermore, our system achieves the best performance on cross-corpora evaluation and comparative performance in terms of computational efficiency. Availability: The source code and scripts used in this article are available for academic use at http://staff.science.uva.nl/∼bui/PPIs.zip |
| first_indexed | 2024-10-01T04:24:32Z |
| format | Journal Article |
| id | ntu-10356/96394 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:24:32Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | ntu-10356/963942020-05-28T07:17:54Z A hybrid approach to extract protein-protein interactions Sloot, Peter M. A. Bui, Quoc-Chinh Katrenko, Sophia School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences Motivation: Protein–protein interactions (PPIs) play an important role in understanding biological processes. Although recent research in text mining has achieved a significant progress in automatic PPI extraction from literature, performance of existing systems still needs to be improved. Results: In this study, we propose a novel algorithm for extracting PPIs from literature which consists of two phases. First, we automatically categorize the data into subsets based on its semantic properties and extract candidate PPI pairs from these subsets. Second, we apply support vector machines (SVMs) to classify candidate PPI pairs using features specific for each subset. We obtain promising results on five benchmark datasets: AIMed, BioInfer, HPRD50, IEPA and LLL with F-scores ranging from 60% to 84%, which are comparable with the state-of-the-art PPI extraction systems. Furthermore, our system achieves the best performance on cross-corpora evaluation and comparative performance in terms of computational efficiency. Availability: The source code and scripts used in this article are available for academic use at http://staff.science.uva.nl/∼bui/PPIs.zip Published version 2014-02-19T05:34:42Z 2019-12-06T19:29:54Z 2014-02-19T05:34:42Z 2019-12-06T19:29:54Z 2010 2010 Journal Article Bui, Q.- C., Katrenko, S., & Sloot, P. M. A. (2010). A hybrid approach to extract protein-protein interactions. Bioinformatics, 27(2), 259-265. https://hdl.handle.net/10356/96394 http://hdl.handle.net/10220/18848 10.1093/bioinformatics/btq620 en Bioinformatics © 2010 The Author(s). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences Sloot, Peter M. A. Bui, Quoc-Chinh Katrenko, Sophia A hybrid approach to extract protein-protein interactions |
| title | A hybrid approach to extract protein-protein interactions |
| title_full | A hybrid approach to extract protein-protein interactions |
| title_fullStr | A hybrid approach to extract protein-protein interactions |
| title_full_unstemmed | A hybrid approach to extract protein-protein interactions |
| title_short | A hybrid approach to extract protein-protein interactions |
| title_sort | hybrid approach to extract protein protein interactions |
| topic | DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences |
| url | https://hdl.handle.net/10356/96394 http://hdl.handle.net/10220/18848 |
| work_keys_str_mv | AT slootpeterma ahybridapproachtoextractproteinproteininteractions AT buiquocchinh ahybridapproachtoextractproteinproteininteractions AT katrenkosophia ahybridapproachtoextractproteinproteininteractions AT slootpeterma hybridapproachtoextractproteinproteininteractions AT buiquocchinh hybridapproachtoextractproteinproteininteractions AT katrenkosophia hybridapproachtoextractproteinproteininteractions |