Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions.
Since many proteins express their functional activity by interacting with other proteins and forming protein complexes, it is very useful to identify sets of proteins that form complexes. For that purpose, many prediction methods for protein complexes from protein-protein interactions have been deve...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2013-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC3679142?pdf=render |
| _version_ | 1818143583908134912 |
|---|---|
| author | Peiying Ruan Morihiro Hayashida Osamu Maruyama Tatsuya Akutsu |
| author_facet | Peiying Ruan Morihiro Hayashida Osamu Maruyama Tatsuya Akutsu |
| author_sort | Peiying Ruan |
| collection | DOAJ |
| description | Since many proteins express their functional activity by interacting with other proteins and forming protein complexes, it is very useful to identify sets of proteins that form complexes. For that purpose, many prediction methods for protein complexes from protein-protein interactions have been developed such as MCL, MCODE, RNSC, PCP, RRW, and NWE. These methods have dealt with only complexes with size of more than three because the methods often are based on some density of subgraphs. However, heterodimeric protein complexes that consist of two distinct proteins occupy a large part according to several comprehensive databases of known complexes. In this paper, we propose several feature space mappings from protein-protein interaction data, in which each interaction is weighted based on reliability. Furthermore, we make use of prior knowledge on protein domains to develop feature space mappings, domain composition kernel and its combination kernel with our proposed features. We perform ten-fold cross-validation computational experiments. These results suggest that our proposed kernel considerably outperforms the naive Bayes-based method, which is the best existing method for predicting heterodimeric protein complexes. |
| first_indexed | 2024-12-11T11:33:59Z |
| format | Article |
| id | doaj.art-62138e3786224d3dbf697b1d1ce8a4e9 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-11T11:33:59Z |
| publishDate | 2013-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-62138e3786224d3dbf697b1d1ce8a4e92022-12-22T01:08:48ZengPublic Library of Science (PLoS)PLoS ONE1932-62032013-01-0186e6526510.1371/journal.pone.0065265Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions.Peiying RuanMorihiro HayashidaOsamu MaruyamaTatsuya AkutsuSince many proteins express their functional activity by interacting with other proteins and forming protein complexes, it is very useful to identify sets of proteins that form complexes. For that purpose, many prediction methods for protein complexes from protein-protein interactions have been developed such as MCL, MCODE, RNSC, PCP, RRW, and NWE. These methods have dealt with only complexes with size of more than three because the methods often are based on some density of subgraphs. However, heterodimeric protein complexes that consist of two distinct proteins occupy a large part according to several comprehensive databases of known complexes. In this paper, we propose several feature space mappings from protein-protein interaction data, in which each interaction is weighted based on reliability. Furthermore, we make use of prior knowledge on protein domains to develop feature space mappings, domain composition kernel and its combination kernel with our proposed features. We perform ten-fold cross-validation computational experiments. These results suggest that our proposed kernel considerably outperforms the naive Bayes-based method, which is the best existing method for predicting heterodimeric protein complexes.http://europepmc.org/articles/PMC3679142?pdf=render |
| spellingShingle | Peiying Ruan Morihiro Hayashida Osamu Maruyama Tatsuya Akutsu Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. PLoS ONE |
| title | Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. |
| title_full | Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. |
| title_fullStr | Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. |
| title_full_unstemmed | Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. |
| title_short | Prediction of heterodimeric protein complexes from weighted protein-protein interaction networks using novel features and kernel functions. |
| title_sort | prediction of heterodimeric protein complexes from weighted protein protein interaction networks using novel features and kernel functions |
| url | http://europepmc.org/articles/PMC3679142?pdf=render |
| work_keys_str_mv | AT peiyingruan predictionofheterodimericproteincomplexesfromweightedproteinproteininteractionnetworksusingnovelfeaturesandkernelfunctions AT morihirohayashida predictionofheterodimericproteincomplexesfromweightedproteinproteininteractionnetworksusingnovelfeaturesandkernelfunctions AT osamumaruyama predictionofheterodimericproteincomplexesfromweightedproteinproteininteractionnetworksusingnovelfeaturesandkernelfunctions AT tatsuyaakutsu predictionofheterodimericproteincomplexesfromweightedproteinproteininteractionnetworksusingnovelfeaturesandkernelfunctions |