Abstract
We present a novel method to address multi-labeled protein subcellular localization prediction in Gram-negative bacteria using support vector machines (SVM) as classifiers. For a given protein sequence that may have more than one label, features are extracted from amino acid composition and molecular function related terms in Gene Ontology (GO) as input to SVM. We apply one-against-others SVM to proteins of Gram-negative bacteria in a 5-fold cross-validation. The results of the multi-labeled predictions are evaluated based on two criteria: class number and class category. For the first criterion, our method predicts the number of classes (class number) for each protein at an accuracy rate of 94.1%. For the second criterion, we compare the categories of the actual classes with the predicted classes proportionate to ranks, and obtain an accuracy of 83.2%. Our method is the first approach to predict and evaluate multi-labeled protein subcellular localization for prokaryotic bacteria and we demonstrate that it has a good predictive power.
| Original language | English |
|---|---|
| Title of host publication | 2005 IEEE Computational Systems Bioinformatics Conference, Workshops and Poster Abstracts |
| Pages | 79-80 |
| Number of pages | 2 |
| DOIs | |
| Publication status | Published - 2005 |
| Externally published | Yes |
| Event | 2005 IEEE Computational Systems Bioinformatics Conference, Workshops and Poster Abstracts - Stanford, CA, United States Duration: Aug 8 2005 → Aug 11 2005 |
Other
| Other | 2005 IEEE Computational Systems Bioinformatics Conference, Workshops and Poster Abstracts |
|---|---|
| Country | United States |
| City | Stanford, CA |
| Period | 8/8/05 → 8/11/05 |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
A novel approach for prediction of multi-labeled protein subcellular localization for prokaryotic bacteria. / Su, Chia Yu; Lo, Allan; Lin, Chin Chin; Chang, Fu; Hsu, Wen Lian.
2005 IEEE Computational Systems Bioinformatics Conference, Workshops and Poster Abstracts. 2005. p. 79-80 1540549.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - A novel approach for prediction of multi-labeled protein subcellular localization for prokaryotic bacteria
AU - Su, Chia Yu
AU - Lo, Allan
AU - Lin, Chin Chin
AU - Chang, Fu
AU - Hsu, Wen Lian
PY - 2005
Y1 - 2005
N2 - We present a novel method to address multi-labeled protein subcellular localization prediction in Gram-negative bacteria using support vector machines (SVM) as classifiers. For a given protein sequence that may have more than one label, features are extracted from amino acid composition and molecular function related terms in Gene Ontology (GO) as input to SVM. We apply one-against-others SVM to proteins of Gram-negative bacteria in a 5-fold cross-validation. The results of the multi-labeled predictions are evaluated based on two criteria: class number and class category. For the first criterion, our method predicts the number of classes (class number) for each protein at an accuracy rate of 94.1%. For the second criterion, we compare the categories of the actual classes with the predicted classes proportionate to ranks, and obtain an accuracy of 83.2%. Our method is the first approach to predict and evaluate multi-labeled protein subcellular localization for prokaryotic bacteria and we demonstrate that it has a good predictive power.
AB - We present a novel method to address multi-labeled protein subcellular localization prediction in Gram-negative bacteria using support vector machines (SVM) as classifiers. For a given protein sequence that may have more than one label, features are extracted from amino acid composition and molecular function related terms in Gene Ontology (GO) as input to SVM. We apply one-against-others SVM to proteins of Gram-negative bacteria in a 5-fold cross-validation. The results of the multi-labeled predictions are evaluated based on two criteria: class number and class category. For the first criterion, our method predicts the number of classes (class number) for each protein at an accuracy rate of 94.1%. For the second criterion, we compare the categories of the actual classes with the predicted classes proportionate to ranks, and obtain an accuracy of 83.2%. Our method is the first approach to predict and evaluate multi-labeled protein subcellular localization for prokaryotic bacteria and we demonstrate that it has a good predictive power.
UR - http://www.scopus.com/inward/record.url?scp=33749069488&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33749069488&partnerID=8YFLogxK
U2 - 10.1109/CSBW.2005.11
DO - 10.1109/CSBW.2005.11
M3 - Conference contribution
SN - 0769524427
SN - 9780769524429
SP - 79
EP - 80
BT - 2005 IEEE Computational Systems Bioinformatics Conference, Workshops and Poster Abstracts
ER -