Detecting sequence and structure homology via an integrative kernel: A case-study in recognizing enzymes

Arieshanti, I., Boden, M., Maetschke, S and Buske, F. A. (2009). Detecting sequence and structure homology via an integrative kernel: A case-study in recognizing enzymes. In: Proceedings of the 2009 IEEE Computational Intelligence for Bioinformatics and Computational Biology. IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology 2009, Nashville, Tennessee, U.S.A., (46-52). 30 March - 2 April , 2009. doi:10.1109/CIBCB.2009.4925706


Author Arieshanti, I.
Boden, M.
Maetschke, S
Buske, F. A.
Title of paper Detecting sequence and structure homology via an integrative kernel: A case-study in recognizing enzymes
Conference name IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology 2009
Conference location Nashville, Tennessee, U.S.A.
Conference dates 30 March - 2 April , 2009
Convener Kay C. Wiese
Proceedings title Proceedings of the 2009 IEEE Computational Intelligence for Bioinformatics and Computational Biology
Journal name Cibcb: 2009 Ieee Symposium On Computational Intelligence in Bioinformatics and Computational Biology
Place of Publication United States of America
Publisher IEEE
Publication Year 2009
Sub-type Fully published paper
DOI 10.1109/CIBCB.2009.4925706
ISBN 9781424427567
Volume 2009
Start page 46
End page 52
Total pages 7
Collection year 2010
Language eng
Abstract/Summary Sequence and structure are complementary pieces of information that can be used to infer protein function. We study and compare sequence, structure and sequence-structure integrative kernels to recognize proteins with enzymatic function. Using a support-vector machine, we show that kernels that combine sequence and structure information typically perform better (AUC 0.73) at this task than kernels that exploit either type of information exclusively. We find that the feature space of structure kernels complements that of sequence kernels, making both sources of similarity more accessible to kernel methods.
Subjects 970108 Expanding Knowledge in the Information and Computing Sciences
060102 Bioinformatics
Keyword Sequence
Protein Function
Integrative kernels
Enzyme
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 30 Mar 2010, 13:24:38 EST by Susan Allen on behalf of Institute for Molecular Bioscience