This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection
April-June 2007 (vol. 4 no. 2)
pp. 216-226
ASCII Text
x 
 
Christian Igel, Tobias Glasmachers, Britta Mersch, Nico Pfeifer, Peter Meinicke, "Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection," IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 4, no. 2, pp. 216-226, April-June, 2007.
 
 
BibTex
x
 
@article{ 10.1109/TCBB.2007.070208,
author = {Christian Igel and Tobias Glasmachers and Britta Mersch and Nico Pfeifer and Peter Meinicke},
title = {Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection},
journal ={IEEE/ACM Transactions on Computational Biology and Bioinformatics},
volume = {4},
number = {2},
issn = {1545-5963},
year = {2007},
pages = {216-226},
doi = {http://doi.ieeecomputersociety.org/10.1109/TCBB.2007.070208},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics
TI - Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection
IS - 2
SN - 1545-5963
SP216
EP226
EPD - 216-226
A1 - Christian Igel,
A1 - Tobias Glasmachers,
A1 - Britta Mersch,
A1 - Nico Pfeifer,
A1 - Peter Meinicke,
PY - 2007
KW - Sequence analysis
KW - oligo kernel
KW - translation initiation sites
KW - model selection
KW - kernel target alignment
KW - support vector machines.
VL - 4
JA - IEEE/ACM Transactions on Computational Biology and Bioinformatics
ER -
 
Biological data mining using kernel methods can be improved by a task-specific choice of the kernel function. Oligo kernels for genomic sequence analysis have proven to have a high discriminative power and to provide interpretable results. Oligo kernels that consider subsequences of different lengths can be combined and parameterized to increase their flexibility. For adapting these parameters efficiently, gradient-based optimization of the kernel-target alignment is proposed. The power of this new, general model selection procedure and the benefits of fitting kernels to problem classes are demonstrated by adapting oligo kernels for bacterial gene start detection.
Index Terms:
Sequence analysis, oligo kernel, translation initiation sites, model selection, kernel target alignment, support vector machines.
Citation:
Christian Igel, Tobias Glasmachers, Britta Mersch, Nico Pfeifer, Peter Meinicke, "Gradient-Based Optimization of Kernel-Target Alignment for Sequence Kernels Applied to Bacterial Gene Start Detection," IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 4, no. 2, pp. 216-226, April-June 2007, doi:10.1109/TCBB.2007.070208
Usage of this product signifies your acceptance of the Terms of Use.