Evolutionary optimization of sequence kernels for detection of bacterial gene starts

Britta Mersch; Tobias Glasmachers; Peter Meinicke; Christian Igel

doi:10.1142/S0129065707001214

Evolutionary optimization of sequence kernels for detection of bacterial gene starts

Britta Mersch, Tobias Glasmachers, Peter Meinicke, Christian Igel

18 Citationer (Scopus)

Abstract

Oligo kernels for biological sequence classification have a high discriminative power. A new parameterization for the K-mer oligo kernel is presented, where all oligomers of length K are weighted individually. The task specific choice of these parameters increases the classification performance and reveals information about discriminative features. For adapting the multiple kernel parameters based on cross-validation the covariance matrix adaptation evolution strategy is proposed. It is applied to optimize the trimer oligo kernels for the detection of bacterial gene starts. The resulting kernels lead to higher classification rates, and the adapted parameters reveal the importance of particular triplets for classification, for example of those occurring in the Shine-Dalgarno Sequence.

Originalsprog	Engelsk
Tidsskrift	International Journal of Neural Systems
Vol/bind	17
Udgave nummer	5
Sider (fra-til)	369-381
Antal sider	13
ISSN	0129-0657
DOI	https://doi.org/10.1142/S0129065707001214
Status	Udgivet - 2007
Udgivet eksternt	Ja

Adgang til dokumentet

10.1142/S0129065707001214

Citationsformater

@article{50a314fb359b45d4bd711213cc9a2d92,

title = "Evolutionary optimization of sequence kernels for detection of bacterial gene starts",

abstract = "Oligo kernels for biological sequence classification have a high discriminative power. A new parameterization for the K-mer oligo kernel is presented, where all oligomers of length K are weighted individually. The task specific choice of these parameters increases the classification performance and reveals information about discriminative features. For adapting the multiple kernel parameters based on cross-validation the covariance matrix adaptation evolution strategy is proposed. It is applied to optimize the trimer oligo kernels for the detection of bacterial gene starts. The resulting kernels lead to higher classification rates, and the adapted parameters reveal the importance of particular triplets for classification, for example of those occurring in the Shine-Dalgarno Sequence.",

author = "Britta Mersch and Tobias Glasmachers and Peter Meinicke and Christian Igel",

year = "2007",

doi = "10.1142/S0129065707001214",

language = "English",

volume = "17",

pages = "369--381",

journal = "International Journal of Neural Systems",

issn = "0129-0657",

publisher = "World Scientific Publishing Co. Pte. Ltd.",

number = "5",

}

TY - JOUR

T1 - Evolutionary optimization of sequence kernels for detection of bacterial gene starts

AU - Mersch, Britta

AU - Glasmachers, Tobias

AU - Meinicke, Peter

AU - Igel, Christian

PY - 2007

Y1 - 2007

N2 - Oligo kernels for biological sequence classification have a high discriminative power. A new parameterization for the K-mer oligo kernel is presented, where all oligomers of length K are weighted individually. The task specific choice of these parameters increases the classification performance and reveals information about discriminative features. For adapting the multiple kernel parameters based on cross-validation the covariance matrix adaptation evolution strategy is proposed. It is applied to optimize the trimer oligo kernels for the detection of bacterial gene starts. The resulting kernels lead to higher classification rates, and the adapted parameters reveal the importance of particular triplets for classification, for example of those occurring in the Shine-Dalgarno Sequence.

AB - Oligo kernels for biological sequence classification have a high discriminative power. A new parameterization for the K-mer oligo kernel is presented, where all oligomers of length K are weighted individually. The task specific choice of these parameters increases the classification performance and reveals information about discriminative features. For adapting the multiple kernel parameters based on cross-validation the covariance matrix adaptation evolution strategy is proposed. It is applied to optimize the trimer oligo kernels for the detection of bacterial gene starts. The resulting kernels lead to higher classification rates, and the adapted parameters reveal the importance of particular triplets for classification, for example of those occurring in the Shine-Dalgarno Sequence.

U2 - 10.1142/S0129065707001214

DO - 10.1142/S0129065707001214

M3 - Journal article

C2 - 18098369

SN - 0129-0657

VL - 17

SP - 369

EP - 381

JO - International Journal of Neural Systems

JF - International Journal of Neural Systems

IS - 5

ER -

Evolutionary optimization of sequence kernels for detection of bacterial gene starts

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater