Engineering support vector machine kernels that recognize translation initiation sites

A. Zien, G. Rätsch, S. Mika, B. Schölkopf, T. Lengauer, Klaus Muller

Research output: Contribution to journalArticle

288 Citations (Scopus)

Abstract

Motivation: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). Results: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26% over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.

Original languageEnglish
Pages (from-to)799-807
Number of pages9
JournalBioinformatics
Volume16
Issue number9
Publication statusPublished - 2000 Dec 27
Externally publishedYes

Fingerprint

Support vector machines
Support Vector Machine
kernel
Engineering
Proteins
Bioengineering
Nucleotides
Profitability
Protein Sequence
Kernel Function
Classification Problems
Profit
Protein
Demonstrate
Evidence
Knowledge

ASJC Scopus subject areas

  • Clinical Biochemistry
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Zien, A., Rätsch, G., Mika, S., Schölkopf, B., Lengauer, T., & Muller, K. (2000). Engineering support vector machine kernels that recognize translation initiation sites. Bioinformatics, 16(9), 799-807.

Engineering support vector machine kernels that recognize translation initiation sites. / Zien, A.; Rätsch, G.; Mika, S.; Schölkopf, B.; Lengauer, T.; Muller, Klaus.

In: Bioinformatics, Vol. 16, No. 9, 27.12.2000, p. 799-807.

Research output: Contribution to journalArticle

Zien, A, Rätsch, G, Mika, S, Schölkopf, B, Lengauer, T & Muller, K 2000, 'Engineering support vector machine kernels that recognize translation initiation sites', Bioinformatics, vol. 16, no. 9, pp. 799-807.
Zien A, Rätsch G, Mika S, Schölkopf B, Lengauer T, Muller K. Engineering support vector machine kernels that recognize translation initiation sites. Bioinformatics. 2000 Dec 27;16(9):799-807.
Zien, A. ; Rätsch, G. ; Mika, S. ; Schölkopf, B. ; Lengauer, T. ; Muller, Klaus. / Engineering support vector machine kernels that recognize translation initiation sites. In: Bioinformatics. 2000 ; Vol. 16, No. 9. pp. 799-807.
@article{afbece22e32c4b9fb6f629fcecb33a0a,
title = "Engineering support vector machine kernels that recognize translation initiation sites",
abstract = "Motivation: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). Results: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26{\%} over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.",
author = "A. Zien and G. R{\"a}tsch and S. Mika and B. Sch{\"o}lkopf and T. Lengauer and Klaus Muller",
year = "2000",
month = "12",
day = "27",
language = "English",
volume = "16",
pages = "799--807",
journal = "Bioinformatics",
issn = "1367-4803",
publisher = "Oxford University Press",
number = "9",

}

TY - JOUR

T1 - Engineering support vector machine kernels that recognize translation initiation sites

AU - Zien, A.

AU - Rätsch, G.

AU - Mika, S.

AU - Schölkopf, B.

AU - Lengauer, T.

AU - Muller, Klaus

PY - 2000/12/27

Y1 - 2000/12/27

N2 - Motivation: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). Results: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26% over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.

AB - Motivation: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). Results: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26% over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.

UR - http://www.scopus.com/inward/record.url?scp=0033670134&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033670134&partnerID=8YFLogxK

M3 - Article

C2 - 11108702

AN - SCOPUS:0033670134

VL - 16

SP - 799

EP - 807

JO - Bioinformatics

JF - Bioinformatics

SN - 1367-4803

IS - 9

ER -