English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Support vector machines for protein fold class prediction

Markowetz, F., Edler, L., & Vingron, M. (2003). Support vector machines for protein fold class prediction. Biometrical Journal, 45(3), 377-389. doi:10.1002/bimj.200390019.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0010-8B17-5 Version Permalink: http://hdl.handle.net/11858/00-001M-0000-0010-8B18-3
Genre: Journal Article
Alternative Title : Biom. J.

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Markowetz, Florian1, Author
Edler, Lutz, Author
Vingron, Martin2, Author              
Affiliations:
1Max Planck Society, ou_persistent13              
2Gene regulation (Martin Vingron), Dept. of Computational Molecular Biology (Head: Martin Vingron), Max Planck Institute for Molecular Genetics, Max Planck Society, ou_1479639              

Content

show
hide
Free keywords: protein fold class prediction, support vector machines, statistical classification methods, neural networks, confusion matrix
 Abstract: Knowledge of the three-dimensional structure of a protein is essential for describing and understanding its function. Today, a large number of known protein sequences faces a small number of identified structures. Thus, the need arises to predict structure from sequence without using time-consuming experimental identification. In this paper the performance of Support Vector Machines (SVMs) is compared to Neural Networks and to standard statistical classification methods as Discriminant Analysis and Nearest Neighbor Classification. We show that SVMs can beat the competing methods on a dataset of 268 protein sequences to be classified into a set of 42 fold classes. We discuss misclassification with respect to biological function and similarity. In a second step we examine the performance of SVMs if the embedding is varied from frequencies of single amino acids to frequencies of tripletts of amino acids. This work shows that SVMs provide a promising alternative to standard statistical classification and prediction methods in functional genomics.

Details

show
hide
Language(s): eng - English
 Dates: 2003
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: eDoc: 175056
ISI: 000182686400009
DOI: 10.1002/bimj.200390019
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Biometrical Journal
  Alternative Title : Biom. J.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 45 (3) Sequence Number: - Start / End Page: 377 - 389 Identifier: ISSN: 0323-3847