Bioinformatics Advance Access originally published online on December 7, 2004
Bioinformatics 2005 21(8):1383-1388; doi:10.1093/bioinformatics/bti200
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Support vector machines for separation of mixed plant–pathogen EST collections based on codon usage
1Institut fuer Informatik, Ludwig-Maximilians-Universitaet Muenchen Oettingenstrasse 67, 80538 Muenchen, Germany
2Fakultaet fuer Informatik, Technische Universitaet Muenchen Boltzmannstrasse 3, 85748 Garching b. Muenchen, Germany
3Bioinformatics group, Turku Centre for Biotechnology Finland
4Institute for Bioinformatics GSF—Forschungszentrum fuer Umwelt und Gesundheit, GmbH Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany
5Department of Genome-Oriented Bioinformatics, Wissenschaftszentrum Weihenstephan, Technische Universitaet Muenchen 85350 Freising, Germany
*To whom correspondence should be addressed.
Motivation: Discovery of host and pathogen genes expressed at the plant–pathogen interface often requires the construction of mixed libraries that contain sequences from both genomes. Sequence identification requires high-throughput and reliable classification of genome origin. When using single-pass cDNA sequences difficulties arise from the short sequence length, the lack of sufficient taxonomically relevant sequence data in public databases and ambiguous sequence homology between plant and pathogen genes.
Results: A novel method is described, which is independent of the availability of homologous genes and relies on subtle differences in codon usage between plant and fungal genes. We used support vector machines (SVMs) to identify the probable origin of sequences. SVMs were compared to several other machine learning techniques and to a probabilistic algorithm (PF-IND) for expressed sequence tag (EST) classification also based on codon bias differences. Our software (ECLAT) has achieved a classification accuracy of 93.1% on a test set of 3217 EST sequences from Hordeum vulgare and Blumeria graminis, which is a significant improvement compared to PF-IND (prediction accuracy of 81.2% on the same test set). EST sequences with at least 50 nt of coding sequence can be classified using ECLAT with high confidence. ECLAT allows training of classifiers for any host–pathogen combination for which there are sufficient classified training sequences.
Availability: ECLAT is freely available on the Internet (http://mips.gsf.de/proj/est) or on request as a standalone version.
Contact: friedel{at}informatik.uni-muenchen.de
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  J. E. Gewehr, M. Szugat, and R. Zimmer BioWeka extending the Weka framework for bioinformatics Bioinformatics, March 1, 2007; 23(5): 651 - 653. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 S. Rudd and I. V. Tetko Eclair--a web service for unravelling species origin of sequences sampled from mixed host interfaces Nucleic Acids Res., July 1, 2005; 33(suppl_2): W724 - W727. [Abstract] [Full Text] [PDF]
|
|