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 language | English |
---|---|
Pages (from-to) | 799-807 |
Number of pages | 9 |
Journal | Bioinformatics |
Volume | 16 |
Issue number | 9 |
DOIs | |
Publication status | Published - 2000 |
Bibliographical note
Funding Information:This work was supported by the BMBF (TargId, 0311615) and by the DFG (JA 379/9-1,7-1). Part of the present work was done while BS was with GMD.FIRST. We thank A. G. Pedersen and H. Nielsen for e-mail discussions, providing their data sets and sharing unpublished data. We acknowledge M. Schwan for help with the experiments. We thank the referees for helpful comments.
ASJC Scopus subject areas
- Statistics and Probability
- Biochemistry
- Molecular Biology
- Computer Science Applications
- Computational Theory and Mathematics
- Computational Mathematics