1096-987X/asset/olbannerleft.gif?v=1&s=6a06c9acc9d19b9514883204cd54b2fb803be905)
1096-987X/asset/olbannerright.gif?v=1&s=5c13c2b5f418bc7a48bf448d9b71c474e504844e)
SVMtm: Support vector machines to predict transmembrane segments
Article first published online: 15 JAN 2004
DOI: 10.1002/jcc.10411
Copyright © 2004 Wiley Periodicals, Inc.
1096-987X/asset/cover.gif?v=1&s=4429aac2462ebd499c13b3d7fe983679c5767778 "Journal of Computational Chemistry")
Additional Information
How to Cite
Yuan, Z., Mattick, J. S. and Teasdale, R. D. (2004), SVMtm: Support vector machines to predict transmembrane segments. J. Comput. Chem., 25: 632–636. doi: 10.1002/jcc.10411
Publication History
- Issue published online: 15 JAN 2004
- Article first published online: 15 JAN 2004
- Manuscript Accepted: 24 OCT 2003
- Manuscript Received: 7 AUG 2003
Funded by
- Australian Research Council
- National Institute of Health. Grant Number: NIDDK DK063400
- Abstract
- Article
- References
- Cited By
Keywords:
- SVMtm;
- transmembrane helix prediction;
- location of transmembrane segments;
- coding scheme
Abstract
A new method has been developed for prediction of transmembrane helices using support vector machines. Different coding schemes of protein sequences were explored, and their performances were assessed by crossvalidation tests. The best performance method can predict the transmembrane helices with sensitivity of 93.4% and precision of 92.0%. For each predicted transmembrane segment, a score is given to show the strength of transmembrane signal and the prediction reliability. In particular, this method can distinguish transmembrane proteins from soluble proteins with an accuracy of ∼99%. This method can be used to complement current transmembrane helix prediction methods and can be used for consensus analysis of entire proteomes. The predictor is located at http://genet.imb.uq.edu.au/predictors/SVMtm. © 2004 Wiley Periodicals, Inc. J Comput Chem 25: 632–636, 2004