Secondary structure prediction with support vector machines.
Bioinformatics
; 19(13): 1650-5, 2003 Sep 01.
Article
in En
| MEDLINE
| ID: mdl-12967961
ABSTRACT
MOTIVATION A new method that uses support vector machines (SVMs) to predict protein secondary structure is described and evaluated. The study is designed to develop a reliable prediction method using an alternative technique and to investigate the applicability of SVMs to this type of bioinformatics problem. METHODS:
Binary SVMs are trained to discriminate between two structural classes. The binary classifiers are combined in several ways to predict multi-class secondary structure.RESULTS:
The average three-state prediction accuracy per protein (Q(3)) is estimated by cross-validation to be 77.07 +/- 0.26% with a segment overlap (Sov) score of 73.32 +/- 0.39%. The SVM performs similarly to the 'state-of-the-art' PSIPRED prediction method on a non-homologous test set of 121 proteins despite being trained on substantially fewer examples. A simple consensus of the SVM, PSIPRED and PROFsec achieves significantly higher prediction accuracy than the individual methods.
Search on Google
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Algorithms
/
Artificial Intelligence
/
Proteins
/
Cluster Analysis
/
Models, Statistical
/
Sequence Alignment
/
Sequence Analysis, Protein
Type of study:
Diagnostic_studies
/
Evaluation_studies
/
Prognostic_studies
/
Risk_factors_studies
Language:
En
Journal:
Bioinformatics
Journal subject:
INFORMATICA MEDICA
Year:
2003
Document type:
Article
Affiliation country:
United kingdom