Spitzer, M; Lorkowski, S; Cullen, P; Sczyrba, Alexander ; Fuellen, Georg: IsoSVM - Distinguishing isoforms and paralogs on the protein level. In: BMC Bioinformatics. Jg.7 H. 1. 2006, S. 110 ff.
Inhalt
- Results and discussion
- Importance of maximizing accuracy in distinguishing isoforms and paralogs
- Performance statistics of different classifiers based on three features
- Performance of different classifiers using a canonical training/testing dataset
- Application of the SVM classifier to EST data
- Application of the SVM classifier to an automated phylogeny pipeline
- Limitations of the classifier
- Conclusion
- Methods
- Prerequisites
- Features
- Generation of the training and testing datasets
- Sequence retrieval, homology search and visual classification
- Canonical training and testing dataset
- Homologous regions only
- Training of the SVM
- Training of the radial basis function network
- Assessing performance of classifiers based on three features by jackknife resampling
- Classifiers based on fewer features, thresholds and parameters; measuring performance
- Authors' contributions
- Additional material
- Acknowledgements
- References