Cargando…
Prediction of MHC class I binding peptides, using SVMHC
BACKGROUND: T-cells are key players in regulating a specific immune response. Activation of cytotoxic T-cells requires recognition of specific peptides bound to Major Histocompatibility Complex (MHC) class I molecules. MHC-peptide complexes are potential tools for diagnosis and treatment of pathogen...
Autores principales: | , |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2002
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC129981/ https://www.ncbi.nlm.nih.gov/pubmed/12225620 http://dx.doi.org/10.1186/1471-2105-3-25 |
_version_ | 1782120365092241408 |
---|---|
author | Dönnes, Pierre Elofsson, Arne |
author_facet | Dönnes, Pierre Elofsson, Arne |
author_sort | Dönnes, Pierre |
collection | PubMed |
description | BACKGROUND: T-cells are key players in regulating a specific immune response. Activation of cytotoxic T-cells requires recognition of specific peptides bound to Major Histocompatibility Complex (MHC) class I molecules. MHC-peptide complexes are potential tools for diagnosis and treatment of pathogens and cancer, as well as for the development of peptide vaccines. Only one in 100 to 200 potential binders actually binds to a certain MHC molecule, therefore a good prediction method for MHC class I binding peptides can reduce the number of candidate binders that need to be synthesized and tested. RESULTS: Here, we present a novel approach, SVMHC, based on support vector machines to predict the binding of peptides to MHC class I molecules. This method seems to perform slightly better than two profile based methods, SYFPEITHI and HLA_BIND. The implementation of SVMHC is quite simple and does not involve any manual steps, therefore as more data become available it is trivial to provide prediction for more MHC types. SVMHC currently contains prediction for 26 MHC class I types from the MHCPEP database or alternatively 6 MHC class I types from the higher quality SYFPEITHI database. The prediction models for these MHC types are implemented in a public web service available at http://www.sbc.su.se/svmhc/. CONCLUSIONS: Prediction of MHC class I binding peptides using Support Vector Machines, shows high performance and is easy to apply to a large number of MHC class I types. As more peptide data are put into MHC databases, SVMHC can easily be updated to give prediction for additional MHC class I types. We suggest that the number of binding peptides needed for SVM training is at least 20 sequences. |
format | Text |
id | pubmed-129981 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2002 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-1299812002-11-01 Prediction of MHC class I binding peptides, using SVMHC Dönnes, Pierre Elofsson, Arne BMC Bioinformatics Research article BACKGROUND: T-cells are key players in regulating a specific immune response. Activation of cytotoxic T-cells requires recognition of specific peptides bound to Major Histocompatibility Complex (MHC) class I molecules. MHC-peptide complexes are potential tools for diagnosis and treatment of pathogens and cancer, as well as for the development of peptide vaccines. Only one in 100 to 200 potential binders actually binds to a certain MHC molecule, therefore a good prediction method for MHC class I binding peptides can reduce the number of candidate binders that need to be synthesized and tested. RESULTS: Here, we present a novel approach, SVMHC, based on support vector machines to predict the binding of peptides to MHC class I molecules. This method seems to perform slightly better than two profile based methods, SYFPEITHI and HLA_BIND. The implementation of SVMHC is quite simple and does not involve any manual steps, therefore as more data become available it is trivial to provide prediction for more MHC types. SVMHC currently contains prediction for 26 MHC class I types from the MHCPEP database or alternatively 6 MHC class I types from the higher quality SYFPEITHI database. The prediction models for these MHC types are implemented in a public web service available at http://www.sbc.su.se/svmhc/. CONCLUSIONS: Prediction of MHC class I binding peptides using Support Vector Machines, shows high performance and is easy to apply to a large number of MHC class I types. As more peptide data are put into MHC databases, SVMHC can easily be updated to give prediction for additional MHC class I types. We suggest that the number of binding peptides needed for SVM training is at least 20 sequences. BioMed Central 2002-09-11 /pmc/articles/PMC129981/ /pubmed/12225620 http://dx.doi.org/10.1186/1471-2105-3-25 Text en Copyright ©2002 Dönnes and Elofsson; licensee BioMed Central Ltd. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose, provided this notice is preserved along with the article's original URL. |
spellingShingle | Research article Dönnes, Pierre Elofsson, Arne Prediction of MHC class I binding peptides, using SVMHC |
title | Prediction of MHC class I binding peptides, using SVMHC |
title_full | Prediction of MHC class I binding peptides, using SVMHC |
title_fullStr | Prediction of MHC class I binding peptides, using SVMHC |
title_full_unstemmed | Prediction of MHC class I binding peptides, using SVMHC |
title_short | Prediction of MHC class I binding peptides, using SVMHC |
title_sort | prediction of mhc class i binding peptides, using svmhc |
topic | Research article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC129981/ https://www.ncbi.nlm.nih.gov/pubmed/12225620 http://dx.doi.org/10.1186/1471-2105-3-25 |
work_keys_str_mv | AT donnespierre predictionofmhcclassibindingpeptidesusingsvmhc AT elofssonarne predictionofmhcclassibindingpeptidesusingsvmhc |