Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores
<p>Abstract</p> <p>Background</p> <p>Modelling the interaction between potentially antigenic peptides and Major Histocompatibility Complex (MHC) molecules is a key step in identifying potential T-cell epitopes. For Class II MHC alleles, the binding groove is open at bot...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2006-11-01
|
| Series: | BMC Bioinformatics |
| Online Access: | http://www.biomedcentral.com/1471-2105/7/501 |
| _version_ | 1811311452780232704 |
|---|---|
| author | Flower Darren R Salomon Jesper |
| author_facet | Flower Darren R Salomon Jesper |
| author_sort | Flower Darren R |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>Modelling the interaction between potentially antigenic peptides and Major Histocompatibility Complex (MHC) molecules is a key step in identifying potential T-cell epitopes. For Class II MHC alleles, the binding groove is open at both ends, causing ambiguity in the positional alignment between the groove and peptide, as well as creating uncertainty as to what parts of the peptide interact with the MHC. Moreover, the antigenic peptides have variable lengths, making naive modelling methods difficult to apply. This paper introduces a kernel method that can handle variable length peptides effectively by quantifying similarities between peptide sequences and integrating these into the kernel.</p> <p>Results</p> <p>The kernel approach presented here shows increased prediction accuracy with a significantly higher number of true positives and negatives on multiple MHC class II alleles, when testing data sets from MHCPEP <abbrgrp><abbr bid="B1">1</abbr></abbrgrp>, MCHBN <abbrgrp><abbr bid="B2">2</abbr></abbrgrp>, and MHCBench <abbrgrp><abbr bid="B3">3</abbr></abbrgrp>. Evaluation by cross validation, when segregating binders and non-binders, produced an average of 0.824 A<sub>ROC </sub>for the MHCBench data sets (up from 0.756), and an average of 0.96 A<sub>ROC </sub>for multiple alleles of the MHCPEP database.</p> <p>Conclusion</p> <p>The method improves performance over existing state-of-the-art methods of MHC class II peptide binding predictions by using a custom, knowledge-based representation of peptides. Similarity scores, in contrast to a fixed-length, pocket-specific representation of amino acids, provide a flexible and powerful way of modelling MHC binding, and can easily be applied to other dynamic sequence problems.</p> |
| first_indexed | 2024-04-13T10:18:04Z |
| format | Article |
| id | doaj.art-f5d41f76f6464f8ea57bacf751700cf1 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-04-13T10:18:04Z |
| publishDate | 2006-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-f5d41f76f6464f8ea57bacf751700cf12022-12-22T02:50:38ZengBMCBMC Bioinformatics1471-21052006-11-017150110.1186/1471-2105-7-501Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scoresFlower Darren RSalomon Jesper<p>Abstract</p> <p>Background</p> <p>Modelling the interaction between potentially antigenic peptides and Major Histocompatibility Complex (MHC) molecules is a key step in identifying potential T-cell epitopes. For Class II MHC alleles, the binding groove is open at both ends, causing ambiguity in the positional alignment between the groove and peptide, as well as creating uncertainty as to what parts of the peptide interact with the MHC. Moreover, the antigenic peptides have variable lengths, making naive modelling methods difficult to apply. This paper introduces a kernel method that can handle variable length peptides effectively by quantifying similarities between peptide sequences and integrating these into the kernel.</p> <p>Results</p> <p>The kernel approach presented here shows increased prediction accuracy with a significantly higher number of true positives and negatives on multiple MHC class II alleles, when testing data sets from MHCPEP <abbrgrp><abbr bid="B1">1</abbr></abbrgrp>, MCHBN <abbrgrp><abbr bid="B2">2</abbr></abbrgrp>, and MHCBench <abbrgrp><abbr bid="B3">3</abbr></abbrgrp>. Evaluation by cross validation, when segregating binders and non-binders, produced an average of 0.824 A<sub>ROC </sub>for the MHCBench data sets (up from 0.756), and an average of 0.96 A<sub>ROC </sub>for multiple alleles of the MHCPEP database.</p> <p>Conclusion</p> <p>The method improves performance over existing state-of-the-art methods of MHC class II peptide binding predictions by using a custom, knowledge-based representation of peptides. Similarity scores, in contrast to a fixed-length, pocket-specific representation of amino acids, provide a flexible and powerful way of modelling MHC binding, and can easily be applied to other dynamic sequence problems.</p>http://www.biomedcentral.com/1471-2105/7/501 |
| spellingShingle | Flower Darren R Salomon Jesper Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores BMC Bioinformatics |
| title | Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores |
| title_full | Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores |
| title_fullStr | Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores |
| title_full_unstemmed | Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores |
| title_short | Predicting Class II MHC-Peptide binding: a kernel based approach using similarity scores |
| title_sort | predicting class ii mhc peptide binding a kernel based approach using similarity scores |
| url | http://www.biomedcentral.com/1471-2105/7/501 |
| work_keys_str_mv | AT flowerdarrenr predictingclassiimhcpeptidebindingakernelbasedapproachusingsimilarityscores AT salomonjesper predictingclassiimhcpeptidebindingakernelbasedapproachusingsimilarityscores |