A community resource benchmarking predictions of peptide binding to MHC-I molecules.
Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of enti...
Main Authors: | , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2006-06-01
|
Series: | PLoS Computational Biology |
Online Access: | http://europepmc.org/articles/PMC1475712?pdf=render |
id |
doaj-75f7c2524f2343bdaa3cb01daa5e4673 |
---|---|
record_format |
Article |
spelling |
doaj-75f7c2524f2343bdaa3cb01daa5e46732020-11-25T01:46:01ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582006-06-0126e6510.1371/journal.pcbi.0020065A community resource benchmarking predictions of peptide binding to MHC-I molecules.Bjoern PetersHuynh-Hoa BuiSune FrankildMorten NielsonClaus LundegaardEmrah KostemDerek BaschKasper LamberthMikkel HarndahlWard FleriStephen S WilsonJohn SidneyOle LundSoren BuusAlessandro SetteRecognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools.http://europepmc.org/articles/PMC1475712?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bjoern Peters Huynh-Hoa Bui Sune Frankild Morten Nielson Claus Lundegaard Emrah Kostem Derek Basch Kasper Lamberth Mikkel Harndahl Ward Fleri Stephen S Wilson John Sidney Ole Lund Soren Buus Alessandro Sette |
spellingShingle |
Bjoern Peters Huynh-Hoa Bui Sune Frankild Morten Nielson Claus Lundegaard Emrah Kostem Derek Basch Kasper Lamberth Mikkel Harndahl Ward Fleri Stephen S Wilson John Sidney Ole Lund Soren Buus Alessandro Sette A community resource benchmarking predictions of peptide binding to MHC-I molecules. PLoS Computational Biology |
author_facet |
Bjoern Peters Huynh-Hoa Bui Sune Frankild Morten Nielson Claus Lundegaard Emrah Kostem Derek Basch Kasper Lamberth Mikkel Harndahl Ward Fleri Stephen S Wilson John Sidney Ole Lund Soren Buus Alessandro Sette |
author_sort |
Bjoern Peters |
title |
A community resource benchmarking predictions of peptide binding to MHC-I molecules. |
title_short |
A community resource benchmarking predictions of peptide binding to MHC-I molecules. |
title_full |
A community resource benchmarking predictions of peptide binding to MHC-I molecules. |
title_fullStr |
A community resource benchmarking predictions of peptide binding to MHC-I molecules. |
title_full_unstemmed |
A community resource benchmarking predictions of peptide binding to MHC-I molecules. |
title_sort |
community resource benchmarking predictions of peptide binding to mhc-i molecules. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS Computational Biology |
issn |
1553-734X 1553-7358 |
publishDate |
2006-06-01 |
description |
Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools. |
url |
http://europepmc.org/articles/PMC1475712?pdf=render |
work_keys_str_mv |
AT bjoernpeters acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT huynhhoabui acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT sunefrankild acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT mortennielson acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT clauslundegaard acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT emrahkostem acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT derekbasch acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT kasperlamberth acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT mikkelharndahl acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT wardfleri acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT stephenswilson acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT johnsidney acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT olelund acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT sorenbuus acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT alessandrosette acommunityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT bjoernpeters communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT huynhhoabui communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT sunefrankild communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT mortennielson communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT clauslundegaard communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT emrahkostem communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT derekbasch communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT kasperlamberth communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT mikkelharndahl communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT wardfleri communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT stephenswilson communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT johnsidney communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT olelund communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT sorenbuus communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules AT alessandrosette communityresourcebenchmarkingpredictionsofpeptidebindingtomhcimolecules |
_version_ |
1725021176380522496 |