A probabilistic meta-predictor for the MHC class II binding peptides

Karpenko, Oleksiy; Huang, Lei; Dai, Yang

doi:10.1007/s00251-007-0266-y

Cited by 22 publications

(12 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since there are significant peptide similarities in the "ALL" dataset, this could be due to overfitting. We plan to systematically examine how to best construct consensus predictions for MHC binding in the future, building on work done by us and others in the past [30,39,40]. …”

Section: Discussionmentioning

confidence: 99%

Peptide binding predictions for HLA DR, DP and DQ molecules

et al. 2010

View full text Add to dashboard Cite

BackgroundMHC class II binding predictions are widely used to identify epitope candidates in infectious agents, allergens, cancer and autoantigens. The vast majority of prediction algorithms for human MHC class II to date have targeted HLA molecules encoded in the DR locus. This reflects a significant gap in knowledge as HLA DP and DQ molecules are presumably equally important, and have only been studied less because they are more difficult to handle experimentally.ResultsIn this study, we aimed to narrow this gap by providing a large scale dataset of over 17,000 HLA-peptide binding affinities for a set of 11 HLA DP and DQ alleles. We also expanded our dataset for HLA DR alleles resulting in a total of 40,000 MHC class II binding affinities covering 26 allelic variants. Utilizing this dataset, we generated prediction tools utilizing several machine learning algorithms and evaluated their performance.ConclusionWe found that 1) prediction methodologies developed for HLA DR molecules perform equally well for DP or DQ molecules. 2) Prediction performances were significantly increased compared to previous reports due to the larger amounts of training data available. 3) The presence of homologous peptides between training and testing datasets should be avoided to give real-world estimates of prediction performance metrics, but the relative ranking of different predictors is largely unaffected by the presence of homologous peptides, and predictors intended for end-user applications should include all training data for maximum performance. 4) The recently developed NN-align prediction method significantly outperformed all other algorithms, including a naïve consensus based on all prediction methods. A new consensus method dropping the comparably weak ARB prediction method could outperform the NN-align method, but further research into how to best combine MHC class II binding predictions is required.

show abstract

Section: Discussionmentioning

confidence: 99%

Peptide binding predictions for HLA DR, DP and DQ molecules

et al. 2010

View full text Add to dashboard Cite

show abstract

“…In particular, we will explore the use of optimised voting algorithms to generate a viable meta-predictor, which unites the output of several prediction methods in an intelligent manner so that the combined output is more accurate and more reliable than any individual prediction program. Such approaches have been widely employed in other areas and even in immunoinformatics: Trost et al have addressed class I binding [31], while Karpenko et al have used this approach to predict class II MHCs binding [32]. We will seek to capitalise upon the as-yet-unrealised potential of such approaches.…”

Section: Discussionmentioning

confidence: 99%

MHC Class II Binding Prediction—A Little Help from a Friend

Димитров

Garnev

Flower

et al. 2010

Journal of Biomedicine and Biotechnology

View full text Add to dashboard Cite

Vaccines are the greatest single instrument of prophylaxis against infectious diseases, with immeasurable benefits to human wellbeing. The accurate and reliable prediction of peptide-MHC binding is fundamental to the robust identification of T-cell epitopes and thus the successful design of peptide- and protein-based vaccines. The prediction of MHC class II peptide binding has hitherto proved recalcitrant and refractory. Here we illustrate the utility of existing computational tools for in silico prediction of peptides binding to class II MHCs. Most of the methods, tested in the present study, detect more than the half of the true binders in the top 5% of all possible nonamers generated from one protein. This number increases in the top 10% and 15% and then does not change significantly. For the top 15% the identified binders approach 86%. In terms of lab work this means 85% less expenditure on materials, labour and time. We show that while existing caveats are well founded, nonetheless use of computational models of class II binding can still offer viable help to the work of the immunologist and vaccinologist.

show abstract

“…They are Consensus (6), PM (24), AvgTanh (25) and MetaSVMp, which is based on stacked generalization (26). The first two approaches have been already examined to achieve good performance in the prediction of MHC binding peptides (6,24), while the rest two have been found very successful in other applications of machine learning (25,26). The basic idea of each ensemble approach can be summarized as follows:

Consensus: a set of random peptides is collected as a reference list, and then each predictor ranks peptides in this reference list.

…”

Section: Methodsmentioning

confidence: 99%

“…Among four ensemble strategies in MetaMHC, Consensus is widely explored in the problem of predicting peptides binding to MHC, such as IEDB analysis tools (21). PM has been proposed by Karpenko et al (24) to improve the MHC class II binding prediction, but there are no web servers that implement this strategy. In addition, MetaMHC is the first web server to implement AvgTanh and MetaSVMp for improving the performance of predicting MHC binding peptides.…”

Section: Related Web Serversmentioning

confidence: 99%

MetaMHC: a meta approach to predict peptides binding to MHC molecules

Zhou

Udaka

et al. 2010

Nucleic Acids Research

View full text Add to dashboard Cite

As antigenic peptides binding to major histocompatibility complex (MHC) molecules is the prerequisite of cellular immune responses, an accurate computational predictor will be of great benefit to biologists and immunologists for understanding the underlying mechanism of immune recognition as well as facilitating the process of epitope mapping and vaccine design. Although various computational approaches have been developed, recent experimental results on benchmark data sets show that the development of improved predictors is needed, especially for MHC Class II peptide binding. To make the most of current methods and achieve a higher predictive performance, we developed a new web server, MetaMHC, to integrate the outputs of leading predictors by several popular ensemble strategies. MetaMHC consists of two components: MetaMHCI and MetaMHCII for MHC Class I peptide and MHC Class II peptide binding predictions, respectively. Experimental results by both cross-validation and using an independent data set show that the ensemble approaches outperform individual predictors, being statistically significant. MetaMHC is freely available at http://www.biokdd.fudan.edu.cn/Service/MetaMHC.html.

show abstract

A probabilistic meta-predictor for the MHC class II binding peptides

Cited by 22 publications

References 61 publications

Peptide binding predictions for HLA DR, DP and DQ molecules

Peptide binding predictions for HLA DR, DP and DQ molecules

MHC Class II Binding Prediction—A Little Help from a Friend

MetaMHC: a meta approach to predict peptides binding to MHC molecules

Contact Info

Product

Resources

About