Abstract
A number of machine learning-based predictors have been developed for identifying immunogenic T-cell epitopes based on major histocompatibility complex (MHC) class I and II binding affinities. Rationally selecting the most appropriate tool has been complicated by the evolving training data and machine learning methods. Despite the recent advances made in generating high-quality MHC-eluted, naturally processed ligandome, the reliability of new predictors on these epitopes has yet to be evaluated. This study reports the latest benchmarking on an extensive set of MHC-binding predictors by using newly available, untested data of both synthetic and naturally processed epitopes. 32 human leukocyte antigen (HLA) class I and 24 HLA class II alleles are included in the blind test set. Artificial neural network (ANN)-based approaches demonstrated better performance than regression-based machine learning and structural modeling. Among the 18 predictors benchmarked, ANN-based mhcflurry and nn_align perform the best for MHC class I 9-mer and class II 15-mer predictions, respectively, on binding/non-binding classification (Area Under Curves = 0.911). NetMHCpan4 also demonstrated comparable predictive power. Our customization of mhcflurry to a pan-HLA predictor has achieved similar accuracy to NetMHCpan. The overall accuracy of these methods are comparable between 9-mer and 10-mer testing data. However, the top methods deliver low correlations between the predicted versus the experimental affinities for strong MHC binders. When used on naturally processed MHC-ligands, tools that have been trained on elution data (NetMHCpan4 and MixMHCpred) shows better accuracy than pure binding affinity predictor. The variability of false prediction rate is considerable among HLA types and datasets. Finally, structure-based predictor of Rosetta FlexPepDock is less optimal compared to the machine learning approaches. With our benchmarking of MHC-binding and MHC-elution predictors using a comprehensive metrics, a unbiased view for establishing best practice of T-cell epitope predictions is presented, facilitating future development of methods in immunogenomics.
Highlights
The increasing wealth of immunogenomic information generated by next-generation sequencing (NGS) technologies is boosting the application of cancer immunotherapy that takes full advantage of individual’s adaptive immunity by administrating personalized cancer vaccines. [1,2,3] An essential step in provoking adaptive immunity, delivered by the activated CD8+ or CD4+ T cells, is the recognition of T cell receptor (TCR) to T cell epitopes.[4]
We demonstrate that recent advance in incorporating high-quality naturally presented peptide data from mass spectrometry experiments has improved the accuracy
Our benchmarking of machine learning predictors for major histocompatibility complex (MHC)-binding and MHC-naturally presented antigen peptides contributes to establishing best practice of computational T-cell epitope analysis, which has implication in tumor neoantigen-based cancer vaccine discovery
Summary
The increasing wealth of immunogenomic information generated by next-generation sequencing (NGS) technologies is boosting the application of cancer immunotherapy that takes full advantage of individual’s adaptive immunity by administrating personalized cancer vaccines. [1,2,3] An essential step in provoking adaptive immunity, delivered by the activated CD8+ or CD4+ T cells, is the recognition of T cell receptor (TCR) to T cell epitopes.[4]. The increasing wealth of immunogenomic information generated by next-generation sequencing (NGS) technologies is boosting the application of cancer immunotherapy that takes full advantage of individual’s adaptive immunity by administrating personalized cancer vaccines. [1,2,3] An essential step in provoking adaptive immunity, delivered by the activated CD8+ or CD4+ T cells, is the recognition of T cell receptor (TCR) to T cell epitopes.[4] As sequence repertoire for potential TCR-recognizing epitopes, whole exome or transcriptome from pathogens or tumor cells can be analyzed by bioinformatics pipelines to identify vaccine candidates.[5,6] Among various processes related to antigen presentation, the binding of antigen peptides to MHC proteins is considered to be the major determinant. While all serving the purpose of MHC-binding prediction in general, the increasing method variations among these tools, in combination with the emerging new types of experimental data, render it necessary to rationally select the best approach, especially for the potential applications in cancer vaccine design
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
