A Systematic Assessment of MHC Class II Peptide Binding Predictions and Evaluation of a Consensus Approach

TLDR

Many computational tools exist for predicting MHC class II peptide binding, yet no large‑scale systematic evaluation has been performed. The study aims to benchmark existing MHC class II binding predictors and to develop a consensus method that improves accuracy. Using a dataset of over 10,000 binding affinities, 29 crystal structures, and 664 CD4⁺ T‑cell assays, the authors evaluated public tools and constructed a consensus predictor that aggregates the best performers. The benchmark showed most tools perform poorly (AUC rarely above 0.86) due to variable‑length peptide challenges, but the consensus predictor achieved the best overall performance, and the authors released the datasets for future work.

Abstract

The identification of MHC class II restricted peptide epitopes is an important goal in immunological research. A number of computational tools have been developed for this purpose, but there is a lack of large-scale systematic evaluation of their performance. Herein, we used a comprehensive dataset consisting of more than 10,000 previously unpublished MHC-peptide binding affinities, 29 peptide/MHC crystal structures, and 664 peptides experimentally tested for CD4+ T cell responses to systematically evaluate the performances of publicly available MHC class II binding prediction tools. While in selected instances the best tools were associated with AUC values up to 0.86, in general, class II predictions did not perform as well as historically noted for class I predictions. It appears that the ability of MHC class II molecules to bind variable length peptides, which requires the correct assignment of peptide binding cores, is a critical factor limiting the performance of existing prediction tools. To improve performance, we implemented a consensus prediction approach that combines methods with top performances. We show that this consensus approach achieved best overall performance. Finally, we make the large datasets used publicly available as a benchmark to facilitate further development of MHC class II binding peptide prediction methods.