HLAIIPred: Cross-Attention Mechanism for Modeling the Interaction of HLA Class II Molecules with Peptides

Abstract

We introduce HLAIIPred, a deep learning model to predict peptides presented by class II human leukocyte antigens (HLAII) on the surface of antigen presenting cells. HLAIIPred is trained using a Transformer-based neural network and a dataset comprising of HLAII-presented peptides identified by mass spectrometry. In addition to predicting peptide presentation, the model can also provide important insights into peptide-HLAII interactions by identifying core peptide residues that form such interactions. We evaluate the performance of HLAIIPred on three different tasks, peptide presentation in monoallelic samples, immunogenicity prediction of therapeutic antibodies, and neoantigen prioritization for cancer immunotherapy. Additionally, we created a dataset of biotherapeutics HLAII peptides presented by human dendritic cells. This data is used to develop screening strategies to predict the unwanted immunogenic segments of therapeutic antibodies by HLAII presentation models. HLAIIPred demonstrates superior or equivalent performance when compared to the latest models across all evaluated benchmark datasets. We achieve a 16% increase in prediction of presented peptides compared to the second-best model on a set of unseen peptides presented by less frequent alleles. The model improves clinical immunogenicity prediction, identifies epitopes in therapeutic antibodies and prioritize neoantigens with high accuracy. HIGHLIGHTS* We developed a deep learning model to address the shortcomings of existing models for the prediction of peptides presented by HLAII molecules. * The model is end-to-end and context-free, requiring only a peptide sequence and available HLAII alleles as input. * HLAIIPred outperforms the state-of-the-art models on multiple benchmark datasets. * The model is able to predict the core residues of peptides that interact with HLAIIs. * We created experimental data and developed screening strategies to accurately predict the immunogenic hotspots in therapeutic antibodies.