Hickling, T. P. | bioRxiv Science

bioRxiv2026

Statistical Methodology for Qualification of a Non-Clinical Risk Assessment Peptide:T Cell Proliferation Assay to Support Decision Making

Antibody- and cell-mediated immune responses against biologics, should they occur, can impact treatment efficacy and potentially pose severe risks to patient safety. Therefore, developers have focused on advancing strategies to mitigate such unwanted immunogenicity. Opportunities to address immunogenicity early in the development process, particularly during the drug design phase, have been identified. In vitro and in silico tools that facilitate the identification and removal of sequence liabilities have been established. For example, human cell-based in vitro T cell assays can be used to identify and remove CD4+ T cell epitopes, which are known to play a critical role in the development of anti-drug antibodies against recombinant proteins products as well as the transgenes of gene and therapy. Despite their widespread use in the industry, most of these assays lack thorough characterization, which undermines confidence in the results and comparability across laboratories. In this study, concepts of immunogenicity bioanalytical assay validation for study design and analysis were applied to characterize an internal CD4+ T cell proliferation assay as fit-for-purpose. A statistical path was applied to establish data acceptance criteria for handling of replicates, positivity and negativity of a signal, and donor cohort size. A Bayesian analysis was also performed and is proposed as an approach for sequence de-risking decision making. The in-depth characterization of the CD4+ T cell proliferation assay described here allows for accurate interpretation of the assay outcomes, thereby enhancing confidence in using this approach for mitigating the immunogenicity of biologics by design.

immunology↗

bioRxiv2024

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

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.

bioinformatics↗