Improved prediction of HLA antigen presentation hotspots: Applications for immunogenicity risk assessment of therapeutic proteins. Issue 2 (19th October 2020)

• Record Type: Journal Article
• Authors: Attermann, Anders Steenholdt; Barra, Carolina; Reynisson, Birkir; Schultz, Heidi Schiøler; Leurs, Ulrike; Lamberth, Kasper; Nielsen, Morten
• Is Part Of: Immunology. Volume 162:Issue 2(2021)
• Page Start: 208
• Page End: 219
• Publication Date: 2020-10-19
• Subjects: HLA antigen presentation -- HLA eluted ligands -- immunogenicity assessment -- prediction -- protein immunogenicity; Immunology -- Periodicals
• DOI: 10.1111/imm.13274
• Languages: English
• ISSNs: 0019-2805

Abstract

Summary: Immunogenicity risk assessment is a critical element in protein drug development. Currently, the risk assessment is most often performed using MHC‐associated peptide proteomics (MAPPs) and/or T‐cell activation assays. However, this is a highly costly procedure that encompasses limited sensitivity imposed by sample sizes, the MHC repertoire of the tested donor cohort and the experimental procedures applied. Recent work has suggested that these techniques could be complemented by accurate, high‐throughput and cost‐effective prediction of in silico models. However, this work covered a very limited set of therapeutic proteins and eluted ligand (EL) data. Here, we resolved these limitations by showcasing, in a broader setting, the versatility of in silico models for assessment of protein drug immunogenicity. A method for prediction of MHC class II antigen presentation was developed on the hereto largest available mass spectrometry (MS) HLA‐DR EL data set. Using independent test sets, the performance of the method for prediction of HLA‐DR antigen presentation hotspots was benchmarked. In particular, the method was showcased on a set of protein sequences including four therapeutic proteins and demonstrated to accurately predict the experimental MS hotspot regions at a significantly lower false‐positive rate compared with other methods. This gain in performance was particularly pronounced when compared to the NetMHCIIpan‐3.2 method trained on binding affinity data. These results suggest that in silico methods trained on MS HLA EL data can effectively and accurately be used to complement MAPPs assays for the risk assessment of protein drugs. Abstract : Therapeutic proteins have the drawback of potentially being recognized as non‐self, thus generating an undesired immune response in patients. Currently, MHC‐associated peptide proteomics (MAPPs) experiments and/or T cell activation assays are used to assess this potential immunogenicity, however, these techniques are highly cost‐intensive and share a limited sensitivity imposed primarily by the analyzed samples. Here, the NNAlign_MA machine learning framework was used to develop an in silico model and pipeline that accurately predicts with high fidelity the outcome of MAPPs assays.