In silico immunogenicity risk assessment is a key step in the development path for biologic therapeutics. Computational tools have been used to identify T cell epitopes from primary amino acid sequences and assess the immunogenic potential of therapeutic candidates for several decades. In silico modeling during discovery and preclinical development is recommended as T cell epitopes contained in biologic sequences may activate the immune system, enabling the development of anti-drug antibodies that can reduce drug efficacy and/or induce adverse events. 

This webinar will review an integrated web-based platform called ISPRI (Interactive Screening and Protein Reengineering Interface) which contains a multitude of tools for assessing immunogenic risk of biotherapeutics, such as identification of promiscuous T cell epitopes, and prediction of anti-drug antibody (ADA) responses. Novel artificial intelligence and machine learning (AI/ML) techniques have now been integrated into ISPRI, leading to improved performance. This presentation will focus on ISPRI’s new AI-based models which have led to a 6-fold increase in the correlation between predicted and observed rates of ADAs, while significantly reducing the rate of false negative (low predicted immunogenicity / high observed immunogenicity) by 85%.