As biologic drug providers strive to create more effective protein-based medicines, managing the immunogenicity of therapeutics, the likelihood that the immune system will recognize a treatment as a foreign object, remains a complex challenge. In some cases immunogenicity is wanted, such as in a vaccine; this trains the body to fight off specific diseases. However, with many biotherapeutics a strong immunogenic response can limit the effectiveness of the treatment or cause a more serious illness. This remains a challenge for scientists as the underlying mechanisms of unwanted immunogenicity still aren’t completely understood.
There are many reasons the human body may have an immune response to a biotherapeutic. Genetics appears to be a contributing factor, as different populations react to the same treatment differently. Chemical modifications to the biologic, such as attaching a small molecule drug, could also trigger an immune response. Manufacturing can contribute as well. For example, if manufacturing processes cause small amounts protein to clump together or fold differently than expected, the body may identify it as a foreign substance and attack.
As a result, detecting and preventing unwanted sources of immunogenicity as early in the discovery process as possible has become a top priority for research organizations since biotherapeutic development becomes increasingly costly as it moves downstream.
Predictive analytics has emerged as a leading tool to identify immunogenicity in biotherapeutics during the discovery phase of drug development. With it, researchers can more effectively mine data, make predictions, and gather actionable insight to advance candidates or discard failures. These virtual experiments can be combined with real experiments to provide scientists with more key performance indicators (KPIs) that drive informed
“The best qualification of a prophet is to have a good memory,” English statesman George Savile said centuries ago. His insight is relevant to today’s predictive sciences, whose models depend on past data. The value of a predictive approach depends on the quality and variety of the data supporting it. As such, companies that want to include predictive analytics in their drug development process should encourage data standardization and pre-competitive data sharing. Information systems need to be easily accessible to a wide range of diverse users and support collaboration among specialists with unique expertise.