Immunetrics

Technology

The results are all too familiar. Efficacy signals that vanish in larger studies. Confirmatory trials that cannot be replicated. Labels so narrow they miss the market. And worst of all, late-stage or post-approval safety surprises. These problems are born in the gap between hypotheses and reality, between pilot study and proof of concept. If only your data could truly predict the results of every stage of discovery and development.

Biosimulation technology from Immunetrics, Inc. provides a bridge between research, experiments, and trial design decisions. Put simply, we build predictive computer models based on biological mechanisms. Mathematical models have been used to describe complex systems in other industries for years. No one prototypes an airplane, a car, or a space mission without running the empirical data through a computer model. Even the healthcare industry has a history of using models for product development. Now the predictive power of mechanistic modeling can be applied to pharmaceutical and device development. Why is the pharmaceutical industry behind? Medicine's foundation, the biology, is complex and difficult to discern. Only recently have scientists begun to grasp the intricate mechanisms behind many disease states. It is the knowledge of these mechanistic details that makes modeling them possible. However, incorporating detailed biology into the framework of a model remains a daunting task.

What is the value of biosimulation?

Building a model of a complex process provides a level of understanding that is otherwise unreachable. Details can be seen at a very fine resolution, and an unlimited number of virtual scenarios can be explored. For example, performing clinical trials with actual patients is severely limited by cost. However, there is virtually no cost associated with running an in silico trial. Immunetrics technology enables us to perform nearly unlimited in silico trials testing multiple therapeutic regimens in patient cohorts of various sizes, while simultaneously examining multiple clinical endpoints. We can predict which patient groups will respond to a drug, what size trial is best suited for a client's need, which endpoints will provide the most favorable outcome, and when clinical endpoints should be measured.