Algorithm Predicts Efficacy of Cancer Treatment

Immunotherapies are promising new cancer treatments that tend to be less toxic than traditional therapies. However, patients may not always respond to therapy or they may experience significant adverse events.

To address these challenges, researchers recently developed a mathematical model that can accurately predict whether a patient with cancer will respond to immunotherapy, according to a study published by Nature.

Scientists have been searching for a way to determine whether patients will respond to new checkpoint inhibitors and to understand the characteristics underlying why the therapy was successful.

The novel algorithm characterizes the tumor's evolution and its interactions with the immune system, according to the study. The authors said that this mathematical algorithm can more accurately predict how cancer will respond to immunotherapy compared with currently used biomarkers.

"We present an interdisciplinary approach to studying immunotherapy and immune surveillance of tumors," said senior author Benjamin Greenbaum, PhD. "This approach will hopefully lead to better mechanistic predictive modeling of response and future design of therapies that further take advantage of how the immune system recognizes tumors."

The model may also help discover new therapies that can target the immune system or vaccines for patients who do not respond to immunotherapy, according to the study.

Data from patients with melanoma and lung cancer who received immunotherapy treatment were compiled to create the model. The system can track immune response to the drugs by focusing on neoantigens.

The authors note that neoantigens have the potential to be an immunotherapy target and can be useful for patients with drug resistant disease. The neoantigens may be critical to understanding why sometimes immunotherapy results in autoimmune side effects, according to the authors.

Specifically, the mathematical model can predict immune response in patients with pancreatic cancer.

These models may result in more accurate therapy and prevent potentially dangerous adverse events. Additionally, it could reduce drug costs, as the model could prevent unnecessary treatments, according to the authors.

"This research represents a big step forward in understanding why some tumors are more aggressive than others and being able to predict rationally which neoantigens will be the most effective at stimulating an immune response," said corresponding author Vinod P. Balachandran, MD.