Novel Approach to Predicting Response to Immunotherapy in Melanoma

Researchers have created a gene-expression predictor that determines whether specific patients with melanoma are likely to respond to treatment with immune checkpoint inhibitors, based on a study conducted by Noam Auslander, MD, of the University of Maryland, and colleagues. Published in Nature Medicine, the study suggests that the new predictor, called IMPRES, appears to be accurate across many different melanoma patient data sets, unlike other existing predictors.

“There is a critical need to be able to predict how cancer patients will respond to this type of immunotherapy,” commented Eytan Ruppin, MD, PhD, of the National Cancer Institute’s (NCI) newly established Cancer Data Science Laboratory, who led the study, in a press release. “Being able to predict who is highly likely to respond and who isn’t will enable us to more accurately and precisely guide patients’ treatment.”

The researchers tested IMPRES (the immune-predictive score) on 297 samples from multiple studies. The higher the IMPRES score for a sample, the more likely it was to undergo spontaneous regression. They found that the predictor outperformed existing approaches, with an overall accuracy of AUC = 0.83. In addition, it seemed capable of diagnosing almost all patients who responded to the inhibitors and more than half of those who did not.

“We now know that immunotherapy works, but we do not understand well why a particular therapy will work for some patients but not others,” said Tom Misteli, PhD, Director of the Center for Cancer Research at NCI. “This study is a step forward in developing tools to address this challenge.”