An AI spatial mapping tool that maps the function of proteins in tumors shows promise in assessing the aggressiveness of an individual’s cancer allowing clinicians an improved way to develop targeted treatment regimens.
The research was published recently in the journal RJC Reports.
The tool, developed by researchers at the Universities of Bath and Nottingham, England, can be used in cancers such as clear cell renal cell carcinoma (ccRCC). Patients with ccCRC show differing responses to approved, which make it difficult to chosse the best treatment for each patient. For instance, the recently approved drug belzutifan for treating ccCRC is effective in just under half of the patients with the most common form of the condition.
To understand why some patients respond to belzutifan, while others have a limited response, the Bath and Nottingham investigators studied the function of Hypoxia-Induced Factor Alpha (HIF2α), which is blocked by the drug to treat ccRCC. Previous research has shown that HIF2α levels don’t always correspond to how aggressive the tumor is. Further, and counterintuitively, the higher the levels are of HIF2α, the less active it is.
The result is that higher doses of belzutifan prescribed to patients may not be effective and eventually even make the tumor more drug resistant.
To better understand the tumor dynamics, and to find better treatment options, a multidisciplinary team created the AI tool to map the functional state of the target oncoproteins onto images of the tumor. Dubbed FuncOmap, the tool allows clinicians to directly see where in the tumor the oncoproteins are iteracting, allowing for a more accurate diagnosis of ccRCC and providing better information for appropriate treatment selection.
“People respond to drugs very differently. It is crucial to be able to predict how patients will respond to drugs individually so a therapy can be tailored to be effective whilst giving the lowest dose to minimize side effects,” said Banafshé Larijani, director of the Centre for Therapeutic Innovation at the University of Bath “Our new computational analysis tool uses precision to directly map the functional states of oncoproteins in patients’ tumor sections, so that clinicians can improve patient stratification, enabling personalized medicine.”
Continuing their efforts, the researchers have now begun collaborating with researchers at Stanford University School of Medicine to further develop and optimize the tool for use in the clinical setting.
