Scientists have developed a new AI tool that maps the function of proteins in cancer tumors, enabling doctors to decide how to target treatments in a more precise way.
In cancers such as clear cell renal cell carcinoma (ccRCC), the response to existing treatments is different for each patient, making it difficult to identify the right drug treatment regimen for each patient.
For example, the cancer therapeutic Belzutifan was recently approved for the treatment of ccRCC, but has only a 49% response rate in patients with the most common form of the condition.
To better understand why some patients respond better than others, researchers from the University of Bath and Nottingham studied the function of hypoxia-induced factor alpha (HIF2α), a key target in ccRCC that is blocked by beljutifan.
Previous studies have shown that levels of HIF2α do not correlate with tumor aggressiveness, and when higher levels of the protein were present, HIF2α was less active.
This means that administering high doses of benzutifan potentially exposes the patient to expensive, toxic therapeutics that may not work and may even make the tumor more drug-resistant.
A cross-disciplinary team of biophysicists, biologists and computational scientists developed a new tool called FuncOmap, which maps the functional state of target oncoproteins in tumor images.
This will enable clinicians to directly visualize tumor locations where oncoproteins are interacting, allowing for more accurate diagnosis and informing optimal treatment for each patient.
The study was co-led by Professor Banafshe Larijani, Director of the Center for Therapeutic Innovation at the University of Bath. He said: “People react differently to drugs.
It is therefore crucial to be able to predict how patients will respond to drugs individually so that a therapy can be effective while giving the lowest dose to minimize side effects.
“Our new computational analysis tool uses precision to directly map the functional status of oncoproteins to tumor segments in patients, allowing clinicians to improve patient stratification, enabling personalized medicine.”
The team is now collaborating with Dr. Amanda Kiren’s laboratory at Stanford University School of Medicine (USA) as well as other surgeons and physicians to further develop and optimize the tool in the clinical arena.
This study describes the type of novel and influential research that is the essence of work across disciplines.
It brings together computer science, biology and physics under the umbrella of the UKRI Center for Doctoral Training in Accountable Responsible and Transparent Artificial Intelligence, to provide image analysis with the ability to directly inform clinical decision-making and personalized clinical outcomes in cancer treatment. as well as other diseases.”
Professor Eamonn O’Neill, Head of Computer Science at Bath and Director of the UKRI Center for Doctoral Training in Accountable, Responsible and Transparent AI (ART-AI)
Professor Jonathan Knight FRS, Vice-President (Enterprise) at the University of Bath, said: “The excitement of this paper lies not only in the work reported, but in the example of how it is bridging the fields of biophysics and translational medicine research. “Modern computational science promises to accelerate the translation of research into valuable tools for the clinical environment. This truly enhances the value gained from transdisciplinary studies.”
The research was funded by UKRI Center for Doctoral Training in Accountable Responsible and Transparent Artificial Intelligence (ART-AI)[grantnumberEP/S023437/[grantnumberEP/S023437/[অনুদাননম্বরEP/S023437/[grantnumberEP/S023437/Medical Research Council and University of Bath Alumni Fund, and published in journals BJC report.
Saffrigina, E., etc. (2024). Spatial functional mapping of hypoxia inducible factor heterodimerization and immune checkpoint regulators in clear cell renal cell carcinoma. BJC report. doi.org/10.1038/s44276-023-00033-7.