Understanding why patients respond differently to cancer drugs

An incredible advancement in cancer diagnosis and treatment personalization has emerged with the development of FuncOmap, a novel AI tool that maps the function of proteins within cancerous tumors.

Created by scientists from the Universities of Bath and Nottingham (both UK), this tool enables clinicians to tailor treatments with extraordinary precision based on the functional states of oncoproteins.

In conditions like clear cell renal cell carcinoma (ccRCC), where treatment responses vary among patients, identifying the most effective drug treatment poses a significant challenge. For instance, the therapeutic Belzutifan, newly approved for ccRCC treatment, exhibits a response rate of only 49% in patients with the most common form of the disease.

To unravel the complexities underlying treatment response disparities, the researchers focused on understanding the function of Hypoxia-Induced Factor Alpha (HIF2α), a crucial target in ccRCC that is inhibited by Belzutifan. Contrary to expectations, previous research has revealed that higher expression levels of HIF2α were associated with reduced HIF2α activity, complicating ccRCC treatment decisions and potentially leading to ineffective or harmful therapies if Belzutifan is administered.

To address this challenge, the team developed FuncOmap, which directly maps the functional states of target oncoproteins onto tumor images. By visualizing the precise locations of oncoprotein interactions within tumors, this AI tool empowers clinicians to make more accurate diagnoses and tailor treatments to individual patients, minimizing side effects and optimizing therapeutic outcomes.

Professor Banafshé Larijani, Director of the Centre for Therapeutic Innovation at the University of Bath, emphasized the importance of predicting individual patient responses to drugs for personalized medicine success while minimizing side effects.

“Our new computational analysis tool uses precision to directly map the functional states of oncoproteins in patients’ tumour sections, so that clinicians can improve patient stratification, enabling personalized medicine,” she explained.

Now collaborating with Stanford University School of Medicine (CA, USA), the team aims to further refine FuncOmap for clinical use.

Head of Bath’s Department of Computer Science, Professor Eamonn O’Neill stated, “This study describes the kind of novel and impactful research that is the essence of working across disciplines. It brings together computer science, biology and physics, under the umbrella of the UKRI Centre for Doctoral Training in Accountable Responsible and Transparent Artificial Intelligence, to deliver image analysis that has the capacity to directly inform clinical decision-making and personalized clinical outcomes in cancer treatment as well as other diseases.”