Grant: Doctoral: Vanier Canada Graduate Scholarships

About 25% of bladder cancer patients present with muscle-invasive bladder cancer (MIBC), in which the tumor has grown into the muscle layer of the bladder wall. This form of disease is more aggressive causing patients to experience increasingly severe symptoms and often results in death. To treat MIBC, patients undergo a tumor removal surgery followed by a drug therapy, like chemotherapy. If this initial treatment does not work, patients must have their entire bladder removed, which is a dangerous and life-altering surgery. Thus, we want to optimize our initial treatment strategy to remove the cancer without resorting to bladder removal. After the tumor removal surgery, there are many options for drug therapies. However, currently, we don't know which patients will respond best to which therapy. Selecting the right treatment for a patient is critical to help them avoid bladder removal. This study's goal is to understand what types of patients will respond best to certain therapies. We collected tumor samples from MIBC patients and followed them to see how they responded to different types of drug therapies. We will analyze different characteristics of the tumor samples such as how they look microscopically, their DNA content, presence of immune cells, amongst others. Since we will have many different types of information on the tumor, we will use artificial intelligence (powerful computer algorithms) to combine everything together to predict which patients will respond to which therapies. The results of this study will help in the treatment of MIBC patients, through personalized treatment recommendations that are most effective for their unique cancer, saving many from bladder removal procedures and improve overall outcomes. Moreover, by combining different data types using artificial intelligence, we will be able to explain the biology behind treatment failures in MIBC, to identify new drug targets and improve future therapies for patients.