Grant: CIHR Fellowship

Background In Canada, breast cancer is the second leading cause of cancer deaths among women, making up 25% of cancer cases in women. Triple-negative breast cancer (TNBC) patients lack hormone and growth factor receptors, demanding treatments specifically tailored for TNBC. One method to improve outcomes involves identifying biological markers (biomarkers) to select patients who can benefit most from therapies. Rationale Mutations in BRCA genes significantly increase the risk of breast cancer. BRCA-mutation is an important biomarker, selecting patients who can benefit from targeted therapies called PARP inhibitors. However, not all BRCA-mutant patients respond to these drugs, suggesting other factors may influence treatment outcomes. The immune system and the areas surrounding the tumor (tumor microenvironment, TME) can influence response to PARP inhibitors. Our project aims to clarify the role of the TME in BRCA-mutant patients and use artificial intelligence (AI) to predict who will benefit from PARP inhibitor treatment. Aims 1 Better understand how the TME influences outcomes in BRCA-mutant patients. 2 Use AI to combine tumor gene expression with immune markers to predict to PARP inhibitors. Methods 1 Using breast cancer tissue samples with and without BRCA mutations, we will perform sophisticated gene expression analysis based on tissue compartments and profile the immune response by detecting protein expression with fluorescence. 2 Combine clinical features, gene expression, and immune markers from TNBC patient surgical samples using AI to identify markers of response to PARP inhibitors. Impact Understanding the factors influencing responses to PARP inhibitors can help better predict which patients will respond, with the potential to expand PARP inhibitor use to patients lacking BRCA mutations. Our project will use AI to identify such biomarkers, aiming to enhance treatment strategies for TNBC patients and significantly improve their survival.