Challenge: Triple negative breast cancer (TNBC) is the most aggressive form of breast cancer. Even in the early stages it is treated primarily by chemotherapy, often before surgery. The presence of remaining tumor after chemotherapy signals chemoresistance and poor prognosis resulting in the death of 30 to 40 % of patients with triple negative breast cancer within five years of surgery. These patients go on to receive further chemotherapy (Capecitabine) for 6 months, with only a 15 % benefit in disease-free survival. Identifying the patients who will benefit from this additional chemotherapy is a current unmet need. Preliminary data suggests that liquid biopsy testing of circulating tumor DNA (ctDNA) is highly prognostic in TNBCs. The role of molecular tumor profiling and other plasma molecules (proteins, miRNA) in determining prognosis is unknown. To integrate all these data (tumor tissue and plasma, RNA, DNA, protein) in a predictive algorithm, it will be essential to take advantage of the recent advances in artificial intelligence (AI) methodology.
Solution: The objective of the present study is to integrate multidimensional profiles (genomic, transcriptomic, miRNA analysis, proteomic) to develop multi-omic signatures of good and poor outcome as well as of tumor response to chemotherapy in TNBC patients with residual tumor post-neoadjuvant chemotherapy (NAC). After measurement of ctDNA, mRNA, miRNA, and proteins in both tumor and plasma through liquid biopsies, AI tools developed by MIMs will integrate all these data in an algorithm to develop a novel prognostic signature.
Expected achievements/Impact : The project proposed here will lead to the discovery of novel biomarker signatures using innovative integrative AI strategies. Biomarkers for chemoresistant TNBCs will allow the proper selection of chemotherapy for patients with poor prognosis and the avoidance of the toxicity of unnecessary chemotherapy for good prognosis patients, and this will have a major clinical impact in the most aggressive form of breast cancer, the most common cancer in women.
| Principal Investigator: Mark Basik Jewish General Hospital |
| Co-investigators Sarah Jenna My Intelligent Machines (MIMs) Richard Fajzel Exactis Innovation |
| Ongoing Project |
| $1,500,000 / 3 years |
| Supported by CQDM through: – MEI |
| And by co-funding partners: – Canadian Cancer Society (CCS) – My Intelligent Machines (MIMs) – Exactis Innovation |
