Prediction in Silico of Pathological Response in a Prospective Cohort Study of Early Breast Cancer Patients

Breast cancer (BC) is the most common cancer in women in France with nearly 58,500 new cases and 12,150 deaths estimated in 2018 . Two major achievements have been made in the last five years for breast cancer patients. The first is therapeutic with the approval of immune checkpoint inhibitors in advanced and early triple-negative BC (TNBC) and the impressive efficacy of new antibody-drug conjugated in all BC subtypes. The second is conceptual with the generalization of adaptive therapeutic strategies guided by pathological responses after neoadjuvant therapy in early TNBC, HER2+, HR+ and BRCA mutated breast cancer. This new paradigm in the treatment of cancer patients completely redefined prognostic factors that were previously established with conventional approaches Pathological response remains a major prognostic factor especially for TNBC and HER2 early breast cancer. However, this parameter is evaluated at the end of neoadjuvant treatment and for patients with residual disease, the prognosis remains poor despite some adaptative strategies. Our project is to integrate massive and heterogeneous data concerning the disease (clinical and biological data, imaging and histological results (with multi-omics data)) and patient's environment, personal and familial history. These data are multiple and have dynamic interactions overtime. With the help of mathematical units with biological competences and scientific collaborations, our project is to improve the prediction of treatment response, based on clinical and molecular heterogeneous big data investigation. The main objective of this project is to set up a clinicobiological database prospectively by collecting prospective clinical, biological, pathological and multi-omic data from 300 Patients with early BC treated at the ICO in order to define an algorithm of individual decision for the prediction of the response to this treatment.