Triple negative breast cancers (TNBC) are an aggressive group of breast cancers, with high rates of relapse, poor survival outcomes and limited treatment options. Finding effective personalized treatment options is a critical unmet medical need. PeCaN aims to tackle this challenge through the development of advanced computational models for predicting individualized responses to targeted treatments, based on a deep molecular analysis of the patient and their tumor. In particular, we focus on solving the currently most difficult problem in model development: identifying the regions of the computational model parameter space that lead to the most accurate predictions. For this, we combine novel parameter optimization approaches, artificial intelligence, CRISPR-based cell genetics and single cell omics to generate parameterized models that can be used to predict patient-specific therapy responses and identify new drug targets and biomarkers. Candidates and predictions will be evaluated clinically, potentially providing real world evidence for their utility and offering a strong foundation for the development of future clinical trials.