CO-FUNDED PROJECT BY IVADO
Cardiovascular disease (CVD) remains the leading cause of death worldwide, yet less than half of patients benefit from preventive CVD medications. Drug responses are influenced by patients’ genomic profiles, other individual characteristics, and environmental factors. Until recently, these factors were generally not taken into account in clinical studies, leading to an evaluation of treatments that underestimated their usefulness or failed to detect deleterious effects in certain patient groups. The main objective of this project is to use precision medicine and machine learning techniques to automatically discover individual characteristics that are predictive of disease development or progression and responses to multiple CVD drugs (efficacy and toxicity). The team proposes to integrate multiple data (genetic, multi-omics, imaging, clinical data) and biomarkers using traditional statistical methods and novel machine learning approaches. Their approach will enable the identification and validation of drug targets, and will lead to both the transformation of CVD drug development as well as the improvement of patient care (especially for atherosclerosis-related diseases.
Lead Genome Centre: Génome Québec
Partner: IVADO
Co-investigators:
| Marie-Pierre | Dubé | Université de Montréal |
| Julie | Hussin | Université de Montréal |
| Joëlle | Pineau | McGill |