Directory of Experts
Back to search results

Research project title

Development of an AI algorithm for expressomics and metabolomics data analysis for the early detection of ovarian cancer.

Education level

Master (research-based)

Director/co-director

Director: Mario Jolicoeur

End of display

May 31, 2026

Areas of expertise

Biomedical engineering

Unit(s) and department(s)

Department of Chemical Engineering

Institut de génie biomédical

Conditions

Envoyer votre lettre de motivation, Curriculum vitae et relevé de notes universitaires au professeur Mario Jolicoeur (mario.jolicoeur@polymtl.ca) et au Dr. Jorgelindo da Veiga Moreira, CEO Spheroïde IA inc. (jorgelindo@spheroid.com)

Detailed description

Context: In collaboration with Spheroid IA inc., this research project aims to address the challenge of early detection and personalized treatment of ovarian cancer, through the integration of machine learning, deep learning and kinetic metabolic models. Ovarian cancer is often diagnosed in advanced stages, which limits treatment options and reduces survival rates. Furthermore, the disparity between transcriptomic and metabolomic data poses a significant obstacle to the precise characterization of the metabolic profile of cancer tissues, thereby hindering effective treatment strategies.

Aim of the project: The long-term goal to which this master's project will contribute is to develop a predictive and personalized medicine approach for ovarian cancer, by harnessing the power of omics data analysis and computational modeling. More specifically, this project aims to develop supervised machine learning algorithms for the identification of biomarkers making it possible to differentiate healthy individuals from those suffering from ovarian cancer. These algorithms, paired with an already developed metabolic model, will be designed, selected and trained using transcriptomic and metabolomic data obtained from patient blood samples in collaboration with hospitals and medical clinics. The algorithms can thus be validated according to their predictive capacity for individual metabolic phenotypes and the level of aggressiveness of patients' cancerous tissues.

The importance of this research lies in its potential to transform our ability to diagnose and treat ovarian cancer.

Financing possibility

Funding according to the CRSNG standards