Towards personalized medicine in the management of epilepsy: a machine learning approach in the interpretation of large-scale genomic data

Principal Investigator: Patrick Cossette
Theme : Health
Competition : 2017 Competition: IVADO's Grants for fundamental research projects
Status : Completed
Start : Apr. 1, 2018
End: Dec. 31, 2020
Budget : $172,800.00



Epilepsy is a disease that has negative consequences for the daily lives of patients. It is also difficult to treat. To date, more than 150 epilepsy genes have been identified, which account for approximately 35 percent of cases. Conventional genomic methods have not, however, been able to explain the full spectrum of epilepsy heredity or the resistance to antiepileptic drugs. In fact, conventional studies are not capable of capturing the full complexity of the human genome, such as the interactions among genomic variations (epistasis). In this project, we will investigate how we can use machine learning algorithms in genomic data analysis to detect multivariate patterns, taking advantage of our large dataset of the genomes of individuals with epilepsy. In this multidisciplinary project, neurologists, geneticists, bioinformaticians and computer scientists will join forces and use machine learning algorithms to detect the signatures of genomic variants in patients with drug-resistant epilepsy. Our ability to predict drug resistance will reduce the burden and incidence of this disease.


Lead Genome Centre: Génome Québec


Partner: IVADO



Yoshua Bengio Université de Montréal
François Laviolette Université Laval
Simon Girard Université du Québec à Chicoutimi