Advisor: Brett Trost, The Hospital for Sick Children

Suggested co-advisors: Rozita Dara [1], Angela Canovas [2], Mazyar Fallah [3], Zeny Feng [4], Brandon Lillie [5]

While the control of biological processes is often most closely associated with the regulation of transcription, other regulatory mechanisms are important as well. One such mechanism is the post-translational modifications of proteins, such as phosphorylation. In this project, the student will address the hypothesis that by developing a machine learning model that incorporates information about the effect of missense variants on post-translational modifications, we can more accurately predict the pathogenicity of missense variants in autism and other disorders.

Two-semester project preferred. The student is required to be on-site (Toronto) for the duration of the project.

Knowledge/Skills

Programming in Python and/or R; experience working in a Linux environment; experience using high-performance computing resources; experience in genetics/genomics would be an asset.