New molecular representation, molecular generation, and data mining strategies for thedesign of SARS-CoV-2 therapies

The goal of the project is to facilitate the research and development of new drugs using machine learning. More specifically, exploring new techniques to model molecules and how they can be represented. Doing so will involve training deep learning models on multiple small datasets with the objective of improving the generalization performance on new tasks. The trained models will have to be accurate even in the context of new types of molecules. With the small amount of data available, out-of-distribution techniques will be used. Molecules are dynamic 3D structures but are currently not represented as such. New machine learning models will be created in order to capture the dynamic aspects of molecules. If successful, this will improve the performance of many tasks that requires molecular information.

Faculty Supervisor:

Ioannis Mitliagkas

Student:

Partner:

Valence Discovery Inc

Discipline:

Computer science

Sector:

COVID-19 related Research and Solutions; Pharmaceuticals; Artificial Intelligence

University:

Université de Montréal

Program: