AI-enabled molecular search database

The project aims to facilitate the research and development of new drugs by applying machine learning and deep learning to further develop an AI-assisted molecular search database. The company has an internal dataset holding more than a billion molecules. Two main challenges are keeping the molecule catalog updated and Searching for the desired molecule or a substructure in this voluminous database. Advanced query response techniques powered by AI, can enable the database to respond to molecule similarity and substructure search queries in the desired time frame. Reducing molecule search queries’ response time can significantly speed up the drug discovery activity of researchers and pharmaceutical companies working in this domain.

Faculty Supervisor:

Ioannis Mitliagkas

Student:

Partner:

Valence Discovery Inc

Discipline:

Computer science

Sector:

Pharmaceuticals; Artificial Intelligence; Health and Related Sciences & Technology

University:

Université de Montréal

Program: