Deep learning models for compound design

Traditional drug development strategy is costly, tiresome, and labor-intensive. In the last decade, artificial intelligence (AI) technologies have shown promising results to overcome some of these limitations. However, these computational technologies still cannot efficiently generate novel drugs with expected properties for treating specific diseases. Here we will apply new generation of AI frameworks to design novel compounds with predefined properties. We will collect and analyze the publicly available data from peer-reviewed publications and in-house data to build the AI models. This research will help both the company to address some of its pressing needs and improve the interns’ skills for their future career development.

Faculty Supervisor:

Pingzhao Hu

Student:

Md Mohaiminul Islam;Yan Sun

Partner:

Servier

Discipline:

Computer science

Sector:

University:

University of Manitoba

Program: