Dr. Helen Chen
Professor, Faculty of Public Health
Faculty of Health Sciences
Binh Ho
Cheriton School of Computer Science PhD Candidate
Department of Mathematics
Drug development is a difficult process that costs billions of dollars and takes years, even decades. Whether scientists are trying to understand the potential interactions between two drugs or developing new uses for existing drugs, pharmaceutical research is frequently plagued by wrong turns and dead ends.
A multidisciplinary team of researchers at the University of Waterloo is using machine learning to dramatically increase the speed of drug development. “We have a lot of existing data across a wide range of medical areas, but it is very complex and often not as complete or extensive as we would like,” explains Dr. Helen Chen, Professor of the Practice of Public Health Sciences. “It’s like a very shallow ocean.”
Chen worked with Bing Hu, a PhD candidate in computer science, to analyze and synthesize large amounts of pharmaceutical research data and build machine learning models that can predict drug properties and interactions. To best describe the effects of drugs on the body, they turned to Dr. Anita Leighton, an internationally recognized professor of applied mathematics for her work building mathematical models of the kidney.
“When you train a neural network using machine learning, you often start from scratch,” Hu says. “But by leveraging the vast amount of domain-specific knowledge from biology and medicine, we can build more efficient and more accurate models whose predictions consistently match existing real-world data.”
The team’s models can predict how drugs will interact with specific protein targets and how they will work in the human body in terms of efficacy and safety.
“Personalized treatment is the next frontier in medicine,” says Chen. “Machine learning research like this will put treatments into everyone’s hands.”
The research team’s collaborations are not limited to campus. They collaborate with other experts around the world to collect data, develop hypotheses, and make clinical trials and trials more efficient and effective.
In Ontario, we are working with medical researchers at the Princess Margaret Cancer Center to best understand how to use new technologies strategically. They are also collaborating with researchers at Yonsei University’s Advanced Data Science Institute in South Korea to think about the technology’s potential to impact the world.
“AI is powerful and exciting, but we need to focus on using it to build tools that actually benefit people,” Hu says. “That development must be a collaborative process, working with experts to create the tools needed to achieve the next world-changing breakthrough.”
“One of the most exciting things about this research is that it brings together perspectives from so many disciplines,” Chen says. “The combination of that convergence and the power of AI has made discovery so much faster. What used to be riding a horse from point A to point B is now like riding a high-speed train.”
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or position, and all views, positions, and conclusions expressed herein are those of the authors alone. Read the full text here.
