Research begins this July on a project to apply big data to cancer treatment protocols.

Computer Science and Engineering Assistant Professor Tin Nguyen has received a $490,039 National Science Foundation CAREER award to develop new machine learning techniques that can crunch data — molecular and biological — to determine how an individual’s cancer might progress. The 5-year project is expected to conclude in 2027.

“This work will potentially enhance our ability to distinguish among patients who are in immediate danger and need the most aggressive treatments and those whose disease will progress more slowly,” Nguyen said. “This will lead to reduced health care costs and personal suffering while improving patient care by identifying the correct personalized treatment for each patient.”

The Faculty Early Career Development (CAREER) Program is the NSF’s most prestigious award given to early-career faculty who have the potential to serve as academic role models in research and education and lead advances in the mission of their department or organization.

For Nguyen, whose research interests are disease subtyping, pathway analysis and machine learning, this CAREER grant is crucial for him and his students to continue their research direction.

Advancing the technique of cancer subtyping

Cancer, Nguyen explains in his CAREER grant application, is an umbrella term for a range of disorders, from those that are fast-growing and lethal, to those that are slow to develop and have low potential for progression to death.

It’s also a disease will impact many of us: About 39.5% of men and women in the United States will be diagnosed with cancer at some point, according to the National Cancer Institute at the National Institutes of Health.

In the past few decades, advances in molecular subtyping (a way of classifying cancers based on molecular data and classification models) have helped medical professionals deliver treatments targeted to an individual’s particular case. But there’s room for improvement: Nguyen says a significant percentage of patients do not respond to targeted therapies, or develop resistance over time.

That, he says, implies that tumor characterization and therapeutic interventions are not sufficiently accurate: a situation his CAREER-funded research project could help remedy.

Nguyen and his team plan to utilize machine learning (a type of artificial intelligence that allows computers to predict outcomes without being explicitly programmed to do so) to crunch the vast amount of molecular data available.

“We will develop machine learning techniques to learn from molecular data to predict survival risks of patients,” Nguyen said, “as well as to identify the significant signaling pathways that underly a person’s condition.”

Identifying the signaling pathways (the chemical reactions in which a group of molecules in a cell work together to control a function, such as cell division) and understanding which signaling pathways are involved in a person’s condition, will help medical professionals personalize treatment plans to a greater degree.

On a broader scale, Nguyen’s research could add to our understanding of cancer and provide information on why patients with the same type of cancer, receiving the same treatment, can have different outcomes. And in the long-term, Nguyen said, “it will serve as the foundation for our future projects, identifying clinically applicable biomarkers that can be used in diagnosis, risk prediction and monitoring treatment response and outcome.”