Sept. 19, 2023

Summer students contribute to precision medicine infrastructure with lasting impact

Project will help propel research for years to come

Calgary’s John Zheng discovered early on that he loved math—especially the problem solving that is such a big part of it. 

At around 15, he attended a math camp that sparked an interest in computer programming. Zheng began spending many hours teaching himself coding to solve puzzling problems. He enjoyed it so much that he decided to enroll in computer science at the University of Calgary.

Heading into his fourth year, Zheng continues to love being part of a UCalgary group of students who attend programming competitions under the tutelage of Dr. Farhad Maleki, PhD, an assistant professor in the Dept. of Computer Science.

That’s how Zheng met Kingsley Zhong, another computer science undergrad student at the University of Calgary.

Zhong’s interest in computer science began while enrolled in high school programming classes. He also quickly became involved in the competition scene.

Like Zheng, Zhong is a fan of the challenge that solving problems brings. He especially enjoys working through puzzles logically and seeing the process through to completion.

Both students are keen, making them great candidates for summer studentships at the Libin Cardiovascular Institute. Their professor, Maleki, brought the opportunity to the group of competitors through his collaboration with the Libin Institute’s Dr. James White, PhD, a clinician-researcher who heads the Libin Cardiovascular Institute’s Precision Medicine Initiative (PMI).

The PMI team is building a data infrastructure that will help cardiovascular researchers access rich data resources aiming to improve patient care.

Zheng and Zhong jumped at the opportunity to get hands-on experience building a complicated structure that will have a positive impact on cardiovascular patients.

Both quickly became valued members of the team, spending their summer under the supervision of the PMI data engineer, Matt MacDonald. The duo helped write code for the computer infrastructure, known as a data pipeline. 

There are several steps in building a pipeline. First, using software coding and all their problem-solving abilities, the team strips all personal information from data, such as names, addresses and even dates that could be used to identify individuals.

The data is then extracted from its current format; cleaned up by renaming some of the variables for consistency and filling in the missing fields; and loaded into a new high-performance environment. Finally, the pipeline must be tested, all the errors found and fixed, and the coding checked to ensure it’s simple and flexible enough to stand the test of time.

Although this isn’t easy work, it is important because it can then be harnessed by researchers using AI and machine learning techniques to build powerful diagnostic and predictive tools that are based on data from thousands of patients (all of whom have consented to provide this information.)

These tools will give health care providers the ability to personalize patient care by more accurately assessing risk, making diagnoses and providing treatment options for patients. 

Zheng and Zhong both worked on several parts of the pipeline, including transforming data into a useable format, loading it into a new environment, cleaning it, and finally testing and fixing errors. It’s work that is ongoing.

Both students enjoyed their experience, especially knowing that their work will ultimately have a positive impact on patients.

“Although my impact was indirect, it’s nice being part of something that will help others,” says Zhong.

Zheng agrees, noting the project was “very useful” and the collaborative environment eye-opening.

“I learned a lot of about how software is written in the real world,” he says. “I really enjoyed working together as a team, solving problems together. Everyone had the same goal, and the mindset was ‘let’s work together and create something.’”

Zheng may be entering into the final year of his program, but his love of learning is far from satiated. In fact, he aims for a career in AI-powered big data research.

Zhong, who is going into second year, is leaning towards a career as an entrepreneur or in start ups.

Both have a bright future.

MacDonald says the students’ efforts over the summer will have a lasting impact.

“Within just a brief span John and Kingsley contributed code that will help propel precision medicine research for years to come,” says MacDonald. “They faced unfamiliar challenges—such as vast data volumes and ensuring protection of patient information—and met them. Their impressive technical contributions, as undergraduates, truly exemplify the exceptional talent at the University of Calgary.”

Kingsley Zhong and John Zheng UCalgary computer science students

Kingsley Zhong and John Zheng, UCalgary computer science students, spent their summer working for the Libin Cardiovascular Institute's Precision Medicine Initiative.

Zhong photo supplied Zheng photo ICPC Foundation