FNL’s capstone partnership with Georgetown provides student training opportunity

As a national laboratory, the Frederick National Laboratory for Cancer Research (FNL) is committed to supporting the next generation of biomedical researchers—a generation for which data science skills are becoming increasingly critical.

A headshot of Mark Jensen, cropped in a circle with a teal background
Mark Jensen, Ph.D.
A headshot of Master's student Fuyuan Wang, cropped in a circle with a teal background
Fuyuan Wang

To that end, the FNL signed a trainee affiliation agreement with Georgetown University to provide capstone experiences for students in Georgetown’s new Health Informatics and Data Science (HIDS) master’s program. The first student, Fuyuan Wang, recently completed his capstone under the mentorship of Mark Jensen, Ph.D., Director of Data Management and Interoperability in the FNL Biomedical Informatics and Data Science directorate.

“The Georgetown [HIDS] capstone is designed to provide students with real-world, hands-on experience with industry,” explained Subha Madhavan, Ph.D., associate dean and director of graduate studies for HIDS. “As our capstone partner, the FNL’s team of multidisciplinary scientists and engineers is able to provide a unique practical training experience for our students to apply what they learned in the classroom for high-impact projects in cancer research.”

Data visualization project

Jensen’s connection with HIDS began before it even enrolled its first student. Madhavan put out a call for input from those working in the biomedical data science field to help shape the program. Jensen responded, joining as a pro bono HIDS industry board member. When the first HIDS cohort started looking for capstone projects, Jensen saw an opportunity for the FNL to get involved, which ultimately led to the affiliation agreement.

A screenshot of a data visualization diagram
This data model visualizer presents the data in a graphical structure to make it easier for users to search and understand the data.

Jensen is Director of Data Management and Interoperability, supporting Cancer Research Data Commons (CRDC), the National Cancer Institute’s open-source data resource that enables data collection and sharing across the cancer research community. Among the CRDC is the Integrated Canine Data Commons (ICDC), which stores data on dogs with cancer as a way to compare and learn more about human cancers. The ICDC maintains large quantities of data for each canine patient, which makes it challenging to maintain and search it. Jensen proposed development of a data model visualizer for the ICDC to be conducted as a capstone project. It was completed fully remotely.

“The model can get complicated and hard to read as words,” Jensen said. “But since we get a lot of information as humans out of our visual pattern recognition capabilities, if you can represent that model as a graphical structure that shows each grouping of data, what they are, and how they’re linked. We find it’s a lot easier for users—both people who want to get the data and the people who want to give the data.”

Wang said creating the ICDC data viewer tool as a front-end development project tied in nicely to his skillsets and was also a tremendous learning experience for him.

“It gave me a real working experience, and it gave me a glimpse of how work is done in real life,” Wang said.

He explained that the ICDC utilizes a graph database, a type of database that is particularly useful for capturing complex relationships. However, a graph database is uncommon, and he had not yet encountered it in his studies. The capstone also gave him an opportunity to have a real impact on cancer research, something no homework assignment could provide.

Supporting the future biomedical workforce

Wang stressed the value of the capstone experience, noting it is particularly valuable to international students to enhance their résumés and earn recommendations from respected professionals in the field. For Wang, such a recommendation resulted in a job offer from FNL subcontractor Essential Software, Inc. He is now working on the Serological Sciences Network, a large collaborative NCI effort managed by the FNL to enhance understanding of the immune response to the novel coronavirus, SARS-CoV-2.

However, he is not the only person who benefited from the experience. When asked if he would take another capstone student in the future, Jensen replied, “Definitely, I would. I would do it again, and I would also encourage other groups to get onboard.”

FNL and Georgetown previously signed a memorandum of understanding for research and training and had undertaken several shared activities, including launching a joint seminar series. This capstone partnership represents a next step for enhanced student training.