From Data to Discovery: Inside the Bio-IT Hackathon

By Bio-IT World Staff 

April 1, 2026 | At a time when research is generating more data than ever before, a growing question looms: how do scientists actually make use of it? At the Bio-IT World Hackathon, organizers believe that the answer lies not just in better tools, but in better collaboration—and increasingly, in the intelligent use of AI.  

Allissa Dillman, founder and CEO of BioData Sage, and LaFrancis Gibson, manager for health promotion at ORAU, have hosted Bio-IT World’s Hackathon on behalf of the National Institutes of Health (NIH) Common Fund Data Ecosystem (CFDE) Training Center for years. They join the newest episode of Trends from the Trenches with host Allison Proffitt to discuss how the Hackathon brings together a diverse mix of participants—data scientists, software developers, and life science-based professionals—to work intensively on real-world biomedical data challenges. But unlike traditional coding competitions, this event is deliberately structured around three intertwined goals: creation, education, and collaboration. 

The CFDE Training Center is a large-scale initiative that consists of a diverse set of databases, datasets, tools, and resources from various biomedical programs. The datasets available to participants span a wide range of domains, including genomics and phenotypes.  

The Hackathon is organized into six projects, and participants can choose which one they’d like to explore further.  

• Project 1: Exercise as Medicine: Opposing Molecular Signatures in Health and Disease
• Project 2: Drug Repurposing via Disease Similarity and Biomarker Networks
• Project 3: Visible Neural Networks for Cancer Drug Response (CellMap-VNN)
• Project 4: Illuminating the Molecular Basis of Drug Side Effects
• Project 5: Mining the CFDE for Post-Translational Modification Data
• Project 6: Exercise Mimetics Discovery with Gene Set Foundation Models 

The Hackathon also provides access to cloud-based computing environments, allowing participants to analyze large datasets without the constraints of local infrastructure. This setup is particularly important given the tight deadline. Teams have only 48 hours to develop a working concept, prototype, or analysis. 

Secondary Findings 

But there’s a secondary research goal here as well. In addition to the questions and datasets outlined in the six projects, the organizers plan to explore fundamental questions of team collaboration with AI.  

“We’re really interested to see how different folks with different backgrounds utilize AI,” said Dillman. “How does that look different? How do they come together at the end and put all of those different pieces together?” 

To answer these questions, organizers will observe team workflows in shared cloud environments, analyze interactions with AI tools, and conduct interviews during and after the event. The goal is to better understand not just individual use of AI, but how teams collectively verify, correct, and synthesize AI-generated outputs. 

The Hackathon is open to participants ranging from students to industry professionals—and free to attend. The event is designed to lower barriers and broaden participation. 

“Data is only impactful if people can use it,” said Gibson. “This is where we hope to bridge that gap and allow people to really immerse themselves in this space.”