Machine Learning and Artificial Intelligence (ML/AI) are reshaping data science and scientific discovery. Recognizing the important role of collaboration and knowledge sharing in this space, NCBI hosted the “Building transparent ML/AI solutions to advance biological research codeathon” from February 26 to March 1, 2024. This virtual event brought together biologists, developers, and data scientists passionate about using responsible AI in biological research.
Event Details
The week-long codeathon offered a collaborative environment for ten teams to carry out projects promoting FAIR (Findable, Accessible, Interoperable, and Reusable) ML/AI in biological research. Participants worked together on team-driven projects, networked with peers, and learned from NIH experts. The event also featured a panel discussion, “From Data to Impact: ML/AI for Biological Research.” Topics included workforce development, the need for FAIR and transparent solutions, the importance of data preparation, and the power of leveraging ML/AI in biological research. The panel featured representatives from several NIH Institutes, including:
- Steve Tsang, PhD, National Institutes of Health, Office of the Director
- Emily Greenspan, PhD, National Institutes of Health, National Cancer Institute, AI Data Readiness Challenge
- Zhiyong Lu, PhD FACMI, National Institutes of Health, National Library of Medicine, National Center for Biotechnology Information
- Alison Lin, PhD, National Institutes of Health, Office of the Director
- Nicole Sroka, National Institutes of Health, National Library of Medicine, GenAI Pilot Program
Throughout the week, we received outstanding participation and engagement!
- 100+ individuals participated in the codeathon
- 130+ individuals attended final presentations
- 66 participants from academia, government, and industries across the US and world made up our 10 teams
Each team worked on a distinct project, but also engaged with other teams to explore topics such as data harmonization, machine learning for biological prediction, data standardization, and visualization tools. From predicting drug sensitivity in cancer to visualizing genetic data for educational purposes, each team leveraged ML and/or AI to address complex biological challenges.
Learn more
Learn more about the work by reviewing team repositories and final presentations. Final presentations were recorded and will be made available approximately two weeks after the event.
Stay up to date
Follow us on social @NCBI and join our mailing list to keep up to date with NCBI news and events.
Though this event has concluded, we encourage you to keep an eye out for upcoming codeathons and other outreach events.
Questions?
If you have any questions about NCBI codeathons or interest in participating in future events, please reach out to the NCBI Codeathon Team.