By Jayasree Jaganatha, Renaissance Computing Institute (RENCI) –
Notes, takeaways, and resources from our fourth event (featuring Chris Bizon, Nabarun Dasgupta, and Naim Rashid) –
On May 26, 2022, Carolina Data Science Now hosted the fourth iteration of its seminar series, which strives to link the people, research, and resources by highlighting the many faces of data science across our campus, and demonstrating the integral role data science can play in all disciplines.
This Month’s Speakers
The theme of the event was “Improving Health Outcomes.” The event was moderated by Kari North, and the speakers were selected to provide insight on how data science is used to prevent, address, and develop solutions for long-lasting health issues.
Chris Bizon | Renaissance Computing Institute (RENCI)
Chris Bizon discussed “Heterogeneity in Obesity Creativity Hub: Transdisciplinary Approaches for Precision Research and Treatment,” and presented data science tools used within the Obesity Hub, a project that aims to take a multidisciplinary and multi-modal approach to understanding obesity.
Read more about the lightning talk here.
Nabarun Dasgupta | UNC Injury Prevention Research Center
Innovation Fellow, Gillings School of Global Public Health
Nabarun Dasgupta presented two projects from the Opioid Data Lab: an algorithm to predict out-of-hospital death using insurance claims data and an initiative to understand and communicate the content inside street drugs.
Read more about the lightning talk here.
Naim Rashid | Biostatistics
Research Associate Professor, Lineberger Comprehensive Cancer Center
Naim Rashid spoke on “Cancer Data Science: From Code to Clinic,” which aims to translate data science models for the benefit of cancer patients.
Read more about the lightning talk here.
Speaker Q&A
Questions for the speakers were collected through an EasyRetro board. Topics during this section included:
- The automated ingest and build process used by ROBOKOP to populate its knowledge graphs with the most recent and update findings from scientific papers and authors outside of the project.
- Reasons to encourage scientists to use GitHub, such as acknowledging the large volume of data that needs processing and downstream analysis, gaining the ability to “roll back” to a previous version of a project, and simplifying the sharing process at publication time.
- Overcoming the challenges of working with data that can be affected by a societal stigma by working closely with community partners and taking a non-judgmental approach when conducting research.
- Creating opportunities for multiple teams across campus using the same research tools to share lessons learned and open additional opportunities to cross-fertilize projects, including Slack and Microsoft Teams workspaces.
- Courses and resources available across campus and at the soon-to-launch School of Data Science and Society that focus on introducing baseline data science tools, such as Jupyter Notebook and GitHub, and creating unique pathways for students of all industry backgrounds.
- The analysis of dynamic data, such as timestamps, against static data, such as genes, to determine causation within the Obesity Hub project.
- Potential plans for the application of the work done by the Opioid Data Lab to broader health conditions that may be stigmatized.
- Exploring the influence of pivotal germline and somatic mutations on the subtypes of cancer patients currently identified.
Conversations with the Data Science Community
Ashok Krishnamurthy realized that one of Naim Rashid’s projects overlapped with research that one of his graduate students was pursuing on missing data and uncertainty quantization. He quickly introduced the two in hopes that both are able to benefit from the other’s research.
During the event, several attendees shared resources relevant to the conversation in the chat, including course recommendations, workshops, documentation, and support community. A full list of educational programs, funding opportunities, on-campus support services, tools and software, and more shared during Carolina Data Science Now seminars can be found on our Resources page.
Next Seminar
Our next seminar will be held on June 26 at 12 PM (ET). Register here.
Check out a playlist of our previous events here.