Data Management for Large (Deep Learning) Models Hackathon
Calling all bioinformatics problem solving enthusiasts! CMU Libraries, in partnership with DNAnexus, is hosting a three-day hackathon. Get ready to dive into graph extraction for large models in the biomedical space. Fill out this brief applicaton here. Applications close on Tuesday, September 26th.
The hackathon is a collaborative event, with each team working on a dedicated part of the problem. The teams will be focused on the following topics:
- Knowledge graph based validation for variant (genomic) assertions
- Continuous monitoring for RLHF; Flexible infrastructure for layering assertions with rollback
- Flexible tokenization or graph-based loading of complex data types
- Assertion tracking in large models
- Column headers for data harmonization
- Time-resolved vector positioning in large models
- Cohort based vcfs to knowledge graphs
- Virus-associated changes in disease trajectories
- Metagenomic features associated with health and disease
All pipelines and other scripts, software, and programs generated in this hackathon will be added to a public GitHub repository designed for that purpose. The outputs are often published as preprints or on the F1000 hackathon channel.
In-Person Event Information:
Indoor meetings and university-sponsored events of up to 50 persons are permitted. Due to COVID-19 campus restrictions, in-person workshops and events are only open to current CMU affiliates at this time.
Outdoor meetings and university-sponsored events are permitted up to 50% of outdoor facility capacity.
For more information on in-person activities and spaces, please visit the university's COVID-19 Updates Guide
Workshops and events for Carnegie Mellon University Libraries are open to all, regardless of race, color, national origin, sex, disability, age, sexual orientation, gender identity, religion, creed, ancestry, belief, veteran status or genetic information.
If you require accessibility accommodations, please contact the event organizer.